kjappelbaum/chemnlp-chem-caption
收藏Hugging Face2023-11-07 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/kjappelbaum/chemnlp-chem-caption
下载链接
链接失效反馈官方服务:
资源简介:
---
dataset_info:
- config_name: default
features:
- name: representation
dtype: string
- name: representation_type
dtype: string
- name: prompt_template
dtype: string
- name: completion_template
dtype: string
- name: completion
dtype: string
- name: completion_names
dtype: string
- name: completion_labels
dtype: string
- name: constraint
dtype: string
- name: filled_prompt
dtype: string
- name: filled_completion
dtype: string
splits:
- name: train
num_bytes: 206763010
num_examples: 323500
download_size: 15384432
dataset_size: 206763010
- config_name: rdkit_feat
features:
- name: representation_type
dtype: string
- name: num_valence_electrons
dtype: int64
- name: rotable_proportion
dtype: float64
- name: non_rotable_proportion
dtype: float64
- name: num_unspecified_bond
dtype: float64
- name: num_single_bonds
dtype: float64
- name: num_double_bonds
dtype: float64
- name: num_triple_bonds
dtype: float64
- name: num_quadruple_bonds
dtype: float64
- name: num_quintuple_bonds
dtype: float64
- name: num_hextuple_bonds
dtype: float64
- name: num_oneandahalf_bonds
dtype: float64
- name: num_twoandahalf_bonds
dtype: float64
- name: num_threeandahalf_bonds
dtype: float64
- name: num_fourandahalf_bonds
dtype: float64
- name: num_fiveandahalf_bonds
dtype: float64
- name: num_aromatic_bonds
dtype: float64
- name: num_ionic_bonds
dtype: float64
- name: num_hydrogen_bonds
dtype: float64
- name: num_threecenter_bonds
dtype: float64
- name: num_dativeone_bonds
dtype: float64
- name: num_dative_bonds
dtype: float64
- name: num_other_bonds
dtype: float64
- name: num_zero_bonds
dtype: float64
- name: num_bonds
dtype: int64
- name: molecular_formula
dtype: string
- name: monoisotopic_molecular_mass
dtype: float64
- name: num_carbon_atoms
dtype: int64
- name: num_hydrogen_atoms
dtype: int64
- name: num_nitrogen_atoms
dtype: int64
- name: num_oxygen_atoms
dtype: int64
- name: carbon_mass
dtype: float64
- name: hydrogen_mass
dtype: float64
- name: nitrogen_mass
dtype: float64
- name: oxygen_mass
dtype: float64
- name: num_hydrogen_bond_acceptors
dtype: int64
- name: num_hydrogen_bond_donors
dtype: int64
- name: num_lipinski_violations
dtype: int64
- name: inertial_shape_factor
dtype: float64
- name: eccentricity
dtype: float64
- name: asphericity
dtype: float64
- name: npr1_value
dtype: float64
- name: npr2_value
dtype: float64
- name: pmi1_value
dtype: float64
- name: pmi2_value
dtype: float64
- name: pmi3_value
dtype: float64
- name: num_chiral_centers
dtype: int64
- name: representation
dtype: string
- name: __index_level_0__
dtype: int64
splits:
- name: train
num_bytes: 41660808
num_examples: 82337
download_size: 16423699
dataset_size: 41660808
- config_name: rdkit_feat_0
features:
- name: tert-butyloxycarbonyl_count
dtype: int64
- name: representation_type
dtype: string
- name: trityl_count
dtype: int64
- name: 3,5-dimethoxyphenylisoproxycarbonyl_count
dtype: int64
- name: 2-(4-biphenyl)isopropoxycarbonyl_count
dtype: int64
- name: 2-nitrophenylsulfenyl_count
dtype: int64
- name: boc_count
dtype: int64
- name: trt_count
dtype: int64
- name: ddz_count
dtype: int64
- name: bpoc_count
dtype: int64
- name: nps_count
dtype: int64
- name: 9-fluorenylmethoxycarbonyl_count
dtype: int64
- name: 2-(4-nitrophenylsulfonyl)ethoxycarbonyl_count
dtype: int64
- name: (1,1-dioxobenzo[b]thiophene-2-yl)methyloxycarbonyl_count
dtype: int64
- name: (1,1-dioxonaptho[1,2-b]thiophene-2-yl)methyloxycarbonyl_count
dtype: int64
- name: 1-(4,4-dimethyl-2,6-dioxocyclohex-1-ylidene)-3-methylbutyl_count
dtype: int64
- name: 2,7-di-tert-butyl-fmoc_count
dtype: int64
- name: 2-fluoro-fmoc_count
dtype: int64
- name: 2-monoisooctyl-fmoc_count
dtype: int64
- name: 2,7-diisooctyl-fmoc_count
dtype: int64
- name: tetrachlorophthaloyl_count
dtype: int64
- name: 2-[phenyl(methyl)sulfonio])ethyloxycarbonyltetrafluoroborate_count
dtype: int64
- name: ethanesulfonylethoxycarbonyl_count
dtype: int64
- name: 2-(4-sulfophenylsulfonyl)ethoxycarbonyl_count
dtype: int64
- name: fmoc_count
dtype: int64
- name: nsc_count
dtype: int64
- name: bsmoc_count
dtype: int64
- name: alpha-nsmoc_count
dtype: int64
- name: ivdde_count
dtype: int64
- name: fmoc*_count
dtype: int64
- name: fmoc(fmoc(2f))_count
dtype: int64
- name: mio-fmoc_count
dtype: int64
- name: dio-fmoc_count
dtype: int64
- name: tcp_count
dtype: int64
- name: pms_count
dtype: int64
- name: esc_count
dtype: int64
- name: sps_count
dtype: int64
- name: benzyloxycarbonyl_count
dtype: int64
- name: allyloxycarbonyl_count
dtype: int64
- name: o-nitrobenzenesulfonyl_count
dtype: int64
- name: 2,4-dinitrobenzenesulfonyl_count
dtype: int64
- name: benzothiazole-2-sulfonyl_count
dtype: int64
- name: 2,2,2-trichloroethyloxycarbonyl_count
dtype: int64
- name: dithiasuccinoyl_count
dtype: int64
- name: p-nitrobenzyloxycarbonyl_count
dtype: int64
- name: alpha-azidoacids_count
dtype: int64
- name: proparglyoxycarbonyl_count
dtype: int64
- name: o-nitrobenzylcarbonyl_count
dtype: int64
- name: 4-nitroveratryloxycarbonyl_count
dtype: int64
- name: 2-(2-nitrophenyl)propyloxycarbonyl_count
dtype: int64
- name: 2-(3,4-methylenedioxy-6-nitrophenyl)propyloxycarbonyl_count
dtype: int64
- name: 9-(4-bromophenyl)-9-fluorenyl_count
dtype: int64
- name: azidomethoxycarbonyl_count
dtype: int64
- name: hexafluoroacetone_count
dtype: int64
- name: Z_count
dtype: int64
- name: alloc_count
dtype: int64
- name: o-nbs_count
dtype: int64
- name: d-nbs_count
dtype: int64
- name: bts_count
dtype: int64
- name: troc_count
dtype: int64
- name: dts_count
dtype: int64
- name: pnz_count
dtype: int64
- name: poc_count
dtype: int64
- name: onz_count
dtype: int64
- name: nvoc_count
dtype: int64
- name: nppoc_count
dtype: int64
- name: mnppoc_count
dtype: int64
- name: brphf_count
dtype: int64
- name: azoc_count
dtype: int64
- name: hfa_count
dtype: int64
- name: 2-chlorobenzyloxycarbonyl_count
dtype: int64
- name: 4-methyltrityl_count
dtype: int64
- name: cl-z_count
dtype: int64
- name: mtt_count
dtype: int64
- name: 1-(4,4-dimethyl-2,6-dioxocylohex-1-ylidene)-3-methylbutyl_count
dtype: int64
- name: trifluoroacetyl_count
dtype: int64
- name: 2-(methylsulfonyl)ethoxycarbonyl_count
dtype: int64
- name: tfa_count
dtype: int64
- name: msc_count
dtype: int64
- name: phenyldisulphanylethyloxycarbonyl_count
dtype: int64
- name: 2-pyridyldisulphanylethyloxycarbonyl_count
dtype: int64
- name: phdec_count
dtype: int64
- name: pydec_count
dtype: int64
- name: tert-butyl_count
dtype: int64
- name: 2-chlorotrityl_count
dtype: int64
- name: 2-4-dimethyoxybenzyl_count
dtype: int64
- name: 2-phenylisopropyl_count
dtype: int64
- name: 5-phenyl-3,4-ethylenedioxythenyl_count
dtype: int64
- name: bu_count
dtype: int64
- name: 2-cl-trt_count
dtype: int64
- name: dmb_count
dtype: int64
- name: 2-ph-pr_count
dtype: int64
- name: phenyl-edotn_count
dtype: int64
- name: 9-fluorenylmethyl_count
dtype: int64
- name: 4-(N-[1-(4,4-dimethyl-2,6-dioxocylocheylidene)-3-methylbutyl]-amino)benzyl_count
dtype: int64
- name: methyl_count
dtype: int64
- name: ethyl_count
dtype: int64
- name: carbamoylmethyl_count
dtype: int64
- name: fm_count
dtype: int64
- name: dmab_count
dtype: int64
- name: me_count
dtype: int64
- name: et_count
dtype: int64
- name: cam_count
dtype: int64
- name: allyl_count
dtype: int64
- name: benzyl_count
dtype: int64
- name: phenacyl_count
dtype: int64
- name: p-nitrobenzyl_count
dtype: int64
- name: 2-trimethylsilyethyl_count
dtype: int64
- name: (2-phenyl-2-trimethylsilyl)ethyl_count
dtype: int64
- name: 2-(trimethylsilyl)isopropyl_count
dtype: int64
- name: 2,2,2-trichloroethyl_count
dtype: int64
- name: p-hydroxyphenacyl_count
dtype: int64
- name: 4,5-dimethyoxy-2-nitrobenzyl_count
dtype: int64
- name: 1,1-dimethylallyl_count
dtype: int64
- name: pentaaminecobalt_III_count
dtype: int64
- name: al_count
dtype: int64
- name: bn_count
dtype: int64
- name: pac_count
dtype: int64
- name: pnb_count
dtype: int64
- name: tmse_count
dtype: int64
- name: ptmse_count
dtype: int64
- name: tmsi_count
dtype: int64
- name: tce_count
dtype: int64
- name: php_count
dtype: int64
- name: dmnb_count
dtype: int64
- name: dma_count
dtype: int64
- name: cyclohexyl_count
dtype: int64
- name: b-menthyl_count
dtype: int64
- name: b-3-methylpent-3-yl_count
dtype: int64
- name: 4-(3,6,9-trioxadecyl)oxybenzyl_count
dtype: int64
- name: chx_count
dtype: int64
- name: men_count
dtype: int64
- name: mpe_count
dtype: int64
- name: tegbz_count
dtype: int64
- name: 9-fluoroenylmethyl_count
dtype: int64
- name: 4-(N-[1-(4,4-dimethyl-2,6-dioxocyclohexylidene)-3-methyl-butyl]-amino)benzyl_count
dtype: int64
- name: trimethylsilylethyl_count
dtype: int64
- name: 4,5-dimethoxy-2-nitrobenzyloxycarbonyl_count
dtype: int64
- name: pseudoprolines_count
dtype: int64
- name: 2-hydroxy-4-methoxybenzyl_count
dtype: int64
- name: 2,4-dimethoxybenzyl_count
dtype: int64
- name: 2,4,6-trimethoxybenzyl_count
dtype: int64
- name: 1-methyl-3-indolylmethyl_count
dtype: int64
- name: 3,4-ethylene-dioxy-2-thenyl_count
dtype: int64
- name: hmb_count
dtype: int64
- name: tmob_count
dtype: int64
- name: mim_count
dtype: int64
- name: edot_count
dtype: int64
- name: 4-methoxy-2-nitro-benzyl_count
dtype: int64
- name: (6-hydroxy-3-oxido-1,3-benz[d]oxathiol-5-yl)methyl_count
dtype: int64
- name: 2-hydroxy-4-methoxy-5-(methylsulfinyl)benzyl_count
dtype: int64
- name: n-boc-n-methyl[2-(methylamino)ethyl]carbamoyl-hmb_count
dtype: int64
- name: 9-xanthenyl_count
dtype: int64
- name: cyclopropyldimethylcarbinyl_count
dtype: int64
- name: 4,4-dimethoxybenzhydryl_count
dtype: int64
- name: xan_count
dtype: int64
- name: cpd_count
dtype: int64
- name: mbh_count
dtype: int64
- name: p-toluenesulfonyl_count
dtype: int64
- name: 2,2,5,7,8-pentamethylchroman-6-sulfonyl_count
dtype: int64
- name: 2,2,4,6,7-pentamethyl-2,3-dihydrobenzofuran-5-sulfonyl_count
dtype: int64
- name: mesityl-2-sulfonyl_count
dtype: int64
- name: 4-methoxy-2,3,6-trimethylphenylsulfonyl_count
dtype: int64
- name: 1,2-dimethylindole-3-sulfonyl_count
dtype: int64
- name: w,w-bis-tert-butyloxycarbonyl_count
dtype: int64
- name: 5-dibenzosuberenyl_count
dtype: int64
- name: 5-dibenzosuberyl_count
dtype: int64
- name: 2-methoxy-5-dibenzosuberyl_count
dtype: int64
- name: nitro_count
dtype: int64
- name: tos_count
dtype: int64
- name: pmc_count
dtype: int64
- name: pbf_count
dtype: int64
- name: mts_count
dtype: int64
- name: mtr_count
dtype: int64
- name: mis_count
dtype: int64
- name: bis-boc_count
dtype: int64
- name: suben_count
dtype: int64
- name: sub_count
dtype: int64
- name: mesub_count
dtype: int64
- name: no2_count
dtype: int64
- name: w,w-bis-benzyloxycarbonyl_count
dtype: int64
- name: w,w-bis-allyloxycarbonyl_count
dtype: int64
- name: z-small_count
dtype: int64
- name: p-methylbenzyl_count
dtype: int64
- name: p-methoxybenzyl_count
dtype: int64
- name: monomethoxytrityl_count
dtype: int64
- name: trimethoxybenzyl_count
dtype: int64
- name: 2,2,4,6,7-pentamethyl-5-dihydrobenzofuranylmethyl_count
dtype: int64
- name: 1-adamantyl_count
dtype: int64
- name: meb_count
dtype: int64
- name: mob_count
dtype: int64
- name: mmt_count
dtype: int64
- name: pmbf_count
dtype: int64
- name: 1-ada_count
dtype: int64
- name: 2-(2,4-dinitrophenyl)ethyl_count
dtype: int64
- name: 9-fluororenylmethoxycarbonyl_count
dtype: int64
- name: dnpe_count
dtype: int64
- name: acetamidomethyl_count
dtype: int64
- name: phenylacetamidomethyl_count
dtype: int64
- name: 5-tert-butylmercapto_count
dtype: int64
- name: 3-nitro-2-pyridinesulfenyl_count
dtype: int64
- name: 2-pyridinesulfenyl_count
dtype: int64
- name: N-allyloxycarbonyl-N-[2,3,5,6-tetrafluoro-4-(phenylthio)phenyl]]aminomethyl_count
dtype: int64
- name: o-nitrobenzyl_count
dtype: int64
- name: 4-picolyl_count
dtype: int64
- name: ninhydrin_count
dtype: int64
- name: acm_count
dtype: int64
- name: phacm_count
dtype: int64
- name: sbu_count
dtype: int64
- name: npys_count
dtype: int64
- name: s-pyr_count
dtype: int64
- name: fsam_count
dtype: int64
- name: onb_count
dtype: int64
- name: nin_count
dtype: int64
- name: n-tosyl_count
dtype: int64
- name: n-trityl_count
dtype: int64
- name: n-monomethoxytrityl_count
dtype: int64
- name: n-methyltrityl_count
dtype: int64
- name: n-tert-butyloxycarbonyl_count
dtype: int64
- name: n-2,4-dimethylpent-3-yloxycarbonyl_count
dtype: int64
- name: n-benzyloxymethyl_count
dtype: int64
- name: n-tert-butoxymethyl_count
dtype: int64
- name: ntos_count
dtype: int64
- name: ntrt_count
dtype: int64
- name: nmtt_count
dtype: int64
- name: nmmt_count
dtype: int64
- name: nboc_count
dtype: int64
- name: ndoc_count
dtype: int64
- name: nbom_count
dtype: int64
- name: nbum_count
dtype: int64
- name: N-9-fluorenylmethoxycarbonyl_count
dtype: int64
- name: N-2,6-dimethoxybenzoyl_count
dtype: int64
- name: dmbz_count
dtype: int64
- name: N-2,4-dinitrophenyl_count
dtype: int64
- name: dnp_count
dtype: int64
- name: cyclohexyl;_count
dtype: int64
- name: tert-butyldimethylsilyl_count
dtype: int64
- name: tbdms_count
dtype: int64
- name: tert-butyldiphenylsilyl_count
dtype: int64
- name: propargyloxycarbonyl_count
dtype: int64
- name: tbdps_count
dtype: int64
- name: 2,6-dichlorobenzyl_count
dtype: int64
- name: 2-bromobenzyl_count
dtype: int64
- name: 2-bromobenzyloxycarbonyl_count
dtype: int64
- name: 3-pentyl_count
dtype: int64
- name: dcb_count
dtype: int64
- name: brbn_count
dtype: int64
- name: brz_count
dtype: int64
- name: pen_count
dtype: int64
- name: tegb_count
dtype: int64
- name: boc-n-methyl-n-[2-(methylamino)ethyl]carbamoyl_count
dtype: int64
- name: boc-nmec_count
dtype: int64
- name: formyl_count
dtype: int64
- name: cyclohexyloxycarbonyl_count
dtype: int64
- name: for_count
dtype: int64
- name: hoc_count
dtype: int64
- name: cyclopropane_count
dtype: int64
- name: spiropentane_count
dtype: int64
- name: cyclobutane_count
dtype: int64
- name: cyclopentane_count
dtype: int64
- name: furan_count
dtype: int64
- name: thiophene_count
dtype: int64
- name: pyrrole_count
dtype: int64
- name: 2H-pyrrole_count
dtype: int64
- name: 3H-pyrrole_count
dtype: int64
- name: pyrazole_count
dtype: int64
- name: 2H-imidazole_count
dtype: int64
- name: 1,2,3-triazole_count
dtype: int64
- name: 1,2,4-triazole_count
dtype: int64
- name: 1,2-dithiole_count
dtype: int64
- name: 1,3-dithiole_count
dtype: int64
- name: 3H-1,2-oxathiole_count
dtype: int64
- name: isoxazole_count
dtype: int64
- name: oxazole_count
dtype: int64
- name: thiazole_count
dtype: int64
- name: isothiazole_count
dtype: int64
- name: 1,2,3-oxadiazole_count
dtype: int64
- name: 1,2,4-oxadiazole_count
dtype: int64
- name: 1,2,5-oxadiazole_count
dtype: int64
- name: 1,3,4-oxadiazole_count
dtype: int64
- name: 1,2,3,4-oxatriazole_count
dtype: int64
- name: 1,2,3,5-oxatriazole_count
dtype: int64
- name: 3H-1,2,3-dioxazole_count
dtype: int64
- name: 1,2,4-dioxazole_count
dtype: int64
- name: 1,3,2-dioxazole_count
dtype: int64
- name: 1,3,4-dioxazole_count
dtype: int64
- name: 5H-1,2,5-oxathiazole_count
dtype: int64
- name: 1,3-oxathiole_count
dtype: int64
- name: benzene_count
dtype: int64
- name: cyclohexane_count
dtype: int64
- name: 2H-pyran_count
dtype: int64
- name: 4H-pyran_count
dtype: int64
- name: 2H-pyran-2-one_count
dtype: int64
- name: 4H-pyran-4-one_count
dtype: int64
- name: 1,2-dioxin_count
dtype: int64
- name: 1,3-dioxin_count
dtype: int64
- name: pyridine_count
dtype: int64
- name: pyridazine_count
dtype: int64
- name: pyrimidine_count
dtype: int64
- name: pyrazine_count
dtype: int64
- name: piperazine_count
dtype: int64
- name: 1,3,5-triazine_count
dtype: int64
- name: 1,2,4-triazine_count
dtype: int64
- name: 1,2,3-triazine_count
dtype: int64
- name: 4H-1,2-Oxazine_count
dtype: int64
- name: 2H-1,3-Oxazine_count
dtype: int64
- name: 6H-1,3-Oxazine_count
dtype: int64
- name: 6H-1,2-Oxazine_count
dtype: int64
- name: 1,4-Oxazine_count
dtype: int64
- name: 2H-1,2-Oxazine_count
dtype: int64
- name: 4H-1,4-Oxazine_count
dtype: int64
- name: 1,2,5-Oxathiazine_count
dtype: int64
- name: 1,2,6-Oxathiazine_count
dtype: int64
- name: 1,2,4-Oxadiazine_count
dtype: int64
- name: 1,3,5-Oxadiazine_count
dtype: int64
- name: morpholine_count
dtype: int64
- name: azepine_count
dtype: int64
- name: oxepin_count
dtype: int64
- name: thiepin_count
dtype: int64
- name: 4H-1,2-diazepine_count
dtype: int64
- name: indene_count
dtype: int64
- name: 2H-indene_count
dtype: int64
- name: benzofuran_count
dtype: int64
- name: isobenzofuran_count
dtype: int64
- name: benzo[b]thiophene_count
dtype: int64
- name: benzo[c]thiophene_count
dtype: int64
- name: indole_count
dtype: int64
- name: 3H-indole_count
dtype: int64
- name: 1H-indole_count
dtype: int64
- name: cyclopenta[b]pyridine_count
dtype: int64
- name: pyrano[3,4-b]-pyrrole_count
dtype: int64
- name: indazole_count
dtype: int64
- name: benzisoxazole_count
dtype: int64
- name: benzoxazole_count
dtype: int64
- name: 2,1-benzisoxazole_count
dtype: int64
- name: naphthalene_count
dtype: int64
- name: 1,2,3,4-tetrahydronaphthalene_count
dtype: int64
- name: octahydronaphthalene_count
dtype: int64
- name: 2H-1-benzopyran_count
dtype: int64
- name: 2H-1-benzopyran-2-one_count
dtype: int64
- name: 4H-1-benzopyran-4-one_count
dtype: int64
- name: 1H-2-benzopyran-1-one_count
dtype: int64
- name: 3H-2-benzopyran-1-one_count
dtype: int64
- name: quinoline_count
dtype: int64
- name: isoquinoline_count
dtype: int64
- name: cinnoline_count
dtype: int64
- name: quinazoline_count
dtype: int64
- name: 1,8-napthyhridine_count
dtype: int64
- name: 1,7-napththyridine_count
dtype: int64
- name: 1,5-napththridine_count
dtype: int64
- name: 1,6-napthyridine_count
dtype: int64
- name: 2H-1,3-benzoxazine_count
dtype: int64
- name: 2H-1,4-benzoxazine_count
dtype: int64
- name: 1H-2,3-benzoxazine_count
dtype: int64
- name: 4H-3,1-benzoxazine_count
dtype: int64
- name: 2H-1,2-benzoxazine_count
dtype: int64
- name: 4H-1,3-benzoxazine_count
dtype: int64
- name: anthracene_count
dtype: int64
- name: phenanthrene_count
dtype: int64
- name: phenalene_count
dtype: int64
- name: fluorene_count
dtype: int64
- name: carbazole_count
dtype: int64
- name: xanthene_count
dtype: int64
- name: acridine_count
dtype: int64
- name: norpinane_count
dtype: int64
- name: 7H-purine_count
dtype: int64
- name: steroid_ring_system_count
dtype: int64
- name: imidazole_count
dtype: int64
- name: thiazol-2-amine_count
dtype: int64
- name: tetrazole_count
dtype: int64
- name: cytosine_count
dtype: int64
- name: adenine_count
dtype: int64
- name: 5-methylindole_count
dtype: int64
- name: isocaffeine_count
dtype: int64
- name: tetrazolethiol_count
dtype: int64
- name: 3-methylisoxazole_count
dtype: int64
- name: 1-methylimidazole_count
dtype: int64
- name: 2-methylimidazole_count
dtype: int64
- name: guanine_count
dtype: int64
- name: tosufloxacin_count
dtype: int64
- name: acetamido_count
dtype: int64
- name: acetoacetyl_count
dtype: int64
- name: acetyl_count
dtype: int64
- name: acryloyl_count
dtype: int64
- name: alanyl_count
dtype: int64
- name: beta-alanyl_count
dtype: int64
- name: allylidene_count
dtype: int64
- name: amidino_count
dtype: int64
- name: amino_count
dtype: int64
- name: amyl_count
dtype: int64
- name: anilino_count
dtype: int64
- name: anisidino_count
dtype: int64
- name: anthranoyl_count
dtype: int64
- name: arsino_count
dtype: int64
- name: azelaoyl_count
dtype: int64
- name: azido_count
dtype: int64
- name: azo_count
dtype: int64
- name: azoxy_count
dtype: int64
- name: benzal_count
dtype: int64
- name: benzamido_count
dtype: int64
- name: benzhydrol_count
dtype: int64
- name: benzoxy_count
dtype: int64
- name: benzoyl_count
dtype: int64
- name: benzylidene_count
dtype: int64
- name: benzylidyne_count
dtype: int64
- name: biphenylyl_count
dtype: int64
- name: biphenylene_count
dtype: int64
- name: butoxy_count
dtype: int64
- name: sec-butoxy_count
dtype: int64
- name: tert-butoxy_count
dtype: int64
- name: butyl_count
dtype: int64
- name: sec-butyl_count
dtype: int64
- name: butyryl_count
dtype: int64
- name: caproyl_count
dtype: int64
- name: capryl_count
dtype: int64
- name: capryloyl_count
dtype: int64
- name: carbamido_count
dtype: int64
- name: carbamoyl_count
dtype: int64
- name: carbamyl_count
dtype: int64
- name: carbazoyl_count
dtype: int64
- name: carbethoxy_count
dtype: int64
- name: carbonyl_count
dtype: int64
- name: carboxy_count
dtype: int64
- name: cetyl_count
dtype: int64
- name: chloroformyl_count
dtype: int64
- name: cinnamoyl_count
dtype: int64
- name: cinnamyl_count
dtype: int64
- name: cinnamylidene_count
dtype: int64
- name: cresyl_count
dtype: int64
- name: crotonoyl_count
dtype: int64
- name: crotyl_count
dtype: int64
- name: cyanamido_count
dtype: int64
- name: cyanato_count
dtype: int64
- name: cyano_count
dtype: int64
- name: decanedioyl_count
dtype: int64
- name: decanoyl_count
dtype: int64
- name: diazo_count
dtype: int64
- name: diazoamino_count
dtype: int64
- name: disilanyl_count
dtype: int64
- name: disiloxanyloxy_count
dtype: int64
- name: disulfinyl_count
dtype: int64
- name: dithio_count
dtype: int64
- name: enanthoyl_count
dtype: int64
- name: epoxy_count
dtype: int64
- name: ethenyl_count
dtype: int64
- name: ethynyl_count
dtype: int64
- name: ethoxy_count
dtype: int64
- name: ethylene_count
dtype: int64
- name: ethylidene_count
dtype: int64
- name: ethylthio_count
dtype: int64
- name: formamido_count
dtype: int64
- name: furmaroyl_count
dtype: int64
- name: furfuryl_count
dtype: int64
- name: furfurylidene_count
dtype: int64
- name: glutamoyl_count
dtype: int64
- name: glutaryl_count
dtype: int64
- name: glycylamino_count
dtype: int64
- name: glycoloyl_count
dtype: int64
- name: glycyl_count
dtype: int64
- name: glyoxyoyl_count
dtype: int64
- name: guanidino_count
dtype: int64
- name: guanyl_count
dtype: int64
- name: heptadecanoyl_count
dtype: int64
- name: heptanamido_count
dtype: int64
- name: heptanoyl_count
dtype: int64
- name: hexadecanoyl_count
dtype: int64
- name: hexamethylene_count
dtype: int64
- name: hexanedioyl_count
dtype: int64
- name: hippuryl_count
dtype: int64
- name: hydrazino_count
dtype: int64
- name: hydrazo_count
dtype: int64
- name: hydrocinnamoyl_count
dtype: int64
- name: hydroperoxy_count
dtype: int64
- name: hydroxyamino_count
dtype: int64
- name: imino_count
dtype: int64
- name: iodoso_count
dtype: int64
- name: iodyl_count
dtype: int64
- name: isoamyl_count
dtype: int64
- name: isobutenyl_count
dtype: int64
- name: isobutoxy_count
dtype: int64
- name: isobutyl_count
dtype: int64
- name: isobutylidene_count
dtype: int64
- name: isobutyryl_count
dtype: int64
- name: isocyanato_count
dtype: int64
- name: isocyano_count
dtype: int64
- name: isohexyl_count
dtype: int64
- name: isoleucyl_count
dtype: int64
- name: isonitroso_count
dtype: int64
- name: isopentyl_count
dtype: int64
- name: isopentylidene_count
dtype: int64
- name: isopropenyl_count
dtype: int64
- name: isopropoxy_count
dtype: int64
- name: isopropyl_count
dtype: int64
- name: isopropylidene_count
dtype: int64
- name: isothiocynato_count
dtype: int64
- name: isovaleryl_count
dtype: int64
- name: lactoyl_count
dtype: int64
- name: lauroyl_count
dtype: int64
- name: lauryl_count
dtype: int64
- name: leucyl_count
dtype: int64
- name: levulinoyl_count
dtype: int64
- name: malonyl_count
dtype: int64
- name: mandeloyl_count
dtype: int64
- name: mercapto_count
dtype: int64
- name: mesityl_count
dtype: int64
- name: methacryloyl_count
dtype: int64
- name: methallyl_count
dtype: int64
- name: methionyl_count
dtype: int64
- name: methoxy_count
dtype: int64
- name: methylene_count
dtype: int64
- name: methylthio_count
dtype: int64
- name: myristoyl_count
dtype: int64
- name: myristyl_count
dtype: int64
- name: naphthyl_count
dtype: int64
- name: naphthylene_count
dtype: int64
- name: neopentyl_count
dtype: int64
- name: nitramino_count
dtype: int64
- name: nitrosamino_count
dtype: int64
- name: nitroso_count
dtype: int64
- name: nonanoyl_count
dtype: int64
- name: oleoyl_count
dtype: int64
- name: oxalyl_count
dtype: int64
- name: oxo_count
dtype: int64
- name: palmitoyl_count
dtype: int64
- name: pentamethylene_count
dtype: int64
- name: pentyl_count
dtype: int64
- name: tert-pentyl_count
dtype: int64
- name: phenacylidene_count
dtype: int64
- name: phenethyl_count
dtype: int64
- name: phenoxy_count
dtype: int64
- name: phenyl_count
dtype: int64
- name: phenylene_count
dtype: int64
- name: phosphino_count
dtype: int64
- name: phosphinyl_count
dtype: int64
- name: phospho_count
dtype: int64
- name: phosphono_count
dtype: int64
- name: phthaloyl_count
dtype: int64
- name: picryl_count
dtype: int64
- name: pimeloyl_count
dtype: int64
- name: piperidino_count
dtype: int64
- name: pivaloyl_count
dtype: int64
- name: prenyl_count
dtype: int64
- name: propargyl_count
dtype: int64
- name: 1-propenyl_count
dtype: int64
- name: 2-propenyl_count
dtype: int64
- name: propionyl_count
dtype: int64
- name: propoxy_count
dtype: int64
- name: propyl_count
dtype: int64
- name: propylidene_count
dtype: int64
- name: pyrryl_count
dtype: int64
- name: salicyloyl_count
dtype: int64
- name: selenyl_count
dtype: int64
- name: seryl_count
dtype: int64
- name: siloxy_count
dtype: int64
- name: silyl_count
dtype: int64
- name: silyene_count
dtype: int64
- name: sorboyl_count
dtype: int64
- name: stearoyl_count
dtype: int64
- name: stearyl_count
dtype: int64
- name: styryl_count
dtype: int64
- name: suberoyl_count
dtype: int64
- name: succinyl_count
dtype: int64
- name: sulfamino_count
dtype: int64
- name: sulfamoyl_count
dtype: int64
- name: sulfanilyl_count
dtype: int64
- name: sulfeno_count
dtype: int64
- name: sulfhydryl_count
dtype: int64
- name: sulfinyl_count
dtype: int64
- name: sulfo_count
dtype: int64
- name: sulfonyl_count
dtype: int64
- name: terephthaloyl_count
dtype: int64
- name: tetramethylene_count
dtype: int64
- name: thienyl_count
dtype: int64
- name: thiocarbonyl_count
dtype: int64
- name: thiocarboxy_count
dtype: int64
- name: thiocyanato_count
dtype: int64
- name: thionyl_count
dtype: int64
- name: threonyl_count
dtype: int64
- name: toluidino_count
dtype: int64
- name: toluoyl_count
dtype: int64
- name: tolyl_count
dtype: int64
- name: alpha-tolyl_count
dtype: int64
- name: tolylene_count
dtype: int64
- name: tosyl_count
dtype: int64
- name: triazano_count
dtype: int64
- name: trimethylene_count
dtype: int64
- name: valeryl_count
dtype: int64
- name: valyl_count
dtype: int64
- name: vinyl_count
dtype: int64
- name: vinylidene_count
dtype: int64
- name: xylidino_count
dtype: int64
- name: xylyl_count
dtype: int64
- name: xylylene_count
dtype: int64
- name: propiolamide_count
dtype: int64
- name: fumarate ester_count
dtype: int64
- name: allenamide_count
dtype: int64
- name: propiolonitrile_count
dtype: int64
- name: propargylamide_count
dtype: int64
- name: arylsulfonyl bicyclobutane_count
dtype: int64
- name: haloalkane_count
dtype: int64
- name: alpha-halomethyl_count
dtype: int64
- name: alpha-haloamide_count
dtype: int64
- name: alpha-haloester_count
dtype: int64
- name: epoxide_count
dtype: int64
- name: aziridine_count
dtype: int64
- name: nitroalkane_count
dtype: int64
- name: acrylamide_count
dtype: int64
- name: cyanoenone_count
dtype: int64
- name: aldehyde_count
dtype: int64
- name: ketone_count
dtype: int64
- name: nitrile_count
dtype: int64
- name: cyanamide_count
dtype: int64
- name: isothicyanate_count
dtype: int64
- name: sulfone_count
dtype: int64
- name: sulfonyl fluoride_count
dtype: int64
- name: sulfonimidoyl fluoride_count
dtype: int64
- name: aryl fluorosulfate_count
dtype: int64
- name: ester_count
dtype: int64
- name: sulfonamide_count
dtype: int64
- name: 2-carbonyl arylboronic acid_count
dtype: int64
- name: n-methyl isoxazolium_count
dtype: int64
- name: oxaziridine_count
dtype: int64
- name: carboxyl_count
dtype: int64
- name: ether_count
dtype: int64
- name: alkanol_count
dtype: int64
- name: thiol_count
dtype: int64
- name: halogen_count
dtype: int64
- name: amine_count
dtype: int64
- name: amide_count
dtype: int64
- name: num_valence_electrons
dtype: int64
- name: rotable_proportion
dtype: float64
- name: non_rotable_proportion
dtype: float64
- name: num_unspecified_bond
dtype: float64
- name: num_single_bonds
dtype: float64
- name: num_double_bonds
dtype: float64
- name: num_triple_bonds
dtype: float64
- name: num_quadruple_bonds
dtype: float64
- name: num_quintuple_bonds
dtype: float64
- name: num_hextuple_bonds
dtype: float64
- name: num_oneandahalf_bonds
dtype: float64
- name: num_twoandahalf_bonds
dtype: float64
- name: num_threeandahalf_bonds
dtype: float64
- name: num_fourandahalf_bonds
dtype: float64
- name: num_fiveandahalf_bonds
dtype: float64
- name: num_aromatic_bonds
dtype: float64
- name: num_ionic_bonds
dtype: float64
- name: num_hydrogen_bonds
dtype: float64
- name: num_threecenter_bonds
dtype: float64
- name: num_dativeone_bonds
dtype: float64
- name: num_dative_bonds
dtype: float64
- name: num_other_bonds
dtype: float64
- name: num_zero_bonds
dtype: float64
- name: num_bonds
dtype: int64
- name: molecular_formula
dtype: string
- name: monoisotopic_molecular_mass
dtype: float64
- name: carbon_mass
dtype: float64
- name: hydrogen_mass
dtype: float64
- name: nitrogen_mass
dtype: float64
- name: oxygen_mass
dtype: float64
- name: num_carbon_atoms
dtype: int64
- name: num_hydrogen_atoms
dtype: int64
- name: num_nitrogen_atoms
dtype: int64
- name: num_oxygen_atoms
dtype: int64
- name: num_hydrogen_bond_acceptors
dtype: int64
- name: num_hydrogen_bond_donors
dtype: int64
- name: num_lipinski_violations
dtype: int64
- name: inertial_shape_factor
dtype: float64
- name: eccentricity
dtype: float64
- name: asphericity
dtype: float64
- name: npr1_value
dtype: float64
- name: npr2_value
dtype: float64
- name: pmi1_value
dtype: float64
- name: pmi2_value
dtype: float64
- name: pmi3_value
dtype: float64
- name: num_chiral_centers
dtype: int64
- name: representation
dtype: string
splits:
- name: train
num_bytes: 2764418
num_examples: 500
download_size: 488332
dataset_size: 2764418
- config_name: rdkit_feat_1
features:
- name: tert-butyloxycarbonyl_count
dtype: int64
- name: representation_type
dtype: string
- name: trityl_count
dtype: int64
- name: 3,5-dimethoxyphenylisoproxycarbonyl_count
dtype: int64
- name: 2-(4-biphenyl)isopropoxycarbonyl_count
dtype: int64
- name: 2-nitrophenylsulfenyl_count
dtype: int64
- name: boc_count
dtype: int64
- name: trt_count
dtype: int64
- name: ddz_count
dtype: int64
- name: bpoc_count
dtype: int64
- name: nps_count
dtype: int64
- name: 9-fluorenylmethoxycarbonyl_count
dtype: int64
- name: 2-(4-nitrophenylsulfonyl)ethoxycarbonyl_count
dtype: int64
- name: (1,1-dioxobenzo[b]thiophene-2-yl)methyloxycarbonyl_count
dtype: int64
- name: (1,1-dioxonaptho[1,2-b]thiophene-2-yl)methyloxycarbonyl_count
dtype: int64
- name: 1-(4,4-dimethyl-2,6-dioxocyclohex-1-ylidene)-3-methylbutyl_count
dtype: int64
- name: 2,7-di-tert-butyl-fmoc_count
dtype: int64
- name: 2-fluoro-fmoc_count
dtype: int64
- name: 2-monoisooctyl-fmoc_count
dtype: int64
- name: 2,7-diisooctyl-fmoc_count
dtype: int64
- name: tetrachlorophthaloyl_count
dtype: int64
- name: 2-[phenyl(methyl)sulfonio])ethyloxycarbonyltetrafluoroborate_count
dtype: int64
- name: ethanesulfonylethoxycarbonyl_count
dtype: int64
- name: 2-(4-sulfophenylsulfonyl)ethoxycarbonyl_count
dtype: int64
- name: fmoc_count
dtype: int64
- name: nsc_count
dtype: int64
- name: bsmoc_count
dtype: int64
- name: alpha-nsmoc_count
dtype: int64
- name: ivdde_count
dtype: int64
- name: fmoc*_count
dtype: int64
- name: fmoc(fmoc(2f))_count
dtype: int64
- name: mio-fmoc_count
dtype: int64
- name: dio-fmoc_count
dtype: int64
- name: tcp_count
dtype: int64
- name: pms_count
dtype: int64
- name: esc_count
dtype: int64
- name: sps_count
dtype: int64
- name: benzyloxycarbonyl_count
dtype: int64
- name: allyloxycarbonyl_count
dtype: int64
- name: o-nitrobenzenesulfonyl_count
dtype: int64
- name: 2,4-dinitrobenzenesulfonyl_count
dtype: int64
- name: benzothiazole-2-sulfonyl_count
dtype: int64
- name: 2,2,2-trichloroethyloxycarbonyl_count
dtype: int64
- name: dithiasuccinoyl_count
dtype: int64
- name: p-nitrobenzyloxycarbonyl_count
dtype: int64
- name: alpha-azidoacids_count
dtype: int64
- name: proparglyoxycarbonyl_count
dtype: int64
- name: o-nitrobenzylcarbonyl_count
dtype: int64
- name: 4-nitroveratryloxycarbonyl_count
dtype: int64
- name: 2-(2-nitrophenyl)propyloxycarbonyl_count
dtype: int64
- name: 2-(3,4-methylenedioxy-6-nitrophenyl)propyloxycarbonyl_count
dtype: int64
- name: 9-(4-bromophenyl)-9-fluorenyl_count
dtype: int64
- name: azidomethoxycarbonyl_count
dtype: int64
- name: hexafluoroacetone_count
dtype: int64
- name: Z_count
dtype: int64
- name: alloc_count
dtype: int64
- name: o-nbs_count
dtype: int64
- name: d-nbs_count
dtype: int64
- name: bts_count
dtype: int64
- name: troc_count
dtype: int64
- name: dts_count
dtype: int64
- name: pnz_count
dtype: int64
- name: poc_count
dtype: int64
- name: onz_count
dtype: int64
- name: nvoc_count
dtype: int64
- name: nppoc_count
dtype: int64
- name: mnppoc_count
dtype: int64
- name: brphf_count
dtype: int64
- name: azoc_count
dtype: int64
- name: hfa_count
dtype: int64
- name: 2-chlorobenzyloxycarbonyl_count
dtype: int64
- name: 4-methyltrityl_count
dtype: int64
- name: cl-z_count
dtype: int64
- name: mtt_count
dtype: int64
- name: 1-(4,4-dimethyl-2,6-dioxocylohex-1-ylidene)-3-methylbutyl_count
dtype: int64
- name: trifluoroacetyl_count
dtype: int64
- name: 2-(methylsulfonyl)ethoxycarbonyl_count
dtype: int64
- name: tfa_count
dtype: int64
- name: msc_count
dtype: int64
- name: phenyldisulphanylethyloxycarbonyl_count
dtype: int64
- name: 2-pyridyldisulphanylethyloxycarbonyl_count
dtype: int64
- name: phdec_count
dtype: int64
- name: pydec_count
dtype: int64
- name: tert-butyl_count
dtype: int64
- name: 2-chlorotrityl_count
dtype: int64
- name: 2-4-dimethyoxybenzyl_count
dtype: int64
- name: 2-phenylisopropyl_count
dtype: int64
- name: 5-phenyl-3,4-ethylenedioxythenyl_count
dtype: int64
- name: bu_count
dtype: int64
- name: 2-cl-trt_count
dtype: int64
- name: dmb_count
dtype: int64
- name: 2-ph-pr_count
dtype: int64
- name: phenyl-edotn_count
dtype: int64
- name: 9-fluorenylmethyl_count
dtype: int64
- name: 4-(N-[1-(4,4-dimethyl-2,6-dioxocylocheylidene)-3-methylbutyl]-amino)benzyl_count
dtype: int64
- name: methyl_count
dtype: int64
- name: ethyl_count
dtype: int64
- name: carbamoylmethyl_count
dtype: int64
- name: fm_count
dtype: int64
- name: dmab_count
dtype: int64
- name: me_count
dtype: int64
- name: et_count
dtype: int64
- name: cam_count
dtype: int64
- name: allyl_count
dtype: int64
- name: benzyl_count
dtype: int64
- name: phenacyl_count
dtype: int64
- name: p-nitrobenzyl_count
dtype: int64
- name: 2-trimethylsilyethyl_count
dtype: int64
- name: (2-phenyl-2-trimethylsilyl)ethyl_count
dtype: int64
- name: 2-(trimethylsilyl)isopropyl_count
dtype: int64
- name: 2,2,2-trichloroethyl_count
dtype: int64
- name: p-hydroxyphenacyl_count
dtype: int64
- name: 4,5-dimethyoxy-2-nitrobenzyl_count
dtype: int64
- name: 1,1-dimethylallyl_count
dtype: int64
- name: pentaaminecobalt_III_count
dtype: int64
- name: al_count
dtype: int64
- name: bn_count
dtype: int64
- name: pac_count
dtype: int64
- name: pnb_count
dtype: int64
- name: tmse_count
dtype: int64
- name: ptmse_count
dtype: int64
- name: tmsi_count
dtype: int64
- name: tce_count
dtype: int64
- name: php_count
dtype: int64
- name: dmnb_count
dtype: int64
- name: dma_count
dtype: int64
- name: cyclohexyl_count
dtype: int64
- name: b-menthyl_count
dtype: int64
- name: b-3-methylpent-3-yl_count
dtype: int64
- name: 4-(3,6,9-trioxadecyl)oxybenzyl_count
dtype: int64
- name: chx_count
dtype: int64
- name: men_count
dtype: int64
- name: mpe_count
dtype: int64
- name: tegbz_count
dtype: int64
- name: 9-fluoroenylmethyl_count
dtype: int64
- name: 4-(N-[1-(4,4-dimethyl-2,6-dioxocyclohexylidene)-3-methyl-butyl]-amino)benzyl_count
dtype: int64
- name: trimethylsilylethyl_count
dtype: int64
- name: 4,5-dimethoxy-2-nitrobenzyloxycarbonyl_count
dtype: int64
- name: pseudoprolines_count
dtype: int64
- name: 2-hydroxy-4-methoxybenzyl_count
dtype: int64
- name: 2,4-dimethoxybenzyl_count
dtype: int64
- name: 2,4,6-trimethoxybenzyl_count
dtype: int64
- name: 1-methyl-3-indolylmethyl_count
dtype: int64
- name: 3,4-ethylene-dioxy-2-thenyl_count
dtype: int64
- name: hmb_count
dtype: int64
- name: tmob_count
dtype: int64
- name: mim_count
dtype: int64
- name: edot_count
dtype: int64
- name: 4-methoxy-2-nitro-benzyl_count
dtype: int64
- name: (6-hydroxy-3-oxido-1,3-benz[d]oxathiol-5-yl)methyl_count
dtype: int64
- name: 2-hydroxy-4-methoxy-5-(methylsulfinyl)benzyl_count
dtype: int64
- name: n-boc-n-methyl[2-(methylamino)ethyl]carbamoyl-hmb_count
dtype: int64
- name: 9-xanthenyl_count
dtype: int64
- name: cyclopropyldimethylcarbinyl_count
dtype: int64
- name: 4,4-dimethoxybenzhydryl_count
dtype: int64
- name: xan_count
dtype: int64
- name: cpd_count
dtype: int64
- name: mbh_count
dtype: int64
- name: p-toluenesulfonyl_count
dtype: int64
- name: 2,2,5,7,8-pentamethylchroman-6-sulfonyl_count
dtype: int64
- name: 2,2,4,6,7-pentamethyl-2,3-dihydrobenzofuran-5-sulfonyl_count
dtype: int64
- name: mesityl-2-sulfonyl_count
dtype: int64
- name: 4-methoxy-2,3,6-trimethylphenylsulfonyl_count
dtype: int64
- name: 1,2-dimethylindole-3-sulfonyl_count
dtype: int64
- name: w,w-bis-tert-butyloxycarbonyl_count
dtype: int64
- name: 5-dibenzosuberenyl_count
dtype: int64
- name: 5-dibenzosuberyl_count
dtype: int64
- name: 2-methoxy-5-dibenzosuberyl_count
dtype: int64
- name: nitro_count
dtype: int64
- name: tos_count
dtype: int64
- name: pmc_count
dtype: int64
- name: pbf_count
dtype: int64
- name: mts_count
dtype: int64
- name: mtr_count
dtype: int64
- name: mis_count
dtype: int64
- name: bis-boc_count
dtype: int64
- name: suben_count
dtype: int64
- name: sub_count
dtype: int64
- name: mesub_count
dtype: int64
- name: no2_count
dtype: int64
- name: w,w-bis-benzyloxycarbonyl_count
dtype: int64
- name: w,w-bis-allyloxycarbonyl_count
dtype: int64
- name: z-small_count
dtype: int64
- name: p-methylbenzyl_count
dtype: int64
- name: p-methoxybenzyl_count
dtype: int64
- name: monomethoxytrityl_count
dtype: int64
- name: trimethoxybenzyl_count
dtype: int64
- name: 2,2,4,6,7-pentamethyl-5-dihydrobenzofuranylmethyl_count
dtype: int64
- name: 1-adamantyl_count
dtype: int64
- name: meb_count
dtype: int64
- name: mob_count
dtype: int64
- name: mmt_count
dtype: int64
- name: pmbf_count
dtype: int64
- name: 1-ada_count
dtype: int64
- name: 2-(2,4-dinitrophenyl)ethyl_count
dtype: int64
- name: 9-fluororenylmethoxycarbonyl_count
dtype: int64
- name: dnpe_count
dtype: int64
- name: acetamidomethyl_count
dtype: int64
- name: phenylacetamidomethyl_count
dtype: int64
- name: 5-tert-butylmercapto_count
dtype: int64
- name: 3-nitro-2-pyridinesulfenyl_count
dtype: int64
- name: 2-pyridinesulfenyl_count
dtype: int64
- name: N-allyloxycarbonyl-N-[2,3,5,6-tetrafluoro-4-(phenylthio)phenyl]]aminomethyl_count
dtype: int64
- name: o-nitrobenzyl_count
dtype: int64
- name: 4-picolyl_count
dtype: int64
- name: ninhydrin_count
dtype: int64
- name: acm_count
dtype: int64
- name: phacm_count
dtype: int64
- name: sbu_count
dtype: int64
- name: npys_count
dtype: int64
- name: s-pyr_count
dtype: int64
- name: fsam_count
dtype: int64
- name: onb_count
dtype: int64
- name: nin_count
dtype: int64
- name: n-tosyl_count
dtype: int64
- name: n-trityl_count
dtype: int64
- name: n-monomethoxytrityl_count
dtype: int64
- name: n-methyltrityl_count
dtype: int64
- name: n-tert-butyloxycarbonyl_count
dtype: int64
- name: n-2,4-dimethylpent-3-yloxycarbonyl_count
dtype: int64
- name: n-benzyloxymethyl_count
dtype: int64
- name: n-tert-butoxymethyl_count
dtype: int64
- name: ntos_count
dtype: int64
- name: ntrt_count
dtype: int64
- name: nmtt_count
dtype: int64
- name: nmmt_count
dtype: int64
- name: nboc_count
dtype: int64
- name: ndoc_count
dtype: int64
- name: nbom_count
dtype: int64
- name: nbum_count
dtype: int64
- name: N-9-fluorenylmethoxycarbonyl_count
dtype: int64
- name: N-2,6-dimethoxybenzoyl_count
dtype: int64
- name: dmbz_count
dtype: int64
- name: N-2,4-dinitrophenyl_count
dtype: int64
- name: dnp_count
dtype: int64
- name: cyclohexyl;_count
dtype: int64
- name: tert-butyldimethylsilyl_count
dtype: int64
- name: tbdms_count
dtype: int64
- name: tert-butyldiphenylsilyl_count
dtype: int64
- name: propargyloxycarbonyl_count
dtype: int64
- name: tbdps_count
dtype: int64
- name: 2,6-dichlorobenzyl_count
dtype: int64
- name: 2-bromobenzyl_count
dtype: int64
- name: 2-bromobenzyloxycarbonyl_count
dtype: int64
- name: 3-pentyl_count
dtype: int64
- name: dcb_count
dtype: int64
- name: brbn_count
dtype: int64
- name: brz_count
dtype: int64
- name: pen_count
dtype: int64
- name: tegb_count
dtype: int64
- name: boc-n-methyl-n-[2-(methylamino)ethyl]carbamoyl_count
dtype: int64
- name: boc-nmec_count
dtype: int64
- name: formyl_count
dtype: int64
- name: cyclohexyloxycarbonyl_count
dtype: int64
- name: for_count
dtype: int64
- name: hoc_count
dtype: int64
- name: cyclopropane_count
dtype: int64
- name: spiropentane_count
dtype: int64
- name: cyclobutane_count
dtype: int64
- name: cyclopentane_count
dtype: int64
- name: furan_count
dtype: int64
- name: thiophene_count
dtype: int64
- name: pyrrole_count
dtype: int64
- name: 2H-pyrrole_count
dtype: int64
- name: 3H-pyrrole_count
dtype: int64
- name: pyrazole_count
dtype: int64
- name: 2H-imidazole_count
dtype: int64
- name: 1,2,3-triazole_count
dtype: int64
- name: 1,2,4-triazole_count
dtype: int64
- name: 1,2-dithiole_count
dtype: int64
- name: 1,3-dithiole_count
dtype: int64
- name: 3H-1,2-oxathiole_count
dtype: int64
- name: isoxazole_count
dtype: int64
- name: oxazole_count
dtype: int64
- name: thiazole_count
dtype: int64
- name: isothiazole_count
dtype: int64
- name: 1,2,3-oxadiazole_count
dtype: int64
- name: 1,2,4-oxadiazole_count
dtype: int64
- name: 1,2,5-oxadiazole_count
dtype: int64
- name: 1,3,4-oxadiazole_count
dtype: int64
- name: 1,2,3,4-oxatriazole_count
dtype: int64
- name: 1,2,3,5-oxatriazole_count
dtype: int64
- name: 3H-1,2,3-dioxazole_count
dtype: int64
- name: 1,2,4-dioxazole_count
dtype: int64
- name: 1,3,2-dioxazole_count
dtype: int64
- name: 1,3,4-dioxazole_count
dtype: int64
- name: 5H-1,2,5-oxathiazole_count
dtype: int64
- name: 1,3-oxathiole_count
dtype: int64
- name: benzene_count
dtype: int64
- name: cyclohexane_count
dtype: int64
- name: 2H-pyran_count
dtype: int64
- name: 4H-pyran_count
dtype: int64
- name: 2H-pyran-2-one_count
dtype: int64
- name: 4H-pyran-4-one_count
dtype: int64
- name: 1,2-dioxin_count
dtype: int64
- name: 1,3-dioxin_count
dtype: int64
- name: pyridine_count
dtype: int64
- name: pyridazine_count
dtype: int64
- name: pyrimidine_count
dtype: int64
- name: pyrazine_count
dtype: int64
- name: piperazine_count
dtype: int64
- name: 1,3,5-triazine_count
dtype: int64
- name: 1,2,4-triazine_count
dtype: int64
- name: 1,2,3-triazine_count
dtype: int64
- name: 4H-1,2-Oxazine_count
dtype: int64
- name: 2H-1,3-Oxazine_count
dtype: int64
- name: 6H-1,3-Oxazine_count
dtype: int64
- name: 6H-1,2-Oxazine_count
dtype: int64
- name: 1,4-Oxazine_count
dtype: int64
- name: 2H-1,2-Oxazine_count
dtype: int64
- name: 4H-1,4-Oxazine_count
dtype: int64
- name: 1,2,5-Oxathiazine_count
dtype: int64
- name: 1,2,6-Oxathiazine_count
dtype: int64
- name: 1,2,4-Oxadiazine_count
dtype: int64
- name: 1,3,5-Oxadiazine_count
dtype: int64
- name: morpholine_count
dtype: int64
- name: azepine_count
dtype: int64
- name: oxepin_count
dtype: int64
- name: thiepin_count
dtype: int64
- name: 4H-1,2-diazepine_count
dtype: int64
- name: indene_count
dtype: int64
- name: 2H-indene_count
dtype: int64
- name: benzofuran_count
dtype: int64
- name: isobenzofuran_count
dtype: int64
- name: benzo[b]thiophene_count
dtype: int64
- name: benzo[c]thiophene_count
dtype: int64
- name: indole_count
dtype: int64
- name: 3H-indole_count
dtype: int64
- name: 1H-indole_count
dtype: int64
- name: cyclopenta[b]pyridine_count
dtype: int64
- name: pyrano[3,4-b]-pyrrole_count
dtype: int64
- name: indazole_count
dtype: int64
- name: benzisoxazole_count
dtype: int64
- name: benzoxazole_count
dtype: int64
- name: 2,1-benzisoxazole_count
dtype: int64
- name: naphthalene_count
dtype: int64
- name: 1,2,3,4-tetrahydronaphthalene_count
dtype: int64
- name: octahydronaphthalene_count
dtype: int64
- name: 2H-1-benzopyran_count
dtype: int64
- name: 2H-1-benzopyran-2-one_count
dtype: int64
- name: 4H-1-benzopyran-4-one_count
dtype: int64
- name: 1H-2-benzopyran-1-one_count
dtype: int64
- name: 3H-2-benzopyran-1-one_count
dtype: int64
- name: quinoline_count
dtype: int64
- name: isoquinoline_count
dtype: int64
- name: cinnoline_count
dtype: int64
- name: quinazoline_count
dtype: int64
- name: 1,8-napthyhridine_count
dtype: int64
- name: 1,7-napththyridine_count
dtype: int64
- name: 1,5-napththridine_count
dtype: int64
- name: 1,6-napthyridine_count
dtype: int64
- name: 2H-1,3-benzoxazine_count
dtype: int64
- name: 2H-1,4-benzoxazine_count
dtype: int64
- name: 1H-2,3-benzoxazine_count
dtype: int64
- name: 4H-3,1-benzoxazine_count
dtype: int64
- name: 2H-1,2-benzoxazine_count
dtype: int64
- name: 4H-1,3-benzoxazine_count
dtype: int64
- name: anthracene_count
dtype: int64
- name: phenanthrene_count
dtype: int64
- name: phenalene_count
dtype: int64
- name: fluorene_count
dtype: int64
- name: carbazole_count
dtype: int64
- name: xanthene_count
dtype: int64
- name: acridine_count
dtype: int64
- name: norpinane_count
dtype: int64
- name: 7H-purine_count
dtype: int64
- name: steroid_ring_system_count
dtype: int64
- name: imidazole_count
dtype: int64
- name: thiazol-2-amine_count
dtype: int64
- name: tetrazole_count
dtype: int64
- name: cytosine_count
dtype: int64
- name: adenine_count
dtype: int64
- name: 5-methylindole_count
dtype: int64
- name: isocaffeine_count
dtype: int64
- name: tetrazolethiol_count
dtype: int64
- name: 3-methylisoxazole_count
dtype: int64
- name: 1-methylimidazole_count
dtype: int64
- name: 2-methylimidazole_count
dtype: int64
- name: guanine_count
dtype: int64
- name: tosufloxacin_count
dtype: int64
- name: acetamido_count
dtype: int64
- name: acetoacetyl_count
dtype: int64
- name: acetyl_count
dtype: int64
- name: acryloyl_count
dtype: int64
- name: alanyl_count
dtype: int64
- name: beta-alanyl_count
dtype: int64
- name: allylidene_count
dtype: int64
- name: amidino_count
dtype: int64
- name: amino_count
dtype: int64
- name: amyl_count
dtype: int64
- name: anilino_count
dtype: int64
- name: anisidino_count
dtype: int64
- name: anthranoyl_count
dtype: int64
- name: arsino_count
dtype: int64
- name: azelaoyl_count
dtype: int64
- name: azido_count
dtype: int64
- name: azo_count
dtype: int64
- name: azoxy_count
dtype: int64
- name: benzal_count
dtype: int64
- name: benzamido_count
dtype: int64
- name: benzhydrol_count
dtype: int64
- name: benzoxy_count
dtype: int64
- name: benzoyl_count
dtype: int64
- name: benzylidene_count
dtype: int64
- name: benzylidyne_count
dtype: int64
- name: biphenylyl_count
dtype: int64
- name: biphenylene_count
dtype: int64
- name: butoxy_count
dtype: int64
- name: sec-butoxy_count
dtype: int64
- name: tert-butoxy_count
dtype: int64
- name: butyl_count
dtype: int64
- name: sec-butyl_count
dtype: int64
- name: butyryl_count
dtype: int64
- name: caproyl_count
dtype: int64
- name: capryl_count
dtype: int64
- name: capryloyl_count
dtype: int64
- name: carbamido_count
dtype: int64
- name: carbamoyl_count
dtype: int64
- name: carbamyl_count
dtype: int64
- name: carbazoyl_count
dtype: int64
- name: carbethoxy_count
dtype: int64
- name: carbonyl_count
dtype: int64
- name: carboxy_count
dtype: int64
- name: cetyl_count
dtype: int64
- name: chloroformyl_count
dtype: int64
- name: cinnamoyl_count
dtype: int64
- name: cinnamyl_count
dtype: int64
- name: cinnamylidene_count
dtype: int64
- name: cresyl_count
dtype: int64
- name: crotonoyl_count
dtype: int64
- name: crotyl_count
dtype: int64
- name: cyanamido_count
dtype: int64
- name: cyanato_count
dtype: int64
- name: cyano_count
dtype: int64
- name: decanedioyl_count
dtype: int64
- name: decanoyl_count
dtype: int64
- name: diazo_count
dtype: int64
- name: diazoamino_count
dtype: int64
- name: disilanyl_count
dtype: int64
- name: disiloxanyloxy_count
dtype: int64
- name: disulfinyl_count
dtype: int64
- name: dithio_count
dtype: int64
- name: enanthoyl_count
dtype: int64
- name: epoxy_count
dtype: int64
- name: ethenyl_count
dtype: int64
- name: ethynyl_count
dtype: int64
- name: ethoxy_count
dtype: int64
- name: ethylene_count
dtype: int64
- name: ethylidene_count
dtype: int64
- name: ethylthio_count
dtype: int64
- name: formamido_count
dtype: int64
- name: furmaroyl_count
dtype: int64
- name: furfuryl_count
dtype: int64
- name: furfurylidene_count
dtype: int64
- name: glutamoyl_count
dtype: int64
- name: glutaryl_count
dtype: int64
- name: glycylamino_count
dtype: int64
- name: glycoloyl_count
dtype: int64
- name: glycyl_count
dtype: int64
- name: glyoxyoyl_count
dtype: int64
- name: guanidino_count
dtype: int64
- name: guanyl_count
dtype: int64
- name: heptadecanoyl_count
dtype: int64
- name: heptanamido_count
dtype: int64
- name: heptanoyl_count
dtype: int64
- name: hexadecanoyl_count
dtype: int64
- name: hexamethylene_count
dtype: int64
- name: hexanedioyl_count
dtype: int64
- name: hippuryl_count
dtype: int64
- name: hydrazino_count
dtype: int64
- name: hydrazo_count
dtype: int64
- name: hydrocinnamoyl_count
dtype: int64
- name: hydroperoxy_count
dtype: int64
- name: hydroxyamino_count
dtype: int64
- name: imino_count
dtype: int64
- name: iodoso_count
dtype: int64
- name: iodyl_count
dtype: int64
- name: isoamyl_count
dtype: int64
- name: isobutenyl_count
dtype: int64
- name: isobutoxy_count
dtype: int64
- name: isobutyl_count
dtype: int64
- name: isobutylidene_count
dtype: int64
- name: isobutyryl_count
dtype: int64
- name: isocyanato_count
dtype: int64
- name: isocyano_count
dtype: int64
- name: isohexyl_count
dtype: int64
- name: isoleucyl_count
dtype: int64
- name: isonitroso_count
dtype: int64
- name: isopentyl_count
dtype: int64
- name: isopentylidene_count
dtype: int64
- name: isopropenyl_count
dtype: int64
- name: isopropoxy_count
dtype: int64
- name: isopropyl_count
dtype: int64
- name: isopropylidene_count
dtype: int64
- name: isothiocynato_count
dtype: int64
- name: isovaleryl_count
dtype: int64
- name: lactoyl_count
dtype: int64
- name: lauroyl_count
dtype: int64
- name: lauryl_count
dtype: int64
- name: leucyl_count
dtype: int64
- name: levulinoyl_count
dtype: int64
- name: malonyl_count
dtype: int64
- name: mandeloyl_count
dtype: int64
- name: mercapto_count
dtype: int64
- name: mesityl_count
dtype: int64
- name: methacryloyl_count
dtype: int64
- name: methallyl_count
dtype: int64
- name: methionyl_count
dtype: int64
- name: methoxy_count
dtype: int64
- name: methylene_count
dtype: int64
- name: methylthio_count
dtype: int64
- name: myristoyl_count
dtype: int64
- name: myristyl_count
dtype: int64
- name: naphthyl_count
dtype: int64
- name: naphthylene_count
dtype: int64
- name: neopentyl_count
dtype: int64
- name: nitramino_count
dtype: int64
- name: nitrosamino_count
dtype: int64
- name: nitroso_count
dtype: int64
- name: nonanoyl_count
dtype: int64
- name: oleoyl_count
dtype: int64
- name: oxalyl_count
dtype: int64
- name: oxo_count
dtype: int64
- name: palmitoyl_count
dtype: int64
- name: pentamethylene_count
dtype: int64
- name: pentyl_count
dtype: int64
- name: tert-pentyl_count
dtype: int64
- name: phenacylidene_count
dtype: int64
- name: phenethyl_count
dtype: int64
- name: phenoxy_count
dtype: int64
- name: phenyl_count
dtype: int64
- name: phenylene_count
dtype: int64
- name: phosphino_count
dtype: int64
- name: phosphinyl_count
dtype: int64
- name: phospho_count
dtype: int64
- name: phosphono_count
dtype: int64
- name: phthaloyl_count
dtype: int64
- name: picryl_count
dtype: int64
- name: pimeloyl_count
dtype: int64
- name: piperidino_count
dtype: int64
- name: pivaloyl_count
dtype: int64
- name: prenyl_count
dtype: int64
- name: propargyl_count
dtype: int64
- name: 1-propenyl_count
dtype: int64
- name: 2-propenyl_count
dtype: int64
- name: propionyl_count
dtype: int64
- name: propoxy_count
dtype: int64
- name: propyl_count
dtype: int64
- name: propylidene_count
dtype: int64
- name: pyrryl_count
dtype: int64
- name: salicyloyl_count
dtype: int64
- name: selenyl_count
dtype: int64
- name: seryl_count
dtype: int64
- name: siloxy_count
dtype: int64
- name: silyl_count
dtype: int64
- name: silyene_count
dtype: int64
- name: sorboyl_count
dtype: int64
- name: stearoyl_count
dtype: int64
- name: stearyl_count
dtype: int64
- name: styryl_count
dtype: int64
- name: suberoyl_count
dtype: int64
- name: succinyl_count
dtype: int64
- name: sulfamino_count
dtype: int64
- name: sulfamoyl_count
dtype: int64
- name: sulfanilyl_count
dtype: int64
- name: sulfeno_count
dtype: int64
- name: sulfhydryl_count
dtype: int64
- name: sulfinyl_count
dtype: int64
- name: sulfo_count
dtype: int64
- name: sulfonyl_count
dtype: int64
- name: terephthaloyl_count
dtype: int64
- name: tetramethylene_count
dtype: int64
- name: thienyl_count
dtype: int64
- name: thiocarbonyl_count
dtype: int64
- name: thiocarboxy_count
dtype: int64
- name: thiocyanato_count
dtype: int64
- name: thionyl_count
dtype: int64
- name: threonyl_count
dtype: int64
- name: toluidino_count
dtype: int64
- name: toluoyl_count
dtype: int64
- name: tolyl_count
dtype: int64
- name: alpha-tolyl_count
dtype: int64
- name: tolylene_count
dtype: int64
- name: tosyl_count
dtype: int64
- name: triazano_count
dtype: int64
- name: trimethylene_count
dtype: int64
- name: valeryl_count
dtype: int64
- name: valyl_count
dtype: int64
- name: vinyl_count
dtype: int64
- name: vinylidene_count
dtype: int64
- name: xylidino_count
dtype: int64
- name: xylyl_count
dtype: int64
- name: xylylene_count
dtype: int64
- name: propiolamide_count
dtype: int64
- name: fumarate ester_count
dtype: int64
- name: allenamide_count
dtype: int64
- name: propiolonitrile_count
dtype: int64
- name: propargylamide_count
dtype: int64
- name: arylsulfonyl bicyclobutane_count
dtype: int64
- name: haloalkane_count
dtype: int64
- name: alpha-halomethyl_count
dtype: int64
- name: alpha-haloamide_count
dtype: int64
- name: alpha-haloester_count
dtype: int64
- name: epoxide_count
dtype: int64
- name: aziridine_count
dtype: int64
- name: nitroalkane_count
dtype: int64
- name: acrylamide_count
dtype: int64
- name: cyanoenone_count
dtype: int64
- name: aldehyde_count
dtype: int64
- name: ketone_count
dtype: int64
- name: nitrile_count
dtype: int64
- name: cyanamide_count
dtype: int64
- name: isothicyanate_count
dtype: int64
- name: sulfone_count
dtype: int64
- name: sulfonyl fluoride_count
dtype: int64
- name: sulfonimidoyl fluoride_count
dtype: int64
- name: aryl fluorosulfate_count
dtype: int64
- name: ester_count
dtype: int64
- name: sulfonamide_count
dtype: int64
- name: 2-carbonyl arylboronic acid_count
dtype: int64
- name: n-methyl isoxazolium_count
dtype: int64
- name: oxaziridine_count
dtype: int64
- name: carboxyl_count
dtype: int64
- name: ether_count
dtype: int64
- name: alkanol_count
dtype: int64
- name: thiol_count
dtype: int64
- name: halogen_count
dtype: int64
- name: amine_count
dtype: int64
- name: amide_count
dtype: int64
- name: num_valence_electrons
dtype: int64
- name: rotable_proportion
dtype: float64
- name: non_rotable_proportion
dtype: float64
- name: num_unspecified_bond
dtype: float64
- name: num_single_bonds
dtype: float64
- name: num_double_bonds
dtype: float64
- name: num_triple_bonds
dtype: float64
- name: num_quadruple_bonds
dtype: float64
- name: num_quintuple_bonds
dtype: float64
- name: num_hextuple_bonds
dtype: float64
- name: num_oneandahalf_bonds
dtype: float64
- name: num_twoandahalf_bonds
dtype: float64
- name: num_threeandahalf_bonds
dtype: float64
- name: num_fourandahalf_bonds
dtype: float64
- name: num_fiveandahalf_bonds
dtype: float64
- name: num_aromatic_bonds
dtype: float64
- name: num_ionic_bonds
dtype: float64
- name: num_hydrogen_bonds
dtype: float64
- name: num_threecenter_bonds
dtype: float64
- name: num_dativeone_bonds
dtype: float64
- name: num_dative_bonds
dtype: float64
- name: num_other_bonds
dtype: float64
- name: num_zero_bonds
dtype: float64
- name: num_bonds
dtype: int64
- name: molecular_formula
dtype: string
- name: monoisotopic_molecular_mass
dtype: float64
- name: carbon_mass
dtype: float64
- name: hydrogen_mass
dtype: float64
- name: nitrogen_mass
dtype: float64
- name: oxygen_mass
dtype: float64
- name: num_carbon_atoms
dtype: int64
- name: num_hydrogen_atoms
dtype: int64
- name: num_nitrogen_atoms
dtype: int64
- name: num_oxygen_atoms
dtype: int64
- name: num_hydrogen_bond_acceptors
dtype: int64
- name: num_hydrogen_bond_donors
dtype: int64
- name: num_lipinski_violations
dtype: int64
- name: inertial_shape_factor
dtype: float64
- name: eccentricity
dtype: float64
- name: asphericity
dtype: float64
- name: npr1_value
dtype: float64
- name: npr2_value
dtype: float64
- name: pmi1_value
dtype: float64
- name: pmi2_value
dtype: float64
- name: pmi3_value
dtype: float64
- name: num_chiral_centers
dtype: int64
- name: representation
dtype: string
splits:
- name: train
num_bytes: 2756268
num_examples: 500
download_size: 484582
dataset_size: 2756268
- config_name: rdkit_feat_10
features:
- name: tert-butyloxycarbonyl_count
dtype: int64
- name: representation_type
dtype: string
- name: trityl_count
dtype: int64
- name: 3,5-dimethoxyphenylisoproxycarbonyl_count
dtype: int64
- name: 2-(4-biphenyl)isopropoxycarbonyl_count
dtype: int64
- name: 2-nitrophenylsulfenyl_count
dtype: int64
- name: boc_count
dtype: int64
- name: trt_count
dtype: int64
- name: ddz_count
dtype: int64
- name: bpoc_count
dtype: int64
- name: nps_count
dtype: int64
- name: 9-fluorenylmethoxycarbonyl_count
dtype: int64
- name: 2-(4-nitrophenylsulfonyl)ethoxycarbonyl_count
dtype: int64
- name: (1,1-dioxobenzo[b]thiophene-2-yl)methyloxycarbonyl_count
dtype: int64
- name: (1,1-dioxonaptho[1,2-b]thiophene-2-yl)methyloxycarbonyl_count
dtype: int64
- name: 1-(4,4-dimethyl-2,6-dioxocyclohex-1-ylidene)-3-methylbutyl_count
dtype: int64
- name: 2,7-di-tert-butyl-fmoc_count
dtype: int64
- name: 2-fluoro-fmoc_count
dtype: int64
- name: 2-monoisooctyl-fmoc_count
dtype: int64
- name: 2,7-diisooctyl-fmoc_count
dtype: int64
- name: tetrachlorophthaloyl_count
dtype: int64
- name: 2-[phenyl(methyl)sulfonio])ethyloxycarbonyltetrafluoroborate_count
dtype: int64
- name: ethanesulfonylethoxycarbonyl_count
dtype: int64
- name: 2-(4-sulfophenylsulfonyl)ethoxycarbonyl_count
dtype: int64
- name: fmoc_count
dtype: int64
- name: nsc_count
dtype: int64
- name: bsmoc_count
dtype: int64
- name: alpha-nsmoc_count
dtype: int64
- name: ivdde_count
dtype: int64
- name: fmoc*_count
dtype: int64
- name: fmoc(fmoc(2f))_count
dtype: int64
- name: mio-fmoc_count
dtype: int64
- name: dio-fmoc_count
dtype: int64
- name: tcp_count
dtype: int64
- name: pms_count
dtype: int64
- name: esc_count
dtype: int64
- name: sps_count
dtype: int64
- name: benzyloxycarbonyl_count
dtype: int64
- name: allyloxycarbonyl_count
dtype: int64
- name: o-nitrobenzenesulfonyl_count
dtype: int64
- name: 2,4-dinitrobenzenesulfonyl_count
dtype: int64
- name: benzothiazole-2-sulfonyl_count
dtype: int64
- name: 2,2,2-trichloroethyloxycarbonyl_count
dtype: int64
- name: dithiasuccinoyl_count
dtype: int64
- name: p-nitrobenzyloxycarbonyl_count
dtype: int64
- name: alpha-azidoacids_count
dtype: int64
- name: proparglyoxycarbonyl_count
dtype: int64
- name: o-nitrobenzylcarbonyl_count
dtype: int64
- name: 4-nitroveratryloxycarbonyl_count
dtype: int64
- name: 2-(2-nitrophenyl)propyloxycarbonyl_count
dtype: int64
- name: 2-(3,4-methylenedioxy-6-nitrophenyl)propyloxycarbonyl_count
dtype: int64
- name: 9-(4-bromophenyl)-9-fluorenyl_count
dtype: int64
- name: azidomethoxycarbonyl_count
dtype: int64
- name: hexafluoroacetone_count
dtype: int64
- name: Z_count
dtype: int64
- name: alloc_count
dtype: int64
- name: o-nbs_count
dtype: int64
- name: d-nbs_count
dtype: int64
- name: bts_count
dtype: int64
- name: troc_count
dtype: int64
- name: dts_count
dtype: int64
- name: pnz_count
dtype: int64
- name: poc_count
dtype: int64
- name: onz_count
dtype: int64
- name: nvoc_count
dtype: int64
- name: nppoc_count
dtype: int64
- name: mnppoc_count
dtype: int64
- name: brphf_count
dtype: int64
- name: azoc_count
dtype: int64
- name: hfa_count
dtype: int64
- name: 2-chlorobenzyloxycarbonyl_count
dtype: int64
- name: 4-methyltrityl_count
dtype: int64
- name: cl-z_count
dtype: int64
- name: mtt_count
dtype: int64
- name: 1-(4,4-dimethyl-2,6-dioxocylohex-1-ylidene)-3-methylbutyl_count
dtype: int64
- name: trifluoroacetyl_count
dtype: int64
- name: 2-(methylsulfonyl)ethoxycarbonyl_count
dtype: int64
- name: tfa_count
dtype: int64
- name: msc_count
dtype: int64
- name: phenyldisulphanylethyloxycarbonyl_count
dtype: int64
- name: 2-pyridyldisulphanylethyloxycarbonyl_count
dtype: int64
- name: phdec_count
dtype: int64
- name: pydec_count
dtype: int64
- name: tert-butyl_count
dtype: int64
- name: 2-chlorotrityl_count
dtype: int64
- name: 2-4-dimethyoxybenzyl_count
dtype: int64
- name: 2-phenylisopropyl_count
dtype: int64
- name: 5-phenyl-3,4-ethylenedioxythenyl_count
dtype: int64
- name: bu_count
dtype: int64
- name: 2-cl-trt_count
dtype: int64
- name: dmb_count
dtype: int64
- name: 2-ph-pr_count
dtype: int64
- name: phenyl-edotn_count
dtype: int64
- name: 9-fluorenylmethyl_count
dtype: int64
- name: 4-(N-[1-(4,4-dimethyl-2,6-dioxocylocheylidene)-3-methylbutyl]-amino)benzyl_count
dtype: int64
- name: methyl_count
dtype: int64
- name: ethyl_count
dtype: int64
- name: carbamoylmethyl_count
dtype: int64
- name: fm_count
dtype: int64
- name: dmab_count
dtype: int64
- name: me_count
dtype: int64
- name: et_count
dtype: int64
- name: cam_count
dtype: int64
- name: allyl_count
dtype: int64
- name: benzyl_count
dtype: int64
- name: phenacyl_count
dtype: int64
- name: p-nitrobenzyl_count
dtype: int64
- name: 2-trimethylsilyethyl_count
dtype: int64
- name: (2-phenyl-2-trimethylsilyl)ethyl_count
dtype: int64
- name: 2-(trimethylsilyl)isopropyl_count
dtype: int64
- name: 2,2,2-trichloroethyl_count
dtype: int64
- name: p-hydroxyphenacyl_count
dtype: int64
- name: 4,5-dimethyoxy-2-nitrobenzyl_count
dtype: int64
- name: 1,1-dimethylallyl_count
dtype: int64
- name: pentaaminecobalt_III_count
dtype: int64
- name: al_count
dtype: int64
- name: bn_count
dtype: int64
- name: pac_count
dtype: int64
- name: pnb_count
dtype: int64
- name: tmse_count
dtype: int64
- name: ptmse_count
dtype: int64
- name: tmsi_count
dtype: int64
- name: tce_count
dtype: int64
- name: php_count
dtype: int64
- name: dmnb_count
dtype: int64
- name: dma_count
dtype: int64
- name: cyclohexyl_count
dtype: int64
- name: b-menthyl_count
dtype: int64
- name: b-3-methylpent-3-yl_count
dtype: int64
- name: 4-(3,6,9-trioxadecyl)oxybenzyl_count
dtype: int64
- name: chx_count
dtype: int64
- name: men_count
dtype: int64
- name: mpe_count
dtype: int64
- name: tegbz_count
dtype: int64
- name: 9-fluoroenylmethyl_count
dtype: int64
- name: 4-(N-[1-(4,4-dimethyl-2,6-dioxocyclohexylidene)-3-methyl-butyl]-amino)benzyl_count
dtype: int64
- name: trimethylsilylethyl_count
dtype: int64
- name: 4,5-dimethoxy-2-nitrobenzyloxycarbonyl_count
dtype: int64
- name: pseudoprolines_count
dtype: int64
- name: 2-hydroxy-4-methoxybenzyl_count
dtype: int64
- name: 2,4-dimethoxybenzyl_count
dtype: int64
- name: 2,4,6-trimethoxybenzyl_count
dtype: int64
- name: 1-methyl-3-indolylmethyl_count
dtype: int64
- name: 3,4-ethylene-dioxy-2-thenyl_count
dtype: int64
- name: hmb_count
dtype: int64
- name: tmob_count
dtype: int64
- name: mim_count
dtype: int64
- name: edot_count
dtype: int64
- name: 4-methoxy-2-nitro-benzyl_count
dtype: int64
- name: (6-hydroxy-3-oxido-1,3-benz[d]oxathiol-5-yl)methyl_count
dtype: int64
- name: 2-hydroxy-4-methoxy-5-(methylsulfinyl)benzyl_count
dtype: int64
- name: n-boc-n-methyl[2-(methylamino)ethyl]carbamoyl-hmb_count
dtype: int64
- name: 9-xanthenyl_count
dtype: int64
- name: cyclopropyldimethylcarbinyl_count
dtype: int64
- name: 4,4-dimethoxybenzhydryl_count
dtype: int64
- name: xan_count
dtype: int64
- name: cpd_count
dtype: int64
- name: mbh_count
dtype: int64
- name: p-toluenesulfonyl_count
dtype: int64
- name: 2,2,5,7,8-pentamethylchroman-6-sulfonyl_count
dtype: int64
- name: 2,2,4,6,7-pentamethyl-2,3-dihydrobenzofuran-5-sulfonyl_count
dtype: int64
- name: mesityl-2-sulfonyl_count
dtype: int64
- name: 4-methoxy-2,3,6-trimethylphenylsulfonyl_count
dtype: int64
- name: 1,2-dimethylindole-3-sulfonyl_count
dtype: int64
- name: w,w-bis-tert-butyloxycarbonyl_count
dtype: int64
- name: 5-dibenzosuberenyl_count
dtype: int64
- name: 5-dibenzosuberyl_count
dtype: int64
- name: 2-methoxy-5-dibenzosuberyl_count
dtype: int64
- name: nitro_count
dtype: int64
- name: tos_count
dtype: int64
- name: pmc_count
dtype: int64
- name: pbf_count
dtype: int64
- name: mts_count
dtype: int64
- name: mtr_count
dtype: int64
- name: mis_count
dtype: int64
- name: bis-boc_count
dtype: int64
- name: suben_count
dtype: int64
- name: sub_count
dtype: int64
- name: mesub_count
dtype: int64
- name: no2_count
dtype: int64
- name: w,w-bis-benzyloxycarbonyl_count
dtype: int64
- name: w,w-bis-allyloxycarbonyl_count
dtype: int64
- name: z-small_count
dtype: int64
- name: p-methylbenzyl_count
dtype: int64
- name: p-methoxybenzyl_count
dtype: int64
- name: monomethoxytrityl_count
dtype: int64
- name: trimethoxybenzyl_count
dtype: int64
- name: 2,2,4,6,7-pentamethyl-5-dihydrobenzofuranylmethyl_count
dtype: int64
- name: 1-adamantyl_count
dtype: int64
- name: meb_count
dtype: int64
- name: mob_count
dtype: int64
- name: mmt_count
dtype: int64
- name: pmbf_count
dtype: int64
- name: 1-ada_count
dtype: int64
- name: 2-(2,4-dinitrophenyl)ethyl_count
dtype: int64
- name: 9-fluororenylmethoxycarbonyl_count
dtype: int64
- name: dnpe_count
dtype: int64
- name: acetamidomethyl_count
dtype: int64
- name: phenylacetamidomethyl_count
dtype: int64
- name: 5-tert-butylmercapto_count
dtype: int64
- name: 3-nitro-2-pyridinesulfenyl_count
dtype: int64
- name: 2-pyridinesulfenyl_count
dtype: int64
- name: N-allyloxycarbonyl-N-[2,3,5,6-tetrafluoro-4-(phenylthio)phenyl]]aminomethyl_count
dtype: int64
- name: o-nitrobenzyl_count
dtype: int64
- name: 4-picolyl_count
dtype: int64
- name: ninhydrin_count
dtype: int64
- name: acm_count
dtype: int64
- name: phacm_count
dtype: int64
- name: sbu_count
dtype: int64
- name: npys_count
dtype: int64
- name: s-pyr_count
dtype: int64
- name: fsam_count
dtype: int64
- name: onb_count
dtype: int64
- name: nin_count
dtype: int64
- name: n-tosyl_count
dtype: int64
- name: n-trityl_count
dtype: int64
- name: n-monomethoxytrityl_count
dtype: int64
- name: n-methyltrityl_count
dtype: int64
- name: n-tert-butyloxycarbonyl_count
dtype: int64
- name: n-2,4-dimethylpent-3-yloxycarbonyl_count
dtype: int64
- name: n-benzyloxymethyl_count
dtype: int64
- name: n-tert-butoxymethyl_count
dtype: int64
- name: ntos_count
dtype: int64
- name: ntrt_count
dtype: int64
- name: nmtt_count
dtype: int64
- name: nmmt_count
dtype: int64
- name: nboc_count
dtype: int64
- name: ndoc_count
dtype: int64
- name: nbom_count
dtype: int64
- name: nbum_count
dtype: int64
- name: N-9-fluorenylmethoxycarbonyl_count
dtype: int64
- name: N-2,6-dimethoxybenzoyl_count
dtype: int64
- name: dmbz_count
dtype: int64
- name: N-2,4-dinitrophenyl_count
dtype: int64
- name: dnp_count
dtype: int64
- name: cyclohexyl;_count
dtype: int64
- name: tert-butyldimethylsilyl_count
dtype: int64
- name: tbdms_count
dtype: int64
- name: tert-butyldiphenylsilyl_count
dtype: int64
- name: propargyloxycarbonyl_count
dtype: int64
- name: tbdps_count
dtype: int64
- name: 2,6-dichlorobenzyl_count
dtype: int64
- name: 2-bromobenzyl_count
dtype: int64
- name: 2-bromobenzyloxycarbonyl_count
dtype: int64
- name: 3-pentyl_count
dtype: int64
- name: dcb_count
dtype: int64
- name: brbn_count
dtype: int64
- name: brz_count
dtype: int64
- name: pen_count
dtype: int64
- name: tegb_count
dtype: int64
- name: boc-n-methyl-n-[2-(methylamino)ethyl]carbamoyl_count
dtype: int64
- name: boc-nmec_count
dtype: int64
- name: formyl_count
dtype: int64
- name: cyclohexyloxycarbonyl_count
dtype: int64
- name: for_count
dtype: int64
- name: hoc_count
dtype: int64
- name: cyclopropane_count
dtype: int64
- name: spiropentane_count
dtype: int64
- name: cyclobutane_count
dtype: int64
- name: cyclopentane_count
dtype: int64
- name: furan_count
dtype: int64
- name: thiophene_count
dtype: int64
- name: pyrrole_count
dtype: int64
- name: 2H-pyrrole_count
dtype: int64
- name: 3H-pyrrole_count
dtype: int64
- name: pyrazole_count
dtype: int64
- name: 2H-imidazole_count
dtype: int64
- name: 1,2,3-triazole_count
dtype: int64
- name: 1,2,4-triazole_count
dtype: int64
- name: 1,2-dithiole_count
dtype: int64
- name: 1,3-dithiole_count
dtype: int64
- name: 3H-1,2-oxathiole_count
dtype: int64
- name: isoxazole_count
dtype: int64
- name: oxazole_count
dtype: int64
- name: thiazole_count
dtype: int64
- name: isothiazole_count
dtype: int64
- name: 1,2,3-oxadiazole_count
dtype: int64
- name: 1,2,4-oxadiazole_count
dtype: int64
- name: 1,2,5-oxadiazole_count
dtype: int64
- name: 1,3,4-oxadiazole_count
dtype: int64
- name: 1,2,3,4-oxatriazole_count
dtype: int64
- name: 1,2,3,5-oxatriazole_count
dtype: int64
- name: 3H-1,2,3-dioxazole_count
dtype: int64
- name: 1,2,4-dioxazole_count
dtype: int64
- name: 1,3,2-dioxazole_count
dtype: int64
- name: 1,3,4-dioxazole_count
dtype: int64
- name: 5H-1,2,5-oxathiazole_count
dtype: int64
- name: 1,3-oxathiole_count
dtype: int64
- name: benzene_count
dtype: int64
- name: cyclohexane_count
dtype: int64
- name: 2H-pyran_count
dtype: int64
- name: 4H-pyran_count
dtype: int64
- name: 2H-pyran-2-one_count
dtype: int64
- name: 4H-pyran-4-one_count
dtype: int64
- name: 1,2-dioxin_count
dtype: int64
- name: 1,3-dioxin_count
dtype: int64
- name: pyridine_count
dtype: int64
- name: pyridazine_count
dtype: int64
- name: pyrimidine_count
dtype: int64
- name: pyrazine_count
dtype: int64
- name: piperazine_count
dtype: int64
- name: 1,3,5-triazine_count
dtype: int64
- name: 1,2,4-triazine_count
dtype: int64
- name: 1,2,3-triazine_count
dtype: int64
- name: 4H-1,2-Oxazine_count
dtype: int64
- name: 2H-1,3-Oxazine_count
dtype: int64
- name: 6H-1,3-Oxazine_count
dtype: int64
- name: 6H-1,2-Oxazine_count
dtype: int64
- name: 1,4-Oxazine_count
dtype: int64
- name: 2H-1,2-Oxazine_count
dtype: int64
- name: 4H-1,4-Oxazine_count
dtype: int64
- name: 1,2,5-Oxathiazine_count
dtype: int64
- name: 1,2,6-Oxathiazine_count
dtype: int64
- name: 1,2,4-Oxadiazine_count
dtype: int64
- name: 1,3,5-Oxadiazine_count
dtype: int64
- name: morpholine_count
dtype: int64
- name: azepine_count
dtype: int64
- name: oxepin_count
dtype: int64
- name: thiepin_count
dtype: int64
- name: 4H-1,2-diazepine_count
dtype: int64
- name: indene_count
dtype: int64
- name: 2H-indene_count
dtype: int64
- name: benzofuran_count
dtype: int64
- name: isobenzofuran_count
dtype: int64
- name: benzo[b]thiophene_count
dtype: int64
- name: benzo[c]thiophene_count
dtype: int64
- name: indole_count
dtype: int64
- name: 3H-indole_count
dtype: int64
- name: 1H-indole_count
dtype: int64
- name: cyclopenta[b]pyridine_count
dtype: int64
- name: pyrano[3,4-b]-pyrrole_count
dtype: int64
- name: indazole_count
dtype: int64
- name: benzisoxazole_count
dtype: int64
- name: benzoxazole_count
dtype: int64
- name: 2,1-benzisoxazole_count
dtype: int64
- name: naphthalene_count
dtype: int64
- name: 1,2,3,4-tetrahydronaphthalene_count
dtype: int64
- name: octahydronaphthalene_count
dtype: int64
- name: 2H-1-benzopyran_count
dtype: int64
- name: 2H-1-benzopyran-2-one_count
dtype: int64
- name: 4H-1-benzopyran-4-one_count
dtype: int64
- name: 1H-2-benzopyran-1-one_count
dtype: int64
- name: 3H-2-benzopyran-1-one_count
dtype: int64
- name: quinoline_count
dtype: int64
- name: isoquinoline_count
dtype: int64
- name: cinnoline_count
dtype: int64
- name: quinazoline_count
dtype: int64
- name: 1,8-napthyhridine_count
dtype: int64
- name: 1,7-napththyridine_count
dtype: int64
- name: 1,5-napththridine_count
dtype: int64
- name: 1,6-napthyridine_count
dtype: int64
- name: 2H-1,3-benzoxazine_count
dtype: int64
- name: 2H-1,4-benzoxazine_count
dtype: int64
- name: 1H-2,3-benzoxazine_count
dtype: int64
- name: 4H-3,1-benzoxazine_count
dtype: int64
- name: 2H-1,2-benzoxazine_count
dtype: int64
- name: 4H-1,3-benzoxazine_count
dtype: int64
- name: anthracene_count
dtype: int64
- name: phenanthrene_count
dtype: int64
- name: phenalene_count
dtype: int64
- name: fluorene_count
dtype: int64
- name: carbazole_count
dtype: int64
- name: xanthene_count
dtype: int64
- name: acridine_count
dtype: int64
- name: norpinane_count
dtype: int64
- name: 7H-purine_count
dtype: int64
- name: steroid_ring_system_count
dtype: int64
- name: imidazole_count
dtype: int64
- name: thiazol-2-amine_count
dtype: int64
- name: tetrazole_count
dtype: int64
- name: cytosine_count
dtype: int64
- name: adenine_count
dtype: int64
- name: 5-methylindole_count
dtype: int64
- name: isocaffeine_count
dtype: int64
- name: tetrazolethiol_count
dtype: int64
- name: 3-methylisoxazole_count
dtype: int64
- name: 1-methylimidazole_count
dtype: int64
- name: 2-methylimidazole_count
dtype: int64
- name: guanine_count
dtype: int64
- name: tosufloxacin_count
dtype: int64
- name: acetamido_count
dtype: int64
- name: acetoacetyl_count
dtype: int64
- name: acetyl_count
dtype: int64
- name: acryloyl_count
dtype: int64
- name: alanyl_count
dtype: int64
- name: beta-alanyl_count
dtype: int64
- name: allylidene_count
dtype: int64
- name: amidino_count
dtype: int64
- name: amino_count
dtype: int64
- name: amyl_count
dtype: int64
- name: anilino_count
dtype: int64
- name: anisidino_count
dtype: int64
- name: anthranoyl_count
dtype: int64
- name: arsino_count
dtype: int64
- name: azelaoyl_count
dtype: int64
- name: azido_count
dtype: int64
- name: azo_count
dtype: int64
- name: azoxy_count
dtype: int64
- name: benzal_count
dtype: int64
- name: benzamido_count
dtype: int64
- name: benzhydrol_count
dtype: int64
- name: benzoxy_count
dtype: int64
- name: benzoyl_count
dtype: int64
- name: benzylidene_count
dtype: int64
- name: benzylidyne_count
dtype: int64
- name: biphenylyl_count
dtype: int64
- name: biphenylene_count
dtype: int64
- name: butoxy_count
dtype: int64
- name: sec-butoxy_count
dtype: int64
- name: tert-butoxy_count
dtype: int64
- name: butyl_count
dtype: int64
- name: sec-butyl_count
dtype: int64
- name: butyryl_count
dtype: int64
- name: caproyl_count
dtype: int64
- name: capryl_count
dtype: int64
- name: capryloyl_count
dtype: int64
- name: carbamido_count
dtype: int64
- name: carbamoyl_count
dtype: int64
- name: carbamyl_count
dtype: int64
- name: carbazoyl_count
dtype: int64
- name: carbethoxy_count
dtype: int64
- name: carbonyl_count
dtype: int64
- name: carboxy_count
dtype: int64
- name: cetyl_count
dtype: int64
- name: chloroformyl_count
dtype: int64
- name: cinnamoyl_count
dtype: int64
- name: cinnamyl_count
dtype: int64
- name: cinnamylidene_count
dtype: int64
- name: cresyl_count
dtype: int64
- name: crotonoyl_count
dtype: int64
- name: crotyl_count
dtype: int64
- name: cyanamido_count
dtype: int64
- name: cyanato_count
dtype: int64
- name: cyano_count
dtype: int64
- name: decanedioyl_count
dtype: int64
- name: decanoyl_count
dtype: int64
- name: diazo_count
dtype: int64
- name: diazoamino_count
dtype: int64
- name: disilanyl_count
dtype: int64
- name: disiloxanyloxy_count
dtype: int64
- name: disulfinyl_count
dtype: int64
- name: dithio_count
dtype: int64
- name: enanthoyl_count
dtype: int64
- name: epoxy_count
dtype: int64
- name: ethenyl_count
dtype: int64
- name: ethynyl_count
dtype: int64
- name: ethoxy_count
dtype: int64
- name: ethylene_count
dtype: int64
- name: ethylidene_count
dtype: int64
- name: ethylthio_count
dtype: int64
- name: formamido_count
dtype: int64
- name: furmaroyl_count
dtype: int64
- name: furfuryl_count
dtype: int64
- name: furfurylidene_count
dtype: int64
- name: glutamoyl_count
dtype: int64
- name: glutaryl_count
dtype: int64
- name: glycylamino_count
dtype: int64
- name: glycoloyl_count
dtype: int64
- name: glycyl_count
dtype: int64
- name: glyoxyoyl_count
dtype: int64
- name: guanidino_count
dtype: int64
- name: guanyl_count
dtype: int64
- name: heptadecanoyl_count
dtype: int64
- name: heptanamido_count
dtype: int64
- name: heptanoyl_count
dtype: int64
- name: hexadecanoyl_count
dtype: int64
- name: hexamethylene_count
dtype: int64
- name: hexanedioyl_count
dtype: int64
- name: hippuryl_count
dtype: int64
- name: hydrazino_count
dtype: int64
- name: hydrazo_count
dtype: int64
- name: hydrocinnamoyl_count
dtype: int64
- name: hydroperoxy_count
dtype: int64
- name: hydroxyamino_count
dtype: int64
- name: imino_count
dtype: int64
- name: iodoso_count
dtype: int64
- name: iodyl_count
dtype: int64
- name: isoamyl_count
dtype: int64
- name: isobutenyl_count
dtype: int64
- name: isobutoxy_count
dtype: int64
- name: isobutyl_count
dtype: int64
- name: isobutylidene_count
dtype: int64
- name: isobutyryl_count
dtype: int64
- name: isocyanato_count
dtype: int64
- name: isocyano_count
dtype: int64
- name: isohexyl_count
dtype: int64
- name: isoleucyl_count
dtype: int64
- name: isonitroso_count
dtype: int64
- name: isopentyl_count
dtype: int64
- name: isopentylidene_count
dtype: int64
- name: isopropenyl_count
dtype: int64
- name: isopropoxy_count
dtype: int64
- name: isopropyl_count
dtype: int64
- name: isopropylidene_count
dtype: int64
- name: isothiocynato_count
dtype: int64
- name: isovaleryl_count
dtype: int64
- name: lactoyl_count
dtype: int64
- name: lauroyl_count
dtype: int64
- name: lauryl_count
dtype: int64
- name: leucyl_count
dtype: int64
- name: levulinoyl_count
dtype: int64
- name: malonyl_count
dtype: int64
- name: mandeloyl_count
dtype: int64
- name: mercapto_count
dtype: int64
- name: mesityl_count
dtype: int64
- name: methacryloyl_count
dtype: int64
- name: methallyl_count
dtype: int64
- name: methionyl_count
dtype: int64
- name: methoxy_count
dtype: int64
- name: methylene_count
dtype: int64
- name: methylthio_count
dtype: int64
- name: myristoyl_count
dtype: int64
- name: myristyl_count
dtype: int64
- name: naphthyl_count
dtype: int64
- name: naphthylene_count
dtype: int64
- name: neopentyl_count
dtype: int64
- name: nitramino_count
dtype: int64
- name: nitrosamino_count
dtype: int64
- name: nitroso_count
dtype: int64
- name: nonanoyl_count
dtype: int64
- name: oleoyl_count
dtype: int64
- name: oxalyl_count
dtype: int64
- name: oxo_count
dtype: int64
- name: palmitoyl_count
dtype: int64
- name: pentamethylene_count
dtype: int64
- name: pentyl_count
dtype: int64
- name: tert-pentyl_count
dtype: int64
- name: phenacylidene_count
dtype: int64
- name: phenethyl_count
dtype: int64
- name: phenoxy_count
dtype: int64
- name: phenyl_count
dtype: int64
- name: phenylene_count
dtype: int64
- name: phosphino_count
dtype: int64
- name: phosphinyl_count
dtype: int64
- name: phospho_count
dtype: int64
- name: phosphono_count
dtype: int64
- name: phthaloyl_count
dtype: int64
- name: picryl_count
dtype: int64
- name: pimeloyl_count
dtype: int64
- name: piperidino_count
dtype: int64
- name: pivaloyl_count
dtype: int64
- name: prenyl_count
dtype: int64
- name: propargyl_count
dtype: int64
- name: 1-propenyl_count
dtype: int64
- name: 2-propenyl_count
dtype: int64
- name: propionyl_count
dtype: int64
- name: propoxy_count
dtype: int64
- name: propyl_count
dtype: int64
- name: propylidene_count
dtype: int64
- name: pyrryl_count
dtype: int64
- name: salicyloyl_count
dtype: int64
- name: selenyl_count
dtype: int64
- name: seryl_count
dtype: int64
- name: siloxy_count
dtype: int64
- name: silyl_count
dtype: int64
- name: silyene_count
dtype: int64
- name: sorboyl_count
dtype: int64
- name: stearoyl_count
dtype: int64
- name: stearyl_count
dtype: int64
- name: styryl_count
dtype: int64
- name: suberoyl_count
dtype: int64
- name: succinyl_count
dtype: int64
- name: sulfamino_count
dtype: int64
- name: sulfamoyl_count
dtype: int64
- name: sulfanilyl_count
dtype: int64
- name: sulfeno_count
dtype: int64
- name: sulfhydryl_count
dtype: int64
- name: sulfinyl_count
dtype: int64
- name: sulfo_count
dtype: int64
- name: sulfonyl_count
dtype: int64
- name: terephthaloyl_count
dtype: int64
- name: tetramethylene_count
dtype: int64
- name: thienyl_count
dtype: int64
- name: thiocarbonyl_count
dtype: int64
- name: thiocarboxy_count
dtype: int64
- name: thiocyanato_count
dtype: int64
- name: thionyl_count
dtype: int64
- name: threonyl_count
dtype: int64
- name: toluidino_count
dtype: int64
- name: toluoyl_count
dtype: int64
- name: tolyl_count
dtype: int64
- name: alpha-tolyl_count
dtype: int64
- name: tolylene_count
dtype: int64
- name: tosyl_count
dtype: int64
- name: triazano_count
dtype: int64
- name: trimethylene_count
dtype: int64
- name: valeryl_count
dtype: int64
- name: valyl_count
dtype: int64
- name: vinyl_count
dtype: int64
- name: vinylidene_count
dtype: int64
- name: xylidino_count
dtype: int64
- name: xylyl_count
dtype: int64
- name: xylylene_count
dtype: int64
- name: propiolamide_count
dtype: int64
- name: fumarate ester_count
dtype: int64
- name: allenamide_count
dtype: int64
- name: propiolonitrile_count
dtype: int64
- name: propargylamide_count
dtype: int64
- name: arylsulfonyl bicyclobutane_count
dtype: int64
- name: haloalkane_count
dtype: int64
- name: alpha-halomethyl_count
dtype: int64
- name: alpha-haloamide_count
dtype: int64
- name: alpha-haloester_count
dtype: int64
- name: epoxide_count
dtype: int64
- name: aziridine_count
dtype: int64
- name: nitroalkane_count
dtype: int64
- name: acrylamide_count
dtype: int64
- name: cyanoenone_count
dtype: int64
- name: aldehyde_count
dtype: int64
- name: ketone_count
dtype: int64
- name: nitrile_count
dtype: int64
- name: cyanamide_count
dtype: int64
- name: isothicyanate_count
dtype: int64
- name: sulfone_count
dtype: int64
- name: sulfonyl fluoride_count
dtype: int64
- name: sulfonimidoyl fluoride_count
dtype: int64
- name: aryl fluorosulfate_count
dtype: int64
- name: ester_count
dtype: int64
- name: sulfonamide_count
dtype: int64
- name: 2-carbonyl arylboronic acid_count
dtype: int64
- name: n-methyl isoxazolium_count
dtype: int64
- name: oxaziridine_count
dtype: int64
- name: carboxyl_count
dtype: int64
- name: ether_count
dtype: int64
- name: alkanol_count
dtype: int64
- name: thiol_count
dtype: int64
- name: halogen_count
dtype: int64
- name: amine_count
dtype: int64
- name: amide_count
dtype: int64
- name: num_valence_electrons
dtype: int64
- name: rotable_proportion
dtype: float64
- name: non_rotable_proportion
dtype: float64
- name: num_unspecified_bond
dtype: float64
- name: num_single_bonds
dtype: float64
- name: num_double_bonds
dtype: float64
- name: num_triple_bonds
dtype: float64
- name: num_quadruple_bonds
dtype: float64
- name: num_quintuple_bonds
dtype: float64
- name: num_hextuple_bonds
dtype: float64
- name: num_oneandahalf_bonds
dtype: float64
- name: num_twoandahalf_bonds
dtype: float64
- name: num_threeandahalf_bonds
dtype: float64
- name: num_fourandahalf_bonds
dtype: float64
- name: num_fiveandahalf_bonds
dtype: float64
- name: num_aromatic_bonds
dtype: float64
- name: num_ionic_bonds
dtype: float64
- name: num_hydrogen_bonds
dtype: float64
- name: num_threecenter_bonds
dtype: float64
- name: num_dativeone_bonds
dtype: float64
- name: num_dative_bonds
dtype: float64
- name: num_other_bonds
dtype: float64
- name: num_zero_bonds
dtype: float64
- name: num_bonds
dtype: int64
- name: molecular_formula
dtype: string
- name: monoisotopic_molecular_mass
dtype: float64
- name: carbon_mass
dtype: float64
- name: hydrogen_mass
dtype: float64
- name: nitrogen_mass
dtype: float64
- name: oxygen_mass
dtype: float64
- name: num_carbon_atoms
dtype: int64
- name: num_hydrogen_atoms
dtype: int64
- name: num_nitrogen_atoms
dtype: int64
- name: num_oxygen_atoms
dtype: int64
- name: num_hydrogen_bond_acceptors
dtype: int64
- name: num_hydrogen_bond_donors
dtype: int64
- name: num_lipinski_violations
dtype: int64
- name: inertial_shape_factor
dtype: float64
- name: eccentricity
dtype: float64
- name: asphericity
dtype: float64
- name: npr1_value
dtype: float64
- name: npr2_value
dtype: float64
- name: pmi1_value
dtype: float64
- name: pmi2_value
dtype: float64
- name: pmi3_value
dtype: float64
- name: num_chiral_centers
dtype: int64
- name: representation
dtype: string
splits:
- name: train
num_bytes: 2760228
num_examples: 499
download_size: 518564
dataset_size: 2760228
- config_name: rdkit_feat_11
features:
- name: tert-butyloxycarbonyl_count
dtype: int64
- name: representation_type
dtype: string
- name: trityl_count
dtype: int64
- name: 3,5-dimethoxyphenylisoproxycarbonyl_count
dtype: int64
- name: 2-(4-biphenyl)isopropoxycarbonyl_count
dtype: int64
- name: 2-nitrophenylsulfenyl_count
dtype: int64
- name: boc_count
dtype: int64
- name: trt_count
dtype: int64
- name: ddz_count
dtype: int64
- name: bpoc_count
dtype: int64
- name: nps_count
dtype: int64
- name: 9-fluorenylmethoxycarbonyl_count
dtype: int64
- name: 2-(4-nitrophenylsulfonyl)ethoxycarbonyl_count
dtype: int64
- name: (1,1-dioxobenzo[b]thiophene-2-yl)methyloxycarbonyl_count
dtype: int64
- name: (1,1-dioxonaptho[1,2-b]thiophene-2-yl)methyloxycarbonyl_count
dtype: int64
- name: 1-(4,4-dimethyl-2,6-dioxocyclohex-1-ylidene)-3-methylbutyl_count
dtype: int64
- name: 2,7-di-tert-butyl-fmoc_count
dtype: int64
- name: 2-fluoro-fmoc_count
dtype: int64
- name: 2-monoisooctyl-fmoc_count
dtype: int64
- name: 2,7-diisooctyl-fmoc_count
dtype: int64
- name: tetrachlorophthaloyl_count
dtype: int64
- name: 2-[phenyl(methyl)sulfonio])ethyloxycarbonyltetrafluoroborate_count
dtype: int64
- name: ethanesulfonylethoxycarbonyl_count
dtype: int64
- name: 2-(4-sulfophenylsulfonyl)ethoxycarbonyl_count
dtype: int64
- name: fmoc_count
dtype: int64
- name: nsc_count
dtype: int64
- name: bsmoc_count
dtype: int64
- name: alpha-nsmoc_count
dtype: int64
- name: ivdde_count
dtype: int64
- name: fmoc*_count
dtype: int64
- name: fmoc(fmoc(2f))_count
dtype: int64
- name: mio-fmoc_count
dtype: int64
- name: dio-fmoc_count
dtype: int64
- name: tcp_count
dtype: int64
- name: pms_count
dtype: int64
- name: esc_count
dtype: int64
- name: sps_count
dtype: int64
- name: benzyloxycarbonyl_count
dtype: int64
- name: allyloxycarbonyl_count
dtype: int64
- name: o-nitrobenzenesulfonyl_count
dtype: int64
- name: 2,4-dinitrobenzenesulfonyl_count
dtype: int64
- name: benzothiazole-2-sulfonyl_count
dtype: int64
- name: 2,2,2-trichloroethyloxycarbonyl_count
dtype: int64
- name: dithiasuccinoyl_count
dtype: int64
- name: p-nitrobenzyloxycarbonyl_count
dtype: int64
- name: alpha-azidoacids_count
dtype: int64
- name: proparglyoxycarbonyl_count
dtype: int64
- name: o-nitrobenzylcarbonyl_count
dtype: int64
- name: 4-nitroveratryloxycarbonyl_count
dtype: int64
- name: 2-(2-nitrophenyl)propyloxycarbonyl_count
dtype: int64
- name: 2-(3,4-methylenedioxy-6-nitrophenyl)propyloxycarbonyl_count
dtype: int64
- name: 9-(4-bromophenyl)-9-fluorenyl_count
dtype: int64
- name: azidomethoxycarbonyl_count
dtype: int64
- name: hexafluoroacetone_count
dtype: int64
- name: Z_count
dtype: int64
- name: alloc_count
dtype: int64
- name: o-nbs_count
dtype: int64
- name: d-nbs_count
dtype: int64
- name: bts_count
dtype: int64
- name: troc_count
dtype: int64
- name: dts_count
dtype: int64
- name: pnz_count
dtype: int64
- name: poc_count
dtype: int64
- name: onz_count
dtype: int64
- name: nvoc_count
dtype: int64
- name: nppoc_count
dtype: int64
- name: mnppoc_count
dtype: int64
- name: brphf_count
dtype: int64
- name: azoc_count
dtype: int64
- name: hfa_count
dtype: int64
- name: 2-chlorobenzyloxycarbonyl_count
dtype: int64
- name: 4-methyltrityl_count
dtype: int64
- name: cl-z_count
dtype: int64
- name: mtt_count
dtype: int64
- name: 1-(4,4-dimethyl-2,6-dioxocylohex-1-ylidene)-3-methylbutyl_count
dtype: int64
- name: trifluoroacetyl_count
dtype: int64
- name: 2-(methylsulfonyl)ethoxycarbonyl_count
dtype: int64
- name: tfa_count
dtype: int64
- name: msc_count
dtype: int64
- name: phenyldisulphanylethyloxycarbonyl_count
dtype: int64
- name: 2-pyridyldisulphanylethyloxycarbonyl_count
dtype: int64
- name: phdec_count
dtype: int64
- name: pydec_count
dtype: int64
- name: tert-butyl_count
dtype: int64
- name: 2-chlorotrityl_count
dtype: int64
- name: 2-4-dimethyoxybenzyl_count
dtype: int64
- name: 2-phenylisopropyl_count
dtype: int64
- name: 5-phenyl-3,4-ethylenedioxythenyl_count
dtype: int64
- name: bu_count
dtype: int64
- name: 2-cl-trt_count
dtype: int64
- name: dmb_count
dtype: int64
- name: 2-ph-pr_count
dtype: int64
- name: phenyl-edotn_count
dtype: int64
- name: 9-fluorenylmethyl_count
dtype: int64
- name: 4-(N-[1-(4,4-dimethyl-2,6-dioxocylocheylidene)-3-methylbutyl]-amino)benzyl_count
dtype: int64
- name: methyl_count
dtype: int64
- name: ethyl_count
dtype: int64
- name: carbamoylmethyl_count
dtype: int64
- name: fm_count
dtype: int64
- name: dmab_count
dtype: int64
- name: me_count
dtype: int64
- name: et_count
dtype: int64
- name: cam_count
dtype: int64
- name: allyl_count
dtype: int64
- name: benzyl_count
dtype: int64
- name: phenacyl_count
dtype: int64
- name: p-nitrobenzyl_count
dtype: int64
- name: 2-trimethylsilyethyl_count
dtype: int64
- name: (2-phenyl-2-trimethylsilyl)ethyl_count
dtype: int64
- name: 2-(trimethylsilyl)isopropyl_count
dtype: int64
- name: 2,2,2-trichloroethyl_count
dtype: int64
- name: p-hydroxyphenacyl_count
dtype: int64
- name: 4,5-dimethyoxy-2-nitrobenzyl_count
dtype: int64
- name: 1,1-dimethylallyl_count
dtype: int64
- name: pentaaminecobalt_III_count
dtype: int64
- name: al_count
dtype: int64
- name: bn_count
dtype: int64
- name: pac_count
dtype: int64
- name: pnb_count
dtype: int64
- name: tmse_count
dtype: int64
- name: ptmse_count
dtype: int64
- name: tmsi_count
dtype: int64
- name: tce_count
dtype: int64
- name: php_count
dtype: int64
- name: dmnb_count
dtype: int64
- name: dma_count
dtype: int64
- name: cyclohexyl_count
dtype: int64
- name: b-menthyl_count
dtype: int64
- name: b-3-methylpent-3-yl_count
dtype: int64
- name: 4-(3,6,9-trioxadecyl)oxybenzyl_count
dtype: int64
- name: chx_count
dtype: int64
- name: men_count
dtype: int64
- name: mpe_count
dtype: int64
- name: tegbz_count
dtype: int64
- name: 9-fluoroenylmethyl_count
dtype: int64
- name: 4-(N-[1-(4,4-dimethyl-2,6-dioxocyclohexylidene)-3-methyl-butyl]-amino)benzyl_count
dtype: int64
- name: trimethylsilylethyl_count
dtype: int64
- name: 4,5-dimethoxy-2-nitrobenzyloxycarbonyl_count
dtype: int64
- name: pseudoprolines_count
dtype: int64
- name: 2-hydroxy-4-methoxybenzyl_count
dtype: int64
- name: 2,4-dimethoxybenzyl_count
dtype: int64
- name: 2,4,6-trimethoxybenzyl_count
dtype: int64
- name: 1-methyl-3-indolylmethyl_count
dtype: int64
- name: 3,4-ethylene-dioxy-2-thenyl_count
dtype: int64
- name: hmb_count
dtype: int64
- name: tmob_count
dtype: int64
- name: mim_count
dtype: int64
- name: edot_count
dtype: int64
- name: 4-methoxy-2-nitro-benzyl_count
dtype: int64
- name: (6-hydroxy-3-oxido-1,3-benz[d]oxathiol-5-yl)methyl_count
dtype: int64
- name: 2-hydroxy-4-methoxy-5-(methylsulfinyl)benzyl_count
dtype: int64
- name: n-boc-n-methyl[2-(methylamino)ethyl]carbamoyl-hmb_count
dtype: int64
- name: 9-xanthenyl_count
dtype: int64
- name: cyclopropyldimethylcarbinyl_count
dtype: int64
- name: 4,4-dimethoxybenzhydryl_count
dtype: int64
- name: xan_count
dtype: int64
- name: cpd_count
dtype: int64
- name: mbh_count
dtype: int64
- name: p-toluenesulfonyl_count
dtype: int64
- name: 2,2,5,7,8-pentamethylchroman-6-sulfonyl_count
dtype: int64
- name: 2,2,4,6,7-pentamethyl-2,3-dihydrobenzofuran-5-sulfonyl_count
dtype: int64
- name: mesityl-2-sulfonyl_count
dtype: int64
- name: 4-methoxy-2,3,6-trimethylphenylsulfonyl_count
dtype: int64
- name: 1,2-dimethylindole-3-sulfonyl_count
dtype: int64
- name: w,w-bis-tert-butyloxycarbonyl_count
dtype: int64
- name: 5-dibenzosuberenyl_count
dtype: int64
- name: 5-dibenzosuberyl_count
dtype: int64
- name: 2-methoxy-5-dibenzosuberyl_count
dtype: int64
- name: nitro_count
dtype: int64
- name: tos_count
dtype: int64
- name: pmc_count
dtype: int64
- name: pbf_count
dtype: int64
- name: mts_count
dtype: int64
- name: mtr_count
dtype: int64
- name: mis_count
dtype: int64
- name: bis-boc_count
dtype: int64
- name: suben_count
dtype: int64
- name: sub_count
dtype: int64
- name: mesub_count
dtype: int64
- name: no2_count
dtype: int64
- name: w,w-bis-benzyloxycarbonyl_count
dtype: int64
- name: w,w-bis-allyloxycarbonyl_count
dtype: int64
- name: z-small_count
dtype: int64
- name: p-methylbenzyl_count
dtype: int64
- name: p-methoxybenzyl_count
dtype: int64
- name: monomethoxytrityl_count
dtype: int64
- name: trimethoxybenzyl_count
dtype: int64
- name: 2,2,4,6,7-pentamethyl-5-dihydrobenzofuranylmethyl_count
dtype: int64
- name: 1-adamantyl_count
dtype: int64
- name: meb_count
dtype: int64
- name: mob_count
dtype: int64
- name: mmt_count
dtype: int64
- name: pmbf_count
dtype: int64
- name: 1-ada_count
dtype: int64
- name: 2-(2,4-dinitrophenyl)ethyl_count
dtype: int64
- name: 9-fluororenylmethoxycarbonyl_count
dtype: int64
- name: dnpe_count
dtype: int64
- name: acetamidomethyl_count
dtype: int64
- name: phenylacetamidomethyl_count
dtype: int64
- name: 5-tert-butylmercapto_count
dtype: int64
- name: 3-nitro-2-pyridinesulfenyl_count
dtype: int64
- name: 2-pyridinesulfenyl_count
dtype: int64
- name: N-allyloxycarbonyl-N-[2,3,5,6-tetrafluoro-4-(phenylthio)phenyl]]aminomethyl_count
dtype: int64
- name: o-nitrobenzyl_count
dtype: int64
- name: 4-picolyl_count
dtype: int64
- name: ninhydrin_count
dtype: int64
- name: acm_count
dtype: int64
- name: phacm_count
dtype: int64
- name: sbu_count
dtype: int64
- name: npys_count
dtype: int64
- name: s-pyr_count
dtype: int64
- name: fsam_count
dtype: int64
- name: onb_count
dtype: int64
- name: nin_count
dtype: int64
- name: n-tosyl_count
dtype: int64
- name: n-trityl_count
dtype: int64
- name: n-monomethoxytrityl_count
dtype: int64
- name: n-methyltrityl_count
dtype: int64
- name: n-tert-butyloxycarbonyl_count
dtype: int64
- name: n-2,4-dimethylpent-3-yloxycarbonyl_count
dtype: int64
- name: n-benzyloxymethyl_count
dtype: int64
- name: n-tert-butoxymethyl_count
dtype: int64
- name: ntos_count
dtype: int64
- name: ntrt_count
dtype: int64
- name: nmtt_count
dtype: int64
- name: nmmt_count
dtype: int64
- name: nboc_count
dtype: int64
- name: ndoc_count
dtype: int64
- name: nbom_count
dtype: int64
- name: nbum_count
dtype: int64
- name: N-9-fluorenylmethoxycarbonyl_count
dtype: int64
- name: N-2,6-dimethoxybenzoyl_count
dtype: int64
- name: dmbz_count
dtype: int64
- name: N-2,4-dinitrophenyl_count
dtype: int64
- name: dnp_count
dtype: int64
- name: cyclohexyl;_count
dtype: int64
- name: tert-butyldimethylsilyl_count
dtype: int64
- name: tbdms_count
dtype: int64
- name: tert-butyldiphenylsilyl_count
dtype: int64
- name: propargyloxycarbonyl_count
dtype: int64
- name: tbdps_count
dtype: int64
- name: 2,6-dichlorobenzyl_count
dtype: int64
- name: 2-bromobenzyl_count
dtype: int64
- name: 2-bromobenzyloxycarbonyl_count
dtype: int64
- name: 3-pentyl_count
dtype: int64
- name: dcb_count
dtype: int64
- name: brbn_count
dtype: int64
- name: brz_count
dtype: int64
- name: pen_count
dtype: int64
- name: tegb_count
dtype: int64
- name: boc-n-methyl-n-[2-(methylamino)ethyl]carbamoyl_count
dtype: int64
- name: boc-nmec_count
dtype: int64
- name: formyl_count
dtype: int64
- name: cyclohexyloxycarbonyl_count
dtype: int64
- name: for_count
dtype: int64
- name: hoc_count
dtype: int64
- name: cyclopropane_count
dtype: int64
- name: spiropentane_count
dtype: int64
- name: cyclobutane_count
dtype: int64
- name: cyclopentane_count
dtype: int64
- name: furan_count
dtype: int64
- name: thiophene_count
dtype: int64
- name: pyrrole_count
dtype: int64
- name: 2H-pyrrole_count
dtype: int64
- name: 3H-pyrrole_count
dtype: int64
- name: pyrazole_count
dtype: int64
- name: 2H-imidazole_count
dtype: int64
- name: 1,2,3-triazole_count
dtype: int64
- name: 1,2,4-triazole_count
dtype: int64
- name: 1,2-dithiole_count
dtype: int64
- name: 1,3-dithiole_count
dtype: int64
- name: 3H-1,2-oxathiole_count
dtype: int64
- name: isoxazole_count
dtype: int64
- name: oxazole_count
dtype: int64
- name: thiazole_count
dtype: int64
- name: isothiazole_count
dtype: int64
- name: 1,2,3-oxadiazole_count
dtype: int64
- name: 1,2,4-oxadiazole_count
dtype: int64
- name: 1,2,5-oxadiazole_count
dtype: int64
- name: 1,3,4-oxadiazole_count
dtype: int64
- name: 1,2,3,4-oxatriazole_count
dtype: int64
- name: 1,2,3,5-oxatriazole_count
dtype: int64
- name: 3H-1,2,3-dioxazole_count
dtype: int64
- name: 1,2,4-dioxazole_count
dtype: int64
- name: 1,3,2-dioxazole_count
dtype: int64
- name: 1,3,4-dioxazole_count
dtype: int64
- name: 5H-1,2,5-oxathiazole_count
dtype: int64
- name: 1,3-oxathiole_count
dtype: int64
- name: benzene_count
dtype: int64
- name: cyclohexane_count
dtype: int64
- name: 2H-pyran_count
dtype: int64
- name: 4H-pyran_count
dtype: int64
- name: 2H-pyran-2-one_count
dtype: int64
- name: 4H-pyran-4-one_count
dtype: int64
- name: 1,2-dioxin_count
dtype: int64
- name: 1,3-dioxin_count
dtype: int64
- name: pyridine_count
dtype: int64
- name: pyridazine_count
dtype: int64
- name: pyrimidine_count
dtype: int64
- name: pyrazine_count
dtype: int64
- name: piperazine_count
dtype: int64
- name: 1,3,5-triazine_count
dtype: int64
- name: 1,2,4-triazine_count
dtype: int64
- name: 1,2,3-triazine_count
dtype: int64
- name: 4H-1,2-Oxazine_count
dtype: int64
- name: 2H-1,3-Oxazine_count
dtype: int64
- name: 6H-1,3-Oxazine_count
dtype: int64
- name: 6H-1,2-Oxazine_count
dtype: int64
- name: 1,4-Oxazine_count
dtype: int64
- name: 2H-1,2-Oxazine_count
dtype: int64
- name: 4H-1,4-Oxazine_count
dtype: int64
- name: 1,2,5-Oxathiazine_count
dtype: int64
- name: 1,2,6-Oxathiazine_count
dtype: int64
- name: 1,2,4-Oxadiazine_count
dtype: int64
- name: 1,3,5-Oxadiazine_count
dtype: int64
- name: morpholine_count
dtype: int64
- name: azepine_count
dtype: int64
- name: oxepin_count
dtype: int64
- name: thiepin_count
dtype: int64
- name: 4H-1,2-diazepine_count
dtype: int64
- name: indene_count
dtype: int64
- name: 2H-indene_count
dtype: int64
- name: benzofuran_count
dtype: int64
- name: isobenzofuran_count
dtype: int64
- name: benzo[b]thiophene_count
dtype: int64
- name: benzo[c]thiophene_count
dtype: int64
- name: indole_count
dtype: int64
- name: 3H-indole_count
dtype: int64
- name: 1H-indole_count
dtype: int64
- name: cyclopenta[b]pyridine_count
dtype: int64
- name: pyrano[3,4-b]-pyrrole_count
dtype: int64
- name: indazole_count
dtype: int64
- name: benzisoxazole_count
dtype: int64
- name: benzoxazole_count
dtype: int64
- name: 2,1-benzisoxazole_count
dtype: int64
- name: naphthalene_count
dtype: int64
- name: 1,2,3,4-tetrahydronaphthalene_count
dtype: int64
- name: octahydronaphthalene_count
dtype: int64
- name: 2H-1-benzopyran_count
dtype: int64
- name: 2H-1-benzopyran-2-one_count
dtype: int64
- name: 4H-1-benzopyran-4-one_count
dtype: int64
- name: 1H-2-benzopyran-1-one_count
dtype: int64
- name: 3H-2-benzopyran-1-one_count
dtype: int64
- name: quinoline_count
dtype: int64
- name: isoquinoline_count
dtype: int64
- name: cinnoline_count
dtype: int64
- name: quinazoline_count
dtype: int64
- name: 1,8-napthyhridine_count
dtype: int64
- name: 1,7-napththyridine_count
dtype: int64
- name: 1,5-napththridine_count
dtype: int64
- name: 1,6-napthyridine_count
dtype: int64
- name: 2H-1,3-benzoxazine_count
dtype: int64
- name: 2H-1,4-benzoxazine_count
dtype: int64
- name: 1H-2,3-benzoxazine_count
dtype: int64
- name: 4H-3,1-benzoxazine_count
dtype: int64
- name: 2H-1,2-benzoxazine_count
dtype: int64
- name: 4H-1,3-benzoxazine_count
dtype: int64
- name: anthracene_count
dtype: int64
- name: phenanthrene_count
dtype: int64
- name: phenalene_count
dtype: int64
- name: fluorene_count
dtype: int64
- name: carbazole_count
dtype: int64
- name: xanthene_count
dtype: int64
- name: acridine_count
dtype: int64
- name: norpinane_count
dtype: int64
- name: 7H-purine_count
dtype: int64
- name: steroid_ring_system_count
dtype: int64
- name: imidazole_count
dtype: int64
- name: thiazol-2-amine_count
dtype: int64
- name: tetrazole_count
dtype: int64
- name: cytosine_count
dtype: int64
- name: adenine_count
dtype: int64
- name: 5-methylindole_count
dtype: int64
- name: isocaffeine_count
dtype: int64
- name: tetrazolethiol_count
dtype: int64
- name: 3-methylisoxazole_count
dtype: int64
- name: 1-methylimidazole_count
dtype: int64
- name: 2-methylimidazole_count
dtype: int64
- name: guanine_count
dtype: int64
- name: tosufloxacin_count
dtype: int64
- name: acetamido_count
dtype: int64
- name: acetoacetyl_count
dtype: int64
- name: acetyl_count
dtype: int64
- name: acryloyl_count
dtype: int64
- name: alanyl_count
dtype: int64
- name: beta-alanyl_count
dtype: int64
- name: allylidene_count
dtype: int64
- name: amidino_count
dtype: int64
- name: amino_count
dtype: int64
- name: amyl_count
dtype: int64
- name: anilino_count
dtype: int64
- name: anisidino_count
dtype: int64
- name: anthranoyl_count
dtype: int64
- name: arsino_count
dtype: int64
- name: azelaoyl_count
dtype: int64
- name: azido_count
dtype: int64
- name: azo_count
dtype: int64
- name: azoxy_count
dtype: int64
- name: benzal_count
dtype: int64
- name: benzamido_count
dtype: int64
- name: benzhydrol_count
dtype: int64
- name: benzoxy_count
dtype: int64
- name: benzoyl_count
dtype: int64
- name: benzylidene_count
dtype: int64
- name: benzylidyne_count
dtype: int64
- name: biphenylyl_count
dtype: int64
- name: biphenylene_count
dtype: int64
- name: butoxy_count
dtype: int64
- name: sec-butoxy_count
dtype: int64
- name: tert-butoxy_count
dtype: int64
- name: butyl_count
dtype: int64
- name: sec-butyl_count
dtype: int64
- name: butyryl_count
dtype: int64
- name: caproyl_count
dtype: int64
- name: capryl_count
dtype: int64
- name: capryloyl_count
dtype: int64
- name: carbamido_count
dtype: int64
- name: carbamoyl_count
dtype: int64
- name: carbamyl_count
dtype: int64
- name: carbazoyl_count
dtype: int64
- name: carbethoxy_count
dtype: int64
- name: carbonyl_count
dtype: int64
- name: carboxy_count
dtype: int64
- name: cetyl_count
dtype: int64
- name: chloroformyl_count
dtype: int64
- name: cinnamoyl_count
dtype: int64
- name: cinnamyl_count
dtype: int64
- name: cinnamylidene_count
dtype: int64
- name: cresyl_count
dtype: int64
- name: crotonoyl_count
dtype: int64
- name: crotyl_count
dtype: int64
- name: cyanamido_count
dtype: int64
- name: cyanato_count
dtype: int64
- name: cyano_count
dtype: int64
- name: decanedioyl_count
dtype: int64
- name: decanoyl_count
dtype: int64
- name: diazo_count
dtype: int64
- name: diazoamino_count
dtype: int64
- name: disilanyl_count
dtype: int64
- name: disiloxanyloxy_count
dtype: int64
- name: disulfinyl_count
dtype: int64
- name: dithio_count
dtype: int64
- name: enanthoyl_count
dtype: int64
- name: epoxy_count
dtype: int64
- name: ethenyl_count
dtype: int64
- name: ethynyl_count
dtype: int64
- name: ethoxy_count
dtype: int64
- name: ethylene_count
dtype: int64
- name: ethylidene_count
dtype: int64
- name: ethylthio_count
dtype: int64
- name: formamido_count
dtype: int64
- name: furmaroyl_count
dtype: int64
- name: furfuryl_count
dtype: int64
- name: furfurylidene_count
dtype: int64
- name: glutamoyl_count
dtype: int64
- name: glutaryl_count
dtype: int64
- name: glycylamino_count
dtype: int64
- name: glycoloyl_count
dtype: int64
- name: glycyl_count
dtype: int64
- name: glyoxyoyl_count
dtype: int64
- name: guanidino_count
dtype: int64
- name: guanyl_count
dtype: int64
- name: heptadecanoyl_count
dtype: int64
- name: heptanamido_count
dtype: int64
- name: heptanoyl_count
dtype: int64
- name: hexadecanoyl_count
dtype: int64
- name: hexamethylene_count
dtype: int64
- name: hexanedioyl_count
dtype: int64
- name: hippuryl_count
dtype: int64
- name: hydrazino_count
dtype: int64
- name: hydrazo_count
dtype: int64
- name: hydrocinnamoyl_count
dtype: int64
- name: hydroperoxy_count
dtype: int64
- name: hydroxyamino_count
dtype: int64
- name: imino_count
dtype: int64
- name: iodoso_count
dtype: int64
- name: iodyl_count
dtype: int64
- name: isoamyl_count
dtype: int64
- name: isobutenyl_count
dtype: int64
- name: isobutoxy_count
dtype: int64
- name: isobutyl_count
dtype: int64
- name: isobutylidene_count
dtype: int64
- name: isobutyryl_count
dtype: int64
- name: isocyanato_count
dtype: int64
- name: isocyano_count
dtype: int64
- name: isohexyl_count
dtype: int64
- name: isoleucyl_count
dtype: int64
- name: isonitroso_count
dtype: int64
- name: isopentyl_count
dtype: int64
- name: isopentylidene_count
dtype: int64
- name: isopropenyl_count
dtype: int64
- name: isopropoxy_count
dtype: int64
- name: isopropyl_count
dtype: int64
- name: isopropylidene_count
dtype: int64
- name: isothiocynato_count
dtype: int64
- name: isovaleryl_count
dtype: int64
- name: lactoyl_count
dtype: int64
- name: lauroyl_count
dtype: int64
- name: lauryl_count
dtype: int64
- name: leucyl_count
dtype: int64
- name: levulinoyl_count
dtype: int64
- name: malonyl_count
dtype: int64
- name: mandeloyl_count
dtype: int64
- name: mercapto_count
dtype: int64
- name: mesityl_count
dtype: int64
- name: methacryloyl_count
dtype: int64
- name: methallyl_count
dtype: int64
- name: methionyl_count
dtype: int64
- name: methoxy_count
dtype: int64
- name: methylene_count
dtype: int64
- name: methylthio_count
dtype: int64
- name: myristoyl_count
dtype: int64
- name: myristyl_count
dtype: int64
- name: naphthyl_count
dtype: int64
- name: naphthylene_count
dtype: int64
- name: neopentyl_count
dtype: int64
- name: nitramino_count
dtype: int64
- name: nitrosamino_count
dtype: int64
- name: nitroso_count
dtype: int64
- name: nonanoyl_count
dtype: int64
- name: oleoyl_count
dtype: int64
- name: oxalyl_count
dtype: int64
- name: oxo_count
dtype: int64
- name: palmitoyl_count
dtype: int64
- name: pentamethylene_count
dtype: int64
- name: pentyl_count
dtype: int64
- name: tert-pentyl_count
dtype: int64
- name: phenacylidene_count
dtype: int64
- name: phenethyl_count
dtype: int64
- name: phenoxy_count
dtype: int64
- name: phenyl_count
dtype: int64
- name: phenylene_count
dtype: int64
- name: phosphino_count
dtype: int64
- name: phosphinyl_count
dtype: int64
- name: phospho_count
dtype: int64
- name: phosphono_count
dtype: int64
- name: phthaloyl_count
dtype: int64
- name: picryl_count
dtype: int64
- name: pimeloyl_count
dtype: int64
- name: piperidino_count
dtype: int64
- name: pivaloyl_count
dtype: int64
- name: prenyl_count
dtype: int64
- name: propargyl_count
dtype: int64
- name: 1-propenyl_count
dtype: int64
- name: 2-propenyl_count
dtype: int64
- name: propionyl_count
dtype: int64
- name: propoxy_count
dtype: int64
- name: propyl_count
dtype: int64
- name: propylidene_count
dtype: int64
- name: pyrryl_count
dtype: int64
- name: salicyloyl_count
dtype: int64
- name: selenyl_count
dtype: int64
- name: seryl_count
dtype: int64
- name: siloxy_count
dtype: int64
- name: silyl_count
dtype: int64
- name: silyene_count
dtype: int64
- name: sorboyl_count
dtype: int64
- name: stearoyl_count
dtype: int64
- name: stearyl_count
dtype: int64
- name: styryl_count
dtype: int64
- name: suberoyl_count
dtype: int64
- name: succinyl_count
dtype: int64
- name: sulfamino_count
dtype: int64
- name: sulfamoyl_count
dtype: int64
- name: sulfanilyl_count
dtype: int64
- name: sulfeno_count
dtype: int64
- name: sulfhydryl_count
dtype: int64
- name: sulfinyl_count
dtype: int64
- name: sulfo_count
dtype: int64
- name: sulfonyl_count
dtype: int64
- name: terephthaloyl_count
dtype: int64
- name: tetramethylene_count
dtype: int64
- name: thienyl_count
dtype: int64
- name: thiocarbonyl_count
dtype: int64
- name: thiocarboxy_count
dtype: int64
- name: thiocyanato_count
dtype: int64
- name: thionyl_count
dtype: int64
- name: threonyl_count
dtype: int64
- name: toluidino_count
dtype: int64
- name: toluoyl_count
dtype: int64
- name: tolyl_count
dtype: int64
- name: alpha-tolyl_count
dtype: int64
- name: tolylene_count
dtype: int64
- name: tosyl_count
dtype: int64
- name: triazano_count
dtype: int64
- name: trimethylene_count
dtype: int64
- name: valeryl_count
dtype: int64
- name: valyl_count
dtype: int64
- name: vinyl_count
dtype: int64
- name: vinylidene_count
dtype: int64
- name: xylidino_count
dtype: int64
- name: xylyl_count
dtype: int64
- name: xylylene_count
dtype: int64
- name: propiolamide_count
dtype: int64
- name: fumarate ester_count
dtype: int64
- name: allenamide_count
dtype: int64
- name: propiolonitrile_count
dtype: int64
- name: propargylamide_count
dtype: int64
- name: arylsulfonyl bicyclobutane_count
dtype: int64
- name: haloalkane_count
dtype: int64
- name: alpha-halomethyl_count
dtype: int64
- name: alpha-haloamide_count
dtype: int64
- name: alpha-haloester_count
dtype: int64
- name: epoxide_count
dtype: int64
- name: aziridine_count
dtype: int64
- name: nitroalkane_count
dtype: int64
- name: acrylamide_count
dtype: int64
- name: cyanoenone_count
dtype: int64
- name: aldehyde_count
dtype: int64
- name: ketone_count
dtype: int64
- name: nitrile_count
dtype: int64
- name: cyanamide_count
dtype: int64
- name: isothicyanate_count
dtype: int64
- name: sulfone_count
dtype: int64
- name: sulfonyl fluoride_count
dtype: int64
- name: sulfonimidoyl fluoride_count
dtype: int64
- name: aryl fluorosulfate_count
dtype: int64
- name: ester_count
dtype: int64
- name: sulfonamide_count
dtype: int64
- name: 2-carbonyl arylboronic acid_count
dtype: int64
- name: n-methyl isoxazolium_count
dtype: int64
- name: oxaziridine_count
dtype: int64
- name: carboxyl_count
dtype: int64
- name: ether_count
dtype: int64
- name: alkanol_count
dtype: int64
- name: thiol_count
dtype: int64
- name: halogen_count
dtype: int64
- name: amine_count
dtype: int64
- name: amide_count
dtype: int64
- name: num_valence_electrons
dtype: int64
- name: rotable_proportion
dtype: float64
- name: non_rotable_proportion
dtype: float64
- name: num_unspecified_bond
dtype: float64
- name: num_single_bonds
dtype: float64
- name: num_double_bonds
dtype: float64
- name: num_triple_bonds
dtype: float64
- name: num_quadruple_bonds
dtype: float64
- name: num_quintuple_bonds
dtype: float64
- name: num_hextuple_bonds
dtype: float64
- name: num_oneandahalf_bonds
dtype: float64
- name: num_twoandahalf_bonds
dtype: float64
- name: num_threeandahalf_bonds
dtype: float64
- name: num_fourandahalf_bonds
dtype: float64
- name: num_fiveandahalf_bonds
dtype: float64
- name: num_aromatic_bonds
dtype: float64
- name: num_ionic_bonds
dtype: float64
- name: num_hydrogen_bonds
dtype: float64
- name: num_threecenter_bonds
dtype: float64
- name: num_dativeone_bonds
dtype: float64
- name: num_dative_bonds
dtype: float64
- name: num_other_bonds
dtype: float64
- name: num_zero_bonds
dtype: float64
- name: num_bonds
dtype: int64
- name: molecular_formula
dtype: string
- name: monoisotopic_molecular_mass
dtype: float64
- name: carbon_mass
dtype: float64
- name: hydrogen_mass
dtype: float64
- name: nitrogen_mass
dtype: float64
- name: oxygen_mass
dtype: float64
- name: num_carbon_atoms
dtype: int64
- name: num_hydrogen_atoms
dtype: int64
- name: num_nitrogen_atoms
dtype: int64
- name: num_oxygen_atoms
dtype: int64
- name: num_hydrogen_bond_acceptors
dtype: int64
- name: num_hydrogen_bond_donors
dtype: int64
- name: num_lipinski_violations
dtype: int64
- name: inertial_shape_factor
dtype: float64
- name: eccentricity
dtype: float64
- name: asphericity
dtype: float64
- name: npr1_value
dtype: float64
- name: npr2_value
dtype: float64
- name: pmi1_value
dtype: float64
- name: pmi2_value
dtype: float64
- name: pmi3_value
dtype: float64
- name: num_chiral_centers
dtype: int64
- name: representation
dtype: string
splits:
- name: train
num_bytes: 762717
num_examples: 138
download_size: 429594
dataset_size: 762717
- config_name: rdkit_feat_2
features:
- name: tert-butyloxycarbonyl_count
dtype: int64
- name: representation_type
dtype: string
- name: trityl_count
dtype: int64
- name: 3,5-dimethoxyphenylisoproxycarbonyl_count
dtype: int64
- name: 2-(4-biphenyl)isopropoxycarbonyl_count
dtype: int64
- name: 2-nitrophenylsulfenyl_count
dtype: int64
- name: boc_count
dtype: int64
- name: trt_count
dtype: int64
- name: ddz_count
dtype: int64
- name: bpoc_count
dtype: int64
- name: nps_count
dtype: int64
- name: 9-fluorenylmethoxycarbonyl_count
dtype: int64
- name: 2-(4-nitrophenylsulfonyl)ethoxycarbonyl_count
dtype: int64
- name: (1,1-dioxobenzo[b]thiophene-2-yl)methyloxycarbonyl_count
dtype: int64
- name: (1,1-dioxonaptho[1,2-b]thiophene-2-yl)methyloxycarbonyl_count
dtype: int64
- name: 1-(4,4-dimethyl-2,6-dioxocyclohex-1-ylidene)-3-methylbutyl_count
dtype: int64
- name: 2,7-di-tert-butyl-fmoc_count
dtype: int64
- name: 2-fluoro-fmoc_count
dtype: int64
- name: 2-monoisooctyl-fmoc_count
dtype: int64
- name: 2,7-diisooctyl-fmoc_count
dtype: int64
- name: tetrachlorophthaloyl_count
dtype: int64
- name: 2-[phenyl(methyl)sulfonio])ethyloxycarbonyltetrafluoroborate_count
dtype: int64
- name: ethanesulfonylethoxycarbonyl_count
dtype: int64
- name: 2-(4-sulfophenylsulfonyl)ethoxycarbonyl_count
dtype: int64
- name: fmoc_count
dtype: int64
- name: nsc_count
dtype: int64
- name: bsmoc_count
dtype: int64
- name: alpha-nsmoc_count
dtype: int64
- name: ivdde_count
dtype: int64
- name: fmoc*_count
dtype: int64
- name: fmoc(fmoc(2f))_count
dtype: int64
- name: mio-fmoc_count
dtype: int64
- name: dio-fmoc_count
dtype: int64
- name: tcp_count
dtype: int64
- name: pms_count
dtype: int64
- name: esc_count
dtype: int64
- name: sps_count
dtype: int64
- name: benzyloxycarbonyl_count
dtype: int64
- name: allyloxycarbonyl_count
dtype: int64
- name: o-nitrobenzenesulfonyl_count
dtype: int64
- name: 2,4-dinitrobenzenesulfonyl_count
dtype: int64
- name: benzothiazole-2-sulfonyl_count
dtype: int64
- name: 2,2,2-trichloroethyloxycarbonyl_count
dtype: int64
- name: dithiasuccinoyl_count
dtype: int64
- name: p-nitrobenzyloxycarbonyl_count
dtype: int64
- name: alpha-azidoacids_count
dtype: int64
- name: proparglyoxycarbonyl_count
dtype: int64
- name: o-nitrobenzylcarbonyl_count
dtype: int64
- name: 4-nitroveratryloxycarbonyl_count
dtype: int64
- name: 2-(2-nitrophenyl)propyloxycarbonyl_count
dtype: int64
- name: 2-(3,4-methylenedioxy-6-nitrophenyl)propyloxycarbonyl_count
dtype: int64
- name: 9-(4-bromophenyl)-9-fluorenyl_count
dtype: int64
- name: azidomethoxycarbonyl_count
dtype: int64
- name: hexafluoroacetone_count
dtype: int64
- name: Z_count
dtype: int64
- name: alloc_count
dtype: int64
- name: o-nbs_count
dtype: int64
- name: d-nbs_count
dtype: int64
- name: bts_count
dtype: int64
- name: troc_count
dtype: int64
- name: dts_count
dtype: int64
- name: pnz_count
dtype: int64
- name: poc_count
dtype: int64
- name: onz_count
dtype: int64
- name: nvoc_count
dtype: int64
- name: nppoc_count
dtype: int64
- name: mnppoc_count
dtype: int64
- name: brphf_count
dtype: int64
- name: azoc_count
dtype: int64
- name: hfa_count
dtype: int64
- name: 2-chlorobenzyloxycarbonyl_count
dtype: int64
- name: 4-methyltrityl_count
dtype: int64
- name: cl-z_count
dtype: int64
- name: mtt_count
dtype: int64
- name: 1-(4,4-dimethyl-2,6-dioxocylohex-1-ylidene)-3-methylbutyl_count
dtype: int64
- name: trifluoroacetyl_count
dtype: int64
- name: 2-(methylsulfonyl)ethoxycarbonyl_count
dtype: int64
- name: tfa_count
dtype: int64
- name: msc_count
dtype: int64
- name: phenyldisulphanylethyloxycarbonyl_count
dtype: int64
- name: 2-pyridyldisulphanylethyloxycarbonyl_count
dtype: int64
- name: phdec_count
dtype: int64
- name: pydec_count
dtype: int64
- name: tert-butyl_count
dtype: int64
- name: 2-chlorotrityl_count
dtype: int64
- name: 2-4-dimethyoxybenzyl_count
dtype: int64
- name: 2-phenylisopropyl_count
dtype: int64
- name: 5-phenyl-3,4-ethylenedioxythenyl_count
dtype: int64
- name: bu_count
dtype: int64
- name: 2-cl-trt_count
dtype: int64
- name: dmb_count
dtype: int64
- name: 2-ph-pr_count
dtype: int64
- name: phenyl-edotn_count
dtype: int64
- name: 9-fluorenylmethyl_count
dtype: int64
- name: 4-(N-[1-(4,4-dimethyl-2,6-dioxocylocheylidene)-3-methylbutyl]-amino)benzyl_count
dtype: int64
- name: methyl_count
dtype: int64
- name: ethyl_count
dtype: int64
- name: carbamoylmethyl_count
dtype: int64
- name: fm_count
dtype: int64
- name: dmab_count
dtype: int64
- name: me_count
dtype: int64
- name: et_count
dtype: int64
- name: cam_count
dtype: int64
- name: allyl_count
dtype: int64
- name: benzyl_count
dtype: int64
- name: phenacyl_count
dtype: int64
- name: p-nitrobenzyl_count
dtype: int64
- name: 2-trimethylsilyethyl_count
dtype: int64
- name: (2-phenyl-2-trimethylsilyl)ethyl_count
dtype: int64
- name: 2-(trimethylsilyl)isopropyl_count
dtype: int64
- name: 2,2,2-trichloroethyl_count
dtype: int64
- name: p-hydroxyphenacyl_count
dtype: int64
- name: 4,5-dimethyoxy-2-nitrobenzyl_count
dtype: int64
- name: 1,1-dimethylallyl_count
dtype: int64
- name: pentaaminecobalt_III_count
dtype: int64
- name: al_count
dtype: int64
- name: bn_count
dtype: int64
- name: pac_count
dtype: int64
- name: pnb_count
dtype: int64
- name: tmse_count
dtype: int64
- name: ptmse_count
dtype: int64
- name: tmsi_count
dtype: int64
- name: tce_count
dtype: int64
- name: php_count
dtype: int64
- name: dmnb_count
dtype: int64
- name: dma_count
dtype: int64
- name: cyclohexyl_count
dtype: int64
- name: b-menthyl_count
dtype: int64
- name: b-3-methylpent-3-yl_count
dtype: int64
- name: 4-(3,6,9-trioxadecyl)oxybenzyl_count
dtype: int64
- name: chx_count
dtype: int64
- name: men_count
dtype: int64
- name: mpe_count
dtype: int64
- name: tegbz_count
dtype: int64
- name: 9-fluoroenylmethyl_count
dtype: int64
- name: 4-(N-[1-(4,4-dimethyl-2,6-dioxocyclohexylidene)-3-methyl-butyl]-amino)benzyl_count
dtype: int64
- name: trimethylsilylethyl_count
dtype: int64
- name: 4,5-dimethoxy-2-nitrobenzyloxycarbonyl_count
dtype: int64
- name: pseudoprolines_count
dtype: int64
- name: 2-hydroxy-4-methoxybenzyl_count
dtype: int64
- name: 2,4-dimethoxybenzyl_count
dtype: int64
- name: 2,4,6-trimethoxybenzyl_count
dtype: int64
- name: 1-methyl-3-indolylmethyl_count
dtype: int64
- name: 3,4-ethylene-dioxy-2-thenyl_count
dtype: int64
- name: hmb_count
dtype: int64
- name: tmob_count
dtype: int64
- name: mim_count
dtype: int64
- name: edot_count
dtype: int64
- name: 4-methoxy-2-nitro-benzyl_count
dtype: int64
- name: (6-hydroxy-3-oxido-1,3-benz[d]oxathiol-5-yl)methyl_count
dtype: int64
- name: 2-hydroxy-4-methoxy-5-(methylsulfinyl)benzyl_count
dtype: int64
- name: n-boc-n-methyl[2-(methylamino)ethyl]carbamoyl-hmb_count
dtype: int64
- name: 9-xanthenyl_count
dtype: int64
- name: cyclopropyldimethylcarbinyl_count
dtype: int64
- name: 4,4-dimethoxybenzhydryl_count
dtype: int64
- name: xan_count
dtype: int64
- name: cpd_count
dtype: int64
- name: mbh_count
dtype: int64
- name: p-toluenesulfonyl_count
dtype: int64
- name: 2,2,5,7,8-pentamethylchroman-6-sulfonyl_count
dtype: int64
- name: 2,2,4,6,7-pentamethyl-2,3-dihydrobenzofuran-5-sulfonyl_count
dtype: int64
- name: mesityl-2-sulfonyl_count
dtype: int64
- name: 4-methoxy-2,3,6-trimethylphenylsulfonyl_count
dtype: int64
- name: 1,2-dimethylindole-3-sulfonyl_count
dtype: int64
- name: w,w-bis-tert-butyloxycarbonyl_count
dtype: int64
- name: 5-dibenzosuberenyl_count
dtype: int64
- name: 5-dibenzosuberyl_count
dtype: int64
- name: 2-methoxy-5-dibenzosuberyl_count
dtype: int64
- name: nitro_count
dtype: int64
- name: tos_count
dtype: int64
- name: pmc_count
dtype: int64
- name: pbf_count
dtype: int64
- name: mts_count
dtype: int64
- name: mtr_count
dtype: int64
- name: mis_count
dtype: int64
- name: bis-boc_count
dtype: int64
- name: suben_count
dtype: int64
- name: sub_count
dtype: int64
- name: mesub_count
dtype: int64
- name: no2_count
dtype: int64
- name: w,w-bis-benzyloxycarbonyl_count
dtype: int64
- name: w,w-bis-allyloxycarbonyl_count
dtype: int64
- name: z-small_count
dtype: int64
- name: p-methylbenzyl_count
dtype: int64
- name: p-methoxybenzyl_count
dtype: int64
- name: monomethoxytrityl_count
dtype: int64
- name: trimethoxybenzyl_count
dtype: int64
- name: 2,2,4,6,7-pentamethyl-5-dihydrobenzofuranylmethyl_count
dtype: int64
- name: 1-adamantyl_count
dtype: int64
- name: meb_count
dtype: int64
- name: mob_count
dtype: int64
- name: mmt_count
dtype: int64
- name: pmbf_count
dtype: int64
- name: 1-ada_count
dtype: int64
- name: 2-(2,4-dinitrophenyl)ethyl_count
dtype: int64
- name: 9-fluororenylmethoxycarbonyl_count
dtype: int64
- name: dnpe_count
dtype: int64
- name: acetamidomethyl_count
dtype: int64
- name: phenylacetamidomethyl_count
dtype: int64
- name: 5-tert-butylmercapto_count
dtype: int64
- name: 3-nitro-2-pyridinesulfenyl_count
dtype: int64
- name: 2-pyridinesulfenyl_count
dtype: int64
- name: N-allyloxycarbonyl-N-[2,3,5,6-tetrafluoro-4-(phenylthio)phenyl]]aminomethyl_count
dtype: int64
- name: o-nitrobenzyl_count
dtype: int64
- name: 4-picolyl_count
dtype: int64
- name: ninhydrin_count
dtype: int64
- name: acm_count
dtype: int64
- name: phacm_count
dtype: int64
- name: sbu_count
dtype: int64
- name: npys_count
dtype: int64
- name: s-pyr_count
dtype: int64
- name: fsam_count
dtype: int64
- name: onb_count
dtype: int64
- name: nin_count
dtype: int64
- name: n-tosyl_count
dtype: int64
- name: n-trityl_count
dtype: int64
- name: n-monomethoxytrityl_count
dtype: int64
- name: n-methyltrityl_count
dtype: int64
- name: n-tert-butyloxycarbonyl_count
dtype: int64
- name: n-2,4-dimethylpent-3-yloxycarbonyl_count
dtype: int64
- name: n-benzyloxymethyl_count
dtype: int64
- name: n-tert-butoxymethyl_count
dtype: int64
- name: ntos_count
dtype: int64
- name: ntrt_count
dtype: int64
- name: nmtt_count
dtype: int64
- name: nmmt_count
dtype: int64
- name: nboc_count
dtype: int64
- name: ndoc_count
dtype: int64
- name: nbom_count
dtype: int64
- name: nbum_count
dtype: int64
- name: N-9-fluorenylmethoxycarbonyl_count
dtype: int64
- name: N-2,6-dimethoxybenzoyl_count
dtype: int64
- name: dmbz_count
dtype: int64
- name: N-2,4-dinitrophenyl_count
dtype: int64
- name: dnp_count
dtype: int64
- name: cyclohexyl;_count
dtype: int64
- name: tert-butyldimethylsilyl_count
dtype: int64
- name: tbdms_count
dtype: int64
- name: tert-butyldiphenylsilyl_count
dtype: int64
- name: propargyloxycarbonyl_count
dtype: int64
- name: tbdps_count
dtype: int64
- name: 2,6-dichlorobenzyl_count
dtype: int64
- name: 2-bromobenzyl_count
dtype: int64
- name: 2-bromobenzyloxycarbonyl_count
dtype: int64
- name: 3-pentyl_count
dtype: int64
- name: dcb_count
dtype: int64
- name: brbn_count
dtype: int64
- name: brz_count
dtype: int64
- name: pen_count
dtype: int64
- name: tegb_count
dtype: int64
- name: boc-n-methyl-n-[2-(methylamino)ethyl]carbamoyl_count
dtype: int64
- name: boc-nmec_count
dtype: int64
- name: formyl_count
dtype: int64
- name: cyclohexyloxycarbonyl_count
dtype: int64
- name: for_count
dtype: int64
- name: hoc_count
dtype: int64
- name: cyclopropane_count
dtype: int64
- name: spiropentane_count
dtype: int64
- name: cyclobutane_count
dtype: int64
- name: cyclopentane_count
dtype: int64
- name: furan_count
dtype: int64
- name: thiophene_count
dtype: int64
- name: pyrrole_count
dtype: int64
- name: 2H-pyrrole_count
dtype: int64
- name: 3H-pyrrole_count
dtype: int64
- name: pyrazole_count
dtype: int64
- name: 2H-imidazole_count
dtype: int64
- name: 1,2,3-triazole_count
dtype: int64
- name: 1,2,4-triazole_count
dtype: int64
- name: 1,2-dithiole_count
dtype: int64
- name: 1,3-dithiole_count
dtype: int64
- name: 3H-1,2-oxathiole_count
dtype: int64
- name: isoxazole_count
dtype: int64
- name: oxazole_count
dtype: int64
- name: thiazole_count
dtype: int64
- name: isothiazole_count
dtype: int64
- name: 1,2,3-oxadiazole_count
dtype: int64
- name: 1,2,4-oxadiazole_count
dtype: int64
- name: 1,2,5-oxadiazole_count
dtype: int64
- name: 1,3,4-oxadiazole_count
dtype: int64
- name: 1,2,3,4-oxatriazole_count
dtype: int64
- name: 1,2,3,5-oxatriazole_count
dtype: int64
- name: 3H-1,2,3-dioxazole_count
dtype: int64
- name: 1,2,4-dioxazole_count
dtype: int64
- name: 1,3,2-dioxazole_count
dtype: int64
- name: 1,3,4-dioxazole_count
dtype: int64
- name: 5H-1,2,5-oxathiazole_count
dtype: int64
- name: 1,3-oxathiole_count
dtype: int64
- name: benzene_count
dtype: int64
- name: cyclohexane_count
dtype: int64
- name: 2H-pyran_count
dtype: int64
- name: 4H-pyran_count
dtype: int64
- name: 2H-pyran-2-one_count
dtype: int64
- name: 4H-pyran-4-one_count
dtype: int64
- name: 1,2-dioxin_count
dtype: int64
- name: 1,3-dioxin_count
dtype: int64
- name: pyridine_count
dtype: int64
- name: pyridazine_count
dtype: int64
- name: pyrimidine_count
dtype: int64
- name: pyrazine_count
dtype: int64
- name: piperazine_count
dtype: int64
- name: 1,3,5-triazine_count
dtype: int64
- name: 1,2,4-triazine_count
dtype: int64
- name: 1,2,3-triazine_count
dtype: int64
- name: 4H-1,2-Oxazine_count
dtype: int64
- name: 2H-1,3-Oxazine_count
dtype: int64
- name: 6H-1,3-Oxazine_count
dtype: int64
- name: 6H-1,2-Oxazine_count
dtype: int64
- name: 1,4-Oxazine_count
dtype: int64
- name: 2H-1,2-Oxazine_count
dtype: int64
- name: 4H-1,4-Oxazine_count
dtype: int64
- name: 1,2,5-Oxathiazine_count
dtype: int64
- name: 1,2,6-Oxathiazine_count
dtype: int64
- name: 1,2,4-Oxadiazine_count
dtype: int64
- name: 1,3,5-Oxadiazine_count
dtype: int64
- name: morpholine_count
dtype: int64
- name: azepine_count
dtype: int64
- name: oxepin_count
dtype: int64
- name: thiepin_count
dtype: int64
- name: 4H-1,2-diazepine_count
dtype: int64
- name: indene_count
dtype: int64
- name: 2H-indene_count
dtype: int64
- name: benzofuran_count
dtype: int64
- name: isobenzofuran_count
dtype: int64
- name: benzo[b]thiophene_count
dtype: int64
- name: benzo[c]thiophene_count
dtype: int64
- name: indole_count
dtype: int64
- name: 3H-indole_count
dtype: int64
- name: 1H-indole_count
dtype: int64
- name: cyclopenta[b]pyridine_count
dtype: int64
- name: pyrano[3,4-b]-pyrrole_count
dtype: int64
- name: indazole_count
dtype: int64
- name: benzisoxazole_count
dtype: int64
- name: benzoxazole_count
dtype: int64
- name: 2,1-benzisoxazole_count
dtype: int64
- name: naphthalene_count
dtype: int64
- name: 1,2,3,4-tetrahydronaphthalene_count
dtype: int64
- name: octahydronaphthalene_count
dtype: int64
- name: 2H-1-benzopyran_count
dtype: int64
- name: 2H-1-benzopyran-2-one_count
dtype: int64
- name: 4H-1-benzopyran-4-one_count
dtype: int64
- name: 1H-2-benzopyran-1-one_count
dtype: int64
- name: 3H-2-benzopyran-1-one_count
dtype: int64
- name: quinoline_count
dtype: int64
- name: isoquinoline_count
dtype: int64
- name: cinnoline_count
dtype: int64
- name: quinazoline_count
dtype: int64
- name: 1,8-napthyhridine_count
dtype: int64
- name: 1,7-napththyridine_count
dtype: int64
- name: 1,5-napththridine_count
dtype: int64
- name: 1,6-napthyridine_count
dtype: int64
- name: 2H-1,3-benzoxazine_count
dtype: int64
- name: 2H-1,4-benzoxazine_count
dtype: int64
- name: 1H-2,3-benzoxazine_count
dtype: int64
- name: 4H-3,1-benzoxazine_count
dtype: int64
- name: 2H-1,2-benzoxazine_count
dtype: int64
- name: 4H-1,3-benzoxazine_count
dtype: int64
- name: anthracene_count
dtype: int64
- name: phenanthrene_count
dtype: int64
- name: phenalene_count
dtype: int64
- name: fluorene_count
dtype: int64
- name: carbazole_count
dtype: int64
- name: xanthene_count
dtype: int64
- name: acridine_count
dtype: int64
- name: norpinane_count
dtype: int64
- name: 7H-purine_count
dtype: int64
- name: steroid_ring_system_count
dtype: int64
- name: imidazole_count
dtype: int64
- name: thiazol-2-amine_count
dtype: int64
- name: tetrazole_count
dtype: int64
- name: cytosine_count
dtype: int64
- name: adenine_count
dtype: int64
- name: 5-methylindole_count
dtype: int64
- name: isocaffeine_count
dtype: int64
- name: tetrazolethiol_count
dtype: int64
- name: 3-methylisoxazole_count
dtype: int64
- name: 1-methylimidazole_count
dtype: int64
- name: 2-methylimidazole_count
dtype: int64
- name: guanine_count
dtype: int64
- name: tosufloxacin_count
dtype: int64
- name: acetamido_count
dtype: int64
- name: acetoacetyl_count
dtype: int64
- name: acetyl_count
dtype: int64
- name: acryloyl_count
dtype: int64
- name: alanyl_count
dtype: int64
- name: beta-alanyl_count
dtype: int64
- name: allylidene_count
dtype: int64
- name: amidino_count
dtype: int64
- name: amino_count
dtype: int64
- name: amyl_count
dtype: int64
- name: anilino_count
dtype: int64
- name: anisidino_count
dtype: int64
- name: anthranoyl_count
dtype: int64
- name: arsino_count
dtype: int64
- name: azelaoyl_count
dtype: int64
- name: azido_count
dtype: int64
- name: azo_count
dtype: int64
- name: azoxy_count
dtype: int64
- name: benzal_count
dtype: int64
- name: benzamido_count
dtype: int64
- name: benzhydrol_count
dtype: int64
- name: benzoxy_count
dtype: int64
- name: benzoyl_count
dtype: int64
- name: benzylidene_count
dtype: int64
- name: benzylidyne_count
dtype: int64
- name: biphenylyl_count
dtype: int64
- name: biphenylene_count
dtype: int64
- name: butoxy_count
dtype: int64
- name: sec-butoxy_count
dtype: int64
- name: tert-butoxy_count
dtype: int64
- name: butyl_count
dtype: int64
- name: sec-butyl_count
dtype: int64
- name: butyryl_count
dtype: int64
- name: caproyl_count
dtype: int64
- name: capryl_count
dtype: int64
- name: capryloyl_count
dtype: int64
- name: carbamido_count
dtype: int64
- name: carbamoyl_count
dtype: int64
- name: carbamyl_count
dtype: int64
- name: carbazoyl_count
dtype: int64
- name: carbethoxy_count
dtype: int64
- name: carbonyl_count
dtype: int64
- name: carboxy_count
dtype: int64
- name: cetyl_count
dtype: int64
- name: chloroformyl_count
dtype: int64
- name: cinnamoyl_count
dtype: int64
- name: cinnamyl_count
dtype: int64
- name: cinnamylidene_count
dtype: int64
- name: cresyl_count
dtype: int64
- name: crotonoyl_count
dtype: int64
- name: crotyl_count
dtype: int64
- name: cyanamido_count
dtype: int64
- name: cyanato_count
dtype: int64
- name: cyano_count
dtype: int64
- name: decanedioyl_count
dtype: int64
- name: decanoyl_count
dtype: int64
- name: diazo_count
dtype: int64
- name: diazoamino_count
dtype: int64
- name: disilanyl_count
dtype: int64
- name: disiloxanyloxy_count
dtype: int64
- name: disulfinyl_count
dtype: int64
- name: dithio_count
dtype: int64
- name: enanthoyl_count
dtype: int64
- name: epoxy_count
dtype: int64
- name: ethenyl_count
dtype: int64
- name: ethynyl_count
dtype: int64
- name: ethoxy_count
dtype: int64
- name: ethylene_count
dtype: int64
- name: ethylidene_count
dtype: int64
- name: ethylthio_count
dtype: int64
- name: formamido_count
dtype: int64
- name: furmaroyl_count
dtype: int64
- name: furfuryl_count
dtype: int64
- name: furfurylidene_count
dtype: int64
- name: glutamoyl_count
dtype: int64
- name: glutaryl_count
dtype: int64
- name: glycylamino_count
dtype: int64
- name: glycoloyl_count
dtype: int64
- name: glycyl_count
dtype: int64
- name: glyoxyoyl_count
dtype: int64
- name: guanidino_count
dtype: int64
- name: guanyl_count
dtype: int64
- name: heptadecanoyl_count
dtype: int64
- name: heptanamido_count
dtype: int64
- name: heptanoyl_count
dtype: int64
- name: hexadecanoyl_count
dtype: int64
- name: hexamethylene_count
dtype: int64
- name: hexanedioyl_count
dtype: int64
- name: hippuryl_count
dtype: int64
- name: hydrazino_count
dtype: int64
- name: hydrazo_count
dtype: int64
- name: hydrocinnamoyl_count
dtype: int64
- name: hydroperoxy_count
dtype: int64
- name: hydroxyamino_count
dtype: int64
- name: imino_count
dtype: int64
- name: iodoso_count
dtype: int64
- name: iodyl_count
dtype: int64
- name: isoamyl_count
dtype: int64
- name: isobutenyl_count
dtype: int64
- name: isobutoxy_count
dtype: int64
- name: isobutyl_count
dtype: int64
- name: isobutylidene_count
dtype: int64
- name: isobutyryl_count
dtype: int64
- name: isocyanato_count
dtype: int64
- name: isocyano_count
dtype: int64
- name: isohexyl_count
dtype: int64
- name: isoleucyl_count
dtype: int64
- name: isonitroso_count
dtype: int64
- name: isopentyl_count
dtype: int64
- name: isopentylidene_count
dtype: int64
- name: isopropenyl_count
dtype: int64
- name: isopropoxy_count
dtype: int64
- name: isopropyl_count
dtype: int64
- name: isopropylidene_count
dtype: int64
- name: isothiocynato_count
dtype: int64
- name: isovaleryl_count
dtype: int64
- name: lactoyl_count
dtype: int64
- name: lauroyl_count
dtype: int64
- name: lauryl_count
dtype: int64
- name: leucyl_count
dtype: int64
- name: levulinoyl_count
dtype: int64
- name: malonyl_count
dtype: int64
- name: mandeloyl_count
dtype: int64
- name: mercapto_count
dtype: int64
- name: mesityl_count
dtype: int64
- name: methacryloyl_count
dtype: int64
- name: methallyl_count
dtype: int64
- name: methionyl_count
dtype: int64
- name: methoxy_count
dtype: int64
- name: methylene_count
dtype: int64
- name: methylthio_count
dtype: int64
- name: myristoyl_count
dtype: int64
- name: myristyl_count
dtype: int64
- name: naphthyl_count
dtype: int64
- name: naphthylene_count
dtype: int64
- name: neopentyl_count
dtype: int64
- name: nitramino_count
dtype: int64
- name: nitrosamino_count
dtype: int64
- name: nitroso_count
dtype: int64
- name: nonanoyl_count
dtype: int64
- name: oleoyl_count
dtype: int64
- name: oxalyl_count
dtype: int64
- name: oxo_count
dtype: int64
- name: palmitoyl_count
dtype: int64
- name: pentamethylene_count
dtype: int64
- name: pentyl_count
dtype: int64
- name: tert-pentyl_count
dtype: int64
- name: phenacylidene_count
dtype: int64
- name: phenethyl_count
dtype: int64
- name: phenoxy_count
dtype: int64
- name: phenyl_count
dtype: int64
- name: phenylene_count
dtype: int64
- name: phosphino_count
dtype: int64
- name: phosphinyl_count
dtype: int64
- name: phospho_count
dtype: int64
- name: phosphono_count
dtype: int64
- name: phthaloyl_count
dtype: int64
- name: picryl_count
dtype: int64
- name: pimeloyl_count
dtype: int64
- name: piperidino_count
dtype: int64
- name: pivaloyl_count
dtype: int64
- name: prenyl_count
dtype: int64
- name: propargyl_count
dtype: int64
- name: 1-propenyl_count
dtype: int64
- name: 2-propenyl_count
dtype: int64
- name: propionyl_count
dtype: int64
- name: propoxy_count
dtype: int64
- name: propyl_count
dtype: int64
- name: propylidene_count
dtype: int64
- name: pyrryl_count
dtype: int64
- name: salicyloyl_count
dtype: int64
- name: selenyl_count
dtype: int64
- name: seryl_count
dtype: int64
- name: siloxy_count
dtype: int64
- name: silyl_count
dtype: int64
- name: silyene_count
dtype: int64
- name: sorboyl_count
dtype: int64
- name: stearoyl_count
dtype: int64
- name: stearyl_count
dtype: int64
- name: styryl_count
dtype: int64
- name: suberoyl_count
dtype: int64
- name: succinyl_count
dtype: int64
- name: sulfamino_count
dtype: int64
- name: sulfamoyl_count
dtype: int64
- name: sulfanilyl_count
dtype: int64
- name: sulfeno_count
dtype: int64
- name: sulfhydryl_count
dtype: int64
- name: sulfinyl_count
dtype: int64
- name: sulfo_count
dtype: int64
- name: sulfonyl_count
dtype: int64
- name: terephthaloyl_count
dtype: int64
- name: tetramethylene_count
dtype: int64
- name: thienyl_count
dtype: int64
- name: thiocarbonyl_count
dtype: int64
- name: thiocarboxy_count
dtype: int64
- name: thiocyanato_count
dtype: int64
- name: thionyl_count
dtype: int64
- name: threonyl_count
dtype: int64
- name: toluidino_count
dtype: int64
- name: toluoyl_count
dtype: int64
- name: tolyl_count
dtype: int64
- name: alpha-tolyl_count
dtype: int64
- name: tolylene_count
dtype: int64
- name: tosyl_count
dtype: int64
- name: triazano_count
dtype: int64
- name: trimethylene_count
dtype: int64
- name: valeryl_count
dtype: int64
- name: valyl_count
dtype: int64
- name: vinyl_count
dtype: int64
- name: vinylidene_count
dtype: int64
- name: xylidino_count
dtype: int64
- name: xylyl_count
dtype: int64
- name: xylylene_count
dtype: int64
- name: propiolamide_count
dtype: int64
- name: fumarate ester_count
dtype: int64
- name: allenamide_count
dtype: int64
- name: propiolonitrile_count
dtype: int64
- name: propargylamide_count
dtype: int64
- name: arylsulfonyl bicyclobutane_count
dtype: int64
- name: haloalkane_count
dtype: int64
- name: alpha-halomethyl_count
dtype: int64
- name: alpha-haloamide_count
dtype: int64
- name: alpha-haloester_count
dtype: int64
- name: epoxide_count
dtype: int64
- name: aziridine_count
dtype: int64
- name: nitroalkane_count
dtype: int64
- name: acrylamide_count
dtype: int64
- name: cyanoenone_count
dtype: int64
- name: aldehyde_count
dtype: int64
- name: ketone_count
dtype: int64
- name: nitrile_count
dtype: int64
- name: cyanamide_count
dtype: int64
- name: isothicyanate_count
dtype: int64
- name: sulfone_count
dtype: int64
- name: sulfonyl fluoride_count
dtype: int64
- name: sulfonimidoyl fluoride_count
dtype: int64
- name: aryl fluorosulfate_count
dtype: int64
- name: ester_count
dtype: int64
- name: sulfonamide_count
dtype: int64
- name: 2-carbonyl arylboronic acid_count
dtype: int64
- name: n-methyl isoxazolium_count
dtype: int64
- name: oxaziridine_count
dtype: int64
- name: carboxyl_count
dtype: int64
- name: ether_count
dtype: int64
- name: alkanol_count
dtype: int64
- name: thiol_count
dtype: int64
- name: halogen_count
dtype: int64
- name: amine_count
dtype: int64
- name: amide_count
dtype: int64
- name: num_valence_electrons
dtype: int64
- name: rotable_proportion
dtype: float64
- name: non_rotable_proportion
dtype: float64
- name: num_unspecified_bond
dtype: float64
- name: num_single_bonds
dtype: float64
- name: num_double_bonds
dtype: float64
- name: num_triple_bonds
dtype: float64
- name: num_quadruple_bonds
dtype: float64
- name: num_quintuple_bonds
dtype: float64
- name: num_hextuple_bonds
dtype: float64
- name: num_oneandahalf_bonds
dtype: float64
- name: num_twoandahalf_bonds
dtype: float64
- name: num_threeandahalf_bonds
dtype: float64
- name: num_fourandahalf_bonds
dtype: float64
- name: num_fiveandahalf_bonds
dtype: float64
- name: num_aromatic_bonds
dtype: float64
- name: num_ionic_bonds
dtype: float64
- name: num_hydrogen_bonds
dtype: float64
- name: num_threecenter_bonds
dtype: float64
- name: num_dativeone_bonds
dtype: float64
- name: num_dative_bonds
dtype: float64
- name: num_other_bonds
dtype: float64
- name: num_zero_bonds
dtype: float64
- name: num_bonds
dtype: int64
- name: molecular_formula
dtype: string
- name: monoisotopic_molecular_mass
dtype: float64
- name: carbon_mass
dtype: float64
- name: hydrogen_mass
dtype: float64
- name: nitrogen_mass
dtype: float64
- name: oxygen_mass
dtype: float64
- name: num_carbon_atoms
dtype: int64
- name: num_hydrogen_atoms
dtype: int64
- name: num_nitrogen_atoms
dtype: int64
- name: num_oxygen_atoms
dtype: int64
- name: num_hydrogen_bond_acceptors
dtype: int64
- name: num_hydrogen_bond_donors
dtype: int64
- name: num_lipinski_violations
dtype: int64
- name: inertial_shape_factor
dtype: float64
- name: eccentricity
dtype: float64
- name: asphericity
dtype: float64
- name: npr1_value
dtype: float64
- name: npr2_value
dtype: float64
- name: pmi1_value
dtype: float64
- name: pmi2_value
dtype: float64
- name: pmi3_value
dtype: float64
- name: num_chiral_centers
dtype: int64
- name: representation
dtype: string
splits:
- name: train
num_bytes: 2756085
num_examples: 500
download_size: 497203
dataset_size: 2756085
- config_name: rdkit_feat_3
features:
- name: tert-butyloxycarbonyl_count
dtype: int64
- name: representation_type
dtype: string
- name: trityl_count
dtype: int64
- name: 3,5-dimethoxyphenylisoproxycarbonyl_count
dtype: int64
- name: 2-(4-biphenyl)isopropoxycarbonyl_count
dtype: int64
- name: 2-nitrophenylsulfenyl_count
dtype: int64
- name: boc_count
dtype: int64
- name: trt_count
dtype: int64
- name: ddz_count
dtype: int64
- name: bpoc_count
dtype: int64
- name: nps_count
dtype: int64
- name: 9-fluorenylmethoxycarbonyl_count
dtype: int64
- name: 2-(4-nitrophenylsulfonyl)ethoxycarbonyl_count
dtype: int64
- name: (1,1-dioxobenzo[b]thiophene-2-yl)methyloxycarbonyl_count
dtype: int64
- name: (1,1-dioxonaptho[1,2-b]thiophene-2-yl)methyloxycarbonyl_count
dtype: int64
- name: 1-(4,4-dimethyl-2,6-dioxocyclohex-1-ylidene)-3-methylbutyl_count
dtype: int64
- name: 2,7-di-tert-butyl-fmoc_count
dtype: int64
- name: 2-fluoro-fmoc_count
dtype: int64
- name: 2-monoisooctyl-fmoc_count
dtype: int64
- name: 2,7-diisooctyl-fmoc_count
dtype: int64
- name: tetrachlorophthaloyl_count
dtype: int64
- name: 2-[phenyl(methyl)sulfonio])ethyloxycarbonyltetrafluoroborate_count
dtype: int64
- name: ethanesulfonylethoxycarbonyl_count
dtype: int64
- name: 2-(4-sulfophenylsulfonyl)ethoxycarbonyl_count
dtype: int64
- name: fmoc_count
dtype: int64
- name: nsc_count
dtype: int64
- name: bsmoc_count
dtype: int64
- name: alpha-nsmoc_count
dtype: int64
- name: ivdde_count
dtype: int64
- name: fmoc*_count
dtype: int64
- name: fmoc(fmoc(2f))_count
dtype: int64
- name: mio-fmoc_count
dtype: int64
- name: dio-fmoc_count
dtype: int64
- name: tcp_count
dtype: int64
- name: pms_count
dtype: int64
- name: esc_count
dtype: int64
- name: sps_count
dtype: int64
- name: benzyloxycarbonyl_count
dtype: int64
- name: allyloxycarbonyl_count
dtype: int64
- name: o-nitrobenzenesulfonyl_count
dtype: int64
- name: 2,4-dinitrobenzenesulfonyl_count
dtype: int64
- name: benzothiazole-2-sulfonyl_count
dtype: int64
- name: 2,2,2-trichloroethyloxycarbonyl_count
dtype: int64
- name: dithiasuccinoyl_count
dtype: int64
- name: p-nitrobenzyloxycarbonyl_count
dtype: int64
- name: alpha-azidoacids_count
dtype: int64
- name: proparglyoxycarbonyl_count
dtype: int64
- name: o-nitrobenzylcarbonyl_count
dtype: int64
- name: 4-nitroveratryloxycarbonyl_count
dtype: int64
- name: 2-(2-nitrophenyl)propyloxycarbonyl_count
dtype: int64
- name: 2-(3,4-methylenedioxy-6-nitrophenyl)propyloxycarbonyl_count
dtype: int64
- name: 9-(4-bromophenyl)-9-fluorenyl_count
dtype: int64
- name: azidomethoxycarbonyl_count
dtype: int64
- name: hexafluoroacetone_count
dtype: int64
- name: Z_count
dtype: int64
- name: alloc_count
dtype: int64
- name: o-nbs_count
dtype: int64
- name: d-nbs_count
dtype: int64
- name: bts_count
dtype: int64
- name: troc_count
dtype: int64
- name: dts_count
dtype: int64
- name: pnz_count
dtype: int64
- name: poc_count
dtype: int64
- name: onz_count
dtype: int64
- name: nvoc_count
dtype: int64
- name: nppoc_count
dtype: int64
- name: mnppoc_count
dtype: int64
- name: brphf_count
dtype: int64
- name: azoc_count
dtype: int64
- name: hfa_count
dtype: int64
- name: 2-chlorobenzyloxycarbonyl_count
dtype: int64
- name: 4-methyltrityl_count
dtype: int64
- name: cl-z_count
dtype: int64
- name: mtt_count
dtype: int64
- name: 1-(4,4-dimethyl-2,6-dioxocylohex-1-ylidene)-3-methylbutyl_count
dtype: int64
- name: trifluoroacetyl_count
dtype: int64
- name: 2-(methylsulfonyl)ethoxycarbonyl_count
dtype: int64
- name: tfa_count
dtype: int64
- name: msc_count
dtype: int64
- name: phenyldisulphanylethyloxycarbonyl_count
dtype: int64
- name: 2-pyridyldisulphanylethyloxycarbonyl_count
dtype: int64
- name: phdec_count
dtype: int64
- name: pydec_count
dtype: int64
- name: tert-butyl_count
dtype: int64
- name: 2-chlorotrityl_count
dtype: int64
- name: 2-4-dimethyoxybenzyl_count
dtype: int64
- name: 2-phenylisopropyl_count
dtype: int64
- name: 5-phenyl-3,4-ethylenedioxythenyl_count
dtype: int64
- name: bu_count
dtype: int64
- name: 2-cl-trt_count
dtype: int64
- name: dmb_count
dtype: int64
- name: 2-ph-pr_count
dtype: int64
- name: phenyl-edotn_count
dtype: int64
- name: 9-fluorenylmethyl_count
dtype: int64
- name: 4-(N-[1-(4,4-dimethyl-2,6-dioxocylocheylidene)-3-methylbutyl]-amino)benzyl_count
dtype: int64
- name: methyl_count
dtype: int64
- name: ethyl_count
dtype: int64
- name: carbamoylmethyl_count
dtype: int64
- name: fm_count
dtype: int64
- name: dmab_count
dtype: int64
- name: me_count
dtype: int64
- name: et_count
dtype: int64
- name: cam_count
dtype: int64
- name: allyl_count
dtype: int64
- name: benzyl_count
dtype: int64
- name: phenacyl_count
dtype: int64
- name: p-nitrobenzyl_count
dtype: int64
- name: 2-trimethylsilyethyl_count
dtype: int64
- name: (2-phenyl-2-trimethylsilyl)ethyl_count
dtype: int64
- name: 2-(trimethylsilyl)isopropyl_count
dtype: int64
- name: 2,2,2-trichloroethyl_count
dtype: int64
- name: p-hydroxyphenacyl_count
dtype: int64
- name: 4,5-dimethyoxy-2-nitrobenzyl_count
dtype: int64
- name: 1,1-dimethylallyl_count
dtype: int64
- name: pentaaminecobalt_III_count
dtype: int64
- name: al_count
dtype: int64
- name: bn_count
dtype: int64
- name: pac_count
dtype: int64
- name: pnb_count
dtype: int64
- name: tmse_count
dtype: int64
- name: ptmse_count
dtype: int64
- name: tmsi_count
dtype: int64
- name: tce_count
dtype: int64
- name: php_count
dtype: int64
- name: dmnb_count
dtype: int64
- name: dma_count
dtype: int64
- name: cyclohexyl_count
dtype: int64
- name: b-menthyl_count
dtype: int64
- name: b-3-methylpent-3-yl_count
dtype: int64
- name: 4-(3,6,9-trioxadecyl)oxybenzyl_count
dtype: int64
- name: chx_count
dtype: int64
- name: men_count
dtype: int64
- name: mpe_count
dtype: int64
- name: tegbz_count
dtype: int64
- name: 9-fluoroenylmethyl_count
dtype: int64
- name: 4-(N-[1-(4,4-dimethyl-2,6-dioxocyclohexylidene)-3-methyl-butyl]-amino)benzyl_count
dtype: int64
- name: trimethylsilylethyl_count
dtype: int64
- name: 4,5-dimethoxy-2-nitrobenzyloxycarbonyl_count
dtype: int64
- name: pseudoprolines_count
dtype: int64
- name: 2-hydroxy-4-methoxybenzyl_count
dtype: int64
- name: 2,4-dimethoxybenzyl_count
dtype: int64
- name: 2,4,6-trimethoxybenzyl_count
dtype: int64
- name: 1-methyl-3-indolylmethyl_count
dtype: int64
- name: 3,4-ethylene-dioxy-2-thenyl_count
dtype: int64
- name: hmb_count
dtype: int64
- name: tmob_count
dtype: int64
- name: mim_count
dtype: int64
- name: edot_count
dtype: int64
- name: 4-methoxy-2-nitro-benzyl_count
dtype: int64
- name: (6-hydroxy-3-oxido-1,3-benz[d]oxathiol-5-yl)methyl_count
dtype: int64
- name: 2-hydroxy-4-methoxy-5-(methylsulfinyl)benzyl_count
dtype: int64
- name: n-boc-n-methyl[2-(methylamino)ethyl]carbamoyl-hmb_count
dtype: int64
- name: 9-xanthenyl_count
dtype: int64
- name: cyclopropyldimethylcarbinyl_count
dtype: int64
- name: 4,4-dimethoxybenzhydryl_count
dtype: int64
- name: xan_count
dtype: int64
- name: cpd_count
dtype: int64
- name: mbh_count
dtype: int64
- name: p-toluenesulfonyl_count
dtype: int64
- name: 2,2,5,7,8-pentamethylchroman-6-sulfonyl_count
dtype: int64
- name: 2,2,4,6,7-pentamethyl-2,3-dihydrobenzofuran-5-sulfonyl_count
dtype: int64
- name: mesityl-2-sulfonyl_count
dtype: int64
- name: 4-methoxy-2,3,6-trimethylphenylsulfonyl_count
dtype: int64
- name: 1,2-dimethylindole-3-sulfonyl_count
dtype: int64
- name: w,w-bis-tert-butyloxycarbonyl_count
dtype: int64
- name: 5-dibenzosuberenyl_count
dtype: int64
- name: 5-dibenzosuberyl_count
dtype: int64
- name: 2-methoxy-5-dibenzosuberyl_count
dtype: int64
- name: nitro_count
dtype: int64
- name: tos_count
dtype: int64
- name: pmc_count
dtype: int64
- name: pbf_count
dtype: int64
- name: mts_count
dtype: int64
- name: mtr_count
dtype: int64
- name: mis_count
dtype: int64
- name: bis-boc_count
dtype: int64
- name: suben_count
dtype: int64
- name: sub_count
dtype: int64
- name: mesub_count
dtype: int64
- name: no2_count
dtype: int64
- name: w,w-bis-benzyloxycarbonyl_count
dtype: int64
- name: w,w-bis-allyloxycarbonyl_count
dtype: int64
- name: z-small_count
dtype: int64
- name: p-methylbenzyl_count
dtype: int64
- name: p-methoxybenzyl_count
dtype: int64
- name: monomethoxytrityl_count
dtype: int64
- name: trimethoxybenzyl_count
dtype: int64
- name: 2,2,4,6,7-pentamethyl-5-dihydrobenzofuranylmethyl_count
dtype: int64
- name: 1-adamantyl_count
dtype: int64
- name: meb_count
dtype: int64
- name: mob_count
dtype: int64
- name: mmt_count
dtype: int64
- name: pmbf_count
dtype: int64
- name: 1-ada_count
dtype: int64
- name: 2-(2,4-dinitrophenyl)ethyl_count
dtype: int64
- name: 9-fluororenylmethoxycarbonyl_count
dtype: int64
- name: dnpe_count
dtype: int64
- name: acetamidomethyl_count
dtype: int64
- name: phenylacetamidomethyl_count
dtype: int64
- name: 5-tert-butylmercapto_count
dtype: int64
- name: 3-nitro-2-pyridinesulfenyl_count
dtype: int64
- name: 2-pyridinesulfenyl_count
dtype: int64
- name: N-allyloxycarbonyl-N-[2,3,5,6-tetrafluoro-4-(phenylthio)phenyl]]aminomethyl_count
dtype: int64
- name: o-nitrobenzyl_count
dtype: int64
- name: 4-picolyl_count
dtype: int64
- name: ninhydrin_count
dtype: int64
- name: acm_count
dtype: int64
- name: phacm_count
dtype: int64
- name: sbu_count
dtype: int64
- name: npys_count
dtype: int64
- name: s-pyr_count
dtype: int64
- name: fsam_count
dtype: int64
- name: onb_count
dtype: int64
- name: nin_count
dtype: int64
- name: n-tosyl_count
dtype: int64
- name: n-trityl_count
dtype: int64
- name: n-monomethoxytrityl_count
dtype: int64
- name: n-methyltrityl_count
dtype: int64
- name: n-tert-butyloxycarbonyl_count
dtype: int64
- name: n-2,4-dimethylpent-3-yloxycarbonyl_count
dtype: int64
- name: n-benzyloxymethyl_count
dtype: int64
- name: n-tert-butoxymethyl_count
dtype: int64
- name: ntos_count
dtype: int64
- name: ntrt_count
dtype: int64
- name: nmtt_count
dtype: int64
- name: nmmt_count
dtype: int64
- name: nboc_count
dtype: int64
- name: ndoc_count
dtype: int64
- name: nbom_count
dtype: int64
- name: nbum_count
dtype: int64
- name: N-9-fluorenylmethoxycarbonyl_count
dtype: int64
- name: N-2,6-dimethoxybenzoyl_count
dtype: int64
- name: dmbz_count
dtype: int64
- name: N-2,4-dinitrophenyl_count
dtype: int64
- name: dnp_count
dtype: int64
- name: cyclohexyl;_count
dtype: int64
- name: tert-butyldimethylsilyl_count
dtype: int64
- name: tbdms_count
dtype: int64
- name: tert-butyldiphenylsilyl_count
dtype: int64
- name: propargyloxycarbonyl_count
dtype: int64
- name: tbdps_count
dtype: int64
- name: 2,6-dichlorobenzyl_count
dtype: int64
- name: 2-bromobenzyl_count
dtype: int64
- name: 2-bromobenzyloxycarbonyl_count
dtype: int64
- name: 3-pentyl_count
dtype: int64
- name: dcb_count
dtype: int64
- name: brbn_count
dtype: int64
- name: brz_count
dtype: int64
- name: pen_count
dtype: int64
- name: tegb_count
dtype: int64
- name: boc-n-methyl-n-[2-(methylamino)ethyl]carbamoyl_count
dtype: int64
- name: boc-nmec_count
dtype: int64
- name: formyl_count
dtype: int64
- name: cyclohexyloxycarbonyl_count
dtype: int64
- name: for_count
dtype: int64
- name: hoc_count
dtype: int64
- name: cyclopropane_count
dtype: int64
- name: spiropentane_count
dtype: int64
- name: cyclobutane_count
dtype: int64
- name: cyclopentane_count
dtype: int64
- name: furan_count
dtype: int64
- name: thiophene_count
dtype: int64
- name: pyrrole_count
dtype: int64
- name: 2H-pyrrole_count
dtype: int64
- name: 3H-pyrrole_count
dtype: int64
- name: pyrazole_count
dtype: int64
- name: 2H-imidazole_count
dtype: int64
- name: 1,2,3-triazole_count
dtype: int64
- name: 1,2,4-triazole_count
dtype: int64
- name: 1,2-dithiole_count
dtype: int64
- name: 1,3-dithiole_count
dtype: int64
- name: 3H-1,2-oxathiole_count
dtype: int64
- name: isoxazole_count
dtype: int64
- name: oxazole_count
dtype: int64
- name: thiazole_count
dtype: int64
- name: isothiazole_count
dtype: int64
- name: 1,2,3-oxadiazole_count
dtype: int64
- name: 1,2,4-oxadiazole_count
dtype: int64
- name: 1,2,5-oxadiazole_count
dtype: int64
- name: 1,3,4-oxadiazole_count
dtype: int64
- name: 1,2,3,4-oxatriazole_count
dtype: int64
- name: 1,2,3,5-oxatriazole_count
dtype: int64
- name: 3H-1,2,3-dioxazole_count
dtype: int64
- name: 1,2,4-dioxazole_count
dtype: int64
- name: 1,3,2-dioxazole_count
dtype: int64
- name: 1,3,4-dioxazole_count
dtype: int64
- name: 5H-1,2,5-oxathiazole_count
dtype: int64
- name: 1,3-oxathiole_count
dtype: int64
- name: benzene_count
dtype: int64
- name: cyclohexane_count
dtype: int64
- name: 2H-pyran_count
dtype: int64
- name: 4H-pyran_count
dtype: int64
- name: 2H-pyran-2-one_count
dtype: int64
- name: 4H-pyran-4-one_count
dtype: int64
- name: 1,2-dioxin_count
dtype: int64
- name: 1,3-dioxin_count
dtype: int64
- name: pyridine_count
dtype: int64
- name: pyridazine_count
dtype: int64
- name: pyrimidine_count
dtype: int64
- name: pyrazine_count
dtype: int64
- name: piperazine_count
dtype: int64
- name: 1,3,5-triazine_count
dtype: int64
- name: 1,2,4-triazine_count
dtype: int64
- name: 1,2,3-triazine_count
dtype: int64
- name: 4H-1,2-Oxazine_count
dtype: int64
- name: 2H-1,3-Oxazine_count
dtype: int64
- name: 6H-1,3-Oxazine_count
dtype: int64
- name: 6H-1,2-Oxazine_count
dtype: int64
- name: 1,4-Oxazine_count
dtype: int64
- name: 2H-1,2-Oxazine_count
dtype: int64
- name: 4H-1,4-Oxazine_count
dtype: int64
- name: 1,2,5-Oxathiazine_count
dtype: int64
- name: 1,2,6-Oxathiazine_count
dtype: int64
- name: 1,2,4-Oxadiazine_count
dtype: int64
- name: 1,3,5-Oxadiazine_count
dtype: int64
- name: morpholine_count
dtype: int64
- name: azepine_count
dtype: int64
- name: oxepin_count
dtype: int64
- name: thiepin_count
dtype: int64
- name: 4H-1,2-diazepine_count
dtype: int64
- name: indene_count
dtype: int64
- name: 2H-indene_count
dtype: int64
- name: benzofuran_count
dtype: int64
- name: isobenzofuran_count
dtype: int64
- name: benzo[b]thiophene_count
dtype: int64
- name: benzo[c]thiophene_count
dtype: int64
- name: indole_count
dtype: int64
- name: 3H-indole_count
dtype: int64
- name: 1H-indole_count
dtype: int64
- name: cyclopenta[b]pyridine_count
dtype: int64
- name: pyrano[3,4-b]-pyrrole_count
dtype: int64
- name: indazole_count
dtype: int64
- name: benzisoxazole_count
dtype: int64
- name: benzoxazole_count
dtype: int64
- name: 2,1-benzisoxazole_count
dtype: int64
- name: naphthalene_count
dtype: int64
- name: 1,2,3,4-tetrahydronaphthalene_count
dtype: int64
- name: octahydronaphthalene_count
dtype: int64
- name: 2H-1-benzopyran_count
dtype: int64
- name: 2H-1-benzopyran-2-one_count
dtype: int64
- name: 4H-1-benzopyran-4-one_count
dtype: int64
- name: 1H-2-benzopyran-1-one_count
dtype: int64
- name: 3H-2-benzopyran-1-one_count
dtype: int64
- name: quinoline_count
dtype: int64
- name: isoquinoline_count
dtype: int64
- name: cinnoline_count
dtype: int64
- name: quinazoline_count
dtype: int64
- name: 1,8-napthyhridine_count
dtype: int64
- name: 1,7-napththyridine_count
dtype: int64
- name: 1,5-napththridine_count
dtype: int64
- name: 1,6-napthyridine_count
dtype: int64
- name: 2H-1,3-benzoxazine_count
dtype: int64
- name: 2H-1,4-benzoxazine_count
dtype: int64
- name: 1H-2,3-benzoxazine_count
dtype: int64
- name: 4H-3,1-benzoxazine_count
dtype: int64
- name: 2H-1,2-benzoxazine_count
dtype: int64
- name: 4H-1,3-benzoxazine_count
dtype: int64
- name: anthracene_count
dtype: int64
- name: phenanthrene_count
dtype: int64
- name: phenalene_count
dtype: int64
- name: fluorene_count
dtype: int64
- name: carbazole_count
dtype: int64
- name: xanthene_count
dtype: int64
- name: acridine_count
dtype: int64
- name: norpinane_count
dtype: int64
- name: 7H-purine_count
dtype: int64
- name: steroid_ring_system_count
dtype: int64
- name: imidazole_count
dtype: int64
- name: thiazol-2-amine_count
dtype: int64
- name: tetrazole_count
dtype: int64
- name: cytosine_count
dtype: int64
- name: adenine_count
dtype: int64
- name: 5-methylindole_count
dtype: int64
- name: isocaffeine_count
dtype: int64
- name: tetrazolethiol_count
dtype: int64
- name: 3-methylisoxazole_count
dtype: int64
- name: 1-methylimidazole_count
dtype: int64
- name: 2-methylimidazole_count
dtype: int64
- name: guanine_count
dtype: int64
- name: tosufloxacin_count
dtype: int64
- name: acetamido_count
dtype: int64
- name: acetoacetyl_count
dtype: int64
- name: acetyl_count
dtype: int64
- name: acryloyl_count
dtype: int64
- name: alanyl_count
dtype: int64
- name: beta-alanyl_count
dtype: int64
- name: allylidene_count
dtype: int64
- name: amidino_count
dtype: int64
- name: amino_count
dtype: int64
- name: amyl_count
dtype: int64
- name: anilino_count
dtype: int64
- name: anisidino_count
dtype: int64
- name: anthranoyl_count
dtype: int64
- name: arsino_count
dtype: int64
- name: azelaoyl_count
dtype: int64
- name: azido_count
dtype: int64
- name: azo_count
dtype: int64
- name: azoxy_count
dtype: int64
- name: benzal_count
dtype: int64
- name: benzamido_count
dtype: int64
- name: benzhydrol_count
dtype: int64
- name: benzoxy_count
dtype: int64
- name: benzoyl_count
dtype: int64
- name: benzylidene_count
dtype: int64
- name: benzylidyne_count
dtype: int64
- name: biphenylyl_count
dtype: int64
- name: biphenylene_count
dtype: int64
- name: butoxy_count
dtype: int64
- name: sec-butoxy_count
dtype: int64
- name: tert-butoxy_count
dtype: int64
- name: butyl_count
dtype: int64
- name: sec-butyl_count
dtype: int64
- name: butyryl_count
dtype: int64
- name: caproyl_count
dtype: int64
- name: capryl_count
dtype: int64
- name: capryloyl_count
dtype: int64
- name: carbamido_count
dtype: int64
- name: carbamoyl_count
dtype: int64
- name: carbamyl_count
dtype: int64
- name: carbazoyl_count
dtype: int64
- name: carbethoxy_count
dtype: int64
- name: carbonyl_count
dtype: int64
- name: carboxy_count
dtype: int64
- name: cetyl_count
dtype: int64
- name: chloroformyl_count
dtype: int64
- name: cinnamoyl_count
dtype: int64
- name: cinnamyl_count
dtype: int64
- name: cinnamylidene_count
dtype: int64
- name: cresyl_count
dtype: int64
- name: crotonoyl_count
dtype: int64
- name: crotyl_count
dtype: int64
- name: cyanamido_count
dtype: int64
- name: cyanato_count
dtype: int64
- name: cyano_count
dtype: int64
- name: decanedioyl_count
dtype: int64
- name: decanoyl_count
dtype: int64
- name: diazo_count
dtype: int64
- name: diazoamino_count
dtype: int64
- name: disilanyl_count
dtype: int64
- name: disiloxanyloxy_count
dtype: int64
- name: disulfinyl_count
dtype: int64
- name: dithio_count
dtype: int64
- name: enanthoyl_count
dtype: int64
- name: epoxy_count
dtype: int64
- name: ethenyl_count
dtype: int64
- name: ethynyl_count
dtype: int64
- name: ethoxy_count
dtype: int64
- name: ethylene_count
dtype: int64
- name: ethylidene_count
dtype: int64
- name: ethylthio_count
dtype: int64
- name: formamido_count
dtype: int64
- name: furmaroyl_count
dtype: int64
- name: furfuryl_count
dtype: int64
- name: furfurylidene_count
dtype: int64
- name: glutamoyl_count
dtype: int64
- name: glutaryl_count
dtype: int64
- name: glycylamino_count
dtype: int64
- name: glycoloyl_count
dtype: int64
- name: glycyl_count
dtype: int64
- name: glyoxyoyl_count
dtype: int64
- name: guanidino_count
dtype: int64
- name: guanyl_count
dtype: int64
- name: heptadecanoyl_count
dtype: int64
- name: heptanamido_count
dtype: int64
- name: heptanoyl_count
dtype: int64
- name: hexadecanoyl_count
dtype: int64
- name: hexamethylene_count
dtype: int64
- name: hexanedioyl_count
dtype: int64
- name: hippuryl_count
dtype: int64
- name: hydrazino_count
dtype: int64
- name: hydrazo_count
dtype: int64
- name: hydrocinnamoyl_count
dtype: int64
- name: hydroperoxy_count
dtype: int64
- name: hydroxyamino_count
dtype: int64
- name: imino_count
dtype: int64
- name: iodoso_count
dtype: int64
- name: iodyl_count
dtype: int64
- name: isoamyl_count
dtype: int64
- name: isobutenyl_count
dtype: int64
- name: isobutoxy_count
dtype: int64
- name: isobutyl_count
dtype: int64
- name: isobutylidene_count
dtype: int64
- name: isobutyryl_count
dtype: int64
- name: isocyanato_count
dtype: int64
- name: isocyano_count
dtype: int64
- name: isohexyl_count
dtype: int64
- name: isoleucyl_count
dtype: int64
- name: isonitroso_count
dtype: int64
- name: isopentyl_count
dtype: int64
- name: isopentylidene_count
dtype: int64
- name: isopropenyl_count
dtype: int64
- name: isopropoxy_count
dtype: int64
- name: isopropyl_count
dtype: int64
- name: isopropylidene_count
dtype: int64
- name: isothiocynato_count
dtype: int64
- name: isovaleryl_count
dtype: int64
- name: lactoyl_count
dtype: int64
- name: lauroyl_count
dtype: int64
- name: lauryl_count
dtype: int64
- name: leucyl_count
dtype: int64
- name: levulinoyl_count
dtype: int64
- name: malonyl_count
dtype: int64
- name: mandeloyl_count
dtype: int64
- name: mercapto_count
dtype: int64
- name: mesityl_count
dtype: int64
- name: methacryloyl_count
dtype: int64
- name: methallyl_count
dtype: int64
- name: methionyl_count
dtype: int64
- name: methoxy_count
dtype: int64
- name: methylene_count
dtype: int64
- name: methylthio_count
dtype: int64
- name: myristoyl_count
dtype: int64
- name: myristyl_count
dtype: int64
- name: naphthyl_count
dtype: int64
- name: naphthylene_count
dtype: int64
- name: neopentyl_count
dtype: int64
- name: nitramino_count
dtype: int64
- name: nitrosamino_count
dtype: int64
- name: nitroso_count
dtype: int64
- name: nonanoyl_count
dtype: int64
- name: oleoyl_count
dtype: int64
- name: oxalyl_count
dtype: int64
- name: oxo_count
dtype: int64
- name: palmitoyl_count
dtype: int64
- name: pentamethylene_count
dtype: int64
- name: pentyl_count
dtype: int64
- name: tert-pentyl_count
dtype: int64
- name: phenacylidene_count
dtype: int64
- name: phenethyl_count
dtype: int64
- name: phenoxy_count
dtype: int64
- name: phenyl_count
dtype: int64
- name: phenylene_count
dtype: int64
- name: phosphino_count
dtype: int64
- name: phosphinyl_count
dtype: int64
- name: phospho_count
dtype: int64
- name: phosphono_count
dtype: int64
- name: phthaloyl_count
dtype: int64
- name: picryl_count
dtype: int64
- name: pimeloyl_count
dtype: int64
- name: piperidino_count
dtype: int64
- name: pivaloyl_count
dtype: int64
- name: prenyl_count
dtype: int64
- name: propargyl_count
dtype: int64
- name: 1-propenyl_count
dtype: int64
- name: 2-propenyl_count
dtype: int64
- name: propionyl_count
dtype: int64
- name: propoxy_count
dtype: int64
- name: propyl_count
dtype: int64
- name: propylidene_count
dtype: int64
- name: pyrryl_count
dtype: int64
- name: salicyloyl_count
dtype: int64
- name: selenyl_count
dtype: int64
- name: seryl_count
dtype: int64
- name: siloxy_count
dtype: int64
- name: silyl_count
dtype: int64
- name: silyene_count
dtype: int64
- name: sorboyl_count
dtype: int64
- name: stearoyl_count
dtype: int64
- name: stearyl_count
dtype: int64
- name: styryl_count
dtype: int64
- name: suberoyl_count
dtype: int64
- name: succinyl_count
dtype: int64
- name: sulfamino_count
dtype: int64
- name: sulfamoyl_count
dtype: int64
- name: sulfanilyl_count
dtype: int64
- name: sulfeno_count
dtype: int64
- name: sulfhydryl_count
dtype: int64
- name: sulfinyl_count
dtype: int64
- name: sulfo_count
dtype: int64
- name: sulfonyl_count
dtype: int64
- name: terephthaloyl_count
dtype: int64
- name: tetramethylene_count
dtype: int64
- name: thienyl_count
dtype: int64
- name: thiocarbonyl_count
dtype: int64
- name: thiocarboxy_count
dtype: int64
- name: thiocyanato_count
dtype: int64
- name: thionyl_count
dtype: int64
- name: threonyl_count
dtype: int64
- name: toluidino_count
dtype: int64
- name: toluoyl_count
dtype: int64
- name: tolyl_count
dtype: int64
- name: alpha-tolyl_count
dtype: int64
- name: tolylene_count
dtype: int64
- name: tosyl_count
dtype: int64
- name: triazano_count
dtype: int64
- name: trimethylene_count
dtype: int64
- name: valeryl_count
dtype: int64
- name: valyl_count
dtype: int64
- name: vinyl_count
dtype: int64
- name: vinylidene_count
dtype: int64
- name: xylidino_count
dtype: int64
- name: xylyl_count
dtype: int64
- name: xylylene_count
dtype: int64
- name: propiolamide_count
dtype: int64
- name: fumarate ester_count
dtype: int64
- name: allenamide_count
dtype: int64
- name: propiolonitrile_count
dtype: int64
- name: propargylamide_count
dtype: int64
- name: arylsulfonyl bicyclobutane_count
dtype: int64
- name: haloalkane_count
dtype: int64
- name: alpha-halomethyl_count
dtype: int64
- name: alpha-haloamide_count
dtype: int64
- name: alpha-haloester_count
dtype: int64
- name: epoxide_count
dtype: int64
- name: aziridine_count
dtype: int64
- name: nitroalkane_count
dtype: int64
- name: acrylamide_count
dtype: int64
- name: cyanoenone_count
dtype: int64
- name: aldehyde_count
dtype: int64
- name: ketone_count
dtype: int64
- name: nitrile_count
dtype: int64
- name: cyanamide_count
dtype: int64
- name: isothicyanate_count
dtype: int64
- name: sulfone_count
dtype: int64
- name: sulfonyl fluoride_count
dtype: int64
- name: sulfonimidoyl fluoride_count
dtype: int64
- name: aryl fluorosulfate_count
dtype: int64
- name: ester_count
dtype: int64
- name: sulfonamide_count
dtype: int64
- name: 2-carbonyl arylboronic acid_count
dtype: int64
- name: n-methyl isoxazolium_count
dtype: int64
- name: oxaziridine_count
dtype: int64
- name: carboxyl_count
dtype: int64
- name: ether_count
dtype: int64
- name: alkanol_count
dtype: int64
- name: thiol_count
dtype: int64
- name: halogen_count
dtype: int64
- name: amine_count
dtype: int64
- name: amide_count
dtype: int64
- name: num_valence_electrons
dtype: int64
- name: rotable_proportion
dtype: float64
- name: non_rotable_proportion
dtype: float64
- name: num_unspecified_bond
dtype: float64
- name: num_single_bonds
dtype: float64
- name: num_double_bonds
dtype: float64
- name: num_triple_bonds
dtype: float64
- name: num_quadruple_bonds
dtype: float64
- name: num_quintuple_bonds
dtype: float64
- name: num_hextuple_bonds
dtype: float64
- name: num_oneandahalf_bonds
dtype: float64
- name: num_twoandahalf_bonds
dtype: float64
- name: num_threeandahalf_bonds
dtype: float64
- name: num_fourandahalf_bonds
dtype: float64
- name: num_fiveandahalf_bonds
dtype: float64
- name: num_aromatic_bonds
dtype: float64
- name: num_ionic_bonds
dtype: float64
- name: num_hydrogen_bonds
dtype: float64
- name: num_threecenter_bonds
dtype: float64
- name: num_dativeone_bonds
dtype: float64
- name: num_dative_bonds
dtype: float64
- name: num_other_bonds
dtype: float64
- name: num_zero_bonds
dtype: float64
- name: num_bonds
dtype: int64
- name: molecular_formula
dtype: string
- name: monoisotopic_molecular_mass
dtype: float64
- name: carbon_mass
dtype: float64
- name: hydrogen_mass
dtype: float64
- name: nitrogen_mass
dtype: float64
- name: oxygen_mass
dtype: float64
- name: num_carbon_atoms
dtype: int64
- name: num_hydrogen_atoms
dtype: int64
- name: num_nitrogen_atoms
dtype: int64
- name: num_oxygen_atoms
dtype: int64
- name: num_hydrogen_bond_acceptors
dtype: int64
- name: num_hydrogen_bond_donors
dtype: int64
- name: num_lipinski_violations
dtype: int64
- name: inertial_shape_factor
dtype: float64
- name: eccentricity
dtype: float64
- name: asphericity
dtype: float64
- name: npr1_value
dtype: float64
- name: npr2_value
dtype: float64
- name: pmi1_value
dtype: float64
- name: pmi2_value
dtype: float64
- name: pmi3_value
dtype: float64
- name: num_chiral_centers
dtype: int64
- name: representation
dtype: string
splits:
- name: train
num_bytes: 2758973
num_examples: 499
download_size: 490161
dataset_size: 2758973
- config_name: rdkit_feat_4
features:
- name: tert-butyloxycarbonyl_count
dtype: int64
- name: representation_type
dtype: string
- name: trityl_count
dtype: int64
- name: 3,5-dimethoxyphenylisoproxycarbonyl_count
dtype: int64
- name: 2-(4-biphenyl)isopropoxycarbonyl_count
dtype: int64
- name: 2-nitrophenylsulfenyl_count
dtype: int64
- name: boc_count
dtype: int64
- name: trt_count
dtype: int64
- name: ddz_count
dtype: int64
- name: bpoc_count
dtype: int64
- name: nps_count
dtype: int64
- name: 9-fluorenylmethoxycarbonyl_count
dtype: int64
- name: 2-(4-nitrophenylsulfonyl)ethoxycarbonyl_count
dtype: int64
- name: (1,1-dioxobenzo[b]thiophene-2-yl)methyloxycarbonyl_count
dtype: int64
- name: (1,1-dioxonaptho[1,2-b]thiophene-2-yl)methyloxycarbonyl_count
dtype: int64
- name: 1-(4,4-dimethyl-2,6-dioxocyclohex-1-ylidene)-3-methylbutyl_count
dtype: int64
- name: 2,7-di-tert-butyl-fmoc_count
dtype: int64
- name: 2-fluoro-fmoc_count
dtype: int64
- name: 2-monoisooctyl-fmoc_count
dtype: int64
- name: 2,7-diisooctyl-fmoc_count
dtype: int64
- name: tetrachlorophthaloyl_count
dtype: int64
- name: 2-[phenyl(methyl)sulfonio])ethyloxycarbonyltetrafluoroborate_count
dtype: int64
- name: ethanesulfonylethoxycarbonyl_count
dtype: int64
- name: 2-(4-sulfophenylsulfonyl)ethoxycarbonyl_count
dtype: int64
- name: fmoc_count
dtype: int64
- name: nsc_count
dtype: int64
- name: bsmoc_count
dtype: int64
- name: alpha-nsmoc_count
dtype: int64
- name: ivdde_count
dtype: int64
- name: fmoc*_count
dtype: int64
- name: fmoc(fmoc(2f))_count
dtype: int64
- name: mio-fmoc_count
dtype: int64
- name: dio-fmoc_count
dtype: int64
- name: tcp_count
dtype: int64
- name: pms_count
dtype: int64
- name: esc_count
dtype: int64
- name: sps_count
dtype: int64
- name: benzyloxycarbonyl_count
dtype: int64
- name: allyloxycarbonyl_count
dtype: int64
- name: o-nitrobenzenesulfonyl_count
dtype: int64
- name: 2,4-dinitrobenzenesulfonyl_count
dtype: int64
- name: benzothiazole-2-sulfonyl_count
dtype: int64
- name: 2,2,2-trichloroethyloxycarbonyl_count
dtype: int64
- name: dithiasuccinoyl_count
dtype: int64
- name: p-nitrobenzyloxycarbonyl_count
dtype: int64
- name: alpha-azidoacids_count
dtype: int64
- name: proparglyoxycarbonyl_count
dtype: int64
- name: o-nitrobenzylcarbonyl_count
dtype: int64
- name: 4-nitroveratryloxycarbonyl_count
dtype: int64
- name: 2-(2-nitrophenyl)propyloxycarbonyl_count
dtype: int64
- name: 2-(3,4-methylenedioxy-6-nitrophenyl)propyloxycarbonyl_count
dtype: int64
- name: 9-(4-bromophenyl)-9-fluorenyl_count
dtype: int64
- name: azidomethoxycarbonyl_count
dtype: int64
- name: hexafluoroacetone_count
dtype: int64
- name: Z_count
dtype: int64
- name: alloc_count
dtype: int64
- name: o-nbs_count
dtype: int64
- name: d-nbs_count
dtype: int64
- name: bts_count
dtype: int64
- name: troc_count
dtype: int64
- name: dts_count
dtype: int64
- name: pnz_count
dtype: int64
- name: poc_count
dtype: int64
- name: onz_count
dtype: int64
- name: nvoc_count
dtype: int64
- name: nppoc_count
dtype: int64
- name: mnppoc_count
dtype: int64
- name: brphf_count
dtype: int64
- name: azoc_count
dtype: int64
- name: hfa_count
dtype: int64
- name: 2-chlorobenzyloxycarbonyl_count
dtype: int64
- name: 4-methyltrityl_count
dtype: int64
- name: cl-z_count
dtype: int64
- name: mtt_count
dtype: int64
- name: 1-(4,4-dimethyl-2,6-dioxocylohex-1-ylidene)-3-methylbutyl_count
dtype: int64
- name: trifluoroacetyl_count
dtype: int64
- name: 2-(methylsulfonyl)ethoxycarbonyl_count
dtype: int64
- name: tfa_count
dtype: int64
- name: msc_count
dtype: int64
- name: phenyldisulphanylethyloxycarbonyl_count
dtype: int64
- name: 2-pyridyldisulphanylethyloxycarbonyl_count
dtype: int64
- name: phdec_count
dtype: int64
- name: pydec_count
dtype: int64
- name: tert-butyl_count
dtype: int64
- name: 2-chlorotrityl_count
dtype: int64
- name: 2-4-dimethyoxybenzyl_count
dtype: int64
- name: 2-phenylisopropyl_count
dtype: int64
- name: 5-phenyl-3,4-ethylenedioxythenyl_count
dtype: int64
- name: bu_count
dtype: int64
- name: 2-cl-trt_count
dtype: int64
- name: dmb_count
dtype: int64
- name: 2-ph-pr_count
dtype: int64
- name: phenyl-edotn_count
dtype: int64
- name: 9-fluorenylmethyl_count
dtype: int64
- name: 4-(N-[1-(4,4-dimethyl-2,6-dioxocylocheylidene)-3-methylbutyl]-amino)benzyl_count
dtype: int64
- name: methyl_count
dtype: int64
- name: ethyl_count
dtype: int64
- name: carbamoylmethyl_count
dtype: int64
- name: fm_count
dtype: int64
- name: dmab_count
dtype: int64
- name: me_count
dtype: int64
- name: et_count
dtype: int64
- name: cam_count
dtype: int64
- name: allyl_count
dtype: int64
- name: benzyl_count
dtype: int64
- name: phenacyl_count
dtype: int64
- name: p-nitrobenzyl_count
dtype: int64
- name: 2-trimethylsilyethyl_count
dtype: int64
- name: (2-phenyl-2-trimethylsilyl)ethyl_count
dtype: int64
- name: 2-(trimethylsilyl)isopropyl_count
dtype: int64
- name: 2,2,2-trichloroethyl_count
dtype: int64
- name: p-hydroxyphenacyl_count
dtype: int64
- name: 4,5-dimethyoxy-2-nitrobenzyl_count
dtype: int64
- name: 1,1-dimethylallyl_count
dtype: int64
- name: pentaaminecobalt_III_count
dtype: int64
- name: al_count
dtype: int64
- name: bn_count
dtype: int64
- name: pac_count
dtype: int64
- name: pnb_count
dtype: int64
- name: tmse_count
dtype: int64
- name: ptmse_count
dtype: int64
- name: tmsi_count
dtype: int64
- name: tce_count
dtype: int64
- name: php_count
dtype: int64
- name: dmnb_count
dtype: int64
- name: dma_count
dtype: int64
- name: cyclohexyl_count
dtype: int64
- name: b-menthyl_count
dtype: int64
- name: b-3-methylpent-3-yl_count
dtype: int64
- name: 4-(3,6,9-trioxadecyl)oxybenzyl_count
dtype: int64
- name: chx_count
dtype: int64
- name: men_count
dtype: int64
- name: mpe_count
dtype: int64
- name: tegbz_count
dtype: int64
- name: 9-fluoroenylmethyl_count
dtype: int64
- name: 4-(N-[1-(4,4-dimethyl-2,6-dioxocyclohexylidene)-3-methyl-butyl]-amino)benzyl_count
dtype: int64
- name: trimethylsilylethyl_count
dtype: int64
- name: 4,5-dimethoxy-2-nitrobenzyloxycarbonyl_count
dtype: int64
- name: pseudoprolines_count
dtype: int64
- name: 2-hydroxy-4-methoxybenzyl_count
dtype: int64
- name: 2,4-dimethoxybenzyl_count
dtype: int64
- name: 2,4,6-trimethoxybenzyl_count
dtype: int64
- name: 1-methyl-3-indolylmethyl_count
dtype: int64
- name: 3,4-ethylene-dioxy-2-thenyl_count
dtype: int64
- name: hmb_count
dtype: int64
- name: tmob_count
dtype: int64
- name: mim_count
dtype: int64
- name: edot_count
dtype: int64
- name: 4-methoxy-2-nitro-benzyl_count
dtype: int64
- name: (6-hydroxy-3-oxido-1,3-benz[d]oxathiol-5-yl)methyl_count
dtype: int64
- name: 2-hydroxy-4-methoxy-5-(methylsulfinyl)benzyl_count
dtype: int64
- name: n-boc-n-methyl[2-(methylamino)ethyl]carbamoyl-hmb_count
dtype: int64
- name: 9-xanthenyl_count
dtype: int64
- name: cyclopropyldimethylcarbinyl_count
dtype: int64
- name: 4,4-dimethoxybenzhydryl_count
dtype: int64
- name: xan_count
dtype: int64
- name: cpd_count
dtype: int64
- name: mbh_count
dtype: int64
- name: p-toluenesulfonyl_count
dtype: int64
- name: 2,2,5,7,8-pentamethylchroman-6-sulfonyl_count
dtype: int64
- name: 2,2,4,6,7-pentamethyl-2,3-dihydrobenzofuran-5-sulfonyl_count
dtype: int64
- name: mesityl-2-sulfonyl_count
dtype: int64
- name: 4-methoxy-2,3,6-trimethylphenylsulfonyl_count
dtype: int64
- name: 1,2-dimethylindole-3-sulfonyl_count
dtype: int64
- name: w,w-bis-tert-butyloxycarbonyl_count
dtype: int64
- name: 5-dibenzosuberenyl_count
dtype: int64
- name: 5-dibenzosuberyl_count
dtype: int64
- name: 2-methoxy-5-dibenzosuberyl_count
dtype: int64
- name: nitro_count
dtype: int64
- name: tos_count
dtype: int64
- name: pmc_count
dtype: int64
- name: pbf_count
dtype: int64
- name: mts_count
dtype: int64
- name: mtr_count
dtype: int64
- name: mis_count
dtype: int64
- name: bis-boc_count
dtype: int64
- name: suben_count
dtype: int64
- name: sub_count
dtype: int64
- name: mesub_count
dtype: int64
- name: no2_count
dtype: int64
- name: w,w-bis-benzyloxycarbonyl_count
dtype: int64
- name: w,w-bis-allyloxycarbonyl_count
dtype: int64
- name: z-small_count
dtype: int64
- name: p-methylbenzyl_count
dtype: int64
- name: p-methoxybenzyl_count
dtype: int64
- name: monomethoxytrityl_count
dtype: int64
- name: trimethoxybenzyl_count
dtype: int64
- name: 2,2,4,6,7-pentamethyl-5-dihydrobenzofuranylmethyl_count
dtype: int64
- name: 1-adamantyl_count
dtype: int64
- name: meb_count
dtype: int64
- name: mob_count
dtype: int64
- name: mmt_count
dtype: int64
- name: pmbf_count
dtype: int64
- name: 1-ada_count
dtype: int64
- name: 2-(2,4-dinitrophenyl)ethyl_count
dtype: int64
- name: 9-fluororenylmethoxycarbonyl_count
dtype: int64
- name: dnpe_count
dtype: int64
- name: acetamidomethyl_count
dtype: int64
- name: phenylacetamidomethyl_count
dtype: int64
- name: 5-tert-butylmercapto_count
dtype: int64
- name: 3-nitro-2-pyridinesulfenyl_count
dtype: int64
- name: 2-pyridinesulfenyl_count
dtype: int64
- name: N-allyloxycarbonyl-N-[2,3,5,6-tetrafluoro-4-(phenylthio)phenyl]]aminomethyl_count
dtype: int64
- name: o-nitrobenzyl_count
dtype: int64
- name: 4-picolyl_count
dtype: int64
- name: ninhydrin_count
dtype: int64
- name: acm_count
dtype: int64
- name: phacm_count
dtype: int64
- name: sbu_count
dtype: int64
- name: npys_count
dtype: int64
- name: s-pyr_count
dtype: int64
- name: fsam_count
dtype: int64
- name: onb_count
dtype: int64
- name: nin_count
dtype: int64
- name: n-tosyl_count
dtype: int64
- name: n-trityl_count
dtype: int64
- name: n-monomethoxytrityl_count
dtype: int64
- name: n-methyltrityl_count
dtype: int64
- name: n-tert-butyloxycarbonyl_count
dtype: int64
- name: n-2,4-dimethylpent-3-yloxycarbonyl_count
dtype: int64
- name: n-benzyloxymethyl_count
dtype: int64
- name: n-tert-butoxymethyl_count
dtype: int64
- name: ntos_count
dtype: int64
- name: ntrt_count
dtype: int64
- name: nmtt_count
dtype: int64
- name: nmmt_count
dtype: int64
- name: nboc_count
dtype: int64
- name: ndoc_count
dtype: int64
- name: nbom_count
dtype: int64
- name: nbum_count
dtype: int64
- name: N-9-fluorenylmethoxycarbonyl_count
dtype: int64
- name: N-2,6-dimethoxybenzoyl_count
dtype: int64
- name: dmbz_count
dtype: int64
- name: N-2,4-dinitrophenyl_count
dtype: int64
- name: dnp_count
dtype: int64
- name: cyclohexyl;_count
dtype: int64
- name: tert-butyldimethylsilyl_count
dtype: int64
- name: tbdms_count
dtype: int64
- name: tert-butyldiphenylsilyl_count
dtype: int64
- name: propargyloxycarbonyl_count
dtype: int64
- name: tbdps_count
dtype: int64
- name: 2,6-dichlorobenzyl_count
dtype: int64
- name: 2-bromobenzyl_count
dtype: int64
- name: 2-bromobenzyloxycarbonyl_count
dtype: int64
- name: 3-pentyl_count
dtype: int64
- name: dcb_count
dtype: int64
- name: brbn_count
dtype: int64
- name: brz_count
dtype: int64
- name: pen_count
dtype: int64
- name: tegb_count
dtype: int64
- name: boc-n-methyl-n-[2-(methylamino)ethyl]carbamoyl_count
dtype: int64
- name: boc-nmec_count
dtype: int64
- name: formyl_count
dtype: int64
- name: cyclohexyloxycarbonyl_count
dtype: int64
- name: for_count
dtype: int64
- name: hoc_count
dtype: int64
- name: cyclopropane_count
dtype: int64
- name: spiropentane_count
dtype: int64
- name: cyclobutane_count
dtype: int64
- name: cyclopentane_count
dtype: int64
- name: furan_count
dtype: int64
- name: thiophene_count
dtype: int64
- name: pyrrole_count
dtype: int64
- name: 2H-pyrrole_count
dtype: int64
- name: 3H-pyrrole_count
dtype: int64
- name: pyrazole_count
dtype: int64
- name: 2H-imidazole_count
dtype: int64
- name: 1,2,3-triazole_count
dtype: int64
- name: 1,2,4-triazole_count
dtype: int64
- name: 1,2-dithiole_count
dtype: int64
- name: 1,3-dithiole_count
dtype: int64
- name: 3H-1,2-oxathiole_count
dtype: int64
- name: isoxazole_count
dtype: int64
- name: oxazole_count
dtype: int64
- name: thiazole_count
dtype: int64
- name: isothiazole_count
dtype: int64
- name: 1,2,3-oxadiazole_count
dtype: int64
- name: 1,2,4-oxadiazole_count
dtype: int64
- name: 1,2,5-oxadiazole_count
dtype: int64
- name: 1,3,4-oxadiazole_count
dtype: int64
- name: 1,2,3,4-oxatriazole_count
dtype: int64
- name: 1,2,3,5-oxatriazole_count
dtype: int64
- name: 3H-1,2,3-dioxazole_count
dtype: int64
- name: 1,2,4-dioxazole_count
dtype: int64
- name: 1,3,2-dioxazole_count
dtype: int64
- name: 1,3,4-dioxazole_count
dtype: int64
- name: 5H-1,2,5-oxathiazole_count
dtype: int64
- name: 1,3-oxathiole_count
dtype: int64
- name: benzene_count
dtype: int64
- name: cyclohexane_count
dtype: int64
- name: 2H-pyran_count
dtype: int64
- name: 4H-pyran_count
dtype: int64
- name: 2H-pyran-2-one_count
dtype: int64
- name: 4H-pyran-4-one_count
dtype: int64
- name: 1,2-dioxin_count
dtype: int64
- name: 1,3-dioxin_count
dtype: int64
- name: pyridine_count
dtype: int64
- name: pyridazine_count
dtype: int64
- name: pyrimidine_count
dtype: int64
- name: pyrazine_count
dtype: int64
- name: piperazine_count
dtype: int64
- name: 1,3,5-triazine_count
dtype: int64
- name: 1,2,4-triazine_count
dtype: int64
- name: 1,2,3-triazine_count
dtype: int64
- name: 4H-1,2-Oxazine_count
dtype: int64
- name: 2H-1,3-Oxazine_count
dtype: int64
- name: 6H-1,3-Oxazine_count
dtype: int64
- name: 6H-1,2-Oxazine_count
dtype: int64
- name: 1,4-Oxazine_count
dtype: int64
- name: 2H-1,2-Oxazine_count
dtype: int64
- name: 4H-1,4-Oxazine_count
dtype: int64
- name: 1,2,5-Oxathiazine_count
dtype: int64
- name: 1,2,6-Oxathiazine_count
dtype: int64
- name: 1,2,4-Oxadiazine_count
dtype: int64
- name: 1,3,5-Oxadiazine_count
dtype: int64
- name: morpholine_count
dtype: int64
- name: azepine_count
dtype: int64
- name: oxepin_count
dtype: int64
- name: thiepin_count
dtype: int64
- name: 4H-1,2-diazepine_count
dtype: int64
- name: indene_count
dtype: int64
- name: 2H-indene_count
dtype: int64
- name: benzofuran_count
dtype: int64
- name: isobenzofuran_count
dtype: int64
- name: benzo[b]thiophene_count
dtype: int64
- name: benzo[c]thiophene_count
dtype: int64
- name: indole_count
dtype: int64
- name: 3H-indole_count
dtype: int64
- name: 1H-indole_count
dtype: int64
- name: cyclopenta[b]pyridine_count
dtype: int64
- name: pyrano[3,4-b]-pyrrole_count
dtype: int64
- name: indazole_count
dtype: int64
- name: benzisoxazole_count
dtype: int64
- name: benzoxazole_count
dtype: int64
- name: 2,1-benzisoxazole_count
dtype: int64
- name: naphthalene_count
dtype: int64
- name: 1,2,3,4-tetrahydronaphthalene_count
dtype: int64
- name: octahydronaphthalene_count
dtype: int64
- name: 2H-1-benzopyran_count
dtype: int64
- name: 2H-1-benzopyran-2-one_count
dtype: int64
- name: 4H-1-benzopyran-4-one_count
dtype: int64
- name: 1H-2-benzopyran-1-one_count
dtype: int64
- name: 3H-2-benzopyran-1-one_count
dtype: int64
- name: quinoline_count
dtype: int64
- name: isoquinoline_count
dtype: int64
- name: cinnoline_count
dtype: int64
- name: quinazoline_count
dtype: int64
- name: 1,8-napthyhridine_count
dtype: int64
- name: 1,7-napththyridine_count
dtype: int64
- name: 1,5-napththridine_count
dtype: int64
- name: 1,6-napthyridine_count
dtype: int64
- name: 2H-1,3-benzoxazine_count
dtype: int64
- name: 2H-1,4-benzoxazine_count
dtype: int64
- name: 1H-2,3-benzoxazine_count
dtype: int64
- name: 4H-3,1-benzoxazine_count
dtype: int64
- name: 2H-1,2-benzoxazine_count
dtype: int64
- name: 4H-1,3-benzoxazine_count
dtype: int64
- name: anthracene_count
dtype: int64
- name: phenanthrene_count
dtype: int64
- name: phenalene_count
dtype: int64
- name: fluorene_count
dtype: int64
- name: carbazole_count
dtype: int64
- name: xanthene_count
dtype: int64
- name: acridine_count
dtype: int64
- name: norpinane_count
dtype: int64
- name: 7H-purine_count
dtype: int64
- name: steroid_ring_system_count
dtype: int64
- name: imidazole_count
dtype: int64
- name: thiazol-2-amine_count
dtype: int64
- name: tetrazole_count
dtype: int64
- name: cytosine_count
dtype: int64
- name: adenine_count
dtype: int64
- name: 5-methylindole_count
dtype: int64
- name: isocaffeine_count
dtype: int64
- name: tetrazolethiol_count
dtype: int64
- name: 3-methylisoxazole_count
dtype: int64
- name: 1-methylimidazole_count
dtype: int64
- name: 2-methylimidazole_count
dtype: int64
- name: guanine_count
dtype: int64
- name: tosufloxacin_count
dtype: int64
- name: acetamido_count
dtype: int64
- name: acetoacetyl_count
dtype: int64
- name: acetyl_count
dtype: int64
- name: acryloyl_count
dtype: int64
- name: alanyl_count
dtype: int64
- name: beta-alanyl_count
dtype: int64
- name: allylidene_count
dtype: int64
- name: amidino_count
dtype: int64
- name: amino_count
dtype: int64
- name: amyl_count
dtype: int64
- name: anilino_count
dtype: int64
- name: anisidino_count
dtype: int64
- name: anthranoyl_count
dtype: int64
- name: arsino_count
dtype: int64
- name: azelaoyl_count
dtype: int64
- name: azido_count
dtype: int64
- name: azo_count
dtype: int64
- name: azoxy_count
dtype: int64
- name: benzal_count
dtype: int64
- name: benzamido_count
dtype: int64
- name: benzhydrol_count
dtype: int64
- name: benzoxy_count
dtype: int64
- name: benzoyl_count
dtype: int64
- name: benzylidene_count
dtype: int64
- name: benzylidyne_count
dtype: int64
- name: biphenylyl_count
dtype: int64
- name: biphenylene_count
dtype: int64
- name: butoxy_count
dtype: int64
- name: sec-butoxy_count
dtype: int64
- name: tert-butoxy_count
dtype: int64
- name: butyl_count
dtype: int64
- name: sec-butyl_count
dtype: int64
- name: butyryl_count
dtype: int64
- name: caproyl_count
dtype: int64
- name: capryl_count
dtype: int64
- name: capryloyl_count
dtype: int64
- name: carbamido_count
dtype: int64
- name: carbamoyl_count
dtype: int64
- name: carbamyl_count
dtype: int64
- name: carbazoyl_count
dtype: int64
- name: carbethoxy_count
dtype: int64
- name: carbonyl_count
dtype: int64
- name: carboxy_count
dtype: int64
- name: cetyl_count
dtype: int64
- name: chloroformyl_count
dtype: int64
- name: cinnamoyl_count
dtype: int64
- name: cinnamyl_count
dtype: int64
- name: cinnamylidene_count
dtype: int64
- name: cresyl_count
dtype: int64
- name: crotonoyl_count
dtype: int64
- name: crotyl_count
dtype: int64
- name: cyanamido_count
dtype: int64
- name: cyanato_count
dtype: int64
- name: cyano_count
dtype: int64
- name: decanedioyl_count
dtype: int64
- name: decanoyl_count
dtype: int64
- name: diazo_count
dtype: int64
- name: diazoamino_count
dtype: int64
- name: disilanyl_count
dtype: int64
- name: disiloxanyloxy_count
dtype: int64
- name: disulfinyl_count
dtype: int64
- name: dithio_count
dtype: int64
- name: enanthoyl_count
dtype: int64
- name: epoxy_count
dtype: int64
- name: ethenyl_count
dtype: int64
- name: ethynyl_count
dtype: int64
- name: ethoxy_count
dtype: int64
- name: ethylene_count
dtype: int64
- name: ethylidene_count
dtype: int64
- name: ethylthio_count
dtype: int64
- name: formamido_count
dtype: int64
- name: furmaroyl_count
dtype: int64
- name: furfuryl_count
dtype: int64
- name: furfurylidene_count
dtype: int64
- name: glutamoyl_count
dtype: int64
- name: glutaryl_count
dtype: int64
- name: glycylamino_count
dtype: int64
- name: glycoloyl_count
dtype: int64
- name: glycyl_count
dtype: int64
- name: glyoxyoyl_count
dtype: int64
- name: guanidino_count
dtype: int64
- name: guanyl_count
dtype: int64
- name: heptadecanoyl_count
dtype: int64
- name: heptanamido_count
dtype: int64
- name: heptanoyl_count
dtype: int64
- name: hexadecanoyl_count
dtype: int64
- name: hexamethylene_count
dtype: int64
- name: hexanedioyl_count
dtype: int64
- name: hippuryl_count
dtype: int64
- name: hydrazino_count
dtype: int64
- name: hydrazo_count
dtype: int64
- name: hydrocinnamoyl_count
dtype: int64
- name: hydroperoxy_count
dtype: int64
- name: hydroxyamino_count
dtype: int64
- name: imino_count
dtype: int64
- name: iodoso_count
dtype: int64
- name: iodyl_count
dtype: int64
- name: isoamyl_count
dtype: int64
- name: isobutenyl_count
dtype: int64
- name: isobutoxy_count
dtype: int64
- name: isobutyl_count
dtype: int64
- name: isobutylidene_count
dtype: int64
- name: isobutyryl_count
dtype: int64
- name: isocyanato_count
dtype: int64
- name: isocyano_count
dtype: int64
- name: isohexyl_count
dtype: int64
- name: isoleucyl_count
dtype: int64
- name: isonitroso_count
dtype: int64
- name: isopentyl_count
dtype: int64
- name: isopentylidene_count
dtype: int64
- name: isopropenyl_count
dtype: int64
- name: isopropoxy_count
dtype: int64
- name: isopropyl_count
dtype: int64
- name: isopropylidene_count
dtype: int64
- name: isothiocynato_count
dtype: int64
- name: isovaleryl_count
dtype: int64
- name: lactoyl_count
dtype: int64
- name: lauroyl_count
dtype: int64
- name: lauryl_count
dtype: int64
- name: leucyl_count
dtype: int64
- name: levulinoyl_count
dtype: int64
- name: malonyl_count
dtype: int64
- name: mandeloyl_count
dtype: int64
- name: mercapto_count
dtype: int64
- name: mesityl_count
dtype: int64
- name: methacryloyl_count
dtype: int64
- name: methallyl_count
dtype: int64
- name: methionyl_count
dtype: int64
- name: methoxy_count
dtype: int64
- name: methylene_count
dtype: int64
- name: methylthio_count
dtype: int64
- name: myristoyl_count
dtype: int64
- name: myristyl_count
dtype: int64
- name: naphthyl_count
dtype: int64
- name: naphthylene_count
dtype: int64
- name: neopentyl_count
dtype: int64
- name: nitramino_count
dtype: int64
- name: nitrosamino_count
dtype: int64
- name: nitroso_count
dtype: int64
- name: nonanoyl_count
dtype: int64
- name: oleoyl_count
dtype: int64
- name: oxalyl_count
dtype: int64
- name: oxo_count
dtype: int64
- name: palmitoyl_count
dtype: int64
- name: pentamethylene_count
dtype: int64
- name: pentyl_count
dtype: int64
- name: tert-pentyl_count
dtype: int64
- name: phenacylidene_count
dtype: int64
- name: phenethyl_count
dtype: int64
- name: phenoxy_count
dtype: int64
- name: phenyl_count
dtype: int64
- name: phenylene_count
dtype: int64
- name: phosphino_count
dtype: int64
- name: phosphinyl_count
dtype: int64
- name: phospho_count
dtype: int64
- name: phosphono_count
dtype: int64
- name: phthaloyl_count
dtype: int64
- name: picryl_count
dtype: int64
- name: pimeloyl_count
dtype: int64
- name: piperidino_count
dtype: int64
- name: pivaloyl_count
dtype: int64
- name: prenyl_count
dtype: int64
- name: propargyl_count
dtype: int64
- name: 1-propenyl_count
dtype: int64
- name: 2-propenyl_count
dtype: int64
- name: propionyl_count
dtype: int64
- name: propoxy_count
dtype: int64
- name: propyl_count
dtype: int64
- name: propylidene_count
dtype: int64
- name: pyrryl_count
dtype: int64
- name: salicyloyl_count
dtype: int64
- name: selenyl_count
dtype: int64
- name: seryl_count
dtype: int64
- name: siloxy_count
dtype: int64
- name: silyl_count
dtype: int64
- name: silyene_count
dtype: int64
- name: sorboyl_count
dtype: int64
- name: stearoyl_count
dtype: int64
- name: stearyl_count
dtype: int64
- name: styryl_count
dtype: int64
- name: suberoyl_count
dtype: int64
- name: succinyl_count
dtype: int64
- name: sulfamino_count
dtype: int64
- name: sulfamoyl_count
dtype: int64
- name: sulfanilyl_count
dtype: int64
- name: sulfeno_count
dtype: int64
- name: sulfhydryl_count
dtype: int64
- name: sulfinyl_count
dtype: int64
- name: sulfo_count
dtype: int64
- name: sulfonyl_count
dtype: int64
- name: terephthaloyl_count
dtype: int64
- name: tetramethylene_count
dtype: int64
- name: thienyl_count
dtype: int64
- name: thiocarbonyl_count
dtype: int64
- name: thiocarboxy_count
dtype: int64
- name: thiocyanato_count
dtype: int64
- name: thionyl_count
dtype: int64
- name: threonyl_count
dtype: int64
- name: toluidino_count
dtype: int64
- name: toluoyl_count
dtype: int64
- name: tolyl_count
dtype: int64
- name: alpha-tolyl_count
dtype: int64
- name: tolylene_count
dtype: int64
- name: tosyl_count
dtype: int64
- name: triazano_count
dtype: int64
- name: trimethylene_count
dtype: int64
- name: valeryl_count
dtype: int64
- name: valyl_count
dtype: int64
- name: vinyl_count
dtype: int64
- name: vinylidene_count
dtype: int64
- name: xylidino_count
dtype: int64
- name: xylyl_count
dtype: int64
- name: xylylene_count
dtype: int64
- name: propiolamide_count
dtype: int64
- name: fumarate ester_count
dtype: int64
- name: allenamide_count
dtype: int64
- name: propiolonitrile_count
dtype: int64
- name: propargylamide_count
dtype: int64
- name: arylsulfonyl bicyclobutane_count
dtype: int64
- name: haloalkane_count
dtype: int64
- name: alpha-halomethyl_count
dtype: int64
- name: alpha-haloamide_count
dtype: int64
- name: alpha-haloester_count
dtype: int64
- name: epoxide_count
dtype: int64
- name: aziridine_count
dtype: int64
- name: nitroalkane_count
dtype: int64
- name: acrylamide_count
dtype: int64
- name: cyanoenone_count
dtype: int64
- name: aldehyde_count
dtype: int64
- name: ketone_count
dtype: int64
- name: nitrile_count
dtype: int64
- name: cyanamide_count
dtype: int64
- name: isothicyanate_count
dtype: int64
- name: sulfone_count
dtype: int64
- name: sulfonyl fluoride_count
dtype: int64
- name: sulfonimidoyl fluoride_count
dtype: int64
- name: aryl fluorosulfate_count
dtype: int64
- name: ester_count
dtype: int64
- name: sulfonamide_count
dtype: int64
- name: 2-carbonyl arylboronic acid_count
dtype: int64
- name: n-methyl isoxazolium_count
dtype: int64
- name: oxaziridine_count
dtype: int64
- name: carboxyl_count
dtype: int64
- name: ether_count
dtype: int64
- name: alkanol_count
dtype: int64
- name: thiol_count
dtype: int64
- name: halogen_count
dtype: int64
- name: amine_count
dtype: int64
- name: amide_count
dtype: int64
- name: num_valence_electrons
dtype: int64
- name: rotable_proportion
dtype: float64
- name: non_rotable_proportion
dtype: float64
- name: num_unspecified_bond
dtype: float64
- name: num_single_bonds
dtype: float64
- name: num_double_bonds
dtype: float64
- name: num_triple_bonds
dtype: float64
- name: num_quadruple_bonds
dtype: float64
- name: num_quintuple_bonds
dtype: float64
- name: num_hextuple_bonds
dtype: float64
- name: num_oneandahalf_bonds
dtype: float64
- name: num_twoandahalf_bonds
dtype: float64
- name: num_threeandahalf_bonds
dtype: float64
- name: num_fourandahalf_bonds
dtype: float64
- name: num_fiveandahalf_bonds
dtype: float64
- name: num_aromatic_bonds
dtype: float64
- name: num_ionic_bonds
dtype: float64
- name: num_hydrogen_bonds
dtype: float64
- name: num_threecenter_bonds
dtype: float64
- name: num_dativeone_bonds
dtype: float64
- name: num_dative_bonds
dtype: float64
- name: num_other_bonds
dtype: float64
- name: num_zero_bonds
dtype: float64
- name: num_bonds
dtype: int64
- name: molecular_formula
dtype: string
- name: monoisotopic_molecular_mass
dtype: float64
- name: carbon_mass
dtype: float64
- name: hydrogen_mass
dtype: float64
- name: nitrogen_mass
dtype: float64
- name: oxygen_mass
dtype: float64
- name: num_carbon_atoms
dtype: int64
- name: num_hydrogen_atoms
dtype: int64
- name: num_nitrogen_atoms
dtype: int64
- name: num_oxygen_atoms
dtype: int64
- name: num_hydrogen_bond_acceptors
dtype: int64
- name: num_hydrogen_bond_donors
dtype: int64
- name: num_lipinski_violations
dtype: int64
- name: inertial_shape_factor
dtype: float64
- name: eccentricity
dtype: float64
- name: asphericity
dtype: float64
- name: npr1_value
dtype: float64
- name: npr2_value
dtype: float64
- name: pmi1_value
dtype: float64
- name: pmi2_value
dtype: float64
- name: pmi3_value
dtype: float64
- name: num_chiral_centers
dtype: int64
- name: representation
dtype: string
splits:
- name: train
num_bytes: 2763808
num_examples: 500
download_size: 520434
dataset_size: 2763808
- config_name: rdkit_feat_5
features:
- name: tert-butyloxycarbonyl_count
dtype: int64
- name: representation_type
dtype: string
- name: trityl_count
dtype: int64
- name: 3,5-dimethoxyphenylisoproxycarbonyl_count
dtype: int64
- name: 2-(4-biphenyl)isopropoxycarbonyl_count
dtype: int64
- name: 2-nitrophenylsulfenyl_count
dtype: int64
- name: boc_count
dtype: int64
- name: trt_count
dtype: int64
- name: ddz_count
dtype: int64
- name: bpoc_count
dtype: int64
- name: nps_count
dtype: int64
- name: 9-fluorenylmethoxycarbonyl_count
dtype: int64
- name: 2-(4-nitrophenylsulfonyl)ethoxycarbonyl_count
dtype: int64
- name: (1,1-dioxobenzo[b]thiophene-2-yl)methyloxycarbonyl_count
dtype: int64
- name: (1,1-dioxonaptho[1,2-b]thiophene-2-yl)methyloxycarbonyl_count
dtype: int64
- name: 1-(4,4-dimethyl-2,6-dioxocyclohex-1-ylidene)-3-methylbutyl_count
dtype: int64
- name: 2,7-di-tert-butyl-fmoc_count
dtype: int64
- name: 2-fluoro-fmoc_count
dtype: int64
- name: 2-monoisooctyl-fmoc_count
dtype: int64
- name: 2,7-diisooctyl-fmoc_count
dtype: int64
- name: tetrachlorophthaloyl_count
dtype: int64
- name: 2-[phenyl(methyl)sulfonio])ethyloxycarbonyltetrafluoroborate_count
dtype: int64
- name: ethanesulfonylethoxycarbonyl_count
dtype: int64
- name: 2-(4-sulfophenylsulfonyl)ethoxycarbonyl_count
dtype: int64
- name: fmoc_count
dtype: int64
- name: nsc_count
dtype: int64
- name: bsmoc_count
dtype: int64
- name: alpha-nsmoc_count
dtype: int64
- name: ivdde_count
dtype: int64
- name: fmoc*_count
dtype: int64
- name: fmoc(fmoc(2f))_count
dtype: int64
- name: mio-fmoc_count
dtype: int64
- name: dio-fmoc_count
dtype: int64
- name: tcp_count
dtype: int64
- name: pms_count
dtype: int64
- name: esc_count
dtype: int64
- name: sps_count
dtype: int64
- name: benzyloxycarbonyl_count
dtype: int64
- name: allyloxycarbonyl_count
dtype: int64
- name: o-nitrobenzenesulfonyl_count
dtype: int64
- name: 2,4-dinitrobenzenesulfonyl_count
dtype: int64
- name: benzothiazole-2-sulfonyl_count
dtype: int64
- name: 2,2,2-trichloroethyloxycarbonyl_count
dtype: int64
- name: dithiasuccinoyl_count
dtype: int64
- name: p-nitrobenzyloxycarbonyl_count
dtype: int64
- name: alpha-azidoacids_count
dtype: int64
- name: proparglyoxycarbonyl_count
dtype: int64
- name: o-nitrobenzylcarbonyl_count
dtype: int64
- name: 4-nitroveratryloxycarbonyl_count
dtype: int64
- name: 2-(2-nitrophenyl)propyloxycarbonyl_count
dtype: int64
- name: 2-(3,4-methylenedioxy-6-nitrophenyl)propyloxycarbonyl_count
dtype: int64
- name: 9-(4-bromophenyl)-9-fluorenyl_count
dtype: int64
- name: azidomethoxycarbonyl_count
dtype: int64
- name: hexafluoroacetone_count
dtype: int64
- name: Z_count
dtype: int64
- name: alloc_count
dtype: int64
- name: o-nbs_count
dtype: int64
- name: d-nbs_count
dtype: int64
- name: bts_count
dtype: int64
- name: troc_count
dtype: int64
- name: dts_count
dtype: int64
- name: pnz_count
dtype: int64
- name: poc_count
dtype: int64
- name: onz_count
dtype: int64
- name: nvoc_count
dtype: int64
- name: nppoc_count
dtype: int64
- name: mnppoc_count
dtype: int64
- name: brphf_count
dtype: int64
- name: azoc_count
dtype: int64
- name: hfa_count
dtype: int64
- name: 2-chlorobenzyloxycarbonyl_count
dtype: int64
- name: 4-methyltrityl_count
dtype: int64
- name: cl-z_count
dtype: int64
- name: mtt_count
dtype: int64
- name: 1-(4,4-dimethyl-2,6-dioxocylohex-1-ylidene)-3-methylbutyl_count
dtype: int64
- name: trifluoroacetyl_count
dtype: int64
- name: 2-(methylsulfonyl)ethoxycarbonyl_count
dtype: int64
- name: tfa_count
dtype: int64
- name: msc_count
dtype: int64
- name: phenyldisulphanylethyloxycarbonyl_count
dtype: int64
- name: 2-pyridyldisulphanylethyloxycarbonyl_count
dtype: int64
- name: phdec_count
dtype: int64
- name: pydec_count
dtype: int64
- name: tert-butyl_count
dtype: int64
- name: 2-chlorotrityl_count
dtype: int64
- name: 2-4-dimethyoxybenzyl_count
dtype: int64
- name: 2-phenylisopropyl_count
dtype: int64
- name: 5-phenyl-3,4-ethylenedioxythenyl_count
dtype: int64
- name: bu_count
dtype: int64
- name: 2-cl-trt_count
dtype: int64
- name: dmb_count
dtype: int64
- name: 2-ph-pr_count
dtype: int64
- name: phenyl-edotn_count
dtype: int64
- name: 9-fluorenylmethyl_count
dtype: int64
- name: 4-(N-[1-(4,4-dimethyl-2,6-dioxocylocheylidene)-3-methylbutyl]-amino)benzyl_count
dtype: int64
- name: methyl_count
dtype: int64
- name: ethyl_count
dtype: int64
- name: carbamoylmethyl_count
dtype: int64
- name: fm_count
dtype: int64
- name: dmab_count
dtype: int64
- name: me_count
dtype: int64
- name: et_count
dtype: int64
- name: cam_count
dtype: int64
- name: allyl_count
dtype: int64
- name: benzyl_count
dtype: int64
- name: phenacyl_count
dtype: int64
- name: p-nitrobenzyl_count
dtype: int64
- name: 2-trimethylsilyethyl_count
dtype: int64
- name: (2-phenyl-2-trimethylsilyl)ethyl_count
dtype: int64
- name: 2-(trimethylsilyl)isopropyl_count
dtype: int64
- name: 2,2,2-trichloroethyl_count
dtype: int64
- name: p-hydroxyphenacyl_count
dtype: int64
- name: 4,5-dimethyoxy-2-nitrobenzyl_count
dtype: int64
- name: 1,1-dimethylallyl_count
dtype: int64
- name: pentaaminecobalt_III_count
dtype: int64
- name: al_count
dtype: int64
- name: bn_count
dtype: int64
- name: pac_count
dtype: int64
- name: pnb_count
dtype: int64
- name: tmse_count
dtype: int64
- name: ptmse_count
dtype: int64
- name: tmsi_count
dtype: int64
- name: tce_count
dtype: int64
- name: php_count
dtype: int64
- name: dmnb_count
dtype: int64
- name: dma_count
dtype: int64
- name: cyclohexyl_count
dtype: int64
- name: b-menthyl_count
dtype: int64
- name: b-3-methylpent-3-yl_count
dtype: int64
- name: 4-(3,6,9-trioxadecyl)oxybenzyl_count
dtype: int64
- name: chx_count
dtype: int64
- name: men_count
dtype: int64
- name: mpe_count
dtype: int64
- name: tegbz_count
dtype: int64
- name: 9-fluoroenylmethyl_count
dtype: int64
- name: 4-(N-[1-(4,4-dimethyl-2,6-dioxocyclohexylidene)-3-methyl-butyl]-amino)benzyl_count
dtype: int64
- name: trimethylsilylethyl_count
dtype: int64
- name: 4,5-dimethoxy-2-nitrobenzyloxycarbonyl_count
dtype: int64
- name: pseudoprolines_count
dtype: int64
- name: 2-hydroxy-4-methoxybenzyl_count
dtype: int64
- name: 2,4-dimethoxybenzyl_count
dtype: int64
- name: 2,4,6-trimethoxybenzyl_count
dtype: int64
- name: 1-methyl-3-indolylmethyl_count
dtype: int64
- name: 3,4-ethylene-dioxy-2-thenyl_count
dtype: int64
- name: hmb_count
dtype: int64
- name: tmob_count
dtype: int64
- name: mim_count
dtype: int64
- name: edot_count
dtype: int64
- name: 4-methoxy-2-nitro-benzyl_count
dtype: int64
- name: (6-hydroxy-3-oxido-1,3-benz[d]oxathiol-5-yl)methyl_count
dtype: int64
- name: 2-hydroxy-4-methoxy-5-(methylsulfinyl)benzyl_count
dtype: int64
- name: n-boc-n-methyl[2-(methylamino)ethyl]carbamoyl-hmb_count
dtype: int64
- name: 9-xanthenyl_count
dtype: int64
- name: cyclopropyldimethylcarbinyl_count
dtype: int64
- name: 4,4-dimethoxybenzhydryl_count
dtype: int64
- name: xan_count
dtype: int64
- name: cpd_count
dtype: int64
- name: mbh_count
dtype: int64
- name: p-toluenesulfonyl_count
dtype: int64
- name: 2,2,5,7,8-pentamethylchroman-6-sulfonyl_count
dtype: int64
- name: 2,2,4,6,7-pentamethyl-2,3-dihydrobenzofuran-5-sulfonyl_count
dtype: int64
- name: mesityl-2-sulfonyl_count
dtype: int64
- name: 4-methoxy-2,3,6-trimethylphenylsulfonyl_count
dtype: int64
- name: 1,2-dimethylindole-3-sulfonyl_count
dtype: int64
- name: w,w-bis-tert-butyloxycarbonyl_count
dtype: int64
- name: 5-dibenzosuberenyl_count
dtype: int64
- name: 5-dibenzosuberyl_count
dtype: int64
- name: 2-methoxy-5-dibenzosuberyl_count
dtype: int64
- name: nitro_count
dtype: int64
- name: tos_count
dtype: int64
- name: pmc_count
dtype: int64
- name: pbf_count
dtype: int64
- name: mts_count
dtype: int64
- name: mtr_count
dtype: int64
- name: mis_count
dtype: int64
- name: bis-boc_count
dtype: int64
- name: suben_count
dtype: int64
- name: sub_count
dtype: int64
- name: mesub_count
dtype: int64
- name: no2_count
dtype: int64
- name: w,w-bis-benzyloxycarbonyl_count
dtype: int64
- name: w,w-bis-allyloxycarbonyl_count
dtype: int64
- name: z-small_count
dtype: int64
- name: p-methylbenzyl_count
dtype: int64
- name: p-methoxybenzyl_count
dtype: int64
- name: monomethoxytrityl_count
dtype: int64
- name: trimethoxybenzyl_count
dtype: int64
- name: 2,2,4,6,7-pentamethyl-5-dihydrobenzofuranylmethyl_count
dtype: int64
- name: 1-adamantyl_count
dtype: int64
- name: meb_count
dtype: int64
- name: mob_count
dtype: int64
- name: mmt_count
dtype: int64
- name: pmbf_count
dtype: int64
- name: 1-ada_count
dtype: int64
- name: 2-(2,4-dinitrophenyl)ethyl_count
dtype: int64
- name: 9-fluororenylmethoxycarbonyl_count
dtype: int64
- name: dnpe_count
dtype: int64
- name: acetamidomethyl_count
dtype: int64
- name: phenylacetamidomethyl_count
dtype: int64
- name: 5-tert-butylmercapto_count
dtype: int64
- name: 3-nitro-2-pyridinesulfenyl_count
dtype: int64
- name: 2-pyridinesulfenyl_count
dtype: int64
- name: N-allyloxycarbonyl-N-[2,3,5,6-tetrafluoro-4-(phenylthio)phenyl]]aminomethyl_count
dtype: int64
- name: o-nitrobenzyl_count
dtype: int64
- name: 4-picolyl_count
dtype: int64
- name: ninhydrin_count
dtype: int64
- name: acm_count
dtype: int64
- name: phacm_count
dtype: int64
- name: sbu_count
dtype: int64
- name: npys_count
dtype: int64
- name: s-pyr_count
dtype: int64
- name: fsam_count
dtype: int64
- name: onb_count
dtype: int64
- name: nin_count
dtype: int64
- name: n-tosyl_count
dtype: int64
- name: n-trityl_count
dtype: int64
- name: n-monomethoxytrityl_count
dtype: int64
- name: n-methyltrityl_count
dtype: int64
- name: n-tert-butyloxycarbonyl_count
dtype: int64
- name: n-2,4-dimethylpent-3-yloxycarbonyl_count
dtype: int64
- name: n-benzyloxymethyl_count
dtype: int64
- name: n-tert-butoxymethyl_count
dtype: int64
- name: ntos_count
dtype: int64
- name: ntrt_count
dtype: int64
- name: nmtt_count
dtype: int64
- name: nmmt_count
dtype: int64
- name: nboc_count
dtype: int64
- name: ndoc_count
dtype: int64
- name: nbom_count
dtype: int64
- name: nbum_count
dtype: int64
- name: N-9-fluorenylmethoxycarbonyl_count
dtype: int64
- name: N-2,6-dimethoxybenzoyl_count
dtype: int64
- name: dmbz_count
dtype: int64
- name: N-2,4-dinitrophenyl_count
dtype: int64
- name: dnp_count
dtype: int64
- name: cyclohexyl;_count
dtype: int64
- name: tert-butyldimethylsilyl_count
dtype: int64
- name: tbdms_count
dtype: int64
- name: tert-butyldiphenylsilyl_count
dtype: int64
- name: propargyloxycarbonyl_count
dtype: int64
- name: tbdps_count
dtype: int64
- name: 2,6-dichlorobenzyl_count
dtype: int64
- name: 2-bromobenzyl_count
dtype: int64
- name: 2-bromobenzyloxycarbonyl_count
dtype: int64
- name: 3-pentyl_count
dtype: int64
- name: dcb_count
dtype: int64
- name: brbn_count
dtype: int64
- name: brz_count
dtype: int64
- name: pen_count
dtype: int64
- name: tegb_count
dtype: int64
- name: boc-n-methyl-n-[2-(methylamino)ethyl]carbamoyl_count
dtype: int64
- name: boc-nmec_count
dtype: int64
- name: formyl_count
dtype: int64
- name: cyclohexyloxycarbonyl_count
dtype: int64
- name: for_count
dtype: int64
- name: hoc_count
dtype: int64
- name: cyclopropane_count
dtype: int64
- name: spiropentane_count
dtype: int64
- name: cyclobutane_count
dtype: int64
- name: cyclopentane_count
dtype: int64
- name: furan_count
dtype: int64
- name: thiophene_count
dtype: int64
- name: pyrrole_count
dtype: int64
- name: 2H-pyrrole_count
dtype: int64
- name: 3H-pyrrole_count
dtype: int64
- name: pyrazole_count
dtype: int64
- name: 2H-imidazole_count
dtype: int64
- name: 1,2,3-triazole_count
dtype: int64
- name: 1,2,4-triazole_count
dtype: int64
- name: 1,2-dithiole_count
dtype: int64
- name: 1,3-dithiole_count
dtype: int64
- name: 3H-1,2-oxathiole_count
dtype: int64
- name: isoxazole_count
dtype: int64
- name: oxazole_count
dtype: int64
- name: thiazole_count
dtype: int64
- name: isothiazole_count
dtype: int64
- name: 1,2,3-oxadiazole_count
dtype: int64
- name: 1,2,4-oxadiazole_count
dtype: int64
- name: 1,2,5-oxadiazole_count
dtype: int64
- name: 1,3,4-oxadiazole_count
dtype: int64
- name: 1,2,3,4-oxatriazole_count
dtype: int64
- name: 1,2,3,5-oxatriazole_count
dtype: int64
- name: 3H-1,2,3-dioxazole_count
dtype: int64
- name: 1,2,4-dioxazole_count
dtype: int64
- name: 1,3,2-dioxazole_count
dtype: int64
- name: 1,3,4-dioxazole_count
dtype: int64
- name: 5H-1,2,5-oxathiazole_count
dtype: int64
- name: 1,3-oxathiole_count
dtype: int64
- name: benzene_count
dtype: int64
- name: cyclohexane_count
dtype: int64
- name: 2H-pyran_count
dtype: int64
- name: 4H-pyran_count
dtype: int64
- name: 2H-pyran-2-one_count
dtype: int64
- name: 4H-pyran-4-one_count
dtype: int64
- name: 1,2-dioxin_count
dtype: int64
- name: 1,3-dioxin_count
dtype: int64
- name: pyridine_count
dtype: int64
- name: pyridazine_count
dtype: int64
- name: pyrimidine_count
dtype: int64
- name: pyrazine_count
dtype: int64
- name: piperazine_count
dtype: int64
- name: 1,3,5-triazine_count
dtype: int64
- name: 1,2,4-triazine_count
dtype: int64
- name: 1,2,3-triazine_count
dtype: int64
- name: 4H-1,2-Oxazine_count
dtype: int64
- name: 2H-1,3-Oxazine_count
dtype: int64
- name: 6H-1,3-Oxazine_count
dtype: int64
- name: 6H-1,2-Oxazine_count
dtype: int64
- name: 1,4-Oxazine_count
dtype: int64
- name: 2H-1,2-Oxazine_count
dtype: int64
- name: 4H-1,4-Oxazine_count
dtype: int64
- name: 1,2,5-Oxathiazine_count
dtype: int64
- name: 1,2,6-Oxathiazine_count
dtype: int64
- name: 1,2,4-Oxadiazine_count
dtype: int64
- name: 1,3,5-Oxadiazine_count
dtype: int64
- name: morpholine_count
dtype: int64
- name: azepine_count
dtype: int64
- name: oxepin_count
dtype: int64
- name: thiepin_count
dtype: int64
- name: 4H-1,2-diazepine_count
dtype: int64
- name: indene_count
dtype: int64
- name: 2H-indene_count
dtype: int64
- name: benzofuran_count
dtype: int64
- name: isobenzofuran_count
dtype: int64
- name: benzo[b]thiophene_count
dtype: int64
- name: benzo[c]thiophene_count
dtype: int64
- name: indole_count
dtype: int64
- name: 3H-indole_count
dtype: int64
- name: 1H-indole_count
dtype: int64
- name: cyclopenta[b]pyridine_count
dtype: int64
- name: pyrano[3,4-b]-pyrrole_count
dtype: int64
- name: indazole_count
dtype: int64
- name: benzisoxazole_count
dtype: int64
- name: benzoxazole_count
dtype: int64
- name: 2,1-benzisoxazole_count
dtype: int64
- name: naphthalene_count
dtype: int64
- name: 1,2,3,4-tetrahydronaphthalene_count
dtype: int64
- name: octahydronaphthalene_count
dtype: int64
- name: 2H-1-benzopyran_count
dtype: int64
- name: 2H-1-benzopyran-2-one_count
dtype: int64
- name: 4H-1-benzopyran-4-one_count
dtype: int64
- name: 1H-2-benzopyran-1-one_count
dtype: int64
- name: 3H-2-benzopyran-1-one_count
dtype: int64
- name: quinoline_count
dtype: int64
- name: isoquinoline_count
dtype: int64
- name: cinnoline_count
dtype: int64
- name: quinazoline_count
dtype: int64
- name: 1,8-napthyhridine_count
dtype: int64
- name: 1,7-napththyridine_count
dtype: int64
- name: 1,5-napththridine_count
dtype: int64
- name: 1,6-napthyridine_count
dtype: int64
- name: 2H-1,3-benzoxazine_count
dtype: int64
- name: 2H-1,4-benzoxazine_count
dtype: int64
- name: 1H-2,3-benzoxazine_count
dtype: int64
- name: 4H-3,1-benzoxazine_count
dtype: int64
- name: 2H-1,2-benzoxazine_count
dtype: int64
- name: 4H-1,3-benzoxazine_count
dtype: int64
- name: anthracene_count
dtype: int64
- name: phenanthrene_count
dtype: int64
- name: phenalene_count
dtype: int64
- name: fluorene_count
dtype: int64
- name: carbazole_count
dtype: int64
- name: xanthene_count
dtype: int64
- name: acridine_count
dtype: int64
- name: norpinane_count
dtype: int64
- name: 7H-purine_count
dtype: int64
- name: steroid_ring_system_count
dtype: int64
- name: imidazole_count
dtype: int64
- name: thiazol-2-amine_count
dtype: int64
- name: tetrazole_count
dtype: int64
- name: cytosine_count
dtype: int64
- name: adenine_count
dtype: int64
- name: 5-methylindole_count
dtype: int64
- name: isocaffeine_count
dtype: int64
- name: tetrazolethiol_count
dtype: int64
- name: 3-methylisoxazole_count
dtype: int64
- name: 1-methylimidazole_count
dtype: int64
- name: 2-methylimidazole_count
dtype: int64
- name: guanine_count
dtype: int64
- name: tosufloxacin_count
dtype: int64
- name: acetamido_count
dtype: int64
- name: acetoacetyl_count
dtype: int64
- name: acetyl_count
dtype: int64
- name: acryloyl_count
dtype: int64
- name: alanyl_count
dtype: int64
- name: beta-alanyl_count
dtype: int64
- name: allylidene_count
dtype: int64
- name: amidino_count
dtype: int64
- name: amino_count
dtype: int64
- name: amyl_count
dtype: int64
- name: anilino_count
dtype: int64
- name: anisidino_count
dtype: int64
- name: anthranoyl_count
dtype: int64
- name: arsino_count
dtype: int64
- name: azelaoyl_count
dtype: int64
- name: azido_count
dtype: int64
- name: azo_count
dtype: int64
- name: azoxy_count
dtype: int64
- name: benzal_count
dtype: int64
- name: benzamido_count
dtype: int64
- name: benzhydrol_count
dtype: int64
- name: benzoxy_count
dtype: int64
- name: benzoyl_count
dtype: int64
- name: benzylidene_count
dtype: int64
- name: benzylidyne_count
dtype: int64
- name: biphenylyl_count
dtype: int64
- name: biphenylene_count
dtype: int64
- name: butoxy_count
dtype: int64
- name: sec-butoxy_count
dtype: int64
- name: tert-butoxy_count
dtype: int64
- name: butyl_count
dtype: int64
- name: sec-butyl_count
dtype: int64
- name: butyryl_count
dtype: int64
- name: caproyl_count
dtype: int64
- name: capryl_count
dtype: int64
- name: capryloyl_count
dtype: int64
- name: carbamido_count
dtype: int64
- name: carbamoyl_count
dtype: int64
- name: carbamyl_count
dtype: int64
- name: carbazoyl_count
dtype: int64
- name: carbethoxy_count
dtype: int64
- name: carbonyl_count
dtype: int64
- name: carboxy_count
dtype: int64
- name: cetyl_count
dtype: int64
- name: chloroformyl_count
dtype: int64
- name: cinnamoyl_count
dtype: int64
- name: cinnamyl_count
dtype: int64
- name: cinnamylidene_count
dtype: int64
- name: cresyl_count
dtype: int64
- name: crotonoyl_count
dtype: int64
- name: crotyl_count
dtype: int64
- name: cyanamido_count
dtype: int64
- name: cyanato_count
dtype: int64
- name: cyano_count
dtype: int64
- name: decanedioyl_count
dtype: int64
- name: decanoyl_count
dtype: int64
- name: diazo_count
dtype: int64
- name: diazoamino_count
dtype: int64
- name: disilanyl_count
dtype: int64
- name: disiloxanyloxy_count
dtype: int64
- name: disulfinyl_count
dtype: int64
- name: dithio_count
dtype: int64
- name: enanthoyl_count
dtype: int64
- name: epoxy_count
dtype: int64
- name: ethenyl_count
dtype: int64
- name: ethynyl_count
dtype: int64
- name: ethoxy_count
dtype: int64
- name: ethylene_count
dtype: int64
- name: ethylidene_count
dtype: int64
- name: ethylthio_count
dtype: int64
- name: formamido_count
dtype: int64
- name: furmaroyl_count
dtype: int64
- name: furfuryl_count
dtype: int64
- name: furfurylidene_count
dtype: int64
- name: glutamoyl_count
dtype: int64
- name: glutaryl_count
dtype: int64
- name: glycylamino_count
dtype: int64
- name: glycoloyl_count
dtype: int64
- name: glycyl_count
dtype: int64
- name: glyoxyoyl_count
dtype: int64
- name: guanidino_count
dtype: int64
- name: guanyl_count
dtype: int64
- name: heptadecanoyl_count
dtype: int64
- name: heptanamido_count
dtype: int64
- name: heptanoyl_count
dtype: int64
- name: hexadecanoyl_count
dtype: int64
- name: hexamethylene_count
dtype: int64
- name: hexanedioyl_count
dtype: int64
- name: hippuryl_count
dtype: int64
- name: hydrazino_count
dtype: int64
- name: hydrazo_count
dtype: int64
- name: hydrocinnamoyl_count
dtype: int64
- name: hydroperoxy_count
dtype: int64
- name: hydroxyamino_count
dtype: int64
- name: imino_count
dtype: int64
- name: iodoso_count
dtype: int64
- name: iodyl_count
dtype: int64
- name: isoamyl_count
dtype: int64
- name: isobutenyl_count
dtype: int64
- name: isobutoxy_count
dtype: int64
- name: isobutyl_count
dtype: int64
- name: isobutylidene_count
dtype: int64
- name: isobutyryl_count
dtype: int64
- name: isocyanato_count
dtype: int64
- name: isocyano_count
dtype: int64
- name: isohexyl_count
dtype: int64
- name: isoleucyl_count
dtype: int64
- name: isonitroso_count
dtype: int64
- name: isopentyl_count
dtype: int64
- name: isopentylidene_count
dtype: int64
- name: isopropenyl_count
dtype: int64
- name: isopropoxy_count
dtype: int64
- name: isopropyl_count
dtype: int64
- name: isopropylidene_count
dtype: int64
- name: isothiocynato_count
dtype: int64
- name: isovaleryl_count
dtype: int64
- name: lactoyl_count
dtype: int64
- name: lauroyl_count
dtype: int64
- name: lauryl_count
dtype: int64
- name: leucyl_count
dtype: int64
- name: levulinoyl_count
dtype: int64
- name: malonyl_count
dtype: int64
- name: mandeloyl_count
dtype: int64
- name: mercapto_count
dtype: int64
- name: mesityl_count
dtype: int64
- name: methacryloyl_count
dtype: int64
- name: methallyl_count
dtype: int64
- name: methionyl_count
dtype: int64
- name: methoxy_count
dtype: int64
- name: methylene_count
dtype: int64
- name: methylthio_count
dtype: int64
- name: myristoyl_count
dtype: int64
- name: myristyl_count
dtype: int64
- name: naphthyl_count
dtype: int64
- name: naphthylene_count
dtype: int64
- name: neopentyl_count
dtype: int64
- name: nitramino_count
dtype: int64
- name: nitrosamino_count
dtype: int64
- name: nitroso_count
dtype: int64
- name: nonanoyl_count
dtype: int64
- name: oleoyl_count
dtype: int64
- name: oxalyl_count
dtype: int64
- name: oxo_count
dtype: int64
- name: palmitoyl_count
dtype: int64
- name: pentamethylene_count
dtype: int64
- name: pentyl_count
dtype: int64
- name: tert-pentyl_count
dtype: int64
- name: phenacylidene_count
dtype: int64
- name: phenethyl_count
dtype: int64
- name: phenoxy_count
dtype: int64
- name: phenyl_count
dtype: int64
- name: phenylene_count
dtype: int64
- name: phosphino_count
dtype: int64
- name: phosphinyl_count
dtype: int64
- name: phospho_count
dtype: int64
- name: phosphono_count
dtype: int64
- name: phthaloyl_count
dtype: int64
- name: picryl_count
dtype: int64
- name: pimeloyl_count
dtype: int64
- name: piperidino_count
dtype: int64
- name: pivaloyl_count
dtype: int64
- name: prenyl_count
dtype: int64
- name: propargyl_count
dtype: int64
- name: 1-propenyl_count
dtype: int64
- name: 2-propenyl_count
dtype: int64
- name: propionyl_count
dtype: int64
- name: propoxy_count
dtype: int64
- name: propyl_count
dtype: int64
- name: propylidene_count
dtype: int64
- name: pyrryl_count
dtype: int64
- name: salicyloyl_count
dtype: int64
- name: selenyl_count
dtype: int64
- name: seryl_count
dtype: int64
- name: siloxy_count
dtype: int64
- name: silyl_count
dtype: int64
- name: silyene_count
dtype: int64
- name: sorboyl_count
dtype: int64
- name: stearoyl_count
dtype: int64
- name: stearyl_count
dtype: int64
- name: styryl_count
dtype: int64
- name: suberoyl_count
dtype: int64
- name: succinyl_count
dtype: int64
- name: sulfamino_count
dtype: int64
- name: sulfamoyl_count
dtype: int64
- name: sulfanilyl_count
dtype: int64
- name: sulfeno_count
dtype: int64
- name: sulfhydryl_count
dtype: int64
- name: sulfinyl_count
dtype: int64
- name: sulfo_count
dtype: int64
- name: sulfonyl_count
dtype: int64
- name: terephthaloyl_count
dtype: int64
- name: tetramethylene_count
dtype: int64
- name: thienyl_count
dtype: int64
- name: thiocarbonyl_count
dtype: int64
- name: thiocarboxy_count
dtype: int64
- name: thiocyanato_count
dtype: int64
- name: thionyl_count
dtype: int64
- name: threonyl_count
dtype: int64
- name: toluidino_count
dtype: int64
- name: toluoyl_count
dtype: int64
- name: tolyl_count
dtype: int64
- name: alpha-tolyl_count
dtype: int64
- name: tolylene_count
dtype: int64
- name: tosyl_count
dtype: int64
- name: triazano_count
dtype: int64
- name: trimethylene_count
dtype: int64
- name: valeryl_count
dtype: int64
- name: valyl_count
dtype: int64
- name: vinyl_count
dtype: int64
- name: vinylidene_count
dtype: int64
- name: xylidino_count
dtype: int64
- name: xylyl_count
dtype: int64
- name: xylylene_count
dtype: int64
- name: propiolamide_count
dtype: int64
- name: fumarate ester_count
dtype: int64
- name: allenamide_count
dtype: int64
- name: propiolonitrile_count
dtype: int64
- name: propargylamide_count
dtype: int64
- name: arylsulfonyl bicyclobutane_count
dtype: int64
- name: haloalkane_count
dtype: int64
- name: alpha-halomethyl_count
dtype: int64
- name: alpha-haloamide_count
dtype: int64
- name: alpha-haloester_count
dtype: int64
- name: epoxide_count
dtype: int64
- name: aziridine_count
dtype: int64
- name: nitroalkane_count
dtype: int64
- name: acrylamide_count
dtype: int64
- name: cyanoenone_count
dtype: int64
- name: aldehyde_count
dtype: int64
- name: ketone_count
dtype: int64
- name: nitrile_count
dtype: int64
- name: cyanamide_count
dtype: int64
- name: isothicyanate_count
dtype: int64
- name: sulfone_count
dtype: int64
- name: sulfonyl fluoride_count
dtype: int64
- name: sulfonimidoyl fluoride_count
dtype: int64
- name: aryl fluorosulfate_count
dtype: int64
- name: ester_count
dtype: int64
- name: sulfonamide_count
dtype: int64
- name: 2-carbonyl arylboronic acid_count
dtype: int64
- name: n-methyl isoxazolium_count
dtype: int64
- name: oxaziridine_count
dtype: int64
- name: carboxyl_count
dtype: int64
- name: ether_count
dtype: int64
- name: alkanol_count
dtype: int64
- name: thiol_count
dtype: int64
- name: halogen_count
dtype: int64
- name: amine_count
dtype: int64
- name: amide_count
dtype: int64
- name: num_valence_electrons
dtype: int64
- name: rotable_proportion
dtype: float64
- name: non_rotable_proportion
dtype: float64
- name: num_unspecified_bond
dtype: float64
- name: num_single_bonds
dtype: float64
- name: num_double_bonds
dtype: float64
- name: num_triple_bonds
dtype: float64
- name: num_quadruple_bonds
dtype: float64
- name: num_quintuple_bonds
dtype: float64
- name: num_hextuple_bonds
dtype: float64
- name: num_oneandahalf_bonds
dtype: float64
- name: num_twoandahalf_bonds
dtype: float64
- name: num_threeandahalf_bonds
dtype: float64
- name: num_fourandahalf_bonds
dtype: float64
- name: num_fiveandahalf_bonds
dtype: float64
- name: num_aromatic_bonds
dtype: float64
- name: num_ionic_bonds
dtype: float64
- name: num_hydrogen_bonds
dtype: float64
- name: num_threecenter_bonds
dtype: float64
- name: num_dativeone_bonds
dtype: float64
- name: num_dative_bonds
dtype: float64
- name: num_other_bonds
dtype: float64
- name: num_zero_bonds
dtype: float64
- name: num_bonds
dtype: int64
- name: molecular_formula
dtype: string
- name: monoisotopic_molecular_mass
dtype: float64
- name: carbon_mass
dtype: float64
- name: hydrogen_mass
dtype: float64
- name: nitrogen_mass
dtype: float64
- name: oxygen_mass
dtype: float64
- name: num_carbon_atoms
dtype: int64
- name: num_hydrogen_atoms
dtype: int64
- name: num_nitrogen_atoms
dtype: int64
- name: num_oxygen_atoms
dtype: int64
- name: num_hydrogen_bond_acceptors
dtype: int64
- name: num_hydrogen_bond_donors
dtype: int64
- name: num_lipinski_violations
dtype: int64
- name: inertial_shape_factor
dtype: float64
- name: eccentricity
dtype: float64
- name: asphericity
dtype: float64
- name: npr1_value
dtype: float64
- name: npr2_value
dtype: float64
- name: pmi1_value
dtype: float64
- name: pmi2_value
dtype: float64
- name: pmi3_value
dtype: float64
- name: num_chiral_centers
dtype: int64
- name: representation
dtype: string
splits:
- name: train
num_bytes: 2773167
num_examples: 499
download_size: 518183
dataset_size: 2773167
- config_name: rdkit_feat_6
features:
- name: tert-butyloxycarbonyl_count
dtype: int64
- name: representation_type
dtype: string
- name: trityl_count
dtype: int64
- name: 3,5-dimethoxyphenylisoproxycarbonyl_count
dtype: int64
- name: 2-(4-biphenyl)isopropoxycarbonyl_count
dtype: int64
- name: 2-nitrophenylsulfenyl_count
dtype: int64
- name: boc_count
dtype: int64
- name: trt_count
dtype: int64
- name: ddz_count
dtype: int64
- name: bpoc_count
dtype: int64
- name: nps_count
dtype: int64
- name: 9-fluorenylmethoxycarbonyl_count
dtype: int64
- name: 2-(4-nitrophenylsulfonyl)ethoxycarbonyl_count
dtype: int64
- name: (1,1-dioxobenzo[b]thiophene-2-yl)methyloxycarbonyl_count
dtype: int64
- name: (1,1-dioxonaptho[1,2-b]thiophene-2-yl)methyloxycarbonyl_count
dtype: int64
- name: 1-(4,4-dimethyl-2,6-dioxocyclohex-1-ylidene)-3-methylbutyl_count
dtype: int64
- name: 2,7-di-tert-butyl-fmoc_count
dtype: int64
- name: 2-fluoro-fmoc_count
dtype: int64
- name: 2-monoisooctyl-fmoc_count
dtype: int64
- name: 2,7-diisooctyl-fmoc_count
dtype: int64
- name: tetrachlorophthaloyl_count
dtype: int64
- name: 2-[phenyl(methyl)sulfonio])ethyloxycarbonyltetrafluoroborate_count
dtype: int64
- name: ethanesulfonylethoxycarbonyl_count
dtype: int64
- name: 2-(4-sulfophenylsulfonyl)ethoxycarbonyl_count
dtype: int64
- name: fmoc_count
dtype: int64
- name: nsc_count
dtype: int64
- name: bsmoc_count
dtype: int64
- name: alpha-nsmoc_count
dtype: int64
- name: ivdde_count
dtype: int64
- name: fmoc*_count
dtype: int64
- name: fmoc(fmoc(2f))_count
dtype: int64
- name: mio-fmoc_count
dtype: int64
- name: dio-fmoc_count
dtype: int64
- name: tcp_count
dtype: int64
- name: pms_count
dtype: int64
- name: esc_count
dtype: int64
- name: sps_count
dtype: int64
- name: benzyloxycarbonyl_count
dtype: int64
- name: allyloxycarbonyl_count
dtype: int64
- name: o-nitrobenzenesulfonyl_count
dtype: int64
- name: 2,4-dinitrobenzenesulfonyl_count
dtype: int64
- name: benzothiazole-2-sulfonyl_count
dtype: int64
- name: 2,2,2-trichloroethyloxycarbonyl_count
dtype: int64
- name: dithiasuccinoyl_count
dtype: int64
- name: p-nitrobenzyloxycarbonyl_count
dtype: int64
- name: alpha-azidoacids_count
dtype: int64
- name: proparglyoxycarbonyl_count
dtype: int64
- name: o-nitrobenzylcarbonyl_count
dtype: int64
- name: 4-nitroveratryloxycarbonyl_count
dtype: int64
- name: 2-(2-nitrophenyl)propyloxycarbonyl_count
dtype: int64
- name: 2-(3,4-methylenedioxy-6-nitrophenyl)propyloxycarbonyl_count
dtype: int64
- name: 9-(4-bromophenyl)-9-fluorenyl_count
dtype: int64
- name: azidomethoxycarbonyl_count
dtype: int64
- name: hexafluoroacetone_count
dtype: int64
- name: Z_count
dtype: int64
- name: alloc_count
dtype: int64
- name: o-nbs_count
dtype: int64
- name: d-nbs_count
dtype: int64
- name: bts_count
dtype: int64
- name: troc_count
dtype: int64
- name: dts_count
dtype: int64
- name: pnz_count
dtype: int64
- name: poc_count
dtype: int64
- name: onz_count
dtype: int64
- name: nvoc_count
dtype: int64
- name: nppoc_count
dtype: int64
- name: mnppoc_count
dtype: int64
- name: brphf_count
dtype: int64
- name: azoc_count
dtype: int64
- name: hfa_count
dtype: int64
- name: 2-chlorobenzyloxycarbonyl_count
dtype: int64
- name: 4-methyltrityl_count
dtype: int64
- name: cl-z_count
dtype: int64
- name: mtt_count
dtype: int64
- name: 1-(4,4-dimethyl-2,6-dioxocylohex-1-ylidene)-3-methylbutyl_count
dtype: int64
- name: trifluoroacetyl_count
dtype: int64
- name: 2-(methylsulfonyl)ethoxycarbonyl_count
dtype: int64
- name: tfa_count
dtype: int64
- name: msc_count
dtype: int64
- name: phenyldisulphanylethyloxycarbonyl_count
dtype: int64
- name: 2-pyridyldisulphanylethyloxycarbonyl_count
dtype: int64
- name: phdec_count
dtype: int64
- name: pydec_count
dtype: int64
- name: tert-butyl_count
dtype: int64
- name: 2-chlorotrityl_count
dtype: int64
- name: 2-4-dimethyoxybenzyl_count
dtype: int64
- name: 2-phenylisopropyl_count
dtype: int64
- name: 5-phenyl-3,4-ethylenedioxythenyl_count
dtype: int64
- name: bu_count
dtype: int64
- name: 2-cl-trt_count
dtype: int64
- name: dmb_count
dtype: int64
- name: 2-ph-pr_count
dtype: int64
- name: phenyl-edotn_count
dtype: int64
- name: 9-fluorenylmethyl_count
dtype: int64
- name: 4-(N-[1-(4,4-dimethyl-2,6-dioxocylocheylidene)-3-methylbutyl]-amino)benzyl_count
dtype: int64
- name: methyl_count
dtype: int64
- name: ethyl_count
dtype: int64
- name: carbamoylmethyl_count
dtype: int64
- name: fm_count
dtype: int64
- name: dmab_count
dtype: int64
- name: me_count
dtype: int64
- name: et_count
dtype: int64
- name: cam_count
dtype: int64
- name: allyl_count
dtype: int64
- name: benzyl_count
dtype: int64
- name: phenacyl_count
dtype: int64
- name: p-nitrobenzyl_count
dtype: int64
- name: 2-trimethylsilyethyl_count
dtype: int64
- name: (2-phenyl-2-trimethylsilyl)ethyl_count
dtype: int64
- name: 2-(trimethylsilyl)isopropyl_count
dtype: int64
- name: 2,2,2-trichloroethyl_count
dtype: int64
- name: p-hydroxyphenacyl_count
dtype: int64
- name: 4,5-dimethyoxy-2-nitrobenzyl_count
dtype: int64
- name: 1,1-dimethylallyl_count
dtype: int64
- name: pentaaminecobalt_III_count
dtype: int64
- name: al_count
dtype: int64
- name: bn_count
dtype: int64
- name: pac_count
dtype: int64
- name: pnb_count
dtype: int64
- name: tmse_count
dtype: int64
- name: ptmse_count
dtype: int64
- name: tmsi_count
dtype: int64
- name: tce_count
dtype: int64
- name: php_count
dtype: int64
- name: dmnb_count
dtype: int64
- name: dma_count
dtype: int64
- name: cyclohexyl_count
dtype: int64
- name: b-menthyl_count
dtype: int64
- name: b-3-methylpent-3-yl_count
dtype: int64
- name: 4-(3,6,9-trioxadecyl)oxybenzyl_count
dtype: int64
- name: chx_count
dtype: int64
- name: men_count
dtype: int64
- name: mpe_count
dtype: int64
- name: tegbz_count
dtype: int64
- name: 9-fluoroenylmethyl_count
dtype: int64
- name: 4-(N-[1-(4,4-dimethyl-2,6-dioxocyclohexylidene)-3-methyl-butyl]-amino)benzyl_count
dtype: int64
- name: trimethylsilylethyl_count
dtype: int64
- name: 4,5-dimethoxy-2-nitrobenzyloxycarbonyl_count
dtype: int64
- name: pseudoprolines_count
dtype: int64
- name: 2-hydroxy-4-methoxybenzyl_count
dtype: int64
- name: 2,4-dimethoxybenzyl_count
dtype: int64
- name: 2,4,6-trimethoxybenzyl_count
dtype: int64
- name: 1-methyl-3-indolylmethyl_count
dtype: int64
- name: 3,4-ethylene-dioxy-2-thenyl_count
dtype: int64
- name: hmb_count
dtype: int64
- name: tmob_count
dtype: int64
- name: mim_count
dtype: int64
- name: edot_count
dtype: int64
- name: 4-methoxy-2-nitro-benzyl_count
dtype: int64
- name: (6-hydroxy-3-oxido-1,3-benz[d]oxathiol-5-yl)methyl_count
dtype: int64
- name: 2-hydroxy-4-methoxy-5-(methylsulfinyl)benzyl_count
dtype: int64
- name: n-boc-n-methyl[2-(methylamino)ethyl]carbamoyl-hmb_count
dtype: int64
- name: 9-xanthenyl_count
dtype: int64
- name: cyclopropyldimethylcarbinyl_count
dtype: int64
- name: 4,4-dimethoxybenzhydryl_count
dtype: int64
- name: xan_count
dtype: int64
- name: cpd_count
dtype: int64
- name: mbh_count
dtype: int64
- name: p-toluenesulfonyl_count
dtype: int64
- name: 2,2,5,7,8-pentamethylchroman-6-sulfonyl_count
dtype: int64
- name: 2,2,4,6,7-pentamethyl-2,3-dihydrobenzofuran-5-sulfonyl_count
dtype: int64
- name: mesityl-2-sulfonyl_count
dtype: int64
- name: 4-methoxy-2,3,6-trimethylphenylsulfonyl_count
dtype: int64
- name: 1,2-dimethylindole-3-sulfonyl_count
dtype: int64
- name: w,w-bis-tert-butyloxycarbonyl_count
dtype: int64
- name: 5-dibenzosuberenyl_count
dtype: int64
- name: 5-dibenzosuberyl_count
dtype: int64
- name: 2-methoxy-5-dibenzosuberyl_count
dtype: int64
- name: nitro_count
dtype: int64
- name: tos_count
dtype: int64
- name: pmc_count
dtype: int64
- name: pbf_count
dtype: int64
- name: mts_count
dtype: int64
- name: mtr_count
dtype: int64
- name: mis_count
dtype: int64
- name: bis-boc_count
dtype: int64
- name: suben_count
dtype: int64
- name: sub_count
dtype: int64
- name: mesub_count
dtype: int64
- name: no2_count
dtype: int64
- name: w,w-bis-benzyloxycarbonyl_count
dtype: int64
- name: w,w-bis-allyloxycarbonyl_count
dtype: int64
- name: z-small_count
dtype: int64
- name: p-methylbenzyl_count
dtype: int64
- name: p-methoxybenzyl_count
dtype: int64
- name: monomethoxytrityl_count
dtype: int64
- name: trimethoxybenzyl_count
dtype: int64
- name: 2,2,4,6,7-pentamethyl-5-dihydrobenzofuranylmethyl_count
dtype: int64
- name: 1-adamantyl_count
dtype: int64
- name: meb_count
dtype: int64
- name: mob_count
dtype: int64
- name: mmt_count
dtype: int64
- name: pmbf_count
dtype: int64
- name: 1-ada_count
dtype: int64
- name: 2-(2,4-dinitrophenyl)ethyl_count
dtype: int64
- name: 9-fluororenylmethoxycarbonyl_count
dtype: int64
- name: dnpe_count
dtype: int64
- name: acetamidomethyl_count
dtype: int64
- name: phenylacetamidomethyl_count
dtype: int64
- name: 5-tert-butylmercapto_count
dtype: int64
- name: 3-nitro-2-pyridinesulfenyl_count
dtype: int64
- name: 2-pyridinesulfenyl_count
dtype: int64
- name: N-allyloxycarbonyl-N-[2,3,5,6-tetrafluoro-4-(phenylthio)phenyl]]aminomethyl_count
dtype: int64
- name: o-nitrobenzyl_count
dtype: int64
- name: 4-picolyl_count
dtype: int64
- name: ninhydrin_count
dtype: int64
- name: acm_count
dtype: int64
- name: phacm_count
dtype: int64
- name: sbu_count
dtype: int64
- name: npys_count
dtype: int64
- name: s-pyr_count
dtype: int64
- name: fsam_count
dtype: int64
- name: onb_count
dtype: int64
- name: nin_count
dtype: int64
- name: n-tosyl_count
dtype: int64
- name: n-trityl_count
dtype: int64
- name: n-monomethoxytrityl_count
dtype: int64
- name: n-methyltrityl_count
dtype: int64
- name: n-tert-butyloxycarbonyl_count
dtype: int64
- name: n-2,4-dimethylpent-3-yloxycarbonyl_count
dtype: int64
- name: n-benzyloxymethyl_count
dtype: int64
- name: n-tert-butoxymethyl_count
dtype: int64
- name: ntos_count
dtype: int64
- name: ntrt_count
dtype: int64
- name: nmtt_count
dtype: int64
- name: nmmt_count
dtype: int64
- name: nboc_count
dtype: int64
- name: ndoc_count
dtype: int64
- name: nbom_count
dtype: int64
- name: nbum_count
dtype: int64
- name: N-9-fluorenylmethoxycarbonyl_count
dtype: int64
- name: N-2,6-dimethoxybenzoyl_count
dtype: int64
- name: dmbz_count
dtype: int64
- name: N-2,4-dinitrophenyl_count
dtype: int64
- name: dnp_count
dtype: int64
- name: cyclohexyl;_count
dtype: int64
- name: tert-butyldimethylsilyl_count
dtype: int64
- name: tbdms_count
dtype: int64
- name: tert-butyldiphenylsilyl_count
dtype: int64
- name: propargyloxycarbonyl_count
dtype: int64
- name: tbdps_count
dtype: int64
- name: 2,6-dichlorobenzyl_count
dtype: int64
- name: 2-bromobenzyl_count
dtype: int64
- name: 2-bromobenzyloxycarbonyl_count
dtype: int64
- name: 3-pentyl_count
dtype: int64
- name: dcb_count
dtype: int64
- name: brbn_count
dtype: int64
- name: brz_count
dtype: int64
- name: pen_count
dtype: int64
- name: tegb_count
dtype: int64
- name: boc-n-methyl-n-[2-(methylamino)ethyl]carbamoyl_count
dtype: int64
- name: boc-nmec_count
dtype: int64
- name: formyl_count
dtype: int64
- name: cyclohexyloxycarbonyl_count
dtype: int64
- name: for_count
dtype: int64
- name: hoc_count
dtype: int64
- name: cyclopropane_count
dtype: int64
- name: spiropentane_count
dtype: int64
- name: cyclobutane_count
dtype: int64
- name: cyclopentane_count
dtype: int64
- name: furan_count
dtype: int64
- name: thiophene_count
dtype: int64
- name: pyrrole_count
dtype: int64
- name: 2H-pyrrole_count
dtype: int64
- name: 3H-pyrrole_count
dtype: int64
- name: pyrazole_count
dtype: int64
- name: 2H-imidazole_count
dtype: int64
- name: 1,2,3-triazole_count
dtype: int64
- name: 1,2,4-triazole_count
dtype: int64
- name: 1,2-dithiole_count
dtype: int64
- name: 1,3-dithiole_count
dtype: int64
- name: 3H-1,2-oxathiole_count
dtype: int64
- name: isoxazole_count
dtype: int64
- name: oxazole_count
dtype: int64
- name: thiazole_count
dtype: int64
- name: isothiazole_count
dtype: int64
- name: 1,2,3-oxadiazole_count
dtype: int64
- name: 1,2,4-oxadiazole_count
dtype: int64
- name: 1,2,5-oxadiazole_count
dtype: int64
- name: 1,3,4-oxadiazole_count
dtype: int64
- name: 1,2,3,4-oxatriazole_count
dtype: int64
- name: 1,2,3,5-oxatriazole_count
dtype: int64
- name: 3H-1,2,3-dioxazole_count
dtype: int64
- name: 1,2,4-dioxazole_count
dtype: int64
- name: 1,3,2-dioxazole_count
dtype: int64
- name: 1,3,4-dioxazole_count
dtype: int64
- name: 5H-1,2,5-oxathiazole_count
dtype: int64
- name: 1,3-oxathiole_count
dtype: int64
- name: benzene_count
dtype: int64
- name: cyclohexane_count
dtype: int64
- name: 2H-pyran_count
dtype: int64
- name: 4H-pyran_count
dtype: int64
- name: 2H-pyran-2-one_count
dtype: int64
- name: 4H-pyran-4-one_count
dtype: int64
- name: 1,2-dioxin_count
dtype: int64
- name: 1,3-dioxin_count
dtype: int64
- name: pyridine_count
dtype: int64
- name: pyridazine_count
dtype: int64
- name: pyrimidine_count
dtype: int64
- name: pyrazine_count
dtype: int64
- name: piperazine_count
dtype: int64
- name: 1,3,5-triazine_count
dtype: int64
- name: 1,2,4-triazine_count
dtype: int64
- name: 1,2,3-triazine_count
dtype: int64
- name: 4H-1,2-Oxazine_count
dtype: int64
- name: 2H-1,3-Oxazine_count
dtype: int64
- name: 6H-1,3-Oxazine_count
dtype: int64
- name: 6H-1,2-Oxazine_count
dtype: int64
- name: 1,4-Oxazine_count
dtype: int64
- name: 2H-1,2-Oxazine_count
dtype: int64
- name: 4H-1,4-Oxazine_count
dtype: int64
- name: 1,2,5-Oxathiazine_count
dtype: int64
- name: 1,2,6-Oxathiazine_count
dtype: int64
- name: 1,2,4-Oxadiazine_count
dtype: int64
- name: 1,3,5-Oxadiazine_count
dtype: int64
- name: morpholine_count
dtype: int64
- name: azepine_count
dtype: int64
- name: oxepin_count
dtype: int64
- name: thiepin_count
dtype: int64
- name: 4H-1,2-diazepine_count
dtype: int64
- name: indene_count
dtype: int64
- name: 2H-indene_count
dtype: int64
- name: benzofuran_count
dtype: int64
- name: isobenzofuran_count
dtype: int64
- name: benzo[b]thiophene_count
dtype: int64
- name: benzo[c]thiophene_count
dtype: int64
- name: indole_count
dtype: int64
- name: 3H-indole_count
dtype: int64
- name: 1H-indole_count
dtype: int64
- name: cyclopenta[b]pyridine_count
dtype: int64
- name: pyrano[3,4-b]-pyrrole_count
dtype: int64
- name: indazole_count
dtype: int64
- name: benzisoxazole_count
dtype: int64
- name: benzoxazole_count
dtype: int64
- name: 2,1-benzisoxazole_count
dtype: int64
- name: naphthalene_count
dtype: int64
- name: 1,2,3,4-tetrahydronaphthalene_count
dtype: int64
- name: octahydronaphthalene_count
dtype: int64
- name: 2H-1-benzopyran_count
dtype: int64
- name: 2H-1-benzopyran-2-one_count
dtype: int64
- name: 4H-1-benzopyran-4-one_count
dtype: int64
- name: 1H-2-benzopyran-1-one_count
dtype: int64
- name: 3H-2-benzopyran-1-one_count
dtype: int64
- name: quinoline_count
dtype: int64
- name: isoquinoline_count
dtype: int64
- name: cinnoline_count
dtype: int64
- name: quinazoline_count
dtype: int64
- name: 1,8-napthyhridine_count
dtype: int64
- name: 1,7-napththyridine_count
dtype: int64
- name: 1,5-napththridine_count
dtype: int64
- name: 1,6-napthyridine_count
dtype: int64
- name: 2H-1,3-benzoxazine_count
dtype: int64
- name: 2H-1,4-benzoxazine_count
dtype: int64
- name: 1H-2,3-benzoxazine_count
dtype: int64
- name: 4H-3,1-benzoxazine_count
dtype: int64
- name: 2H-1,2-benzoxazine_count
dtype: int64
- name: 4H-1,3-benzoxazine_count
dtype: int64
- name: anthracene_count
dtype: int64
- name: phenanthrene_count
dtype: int64
- name: phenalene_count
dtype: int64
- name: fluorene_count
dtype: int64
- name: carbazole_count
dtype: int64
- name: xanthene_count
dtype: int64
- name: acridine_count
dtype: int64
- name: norpinane_count
dtype: int64
- name: 7H-purine_count
dtype: int64
- name: steroid_ring_system_count
dtype: int64
- name: imidazole_count
dtype: int64
- name: thiazol-2-amine_count
dtype: int64
- name: tetrazole_count
dtype: int64
- name: cytosine_count
dtype: int64
- name: adenine_count
dtype: int64
- name: 5-methylindole_count
dtype: int64
- name: isocaffeine_count
dtype: int64
- name: tetrazolethiol_count
dtype: int64
- name: 3-methylisoxazole_count
dtype: int64
- name: 1-methylimidazole_count
dtype: int64
- name: 2-methylimidazole_count
dtype: int64
- name: guanine_count
dtype: int64
- name: tosufloxacin_count
dtype: int64
- name: acetamido_count
dtype: int64
- name: acetoacetyl_count
dtype: int64
- name: acetyl_count
dtype: int64
- name: acryloyl_count
dtype: int64
- name: alanyl_count
dtype: int64
- name: beta-alanyl_count
dtype: int64
- name: allylidene_count
dtype: int64
- name: amidino_count
dtype: int64
- name: amino_count
dtype: int64
- name: amyl_count
dtype: int64
- name: anilino_count
dtype: int64
- name: anisidino_count
dtype: int64
- name: anthranoyl_count
dtype: int64
- name: arsino_count
dtype: int64
- name: azelaoyl_count
dtype: int64
- name: azido_count
dtype: int64
- name: azo_count
dtype: int64
- name: azoxy_count
dtype: int64
- name: benzal_count
dtype: int64
- name: benzamido_count
dtype: int64
- name: benzhydrol_count
dtype: int64
- name: benzoxy_count
dtype: int64
- name: benzoyl_count
dtype: int64
- name: benzylidene_count
dtype: int64
- name: benzylidyne_count
dtype: int64
- name: biphenylyl_count
dtype: int64
- name: biphenylene_count
dtype: int64
- name: butoxy_count
dtype: int64
- name: sec-butoxy_count
dtype: int64
- name: tert-butoxy_count
dtype: int64
- name: butyl_count
dtype: int64
- name: sec-butyl_count
dtype: int64
- name: butyryl_count
dtype: int64
- name: caproyl_count
dtype: int64
- name: capryl_count
dtype: int64
- name: capryloyl_count
dtype: int64
- name: carbamido_count
dtype: int64
- name: carbamoyl_count
dtype: int64
- name: carbamyl_count
dtype: int64
- name: carbazoyl_count
dtype: int64
- name: carbethoxy_count
dtype: int64
- name: carbonyl_count
dtype: int64
- name: carboxy_count
dtype: int64
- name: cetyl_count
dtype: int64
- name: chloroformyl_count
dtype: int64
- name: cinnamoyl_count
dtype: int64
- name: cinnamyl_count
dtype: int64
- name: cinnamylidene_count
dtype: int64
- name: cresyl_count
dtype: int64
- name: crotonoyl_count
dtype: int64
- name: crotyl_count
dtype: int64
- name: cyanamido_count
dtype: int64
- name: cyanato_count
dtype: int64
- name: cyano_count
dtype: int64
- name: decanedioyl_count
dtype: int64
- name: decanoyl_count
dtype: int64
- name: diazo_count
dtype: int64
- name: diazoamino_count
dtype: int64
- name: disilanyl_count
dtype: int64
- name: disiloxanyloxy_count
dtype: int64
- name: disulfinyl_count
dtype: int64
- name: dithio_count
dtype: int64
- name: enanthoyl_count
dtype: int64
- name: epoxy_count
dtype: int64
- name: ethenyl_count
dtype: int64
- name: ethynyl_count
dtype: int64
- name: ethoxy_count
dtype: int64
- name: ethylene_count
dtype: int64
- name: ethylidene_count
dtype: int64
- name: ethylthio_count
dtype: int64
- name: formamido_count
dtype: int64
- name: furmaroyl_count
dtype: int64
- name: furfuryl_count
dtype: int64
- name: furfurylidene_count
dtype: int64
- name: glutamoyl_count
dtype: int64
- name: glutaryl_count
dtype: int64
- name: glycylamino_count
dtype: int64
- name: glycoloyl_count
dtype: int64
- name: glycyl_count
dtype: int64
- name: glyoxyoyl_count
dtype: int64
- name: guanidino_count
dtype: int64
- name: guanyl_count
dtype: int64
- name: heptadecanoyl_count
dtype: int64
- name: heptanamido_count
dtype: int64
- name: heptanoyl_count
dtype: int64
- name: hexadecanoyl_count
dtype: int64
- name: hexamethylene_count
dtype: int64
- name: hexanedioyl_count
dtype: int64
- name: hippuryl_count
dtype: int64
- name: hydrazino_count
dtype: int64
- name: hydrazo_count
dtype: int64
- name: hydrocinnamoyl_count
dtype: int64
- name: hydroperoxy_count
dtype: int64
- name: hydroxyamino_count
dtype: int64
- name: imino_count
dtype: int64
- name: iodoso_count
dtype: int64
- name: iodyl_count
dtype: int64
- name: isoamyl_count
dtype: int64
- name: isobutenyl_count
dtype: int64
- name: isobutoxy_count
dtype: int64
- name: isobutyl_count
dtype: int64
- name: isobutylidene_count
dtype: int64
- name: isobutyryl_count
dtype: int64
- name: isocyanato_count
dtype: int64
- name: isocyano_count
dtype: int64
- name: isohexyl_count
dtype: int64
- name: isoleucyl_count
dtype: int64
- name: isonitroso_count
dtype: int64
- name: isopentyl_count
dtype: int64
- name: isopentylidene_count
dtype: int64
- name: isopropenyl_count
dtype: int64
- name: isopropoxy_count
dtype: int64
- name: isopropyl_count
dtype: int64
- name: isopropylidene_count
dtype: int64
- name: isothiocynato_count
dtype: int64
- name: isovaleryl_count
dtype: int64
- name: lactoyl_count
dtype: int64
- name: lauroyl_count
dtype: int64
- name: lauryl_count
dtype: int64
- name: leucyl_count
dtype: int64
- name: levulinoyl_count
dtype: int64
- name: malonyl_count
dtype: int64
- name: mandeloyl_count
dtype: int64
- name: mercapto_count
dtype: int64
- name: mesityl_count
dtype: int64
- name: methacryloyl_count
dtype: int64
- name: methallyl_count
dtype: int64
- name: methionyl_count
dtype: int64
- name: methoxy_count
dtype: int64
- name: methylene_count
dtype: int64
- name: methylthio_count
dtype: int64
- name: myristoyl_count
dtype: int64
- name: myristyl_count
dtype: int64
- name: naphthyl_count
dtype: int64
- name: naphthylene_count
dtype: int64
- name: neopentyl_count
dtype: int64
- name: nitramino_count
dtype: int64
- name: nitrosamino_count
dtype: int64
- name: nitroso_count
dtype: int64
- name: nonanoyl_count
dtype: int64
- name: oleoyl_count
dtype: int64
- name: oxalyl_count
dtype: int64
- name: oxo_count
dtype: int64
- name: palmitoyl_count
dtype: int64
- name: pentamethylene_count
dtype: int64
- name: pentyl_count
dtype: int64
- name: tert-pentyl_count
dtype: int64
- name: phenacylidene_count
dtype: int64
- name: phenethyl_count
dtype: int64
- name: phenoxy_count
dtype: int64
- name: phenyl_count
dtype: int64
- name: phenylene_count
dtype: int64
- name: phosphino_count
dtype: int64
- name: phosphinyl_count
dtype: int64
- name: phospho_count
dtype: int64
- name: phosphono_count
dtype: int64
- name: phthaloyl_count
dtype: int64
- name: picryl_count
dtype: int64
- name: pimeloyl_count
dtype: int64
- name: piperidino_count
dtype: int64
- name: pivaloyl_count
dtype: int64
- name: prenyl_count
dtype: int64
- name: propargyl_count
dtype: int64
- name: 1-propenyl_count
dtype: int64
- name: 2-propenyl_count
dtype: int64
- name: propionyl_count
dtype: int64
- name: propoxy_count
dtype: int64
- name: propyl_count
dtype: int64
- name: propylidene_count
dtype: int64
- name: pyrryl_count
dtype: int64
- name: salicyloyl_count
dtype: int64
- name: selenyl_count
dtype: int64
- name: seryl_count
dtype: int64
- name: siloxy_count
dtype: int64
- name: silyl_count
dtype: int64
- name: silyene_count
dtype: int64
- name: sorboyl_count
dtype: int64
- name: stearoyl_count
dtype: int64
- name: stearyl_count
dtype: int64
- name: styryl_count
dtype: int64
- name: suberoyl_count
dtype: int64
- name: succinyl_count
dtype: int64
- name: sulfamino_count
dtype: int64
- name: sulfamoyl_count
dtype: int64
- name: sulfanilyl_count
dtype: int64
- name: sulfeno_count
dtype: int64
- name: sulfhydryl_count
dtype: int64
- name: sulfinyl_count
dtype: int64
- name: sulfo_count
dtype: int64
- name: sulfonyl_count
dtype: int64
- name: terephthaloyl_count
dtype: int64
- name: tetramethylene_count
dtype: int64
- name: thienyl_count
dtype: int64
- name: thiocarbonyl_count
dtype: int64
- name: thiocarboxy_count
dtype: int64
- name: thiocyanato_count
dtype: int64
- name: thionyl_count
dtype: int64
- name: threonyl_count
dtype: int64
- name: toluidino_count
dtype: int64
- name: toluoyl_count
dtype: int64
- name: tolyl_count
dtype: int64
- name: alpha-tolyl_count
dtype: int64
- name: tolylene_count
dtype: int64
- name: tosyl_count
dtype: int64
- name: triazano_count
dtype: int64
- name: trimethylene_count
dtype: int64
- name: valeryl_count
dtype: int64
- name: valyl_count
dtype: int64
- name: vinyl_count
dtype: int64
- name: vinylidene_count
dtype: int64
- name: xylidino_count
dtype: int64
- name: xylyl_count
dtype: int64
- name: xylylene_count
dtype: int64
- name: propiolamide_count
dtype: int64
- name: fumarate ester_count
dtype: int64
- name: allenamide_count
dtype: int64
- name: propiolonitrile_count
dtype: int64
- name: propargylamide_count
dtype: int64
- name: arylsulfonyl bicyclobutane_count
dtype: int64
- name: haloalkane_count
dtype: int64
- name: alpha-halomethyl_count
dtype: int64
- name: alpha-haloamide_count
dtype: int64
- name: alpha-haloester_count
dtype: int64
- name: epoxide_count
dtype: int64
- name: aziridine_count
dtype: int64
- name: nitroalkane_count
dtype: int64
- name: acrylamide_count
dtype: int64
- name: cyanoenone_count
dtype: int64
- name: aldehyde_count
dtype: int64
- name: ketone_count
dtype: int64
- name: nitrile_count
dtype: int64
- name: cyanamide_count
dtype: int64
- name: isothicyanate_count
dtype: int64
- name: sulfone_count
dtype: int64
- name: sulfonyl fluoride_count
dtype: int64
- name: sulfonimidoyl fluoride_count
dtype: int64
- name: aryl fluorosulfate_count
dtype: int64
- name: ester_count
dtype: int64
- name: sulfonamide_count
dtype: int64
- name: 2-carbonyl arylboronic acid_count
dtype: int64
- name: n-methyl isoxazolium_count
dtype: int64
- name: oxaziridine_count
dtype: int64
- name: carboxyl_count
dtype: int64
- name: ether_count
dtype: int64
- name: alkanol_count
dtype: int64
- name: thiol_count
dtype: int64
- name: halogen_count
dtype: int64
- name: amine_count
dtype: int64
- name: amide_count
dtype: int64
- name: num_valence_electrons
dtype: int64
- name: rotable_proportion
dtype: float64
- name: non_rotable_proportion
dtype: float64
- name: num_unspecified_bond
dtype: float64
- name: num_single_bonds
dtype: float64
- name: num_double_bonds
dtype: float64
- name: num_triple_bonds
dtype: float64
- name: num_quadruple_bonds
dtype: float64
- name: num_quintuple_bonds
dtype: float64
- name: num_hextuple_bonds
dtype: float64
- name: num_oneandahalf_bonds
dtype: float64
- name: num_twoandahalf_bonds
dtype: float64
- name: num_threeandahalf_bonds
dtype: float64
- name: num_fourandahalf_bonds
dtype: float64
- name: num_fiveandahalf_bonds
dtype: float64
- name: num_aromatic_bonds
dtype: float64
- name: num_ionic_bonds
dtype: float64
- name: num_hydrogen_bonds
dtype: float64
- name: num_threecenter_bonds
dtype: float64
- name: num_dativeone_bonds
dtype: float64
- name: num_dative_bonds
dtype: float64
- name: num_other_bonds
dtype: float64
- name: num_zero_bonds
dtype: float64
- name: num_bonds
dtype: int64
- name: molecular_formula
dtype: string
- name: monoisotopic_molecular_mass
dtype: float64
- name: carbon_mass
dtype: float64
- name: hydrogen_mass
dtype: float64
- name: nitrogen_mass
dtype: float64
- name: oxygen_mass
dtype: float64
- name: num_carbon_atoms
dtype: int64
- name: num_hydrogen_atoms
dtype: int64
- name: num_nitrogen_atoms
dtype: int64
- name: num_oxygen_atoms
dtype: int64
- name: num_hydrogen_bond_acceptors
dtype: int64
- name: num_hydrogen_bond_donors
dtype: int64
- name: num_lipinski_violations
dtype: int64
- name: inertial_shape_factor
dtype: float64
- name: eccentricity
dtype: float64
- name: asphericity
dtype: float64
- name: npr1_value
dtype: float64
- name: npr2_value
dtype: float64
- name: pmi1_value
dtype: float64
- name: pmi2_value
dtype: float64
- name: pmi3_value
dtype: float64
- name: num_chiral_centers
dtype: int64
- name: representation
dtype: string
splits:
- name: train
num_bytes: 2760435
num_examples: 499
download_size: 521279
dataset_size: 2760435
- config_name: rdkit_feat_7
features:
- name: tert-butyloxycarbonyl_count
dtype: int64
- name: representation_type
dtype: string
- name: trityl_count
dtype: int64
- name: 3,5-dimethoxyphenylisoproxycarbonyl_count
dtype: int64
- name: 2-(4-biphenyl)isopropoxycarbonyl_count
dtype: int64
- name: 2-nitrophenylsulfenyl_count
dtype: int64
- name: boc_count
dtype: int64
- name: trt_count
dtype: int64
- name: ddz_count
dtype: int64
- name: bpoc_count
dtype: int64
- name: nps_count
dtype: int64
- name: 9-fluorenylmethoxycarbonyl_count
dtype: int64
- name: 2-(4-nitrophenylsulfonyl)ethoxycarbonyl_count
dtype: int64
- name: (1,1-dioxobenzo[b]thiophene-2-yl)methyloxycarbonyl_count
dtype: int64
- name: (1,1-dioxonaptho[1,2-b]thiophene-2-yl)methyloxycarbonyl_count
dtype: int64
- name: 1-(4,4-dimethyl-2,6-dioxocyclohex-1-ylidene)-3-methylbutyl_count
dtype: int64
- name: 2,7-di-tert-butyl-fmoc_count
dtype: int64
- name: 2-fluoro-fmoc_count
dtype: int64
- name: 2-monoisooctyl-fmoc_count
dtype: int64
- name: 2,7-diisooctyl-fmoc_count
dtype: int64
- name: tetrachlorophthaloyl_count
dtype: int64
- name: 2-[phenyl(methyl)sulfonio])ethyloxycarbonyltetrafluoroborate_count
dtype: int64
- name: ethanesulfonylethoxycarbonyl_count
dtype: int64
- name: 2-(4-sulfophenylsulfonyl)ethoxycarbonyl_count
dtype: int64
- name: fmoc_count
dtype: int64
- name: nsc_count
dtype: int64
- name: bsmoc_count
dtype: int64
- name: alpha-nsmoc_count
dtype: int64
- name: ivdde_count
dtype: int64
- name: fmoc*_count
dtype: int64
- name: fmoc(fmoc(2f))_count
dtype: int64
- name: mio-fmoc_count
dtype: int64
- name: dio-fmoc_count
dtype: int64
- name: tcp_count
dtype: int64
- name: pms_count
dtype: int64
- name: esc_count
dtype: int64
- name: sps_count
dtype: int64
- name: benzyloxycarbonyl_count
dtype: int64
- name: allyloxycarbonyl_count
dtype: int64
- name: o-nitrobenzenesulfonyl_count
dtype: int64
- name: 2,4-dinitrobenzenesulfonyl_count
dtype: int64
- name: benzothiazole-2-sulfonyl_count
dtype: int64
- name: 2,2,2-trichloroethyloxycarbonyl_count
dtype: int64
- name: dithiasuccinoyl_count
dtype: int64
- name: p-nitrobenzyloxycarbonyl_count
dtype: int64
- name: alpha-azidoacids_count
dtype: int64
- name: proparglyoxycarbonyl_count
dtype: int64
- name: o-nitrobenzylcarbonyl_count
dtype: int64
- name: 4-nitroveratryloxycarbonyl_count
dtype: int64
- name: 2-(2-nitrophenyl)propyloxycarbonyl_count
dtype: int64
- name: 2-(3,4-methylenedioxy-6-nitrophenyl)propyloxycarbonyl_count
dtype: int64
- name: 9-(4-bromophenyl)-9-fluorenyl_count
dtype: int64
- name: azidomethoxycarbonyl_count
dtype: int64
- name: hexafluoroacetone_count
dtype: int64
- name: Z_count
dtype: int64
- name: alloc_count
dtype: int64
- name: o-nbs_count
dtype: int64
- name: d-nbs_count
dtype: int64
- name: bts_count
dtype: int64
- name: troc_count
dtype: int64
- name: dts_count
dtype: int64
- name: pnz_count
dtype: int64
- name: poc_count
dtype: int64
- name: onz_count
dtype: int64
- name: nvoc_count
dtype: int64
- name: nppoc_count
dtype: int64
- name: mnppoc_count
dtype: int64
- name: brphf_count
dtype: int64
- name: azoc_count
dtype: int64
- name: hfa_count
dtype: int64
- name: 2-chlorobenzyloxycarbonyl_count
dtype: int64
- name: 4-methyltrityl_count
dtype: int64
- name: cl-z_count
dtype: int64
- name: mtt_count
dtype: int64
- name: 1-(4,4-dimethyl-2,6-dioxocylohex-1-ylidene)-3-methylbutyl_count
dtype: int64
- name: trifluoroacetyl_count
dtype: int64
- name: 2-(methylsulfonyl)ethoxycarbonyl_count
dtype: int64
- name: tfa_count
dtype: int64
- name: msc_count
dtype: int64
- name: phenyldisulphanylethyloxycarbonyl_count
dtype: int64
- name: 2-pyridyldisulphanylethyloxycarbonyl_count
dtype: int64
- name: phdec_count
dtype: int64
- name: pydec_count
dtype: int64
- name: tert-butyl_count
dtype: int64
- name: 2-chlorotrityl_count
dtype: int64
- name: 2-4-dimethyoxybenzyl_count
dtype: int64
- name: 2-phenylisopropyl_count
dtype: int64
- name: 5-phenyl-3,4-ethylenedioxythenyl_count
dtype: int64
- name: bu_count
dtype: int64
- name: 2-cl-trt_count
dtype: int64
- name: dmb_count
dtype: int64
- name: 2-ph-pr_count
dtype: int64
- name: phenyl-edotn_count
dtype: int64
- name: 9-fluorenylmethyl_count
dtype: int64
- name: 4-(N-[1-(4,4-dimethyl-2,6-dioxocylocheylidene)-3-methylbutyl]-amino)benzyl_count
dtype: int64
- name: methyl_count
dtype: int64
- name: ethyl_count
dtype: int64
- name: carbamoylmethyl_count
dtype: int64
- name: fm_count
dtype: int64
- name: dmab_count
dtype: int64
- name: me_count
dtype: int64
- name: et_count
dtype: int64
- name: cam_count
dtype: int64
- name: allyl_count
dtype: int64
- name: benzyl_count
dtype: int64
- name: phenacyl_count
dtype: int64
- name: p-nitrobenzyl_count
dtype: int64
- name: 2-trimethylsilyethyl_count
dtype: int64
- name: (2-phenyl-2-trimethylsilyl)ethyl_count
dtype: int64
- name: 2-(trimethylsilyl)isopropyl_count
dtype: int64
- name: 2,2,2-trichloroethyl_count
dtype: int64
- name: p-hydroxyphenacyl_count
dtype: int64
- name: 4,5-dimethyoxy-2-nitrobenzyl_count
dtype: int64
- name: 1,1-dimethylallyl_count
dtype: int64
- name: pentaaminecobalt_III_count
dtype: int64
- name: al_count
dtype: int64
- name: bn_count
dtype: int64
- name: pac_count
dtype: int64
- name: pnb_count
dtype: int64
- name: tmse_count
dtype: int64
- name: ptmse_count
dtype: int64
- name: tmsi_count
dtype: int64
- name: tce_count
dtype: int64
- name: php_count
dtype: int64
- name: dmnb_count
dtype: int64
- name: dma_count
dtype: int64
- name: cyclohexyl_count
dtype: int64
- name: b-menthyl_count
dtype: int64
- name: b-3-methylpent-3-yl_count
dtype: int64
- name: 4-(3,6,9-trioxadecyl)oxybenzyl_count
dtype: int64
- name: chx_count
dtype: int64
- name: men_count
dtype: int64
- name: mpe_count
dtype: int64
- name: tegbz_count
dtype: int64
- name: 9-fluoroenylmethyl_count
dtype: int64
- name: 4-(N-[1-(4,4-dimethyl-2,6-dioxocyclohexylidene)-3-methyl-butyl]-amino)benzyl_count
dtype: int64
- name: trimethylsilylethyl_count
dtype: int64
- name: 4,5-dimethoxy-2-nitrobenzyloxycarbonyl_count
dtype: int64
- name: pseudoprolines_count
dtype: int64
- name: 2-hydroxy-4-methoxybenzyl_count
dtype: int64
- name: 2,4-dimethoxybenzyl_count
dtype: int64
- name: 2,4,6-trimethoxybenzyl_count
dtype: int64
- name: 1-methyl-3-indolylmethyl_count
dtype: int64
- name: 3,4-ethylene-dioxy-2-thenyl_count
dtype: int64
- name: hmb_count
dtype: int64
- name: tmob_count
dtype: int64
- name: mim_count
dtype: int64
- name: edot_count
dtype: int64
- name: 4-methoxy-2-nitro-benzyl_count
dtype: int64
- name: (6-hydroxy-3-oxido-1,3-benz[d]oxathiol-5-yl)methyl_count
dtype: int64
- name: 2-hydroxy-4-methoxy-5-(methylsulfinyl)benzyl_count
dtype: int64
- name: n-boc-n-methyl[2-(methylamino)ethyl]carbamoyl-hmb_count
dtype: int64
- name: 9-xanthenyl_count
dtype: int64
- name: cyclopropyldimethylcarbinyl_count
dtype: int64
- name: 4,4-dimethoxybenzhydryl_count
dtype: int64
- name: xan_count
dtype: int64
- name: cpd_count
dtype: int64
- name: mbh_count
dtype: int64
- name: p-toluenesulfonyl_count
dtype: int64
- name: 2,2,5,7,8-pentamethylchroman-6-sulfonyl_count
dtype: int64
- name: 2,2,4,6,7-pentamethyl-2,3-dihydrobenzofuran-5-sulfonyl_count
dtype: int64
- name: mesityl-2-sulfonyl_count
dtype: int64
- name: 4-methoxy-2,3,6-trimethylphenylsulfonyl_count
dtype: int64
- name: 1,2-dimethylindole-3-sulfonyl_count
dtype: int64
- name: w,w-bis-tert-butyloxycarbonyl_count
dtype: int64
- name: 5-dibenzosuberenyl_count
dtype: int64
- name: 5-dibenzosuberyl_count
dtype: int64
- name: 2-methoxy-5-dibenzosuberyl_count
dtype: int64
- name: nitro_count
dtype: int64
- name: tos_count
dtype: int64
- name: pmc_count
dtype: int64
- name: pbf_count
dtype: int64
- name: mts_count
dtype: int64
- name: mtr_count
dtype: int64
- name: mis_count
dtype: int64
- name: bis-boc_count
dtype: int64
- name: suben_count
dtype: int64
- name: sub_count
dtype: int64
- name: mesub_count
dtype: int64
- name: no2_count
dtype: int64
- name: w,w-bis-benzyloxycarbonyl_count
dtype: int64
- name: w,w-bis-allyloxycarbonyl_count
dtype: int64
- name: z-small_count
dtype: int64
- name: p-methylbenzyl_count
dtype: int64
- name: p-methoxybenzyl_count
dtype: int64
- name: monomethoxytrityl_count
dtype: int64
- name: trimethoxybenzyl_count
dtype: int64
- name: 2,2,4,6,7-pentamethyl-5-dihydrobenzofuranylmethyl_count
dtype: int64
- name: 1-adamantyl_count
dtype: int64
- name: meb_count
dtype: int64
- name: mob_count
dtype: int64
- name: mmt_count
dtype: int64
- name: pmbf_count
dtype: int64
- name: 1-ada_count
dtype: int64
- name: 2-(2,4-dinitrophenyl)ethyl_count
dtype: int64
- name: 9-fluororenylmethoxycarbonyl_count
dtype: int64
- name: dnpe_count
dtype: int64
- name: acetamidomethyl_count
dtype: int64
- name: phenylacetamidomethyl_count
dtype: int64
- name: 5-tert-butylmercapto_count
dtype: int64
- name: 3-nitro-2-pyridinesulfenyl_count
dtype: int64
- name: 2-pyridinesulfenyl_count
dtype: int64
- name: N-allyloxycarbonyl-N-[2,3,5,6-tetrafluoro-4-(phenylthio)phenyl]]aminomethyl_count
dtype: int64
- name: o-nitrobenzyl_count
dtype: int64
- name: 4-picolyl_count
dtype: int64
- name: ninhydrin_count
dtype: int64
- name: acm_count
dtype: int64
- name: phacm_count
dtype: int64
- name: sbu_count
dtype: int64
- name: npys_count
dtype: int64
- name: s-pyr_count
dtype: int64
- name: fsam_count
dtype: int64
- name: onb_count
dtype: int64
- name: nin_count
dtype: int64
- name: n-tosyl_count
dtype: int64
- name: n-trityl_count
dtype: int64
- name: n-monomethoxytrityl_count
dtype: int64
- name: n-methyltrityl_count
dtype: int64
- name: n-tert-butyloxycarbonyl_count
dtype: int64
- name: n-2,4-dimethylpent-3-yloxycarbonyl_count
dtype: int64
- name: n-benzyloxymethyl_count
dtype: int64
- name: n-tert-butoxymethyl_count
dtype: int64
- name: ntos_count
dtype: int64
- name: ntrt_count
dtype: int64
- name: nmtt_count
dtype: int64
- name: nmmt_count
dtype: int64
- name: nboc_count
dtype: int64
- name: ndoc_count
dtype: int64
- name: nbom_count
dtype: int64
- name: nbum_count
dtype: int64
- name: N-9-fluorenylmethoxycarbonyl_count
dtype: int64
- name: N-2,6-dimethoxybenzoyl_count
dtype: int64
- name: dmbz_count
dtype: int64
- name: N-2,4-dinitrophenyl_count
dtype: int64
- name: dnp_count
dtype: int64
- name: cyclohexyl;_count
dtype: int64
- name: tert-butyldimethylsilyl_count
dtype: int64
- name: tbdms_count
dtype: int64
- name: tert-butyldiphenylsilyl_count
dtype: int64
- name: propargyloxycarbonyl_count
dtype: int64
- name: tbdps_count
dtype: int64
- name: 2,6-dichlorobenzyl_count
dtype: int64
- name: 2-bromobenzyl_count
dtype: int64
- name: 2-bromobenzyloxycarbonyl_count
dtype: int64
- name: 3-pentyl_count
dtype: int64
- name: dcb_count
dtype: int64
- name: brbn_count
dtype: int64
- name: brz_count
dtype: int64
- name: pen_count
dtype: int64
- name: tegb_count
dtype: int64
- name: boc-n-methyl-n-[2-(methylamino)ethyl]carbamoyl_count
dtype: int64
- name: boc-nmec_count
dtype: int64
- name: formyl_count
dtype: int64
- name: cyclohexyloxycarbonyl_count
dtype: int64
- name: for_count
dtype: int64
- name: hoc_count
dtype: int64
- name: cyclopropane_count
dtype: int64
- name: spiropentane_count
dtype: int64
- name: cyclobutane_count
dtype: int64
- name: cyclopentane_count
dtype: int64
- name: furan_count
dtype: int64
- name: thiophene_count
dtype: int64
- name: pyrrole_count
dtype: int64
- name: 2H-pyrrole_count
dtype: int64
- name: 3H-pyrrole_count
dtype: int64
- name: pyrazole_count
dtype: int64
- name: 2H-imidazole_count
dtype: int64
- name: 1,2,3-triazole_count
dtype: int64
- name: 1,2,4-triazole_count
dtype: int64
- name: 1,2-dithiole_count
dtype: int64
- name: 1,3-dithiole_count
dtype: int64
- name: 3H-1,2-oxathiole_count
dtype: int64
- name: isoxazole_count
dtype: int64
- name: oxazole_count
dtype: int64
- name: thiazole_count
dtype: int64
- name: isothiazole_count
dtype: int64
- name: 1,2,3-oxadiazole_count
dtype: int64
- name: 1,2,4-oxadiazole_count
dtype: int64
- name: 1,2,5-oxadiazole_count
dtype: int64
- name: 1,3,4-oxadiazole_count
dtype: int64
- name: 1,2,3,4-oxatriazole_count
dtype: int64
- name: 1,2,3,5-oxatriazole_count
dtype: int64
- name: 3H-1,2,3-dioxazole_count
dtype: int64
- name: 1,2,4-dioxazole_count
dtype: int64
- name: 1,3,2-dioxazole_count
dtype: int64
- name: 1,3,4-dioxazole_count
dtype: int64
- name: 5H-1,2,5-oxathiazole_count
dtype: int64
- name: 1,3-oxathiole_count
dtype: int64
- name: benzene_count
dtype: int64
- name: cyclohexane_count
dtype: int64
- name: 2H-pyran_count
dtype: int64
- name: 4H-pyran_count
dtype: int64
- name: 2H-pyran-2-one_count
dtype: int64
- name: 4H-pyran-4-one_count
dtype: int64
- name: 1,2-dioxin_count
dtype: int64
- name: 1,3-dioxin_count
dtype: int64
- name: pyridine_count
dtype: int64
- name: pyridazine_count
dtype: int64
- name: pyrimidine_count
dtype: int64
- name: pyrazine_count
dtype: int64
- name: piperazine_count
dtype: int64
- name: 1,3,5-triazine_count
dtype: int64
- name: 1,2,4-triazine_count
dtype: int64
- name: 1,2,3-triazine_count
dtype: int64
- name: 4H-1,2-Oxazine_count
dtype: int64
- name: 2H-1,3-Oxazine_count
dtype: int64
- name: 6H-1,3-Oxazine_count
dtype: int64
- name: 6H-1,2-Oxazine_count
dtype: int64
- name: 1,4-Oxazine_count
dtype: int64
- name: 2H-1,2-Oxazine_count
dtype: int64
- name: 4H-1,4-Oxazine_count
dtype: int64
- name: 1,2,5-Oxathiazine_count
dtype: int64
- name: 1,2,6-Oxathiazine_count
dtype: int64
- name: 1,2,4-Oxadiazine_count
dtype: int64
- name: 1,3,5-Oxadiazine_count
dtype: int64
- name: morpholine_count
dtype: int64
- name: azepine_count
dtype: int64
- name: oxepin_count
dtype: int64
- name: thiepin_count
dtype: int64
- name: 4H-1,2-diazepine_count
dtype: int64
- name: indene_count
dtype: int64
- name: 2H-indene_count
dtype: int64
- name: benzofuran_count
dtype: int64
- name: isobenzofuran_count
dtype: int64
- name: benzo[b]thiophene_count
dtype: int64
- name: benzo[c]thiophene_count
dtype: int64
- name: indole_count
dtype: int64
- name: 3H-indole_count
dtype: int64
- name: 1H-indole_count
dtype: int64
- name: cyclopenta[b]pyridine_count
dtype: int64
- name: pyrano[3,4-b]-pyrrole_count
dtype: int64
- name: indazole_count
dtype: int64
- name: benzisoxazole_count
dtype: int64
- name: benzoxazole_count
dtype: int64
- name: 2,1-benzisoxazole_count
dtype: int64
- name: naphthalene_count
dtype: int64
- name: 1,2,3,4-tetrahydronaphthalene_count
dtype: int64
- name: octahydronaphthalene_count
dtype: int64
- name: 2H-1-benzopyran_count
dtype: int64
- name: 2H-1-benzopyran-2-one_count
dtype: int64
- name: 4H-1-benzopyran-4-one_count
dtype: int64
- name: 1H-2-benzopyran-1-one_count
dtype: int64
- name: 3H-2-benzopyran-1-one_count
dtype: int64
- name: quinoline_count
dtype: int64
- name: isoquinoline_count
dtype: int64
- name: cinnoline_count
dtype: int64
- name: quinazoline_count
dtype: int64
- name: 1,8-napthyhridine_count
dtype: int64
- name: 1,7-napththyridine_count
dtype: int64
- name: 1,5-napththridine_count
dtype: int64
- name: 1,6-napthyridine_count
dtype: int64
- name: 2H-1,3-benzoxazine_count
dtype: int64
- name: 2H-1,4-benzoxazine_count
dtype: int64
- name: 1H-2,3-benzoxazine_count
dtype: int64
- name: 4H-3,1-benzoxazine_count
dtype: int64
- name: 2H-1,2-benzoxazine_count
dtype: int64
- name: 4H-1,3-benzoxazine_count
dtype: int64
- name: anthracene_count
dtype: int64
- name: phenanthrene_count
dtype: int64
- name: phenalene_count
dtype: int64
- name: fluorene_count
dtype: int64
- name: carbazole_count
dtype: int64
- name: xanthene_count
dtype: int64
- name: acridine_count
dtype: int64
- name: norpinane_count
dtype: int64
- name: 7H-purine_count
dtype: int64
- name: steroid_ring_system_count
dtype: int64
- name: imidazole_count
dtype: int64
- name: thiazol-2-amine_count
dtype: int64
- name: tetrazole_count
dtype: int64
- name: cytosine_count
dtype: int64
- name: adenine_count
dtype: int64
- name: 5-methylindole_count
dtype: int64
- name: isocaffeine_count
dtype: int64
- name: tetrazolethiol_count
dtype: int64
- name: 3-methylisoxazole_count
dtype: int64
- name: 1-methylimidazole_count
dtype: int64
- name: 2-methylimidazole_count
dtype: int64
- name: guanine_count
dtype: int64
- name: tosufloxacin_count
dtype: int64
- name: acetamido_count
dtype: int64
- name: acetoacetyl_count
dtype: int64
- name: acetyl_count
dtype: int64
- name: acryloyl_count
dtype: int64
- name: alanyl_count
dtype: int64
- name: beta-alanyl_count
dtype: int64
- name: allylidene_count
dtype: int64
- name: amidino_count
dtype: int64
- name: amino_count
dtype: int64
- name: amyl_count
dtype: int64
- name: anilino_count
dtype: int64
- name: anisidino_count
dtype: int64
- name: anthranoyl_count
dtype: int64
- name: arsino_count
dtype: int64
- name: azelaoyl_count
dtype: int64
- name: azido_count
dtype: int64
- name: azo_count
dtype: int64
- name: azoxy_count
dtype: int64
- name: benzal_count
dtype: int64
- name: benzamido_count
dtype: int64
- name: benzhydrol_count
dtype: int64
- name: benzoxy_count
dtype: int64
- name: benzoyl_count
dtype: int64
- name: benzylidene_count
dtype: int64
- name: benzylidyne_count
dtype: int64
- name: biphenylyl_count
dtype: int64
- name: biphenylene_count
dtype: int64
- name: butoxy_count
dtype: int64
- name: sec-butoxy_count
dtype: int64
- name: tert-butoxy_count
dtype: int64
- name: butyl_count
dtype: int64
- name: sec-butyl_count
dtype: int64
- name: butyryl_count
dtype: int64
- name: caproyl_count
dtype: int64
- name: capryl_count
dtype: int64
- name: capryloyl_count
dtype: int64
- name: carbamido_count
dtype: int64
- name: carbamoyl_count
dtype: int64
- name: carbamyl_count
dtype: int64
- name: carbazoyl_count
dtype: int64
- name: carbethoxy_count
dtype: int64
- name: carbonyl_count
dtype: int64
- name: carboxy_count
dtype: int64
- name: cetyl_count
dtype: int64
- name: chloroformyl_count
dtype: int64
- name: cinnamoyl_count
dtype: int64
- name: cinnamyl_count
dtype: int64
- name: cinnamylidene_count
dtype: int64
- name: cresyl_count
dtype: int64
- name: crotonoyl_count
dtype: int64
- name: crotyl_count
dtype: int64
- name: cyanamido_count
dtype: int64
- name: cyanato_count
dtype: int64
- name: cyano_count
dtype: int64
- name: decanedioyl_count
dtype: int64
- name: decanoyl_count
dtype: int64
- name: diazo_count
dtype: int64
- name: diazoamino_count
dtype: int64
- name: disilanyl_count
dtype: int64
- name: disiloxanyloxy_count
dtype: int64
- name: disulfinyl_count
dtype: int64
- name: dithio_count
dtype: int64
- name: enanthoyl_count
dtype: int64
- name: epoxy_count
dtype: int64
- name: ethenyl_count
dtype: int64
- name: ethynyl_count
dtype: int64
- name: ethoxy_count
dtype: int64
- name: ethylene_count
dtype: int64
- name: ethylidene_count
dtype: int64
- name: ethylthio_count
dtype: int64
- name: formamido_count
dtype: int64
- name: furmaroyl_count
dtype: int64
- name: furfuryl_count
dtype: int64
- name: furfurylidene_count
dtype: int64
- name: glutamoyl_count
dtype: int64
- name: glutaryl_count
dtype: int64
- name: glycylamino_count
dtype: int64
- name: glycoloyl_count
dtype: int64
- name: glycyl_count
dtype: int64
- name: glyoxyoyl_count
dtype: int64
- name: guanidino_count
dtype: int64
- name: guanyl_count
dtype: int64
- name: heptadecanoyl_count
dtype: int64
- name: heptanamido_count
dtype: int64
- name: heptanoyl_count
dtype: int64
- name: hexadecanoyl_count
dtype: int64
- name: hexamethylene_count
dtype: int64
- name: hexanedioyl_count
dtype: int64
- name: hippuryl_count
dtype: int64
- name: hydrazino_count
dtype: int64
- name: hydrazo_count
dtype: int64
- name: hydrocinnamoyl_count
dtype: int64
- name: hydroperoxy_count
dtype: int64
- name: hydroxyamino_count
dtype: int64
- name: imino_count
dtype: int64
- name: iodoso_count
dtype: int64
- name: iodyl_count
dtype: int64
- name: isoamyl_count
dtype: int64
- name: isobutenyl_count
dtype: int64
- name: isobutoxy_count
dtype: int64
- name: isobutyl_count
dtype: int64
- name: isobutylidene_count
dtype: int64
- name: isobutyryl_count
dtype: int64
- name: isocyanato_count
dtype: int64
- name: isocyano_count
dtype: int64
- name: isohexyl_count
dtype: int64
- name: isoleucyl_count
dtype: int64
- name: isonitroso_count
dtype: int64
- name: isopentyl_count
dtype: int64
- name: isopentylidene_count
dtype: int64
- name: isopropenyl_count
dtype: int64
- name: isopropoxy_count
dtype: int64
- name: isopropyl_count
dtype: int64
- name: isopropylidene_count
dtype: int64
- name: isothiocynato_count
dtype: int64
- name: isovaleryl_count
dtype: int64
- name: lactoyl_count
dtype: int64
- name: lauroyl_count
dtype: int64
- name: lauryl_count
dtype: int64
- name: leucyl_count
dtype: int64
- name: levulinoyl_count
dtype: int64
- name: malonyl_count
dtype: int64
- name: mandeloyl_count
dtype: int64
- name: mercapto_count
dtype: int64
- name: mesityl_count
dtype: int64
- name: methacryloyl_count
dtype: int64
- name: methallyl_count
dtype: int64
- name: methionyl_count
dtype: int64
- name: methoxy_count
dtype: int64
- name: methylene_count
dtype: int64
- name: methylthio_count
dtype: int64
- name: myristoyl_count
dtype: int64
- name: myristyl_count
dtype: int64
- name: naphthyl_count
dtype: int64
- name: naphthylene_count
dtype: int64
- name: neopentyl_count
dtype: int64
- name: nitramino_count
dtype: int64
- name: nitrosamino_count
dtype: int64
- name: nitroso_count
dtype: int64
- name: nonanoyl_count
dtype: int64
- name: oleoyl_count
dtype: int64
- name: oxalyl_count
dtype: int64
- name: oxo_count
dtype: int64
- name: palmitoyl_count
dtype: int64
- name: pentamethylene_count
dtype: int64
- name: pentyl_count
dtype: int64
- name: tert-pentyl_count
dtype: int64
- name: phenacylidene_count
dtype: int64
- name: phenethyl_count
dtype: int64
- name: phenoxy_count
dtype: int64
- name: phenyl_count
dtype: int64
- name: phenylene_count
dtype: int64
- name: phosphino_count
dtype: int64
- name: phosphinyl_count
dtype: int64
- name: phospho_count
dtype: int64
- name: phosphono_count
dtype: int64
- name: phthaloyl_count
dtype: int64
- name: picryl_count
dtype: int64
- name: pimeloyl_count
dtype: int64
- name: piperidino_count
dtype: int64
- name: pivaloyl_count
dtype: int64
- name: prenyl_count
dtype: int64
- name: propargyl_count
dtype: int64
- name: 1-propenyl_count
dtype: int64
- name: 2-propenyl_count
dtype: int64
- name: propionyl_count
dtype: int64
- name: propoxy_count
dtype: int64
- name: propyl_count
dtype: int64
- name: propylidene_count
dtype: int64
- name: pyrryl_count
dtype: int64
- name: salicyloyl_count
dtype: int64
- name: selenyl_count
dtype: int64
- name: seryl_count
dtype: int64
- name: siloxy_count
dtype: int64
- name: silyl_count
dtype: int64
- name: silyene_count
dtype: int64
- name: sorboyl_count
dtype: int64
- name: stearoyl_count
dtype: int64
- name: stearyl_count
dtype: int64
- name: styryl_count
dtype: int64
- name: suberoyl_count
dtype: int64
- name: succinyl_count
dtype: int64
- name: sulfamino_count
dtype: int64
- name: sulfamoyl_count
dtype: int64
- name: sulfanilyl_count
dtype: int64
- name: sulfeno_count
dtype: int64
- name: sulfhydryl_count
dtype: int64
- name: sulfinyl_count
dtype: int64
- name: sulfo_count
dtype: int64
- name: sulfonyl_count
dtype: int64
- name: terephthaloyl_count
dtype: int64
- name: tetramethylene_count
dtype: int64
- name: thienyl_count
dtype: int64
- name: thiocarbonyl_count
dtype: int64
- name: thiocarboxy_count
dtype: int64
- name: thiocyanato_count
dtype: int64
- name: thionyl_count
dtype: int64
- name: threonyl_count
dtype: int64
- name: toluidino_count
dtype: int64
- name: toluoyl_count
dtype: int64
- name: tolyl_count
dtype: int64
- name: alpha-tolyl_count
dtype: int64
- name: tolylene_count
dtype: int64
- name: tosyl_count
dtype: int64
- name: triazano_count
dtype: int64
- name: trimethylene_count
dtype: int64
- name: valeryl_count
dtype: int64
- name: valyl_count
dtype: int64
- name: vinyl_count
dtype: int64
- name: vinylidene_count
dtype: int64
- name: xylidino_count
dtype: int64
- name: xylyl_count
dtype: int64
- name: xylylene_count
dtype: int64
- name: propiolamide_count
dtype: int64
- name: fumarate ester_count
dtype: int64
- name: allenamide_count
dtype: int64
- name: propiolonitrile_count
dtype: int64
- name: propargylamide_count
dtype: int64
- name: arylsulfonyl bicyclobutane_count
dtype: int64
- name: haloalkane_count
dtype: int64
- name: alpha-halomethyl_count
dtype: int64
- name: alpha-haloamide_count
dtype: int64
- name: alpha-haloester_count
dtype: int64
- name: epoxide_count
dtype: int64
- name: aziridine_count
dtype: int64
- name: nitroalkane_count
dtype: int64
- name: acrylamide_count
dtype: int64
- name: cyanoenone_count
dtype: int64
- name: aldehyde_count
dtype: int64
- name: ketone_count
dtype: int64
- name: nitrile_count
dtype: int64
- name: cyanamide_count
dtype: int64
- name: isothicyanate_count
dtype: int64
- name: sulfone_count
dtype: int64
- name: sulfonyl fluoride_count
dtype: int64
- name: sulfonimidoyl fluoride_count
dtype: int64
- name: aryl fluorosulfate_count
dtype: int64
- name: ester_count
dtype: int64
- name: sulfonamide_count
dtype: int64
- name: 2-carbonyl arylboronic acid_count
dtype: int64
- name: n-methyl isoxazolium_count
dtype: int64
- name: oxaziridine_count
dtype: int64
- name: carboxyl_count
dtype: int64
- name: ether_count
dtype: int64
- name: alkanol_count
dtype: int64
- name: thiol_count
dtype: int64
- name: halogen_count
dtype: int64
- name: amine_count
dtype: int64
- name: amide_count
dtype: int64
- name: num_valence_electrons
dtype: int64
- name: rotable_proportion
dtype: float64
- name: non_rotable_proportion
dtype: float64
- name: num_unspecified_bond
dtype: float64
- name: num_single_bonds
dtype: float64
- name: num_double_bonds
dtype: float64
- name: num_triple_bonds
dtype: float64
- name: num_quadruple_bonds
dtype: float64
- name: num_quintuple_bonds
dtype: float64
- name: num_hextuple_bonds
dtype: float64
- name: num_oneandahalf_bonds
dtype: float64
- name: num_twoandahalf_bonds
dtype: float64
- name: num_threeandahalf_bonds
dtype: float64
- name: num_fourandahalf_bonds
dtype: float64
- name: num_fiveandahalf_bonds
dtype: float64
- name: num_aromatic_bonds
dtype: float64
- name: num_ionic_bonds
dtype: float64
- name: num_hydrogen_bonds
dtype: float64
- name: num_threecenter_bonds
dtype: float64
- name: num_dativeone_bonds
dtype: float64
- name: num_dative_bonds
dtype: float64
- name: num_other_bonds
dtype: float64
- name: num_zero_bonds
dtype: float64
- name: num_bonds
dtype: int64
- name: molecular_formula
dtype: string
- name: monoisotopic_molecular_mass
dtype: float64
- name: carbon_mass
dtype: float64
- name: hydrogen_mass
dtype: float64
- name: nitrogen_mass
dtype: float64
- name: oxygen_mass
dtype: float64
- name: num_carbon_atoms
dtype: int64
- name: num_hydrogen_atoms
dtype: int64
- name: num_nitrogen_atoms
dtype: int64
- name: num_oxygen_atoms
dtype: int64
- name: num_hydrogen_bond_acceptors
dtype: int64
- name: num_hydrogen_bond_donors
dtype: int64
- name: num_lipinski_violations
dtype: int64
- name: inertial_shape_factor
dtype: float64
- name: eccentricity
dtype: float64
- name: asphericity
dtype: float64
- name: npr1_value
dtype: float64
- name: npr2_value
dtype: float64
- name: pmi1_value
dtype: float64
- name: pmi2_value
dtype: float64
- name: pmi3_value
dtype: float64
- name: num_chiral_centers
dtype: int64
- name: representation
dtype: string
splits:
- name: train
num_bytes: 2757656
num_examples: 500
download_size: 490741
dataset_size: 2757656
- config_name: rdkit_feat_8
features:
- name: tert-butyloxycarbonyl_count
dtype: int64
- name: representation_type
dtype: string
- name: trityl_count
dtype: int64
- name: 3,5-dimethoxyphenylisoproxycarbonyl_count
dtype: int64
- name: 2-(4-biphenyl)isopropoxycarbonyl_count
dtype: int64
- name: 2-nitrophenylsulfenyl_count
dtype: int64
- name: boc_count
dtype: int64
- name: trt_count
dtype: int64
- name: ddz_count
dtype: int64
- name: bpoc_count
dtype: int64
- name: nps_count
dtype: int64
- name: 9-fluorenylmethoxycarbonyl_count
dtype: int64
- name: 2-(4-nitrophenylsulfonyl)ethoxycarbonyl_count
dtype: int64
- name: (1,1-dioxobenzo[b]thiophene-2-yl)methyloxycarbonyl_count
dtype: int64
- name: (1,1-dioxonaptho[1,2-b]thiophene-2-yl)methyloxycarbonyl_count
dtype: int64
- name: 1-(4,4-dimethyl-2,6-dioxocyclohex-1-ylidene)-3-methylbutyl_count
dtype: int64
- name: 2,7-di-tert-butyl-fmoc_count
dtype: int64
- name: 2-fluoro-fmoc_count
dtype: int64
- name: 2-monoisooctyl-fmoc_count
dtype: int64
- name: 2,7-diisooctyl-fmoc_count
dtype: int64
- name: tetrachlorophthaloyl_count
dtype: int64
- name: 2-[phenyl(methyl)sulfonio])ethyloxycarbonyltetrafluoroborate_count
dtype: int64
- name: ethanesulfonylethoxycarbonyl_count
dtype: int64
- name: 2-(4-sulfophenylsulfonyl)ethoxycarbonyl_count
dtype: int64
- name: fmoc_count
dtype: int64
- name: nsc_count
dtype: int64
- name: bsmoc_count
dtype: int64
- name: alpha-nsmoc_count
dtype: int64
- name: ivdde_count
dtype: int64
- name: fmoc*_count
dtype: int64
- name: fmoc(fmoc(2f))_count
dtype: int64
- name: mio-fmoc_count
dtype: int64
- name: dio-fmoc_count
dtype: int64
- name: tcp_count
dtype: int64
- name: pms_count
dtype: int64
- name: esc_count
dtype: int64
- name: sps_count
dtype: int64
- name: benzyloxycarbonyl_count
dtype: int64
- name: allyloxycarbonyl_count
dtype: int64
- name: o-nitrobenzenesulfonyl_count
dtype: int64
- name: 2,4-dinitrobenzenesulfonyl_count
dtype: int64
- name: benzothiazole-2-sulfonyl_count
dtype: int64
- name: 2,2,2-trichloroethyloxycarbonyl_count
dtype: int64
- name: dithiasuccinoyl_count
dtype: int64
- name: p-nitrobenzyloxycarbonyl_count
dtype: int64
- name: alpha-azidoacids_count
dtype: int64
- name: proparglyoxycarbonyl_count
dtype: int64
- name: o-nitrobenzylcarbonyl_count
dtype: int64
- name: 4-nitroveratryloxycarbonyl_count
dtype: int64
- name: 2-(2-nitrophenyl)propyloxycarbonyl_count
dtype: int64
- name: 2-(3,4-methylenedioxy-6-nitrophenyl)propyloxycarbonyl_count
dtype: int64
- name: 9-(4-bromophenyl)-9-fluorenyl_count
dtype: int64
- name: azidomethoxycarbonyl_count
dtype: int64
- name: hexafluoroacetone_count
dtype: int64
- name: Z_count
dtype: int64
- name: alloc_count
dtype: int64
- name: o-nbs_count
dtype: int64
- name: d-nbs_count
dtype: int64
- name: bts_count
dtype: int64
- name: troc_count
dtype: int64
- name: dts_count
dtype: int64
- name: pnz_count
dtype: int64
- name: poc_count
dtype: int64
- name: onz_count
dtype: int64
- name: nvoc_count
dtype: int64
- name: nppoc_count
dtype: int64
- name: mnppoc_count
dtype: int64
- name: brphf_count
dtype: int64
- name: azoc_count
dtype: int64
- name: hfa_count
dtype: int64
- name: 2-chlorobenzyloxycarbonyl_count
dtype: int64
- name: 4-methyltrityl_count
dtype: int64
- name: cl-z_count
dtype: int64
- name: mtt_count
dtype: int64
- name: 1-(4,4-dimethyl-2,6-dioxocylohex-1-ylidene)-3-methylbutyl_count
dtype: int64
- name: trifluoroacetyl_count
dtype: int64
- name: 2-(methylsulfonyl)ethoxycarbonyl_count
dtype: int64
- name: tfa_count
dtype: int64
- name: msc_count
dtype: int64
- name: phenyldisulphanylethyloxycarbonyl_count
dtype: int64
- name: 2-pyridyldisulphanylethyloxycarbonyl_count
dtype: int64
- name: phdec_count
dtype: int64
- name: pydec_count
dtype: int64
- name: tert-butyl_count
dtype: int64
- name: 2-chlorotrityl_count
dtype: int64
- name: 2-4-dimethyoxybenzyl_count
dtype: int64
- name: 2-phenylisopropyl_count
dtype: int64
- name: 5-phenyl-3,4-ethylenedioxythenyl_count
dtype: int64
- name: bu_count
dtype: int64
- name: 2-cl-trt_count
dtype: int64
- name: dmb_count
dtype: int64
- name: 2-ph-pr_count
dtype: int64
- name: phenyl-edotn_count
dtype: int64
- name: 9-fluorenylmethyl_count
dtype: int64
- name: 4-(N-[1-(4,4-dimethyl-2,6-dioxocylocheylidene)-3-methylbutyl]-amino)benzyl_count
dtype: int64
- name: methyl_count
dtype: int64
- name: ethyl_count
dtype: int64
- name: carbamoylmethyl_count
dtype: int64
- name: fm_count
dtype: int64
- name: dmab_count
dtype: int64
- name: me_count
dtype: int64
- name: et_count
dtype: int64
- name: cam_count
dtype: int64
- name: allyl_count
dtype: int64
- name: benzyl_count
dtype: int64
- name: phenacyl_count
dtype: int64
- name: p-nitrobenzyl_count
dtype: int64
- name: 2-trimethylsilyethyl_count
dtype: int64
- name: (2-phenyl-2-trimethylsilyl)ethyl_count
dtype: int64
- name: 2-(trimethylsilyl)isopropyl_count
dtype: int64
- name: 2,2,2-trichloroethyl_count
dtype: int64
- name: p-hydroxyphenacyl_count
dtype: int64
- name: 4,5-dimethyoxy-2-nitrobenzyl_count
dtype: int64
- name: 1,1-dimethylallyl_count
dtype: int64
- name: pentaaminecobalt_III_count
dtype: int64
- name: al_count
dtype: int64
- name: bn_count
dtype: int64
- name: pac_count
dtype: int64
- name: pnb_count
dtype: int64
- name: tmse_count
dtype: int64
- name: ptmse_count
dtype: int64
- name: tmsi_count
dtype: int64
- name: tce_count
dtype: int64
- name: php_count
dtype: int64
- name: dmnb_count
dtype: int64
- name: dma_count
dtype: int64
- name: cyclohexyl_count
dtype: int64
- name: b-menthyl_count
dtype: int64
- name: b-3-methylpent-3-yl_count
dtype: int64
- name: 4-(3,6,9-trioxadecyl)oxybenzyl_count
dtype: int64
- name: chx_count
dtype: int64
- name: men_count
dtype: int64
- name: mpe_count
dtype: int64
- name: tegbz_count
dtype: int64
- name: 9-fluoroenylmethyl_count
dtype: int64
- name: 4-(N-[1-(4,4-dimethyl-2,6-dioxocyclohexylidene)-3-methyl-butyl]-amino)benzyl_count
dtype: int64
- name: trimethylsilylethyl_count
dtype: int64
- name: 4,5-dimethoxy-2-nitrobenzyloxycarbonyl_count
dtype: int64
- name: pseudoprolines_count
dtype: int64
- name: 2-hydroxy-4-methoxybenzyl_count
dtype: int64
- name: 2,4-dimethoxybenzyl_count
dtype: int64
- name: 2,4,6-trimethoxybenzyl_count
dtype: int64
- name: 1-methyl-3-indolylmethyl_count
dtype: int64
- name: 3,4-ethylene-dioxy-2-thenyl_count
dtype: int64
- name: hmb_count
dtype: int64
- name: tmob_count
dtype: int64
- name: mim_count
dtype: int64
- name: edot_count
dtype: int64
- name: 4-methoxy-2-nitro-benzyl_count
dtype: int64
- name: (6-hydroxy-3-oxido-1,3-benz[d]oxathiol-5-yl)methyl_count
dtype: int64
- name: 2-hydroxy-4-methoxy-5-(methylsulfinyl)benzyl_count
dtype: int64
- name: n-boc-n-methyl[2-(methylamino)ethyl]carbamoyl-hmb_count
dtype: int64
- name: 9-xanthenyl_count
dtype: int64
- name: cyclopropyldimethylcarbinyl_count
dtype: int64
- name: 4,4-dimethoxybenzhydryl_count
dtype: int64
- name: xan_count
dtype: int64
- name: cpd_count
dtype: int64
- name: mbh_count
dtype: int64
- name: p-toluenesulfonyl_count
dtype: int64
- name: 2,2,5,7,8-pentamethylchroman-6-sulfonyl_count
dtype: int64
- name: 2,2,4,6,7-pentamethyl-2,3-dihydrobenzofuran-5-sulfonyl_count
dtype: int64
- name: mesityl-2-sulfonyl_count
dtype: int64
- name: 4-methoxy-2,3,6-trimethylphenylsulfonyl_count
dtype: int64
- name: 1,2-dimethylindole-3-sulfonyl_count
dtype: int64
- name: w,w-bis-tert-butyloxycarbonyl_count
dtype: int64
- name: 5-dibenzosuberenyl_count
dtype: int64
- name: 5-dibenzosuberyl_count
dtype: int64
- name: 2-methoxy-5-dibenzosuberyl_count
dtype: int64
- name: nitro_count
dtype: int64
- name: tos_count
dtype: int64
- name: pmc_count
dtype: int64
- name: pbf_count
dtype: int64
- name: mts_count
dtype: int64
- name: mtr_count
dtype: int64
- name: mis_count
dtype: int64
- name: bis-boc_count
dtype: int64
- name: suben_count
dtype: int64
- name: sub_count
dtype: int64
- name: mesub_count
dtype: int64
- name: no2_count
dtype: int64
- name: w,w-bis-benzyloxycarbonyl_count
dtype: int64
- name: w,w-bis-allyloxycarbonyl_count
dtype: int64
- name: z-small_count
dtype: int64
- name: p-methylbenzyl_count
dtype: int64
- name: p-methoxybenzyl_count
dtype: int64
- name: monomethoxytrityl_count
dtype: int64
- name: trimethoxybenzyl_count
dtype: int64
- name: 2,2,4,6,7-pentamethyl-5-dihydrobenzofuranylmethyl_count
dtype: int64
- name: 1-adamantyl_count
dtype: int64
- name: meb_count
dtype: int64
- name: mob_count
dtype: int64
- name: mmt_count
dtype: int64
- name: pmbf_count
dtype: int64
- name: 1-ada_count
dtype: int64
- name: 2-(2,4-dinitrophenyl)ethyl_count
dtype: int64
- name: 9-fluororenylmethoxycarbonyl_count
dtype: int64
- name: dnpe_count
dtype: int64
- name: acetamidomethyl_count
dtype: int64
- name: phenylacetamidomethyl_count
dtype: int64
- name: 5-tert-butylmercapto_count
dtype: int64
- name: 3-nitro-2-pyridinesulfenyl_count
dtype: int64
- name: 2-pyridinesulfenyl_count
dtype: int64
- name: N-allyloxycarbonyl-N-[2,3,5,6-tetrafluoro-4-(phenylthio)phenyl]]aminomethyl_count
dtype: int64
- name: o-nitrobenzyl_count
dtype: int64
- name: 4-picolyl_count
dtype: int64
- name: ninhydrin_count
dtype: int64
- name: acm_count
dtype: int64
- name: phacm_count
dtype: int64
- name: sbu_count
dtype: int64
- name: npys_count
dtype: int64
- name: s-pyr_count
dtype: int64
- name: fsam_count
dtype: int64
- name: onb_count
dtype: int64
- name: nin_count
dtype: int64
- name: n-tosyl_count
dtype: int64
- name: n-trityl_count
dtype: int64
- name: n-monomethoxytrityl_count
dtype: int64
- name: n-methyltrityl_count
dtype: int64
- name: n-tert-butyloxycarbonyl_count
dtype: int64
- name: n-2,4-dimethylpent-3-yloxycarbonyl_count
dtype: int64
- name: n-benzyloxymethyl_count
dtype: int64
- name: n-tert-butoxymethyl_count
dtype: int64
- name: ntos_count
dtype: int64
- name: ntrt_count
dtype: int64
- name: nmtt_count
dtype: int64
- name: nmmt_count
dtype: int64
- name: nboc_count
dtype: int64
- name: ndoc_count
dtype: int64
- name: nbom_count
dtype: int64
- name: nbum_count
dtype: int64
- name: N-9-fluorenylmethoxycarbonyl_count
dtype: int64
- name: N-2,6-dimethoxybenzoyl_count
dtype: int64
- name: dmbz_count
dtype: int64
- name: N-2,4-dinitrophenyl_count
dtype: int64
- name: dnp_count
dtype: int64
- name: cyclohexyl;_count
dtype: int64
- name: tert-butyldimethylsilyl_count
dtype: int64
- name: tbdms_count
dtype: int64
- name: tert-butyldiphenylsilyl_count
dtype: int64
- name: propargyloxycarbonyl_count
dtype: int64
- name: tbdps_count
dtype: int64
- name: 2,6-dichlorobenzyl_count
dtype: int64
- name: 2-bromobenzyl_count
dtype: int64
- name: 2-bromobenzyloxycarbonyl_count
dtype: int64
- name: 3-pentyl_count
dtype: int64
- name: dcb_count
dtype: int64
- name: brbn_count
dtype: int64
- name: brz_count
dtype: int64
- name: pen_count
dtype: int64
- name: tegb_count
dtype: int64
- name: boc-n-methyl-n-[2-(methylamino)ethyl]carbamoyl_count
dtype: int64
- name: boc-nmec_count
dtype: int64
- name: formyl_count
dtype: int64
- name: cyclohexyloxycarbonyl_count
dtype: int64
- name: for_count
dtype: int64
- name: hoc_count
dtype: int64
- name: cyclopropane_count
dtype: int64
- name: spiropentane_count
dtype: int64
- name: cyclobutane_count
dtype: int64
- name: cyclopentane_count
dtype: int64
- name: furan_count
dtype: int64
- name: thiophene_count
dtype: int64
- name: pyrrole_count
dtype: int64
- name: 2H-pyrrole_count
dtype: int64
- name: 3H-pyrrole_count
dtype: int64
- name: pyrazole_count
dtype: int64
- name: 2H-imidazole_count
dtype: int64
- name: 1,2,3-triazole_count
dtype: int64
- name: 1,2,4-triazole_count
dtype: int64
- name: 1,2-dithiole_count
dtype: int64
- name: 1,3-dithiole_count
dtype: int64
- name: 3H-1,2-oxathiole_count
dtype: int64
- name: isoxazole_count
dtype: int64
- name: oxazole_count
dtype: int64
- name: thiazole_count
dtype: int64
- name: isothiazole_count
dtype: int64
- name: 1,2,3-oxadiazole_count
dtype: int64
- name: 1,2,4-oxadiazole_count
dtype: int64
- name: 1,2,5-oxadiazole_count
dtype: int64
- name: 1,3,4-oxadiazole_count
dtype: int64
- name: 1,2,3,4-oxatriazole_count
dtype: int64
- name: 1,2,3,5-oxatriazole_count
dtype: int64
- name: 3H-1,2,3-dioxazole_count
dtype: int64
- name: 1,2,4-dioxazole_count
dtype: int64
- name: 1,3,2-dioxazole_count
dtype: int64
- name: 1,3,4-dioxazole_count
dtype: int64
- name: 5H-1,2,5-oxathiazole_count
dtype: int64
- name: 1,3-oxathiole_count
dtype: int64
- name: benzene_count
dtype: int64
- name: cyclohexane_count
dtype: int64
- name: 2H-pyran_count
dtype: int64
- name: 4H-pyran_count
dtype: int64
- name: 2H-pyran-2-one_count
dtype: int64
- name: 4H-pyran-4-one_count
dtype: int64
- name: 1,2-dioxin_count
dtype: int64
- name: 1,3-dioxin_count
dtype: int64
- name: pyridine_count
dtype: int64
- name: pyridazine_count
dtype: int64
- name: pyrimidine_count
dtype: int64
- name: pyrazine_count
dtype: int64
- name: piperazine_count
dtype: int64
- name: 1,3,5-triazine_count
dtype: int64
- name: 1,2,4-triazine_count
dtype: int64
- name: 1,2,3-triazine_count
dtype: int64
- name: 4H-1,2-Oxazine_count
dtype: int64
- name: 2H-1,3-Oxazine_count
dtype: int64
- name: 6H-1,3-Oxazine_count
dtype: int64
- name: 6H-1,2-Oxazine_count
dtype: int64
- name: 1,4-Oxazine_count
dtype: int64
- name: 2H-1,2-Oxazine_count
dtype: int64
- name: 4H-1,4-Oxazine_count
dtype: int64
- name: 1,2,5-Oxathiazine_count
dtype: int64
- name: 1,2,6-Oxathiazine_count
dtype: int64
- name: 1,2,4-Oxadiazine_count
dtype: int64
- name: 1,3,5-Oxadiazine_count
dtype: int64
- name: morpholine_count
dtype: int64
- name: azepine_count
dtype: int64
- name: oxepin_count
dtype: int64
- name: thiepin_count
dtype: int64
- name: 4H-1,2-diazepine_count
dtype: int64
- name: indene_count
dtype: int64
- name: 2H-indene_count
dtype: int64
- name: benzofuran_count
dtype: int64
- name: isobenzofuran_count
dtype: int64
- name: benzo[b]thiophene_count
dtype: int64
- name: benzo[c]thiophene_count
dtype: int64
- name: indole_count
dtype: int64
- name: 3H-indole_count
dtype: int64
- name: 1H-indole_count
dtype: int64
- name: cyclopenta[b]pyridine_count
dtype: int64
- name: pyrano[3,4-b]-pyrrole_count
dtype: int64
- name: indazole_count
dtype: int64
- name: benzisoxazole_count
dtype: int64
- name: benzoxazole_count
dtype: int64
- name: 2,1-benzisoxazole_count
dtype: int64
- name: naphthalene_count
dtype: int64
- name: 1,2,3,4-tetrahydronaphthalene_count
dtype: int64
- name: octahydronaphthalene_count
dtype: int64
- name: 2H-1-benzopyran_count
dtype: int64
- name: 2H-1-benzopyran-2-one_count
dtype: int64
- name: 4H-1-benzopyran-4-one_count
dtype: int64
- name: 1H-2-benzopyran-1-one_count
dtype: int64
- name: 3H-2-benzopyran-1-one_count
dtype: int64
- name: quinoline_count
dtype: int64
- name: isoquinoline_count
dtype: int64
- name: cinnoline_count
dtype: int64
- name: quinazoline_count
dtype: int64
- name: 1,8-napthyhridine_count
dtype: int64
- name: 1,7-napththyridine_count
dtype: int64
- name: 1,5-napththridine_count
dtype: int64
- name: 1,6-napthyridine_count
dtype: int64
- name: 2H-1,3-benzoxazine_count
dtype: int64
- name: 2H-1,4-benzoxazine_count
dtype: int64
- name: 1H-2,3-benzoxazine_count
dtype: int64
- name: 4H-3,1-benzoxazine_count
dtype: int64
- name: 2H-1,2-benzoxazine_count
dtype: int64
- name: 4H-1,3-benzoxazine_count
dtype: int64
- name: anthracene_count
dtype: int64
- name: phenanthrene_count
dtype: int64
- name: phenalene_count
dtype: int64
- name: fluorene_count
dtype: int64
- name: carbazole_count
dtype: int64
- name: xanthene_count
dtype: int64
- name: acridine_count
dtype: int64
- name: norpinane_count
dtype: int64
- name: 7H-purine_count
dtype: int64
- name: steroid_ring_system_count
dtype: int64
- name: imidazole_count
dtype: int64
- name: thiazol-2-amine_count
dtype: int64
- name: tetrazole_count
dtype: int64
- name: cytosine_count
dtype: int64
- name: adenine_count
dtype: int64
- name: 5-methylindole_count
dtype: int64
- name: isocaffeine_count
dtype: int64
- name: tetrazolethiol_count
dtype: int64
- name: 3-methylisoxazole_count
dtype: int64
- name: 1-methylimidazole_count
dtype: int64
- name: 2-methylimidazole_count
dtype: int64
- name: guanine_count
dtype: int64
- name: tosufloxacin_count
dtype: int64
- name: acetamido_count
dtype: int64
- name: acetoacetyl_count
dtype: int64
- name: acetyl_count
dtype: int64
- name: acryloyl_count
dtype: int64
- name: alanyl_count
dtype: int64
- name: beta-alanyl_count
dtype: int64
- name: allylidene_count
dtype: int64
- name: amidino_count
dtype: int64
- name: amino_count
dtype: int64
- name: amyl_count
dtype: int64
- name: anilino_count
dtype: int64
- name: anisidino_count
dtype: int64
- name: anthranoyl_count
dtype: int64
- name: arsino_count
dtype: int64
- name: azelaoyl_count
dtype: int64
- name: azido_count
dtype: int64
- name: azo_count
dtype: int64
- name: azoxy_count
dtype: int64
- name: benzal_count
dtype: int64
- name: benzamido_count
dtype: int64
- name: benzhydrol_count
dtype: int64
- name: benzoxy_count
dtype: int64
- name: benzoyl_count
dtype: int64
- name: benzylidene_count
dtype: int64
- name: benzylidyne_count
dtype: int64
- name: biphenylyl_count
dtype: int64
- name: biphenylene_count
dtype: int64
- name: butoxy_count
dtype: int64
- name: sec-butoxy_count
dtype: int64
- name: tert-butoxy_count
dtype: int64
- name: butyl_count
dtype: int64
- name: sec-butyl_count
dtype: int64
- name: butyryl_count
dtype: int64
- name: caproyl_count
dtype: int64
- name: capryl_count
dtype: int64
- name: capryloyl_count
dtype: int64
- name: carbamido_count
dtype: int64
- name: carbamoyl_count
dtype: int64
- name: carbamyl_count
dtype: int64
- name: carbazoyl_count
dtype: int64
- name: carbethoxy_count
dtype: int64
- name: carbonyl_count
dtype: int64
- name: carboxy_count
dtype: int64
- name: cetyl_count
dtype: int64
- name: chloroformyl_count
dtype: int64
- name: cinnamoyl_count
dtype: int64
- name: cinnamyl_count
dtype: int64
- name: cinnamylidene_count
dtype: int64
- name: cresyl_count
dtype: int64
- name: crotonoyl_count
dtype: int64
- name: crotyl_count
dtype: int64
- name: cyanamido_count
dtype: int64
- name: cyanato_count
dtype: int64
- name: cyano_count
dtype: int64
- name: decanedioyl_count
dtype: int64
- name: decanoyl_count
dtype: int64
- name: diazo_count
dtype: int64
- name: diazoamino_count
dtype: int64
- name: disilanyl_count
dtype: int64
- name: disiloxanyloxy_count
dtype: int64
- name: disulfinyl_count
dtype: int64
- name: dithio_count
dtype: int64
- name: enanthoyl_count
dtype: int64
- name: epoxy_count
dtype: int64
- name: ethenyl_count
dtype: int64
- name: ethynyl_count
dtype: int64
- name: ethoxy_count
dtype: int64
- name: ethylene_count
dtype: int64
- name: ethylidene_count
dtype: int64
- name: ethylthio_count
dtype: int64
- name: formamido_count
dtype: int64
- name: furmaroyl_count
dtype: int64
- name: furfuryl_count
dtype: int64
- name: furfurylidene_count
dtype: int64
- name: glutamoyl_count
dtype: int64
- name: glutaryl_count
dtype: int64
- name: glycylamino_count
dtype: int64
- name: glycoloyl_count
dtype: int64
- name: glycyl_count
dtype: int64
- name: glyoxyoyl_count
dtype: int64
- name: guanidino_count
dtype: int64
- name: guanyl_count
dtype: int64
- name: heptadecanoyl_count
dtype: int64
- name: heptanamido_count
dtype: int64
- name: heptanoyl_count
dtype: int64
- name: hexadecanoyl_count
dtype: int64
- name: hexamethylene_count
dtype: int64
- name: hexanedioyl_count
dtype: int64
- name: hippuryl_count
dtype: int64
- name: hydrazino_count
dtype: int64
- name: hydrazo_count
dtype: int64
- name: hydrocinnamoyl_count
dtype: int64
- name: hydroperoxy_count
dtype: int64
- name: hydroxyamino_count
dtype: int64
- name: imino_count
dtype: int64
- name: iodoso_count
dtype: int64
- name: iodyl_count
dtype: int64
- name: isoamyl_count
dtype: int64
- name: isobutenyl_count
dtype: int64
- name: isobutoxy_count
dtype: int64
- name: isobutyl_count
dtype: int64
- name: isobutylidene_count
dtype: int64
- name: isobutyryl_count
dtype: int64
- name: isocyanato_count
dtype: int64
- name: isocyano_count
dtype: int64
- name: isohexyl_count
dtype: int64
- name: isoleucyl_count
dtype: int64
- name: isonitroso_count
dtype: int64
- name: isopentyl_count
dtype: int64
- name: isopentylidene_count
dtype: int64
- name: isopropenyl_count
dtype: int64
- name: isopropoxy_count
dtype: int64
- name: isopropyl_count
dtype: int64
- name: isopropylidene_count
dtype: int64
- name: isothiocynato_count
dtype: int64
- name: isovaleryl_count
dtype: int64
- name: lactoyl_count
dtype: int64
- name: lauroyl_count
dtype: int64
- name: lauryl_count
dtype: int64
- name: leucyl_count
dtype: int64
- name: levulinoyl_count
dtype: int64
- name: malonyl_count
dtype: int64
- name: mandeloyl_count
dtype: int64
- name: mercapto_count
dtype: int64
- name: mesityl_count
dtype: int64
- name: methacryloyl_count
dtype: int64
- name: methallyl_count
dtype: int64
- name: methionyl_count
dtype: int64
- name: methoxy_count
dtype: int64
- name: methylene_count
dtype: int64
- name: methylthio_count
dtype: int64
- name: myristoyl_count
dtype: int64
- name: myristyl_count
dtype: int64
- name: naphthyl_count
dtype: int64
- name: naphthylene_count
dtype: int64
- name: neopentyl_count
dtype: int64
- name: nitramino_count
dtype: int64
- name: nitrosamino_count
dtype: int64
- name: nitroso_count
dtype: int64
- name: nonanoyl_count
dtype: int64
- name: oleoyl_count
dtype: int64
- name: oxalyl_count
dtype: int64
- name: oxo_count
dtype: int64
- name: palmitoyl_count
dtype: int64
- name: pentamethylene_count
dtype: int64
- name: pentyl_count
dtype: int64
- name: tert-pentyl_count
dtype: int64
- name: phenacylidene_count
dtype: int64
- name: phenethyl_count
dtype: int64
- name: phenoxy_count
dtype: int64
- name: phenyl_count
dtype: int64
- name: phenylene_count
dtype: int64
- name: phosphino_count
dtype: int64
- name: phosphinyl_count
dtype: int64
- name: phospho_count
dtype: int64
- name: phosphono_count
dtype: int64
- name: phthaloyl_count
dtype: int64
- name: picryl_count
dtype: int64
- name: pimeloyl_count
dtype: int64
- name: piperidino_count
dtype: int64
- name: pivaloyl_count
dtype: int64
- name: prenyl_count
dtype: int64
- name: propargyl_count
dtype: int64
- name: 1-propenyl_count
dtype: int64
- name: 2-propenyl_count
dtype: int64
- name: propionyl_count
dtype: int64
- name: propoxy_count
dtype: int64
- name: propyl_count
dtype: int64
- name: propylidene_count
dtype: int64
- name: pyrryl_count
dtype: int64
- name: salicyloyl_count
dtype: int64
- name: selenyl_count
dtype: int64
- name: seryl_count
dtype: int64
- name: siloxy_count
dtype: int64
- name: silyl_count
dtype: int64
- name: silyene_count
dtype: int64
- name: sorboyl_count
dtype: int64
- name: stearoyl_count
dtype: int64
- name: stearyl_count
dtype: int64
- name: styryl_count
dtype: int64
- name: suberoyl_count
dtype: int64
- name: succinyl_count
dtype: int64
- name: sulfamino_count
dtype: int64
- name: sulfamoyl_count
dtype: int64
- name: sulfanilyl_count
dtype: int64
- name: sulfeno_count
dtype: int64
- name: sulfhydryl_count
dtype: int64
- name: sulfinyl_count
dtype: int64
- name: sulfo_count
dtype: int64
- name: sulfonyl_count
dtype: int64
- name: terephthaloyl_count
dtype: int64
- name: tetramethylene_count
dtype: int64
- name: thienyl_count
dtype: int64
- name: thiocarbonyl_count
dtype: int64
- name: thiocarboxy_count
dtype: int64
- name: thiocyanato_count
dtype: int64
- name: thionyl_count
dtype: int64
- name: threonyl_count
dtype: int64
- name: toluidino_count
dtype: int64
- name: toluoyl_count
dtype: int64
- name: tolyl_count
dtype: int64
- name: alpha-tolyl_count
dtype: int64
- name: tolylene_count
dtype: int64
- name: tosyl_count
dtype: int64
- name: triazano_count
dtype: int64
- name: trimethylene_count
dtype: int64
- name: valeryl_count
dtype: int64
- name: valyl_count
dtype: int64
- name: vinyl_count
dtype: int64
- name: vinylidene_count
dtype: int64
- name: xylidino_count
dtype: int64
- name: xylyl_count
dtype: int64
- name: xylylene_count
dtype: int64
- name: propiolamide_count
dtype: int64
- name: fumarate ester_count
dtype: int64
- name: allenamide_count
dtype: int64
- name: propiolonitrile_count
dtype: int64
- name: propargylamide_count
dtype: int64
- name: arylsulfonyl bicyclobutane_count
dtype: int64
- name: haloalkane_count
dtype: int64
- name: alpha-halomethyl_count
dtype: int64
- name: alpha-haloamide_count
dtype: int64
- name: alpha-haloester_count
dtype: int64
- name: epoxide_count
dtype: int64
- name: aziridine_count
dtype: int64
- name: nitroalkane_count
dtype: int64
- name: acrylamide_count
dtype: int64
- name: cyanoenone_count
dtype: int64
- name: aldehyde_count
dtype: int64
- name: ketone_count
dtype: int64
- name: nitrile_count
dtype: int64
- name: cyanamide_count
dtype: int64
- name: isothicyanate_count
dtype: int64
- name: sulfone_count
dtype: int64
- name: sulfonyl fluoride_count
dtype: int64
- name: sulfonimidoyl fluoride_count
dtype: int64
- name: aryl fluorosulfate_count
dtype: int64
- name: ester_count
dtype: int64
- name: sulfonamide_count
dtype: int64
- name: 2-carbonyl arylboronic acid_count
dtype: int64
- name: n-methyl isoxazolium_count
dtype: int64
- name: oxaziridine_count
dtype: int64
- name: carboxyl_count
dtype: int64
- name: ether_count
dtype: int64
- name: alkanol_count
dtype: int64
- name: thiol_count
dtype: int64
- name: halogen_count
dtype: int64
- name: amine_count
dtype: int64
- name: amide_count
dtype: int64
- name: num_valence_electrons
dtype: int64
- name: rotable_proportion
dtype: float64
- name: non_rotable_proportion
dtype: float64
- name: num_unspecified_bond
dtype: float64
- name: num_single_bonds
dtype: float64
- name: num_double_bonds
dtype: float64
- name: num_triple_bonds
dtype: float64
- name: num_quadruple_bonds
dtype: float64
- name: num_quintuple_bonds
dtype: float64
- name: num_hextuple_bonds
dtype: float64
- name: num_oneandahalf_bonds
dtype: float64
- name: num_twoandahalf_bonds
dtype: float64
- name: num_threeandahalf_bonds
dtype: float64
- name: num_fourandahalf_bonds
dtype: float64
- name: num_fiveandahalf_bonds
dtype: float64
- name: num_aromatic_bonds
dtype: float64
- name: num_ionic_bonds
dtype: float64
- name: num_hydrogen_bonds
dtype: float64
- name: num_threecenter_bonds
dtype: float64
- name: num_dativeone_bonds
dtype: float64
- name: num_dative_bonds
dtype: float64
- name: num_other_bonds
dtype: float64
- name: num_zero_bonds
dtype: float64
- name: num_bonds
dtype: int64
- name: molecular_formula
dtype: string
- name: monoisotopic_molecular_mass
dtype: float64
- name: carbon_mass
dtype: float64
- name: hydrogen_mass
dtype: float64
- name: nitrogen_mass
dtype: float64
- name: oxygen_mass
dtype: float64
- name: num_carbon_atoms
dtype: int64
- name: num_hydrogen_atoms
dtype: int64
- name: num_nitrogen_atoms
dtype: int64
- name: num_oxygen_atoms
dtype: int64
- name: num_hydrogen_bond_acceptors
dtype: int64
- name: num_hydrogen_bond_donors
dtype: int64
- name: num_lipinski_violations
dtype: int64
- name: inertial_shape_factor
dtype: float64
- name: eccentricity
dtype: float64
- name: asphericity
dtype: float64
- name: npr1_value
dtype: float64
- name: npr2_value
dtype: float64
- name: pmi1_value
dtype: float64
- name: pmi2_value
dtype: float64
- name: pmi3_value
dtype: float64
- name: num_chiral_centers
dtype: int64
- name: representation
dtype: string
splits:
- name: train
num_bytes: 2737391
num_examples: 495
download_size: 488441
dataset_size: 2737391
- config_name: smarts
features:
- name: representation
dtype: string
- name: representation_type
dtype: string
- name: completion
dtype: int64
- name: completion_labels
dtype: string
- name: smarts
dtype: string
- name: __index_level_0__
dtype: int64
splits:
- name: train
num_bytes: 157359982
num_examples: 812177
download_size: 24877597
dataset_size: 157359982
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- config_name: rdkit_feat
data_files:
- split: train
path: rdkit_feat/train-*
- config_name: rdkit_feat_0
data_files:
- split: train
path: rdkit_feat_0/train-*
- config_name: rdkit_feat_1
data_files:
- split: train
path: rdkit_feat_1/train-*
- config_name: rdkit_feat_10
data_files:
- split: train
path: rdkit_feat_10/train-*
- config_name: rdkit_feat_11
data_files:
- split: train
path: rdkit_feat_11/train-*
- config_name: rdkit_feat_2
data_files:
- split: train
path: rdkit_feat_2/train-*
- config_name: rdkit_feat_3
data_files:
- split: train
path: rdkit_feat_3/train-*
- config_name: rdkit_feat_4
data_files:
- split: train
path: rdkit_feat_4/train-*
- config_name: rdkit_feat_5
data_files:
- split: train
path: rdkit_feat_5/train-*
- config_name: rdkit_feat_6
data_files:
- split: train
path: rdkit_feat_6/train-*
- config_name: rdkit_feat_7
data_files:
- split: train
path: rdkit_feat_7/train-*
- config_name: rdkit_feat_8
data_files:
- split: train
path: rdkit_feat_8/train-*
- config_name: smarts
data_files:
- split: train
path: smarts/train-*
---
# Dataset Card for "chemnlp-chem-caption"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
提供机构:
kjappelbaum
原始信息汇总
数据集概述
数据集配置
配置名称:default
- 特征列表:
- representation: string
- representation_type: string
- prompt_template: string
- completion_template: string
- completion: string
- completion_names: string
- completion_labels: string
- constraint: string
- filled_prompt: string
- filled_completion: string
- 数据分割:
- train: 323500个样本,206763010字节
- 下载大小:15384432字节
- 数据集大小:206763010字节
配置名称:rdkit_feat
- 特征列表:
- representation_type: string
- num_valence_electrons: int64
- rotable_proportion: float64
- non_rotable_proportion: float64
- num_unspecified_bond: float64
- num_single_bonds: float64
- num_double_bonds: float64
- num_triple_bonds: float64
- num_quadruple_bonds: float64
- num_quintuple_bonds: float64
- num_hextuple_bonds: float64
- num_oneandahalf_bonds: float64
- num_twoandahalf_bonds: float64
- num_threeandahalf_bonds: float64
- num_fourandahalf_bonds: float64
- num_fiveandahalf_bonds: float64
- num_aromatic_bonds: float64
- num_ionic_bonds: float64
- num_hydrogen_bonds: float64
- num_threecenter_bonds: float64
- num_dativeone_bonds: float64
- num_dative_bonds: float64
- num_other_bonds: float64
- num_zero_bonds: float64
- num_bonds: int64
- molecular_formula: string
- monoisotopic_molecular_mass: float64
- num_carbon_atoms: int64
- num_hydrogen_atoms: int64
- num_nitrogen_atoms: int64
- num_oxygen_atoms: int64
- carbon_mass: float64
- hydrogen_mass: float64
- nitrogen_mass: float64
- oxygen_mass: float64
- num_hydrogen_bond_acceptors: int64
- num_hydrogen_bond_donors: int64
- num_lipinski_violations: int64
- inertial_shape_factor: float64
- eccentricity: float64
- asphericity: float64
- npr1_value: float64
- npr2_value: float64
- pmi1_value: float64
- pmi2_value: float64
- pmi3_value: float64
- num_chiral_centers: int64
- representation: string
- index_level_0: int64
- 数据分割:
- train: 82337个样本,41660808字节
- 下载大小:16423699字节
- 数据集大小:41660808字节
配置名称:rdkit_feat_0
- 特征列表:
- tert-butyloxycarbonyl_count: int64
- representation_type: string
- trityl_count: int64
- 3,5-dimethoxyphenylisoproxycarbonyl_count: int64
- 2-(4-biphenyl)isopropoxycarbonyl_count: int64
- 2-nitrophenylsulfenyl_count: int64
- boc_count: int64
- trt_count: int64
- ddz_count: int64
- bpoc_count: int64
- nps_count: int64
- 9-fluorenylmethoxycarbonyl_count: int64
- 2-(4-nitrophenylsulfonyl)ethoxycarbonyl_count: int64
- (1,1-dioxobenzo[b]thiophene-2-yl)methyloxycarbonyl_count: int64
- (1,1-dioxonaptho[1,2-b]thiophene-2-yl)methyloxycarbonyl_count: int64
- 1-(4,4-dimethyl-2,6-dioxocyclohex-1-ylidene)-3-methylbutyl_count: int64
- 2,7-di-tert-butyl-fmoc_count: int64
- 2-fluoro-fmoc_count: int64
- 2-monoisooctyl-fmoc_count: int64
- 2,7-diisooctyl-fmoc_count: int64
- tetrachlorophthaloyl_count: int64
- 2-[phenyl(methyl)sulfonio])ethyloxycarbonyltetrafluoroborate_count: int64
- ethanesulfonylethoxycarbonyl_count: int64
- 2-(4-sulfophenylsulfonyl)ethoxycarbonyl_count: int64
- fmoc_count: int64
- nsc_count: int64
- bsmoc_count: int64
- alpha-nsmoc_count: int64
- ivdde_count: int64
- fmoc*_count: int64
- fmoc(fmoc(2f))_count: int64
- mio-fmoc_count: int64
- dio-fmoc_count: int64
- tcp_count: int64
- pms_count: int64
- esc_count: int64
- sps_count: int64
- benzyloxycarbonyl_count: int64
- allyloxycarbonyl_count: int64
- o-nitrobenzenesulfonyl_count: int64
- 2,4-dinitrobenzenesulfonyl_count: int64
- benzothiazole-2-sulfonyl_count: int64
- 2,2,2-trichloroethyloxycarbonyl_count: int64
- dithiasuccinoyl_count: int64
- p-nitrobenzyloxycarbonyl_count: int64
- alpha-azidoacids_count: int64
- proparglyoxycarbonyl_count: int64
- o-nitrobenzylcarbonyl_count: int64
- 4-nitroveratryloxycarbonyl_count: int64
- 2-(2-nitrophenyl)propyloxycarbonyl_count: int64
- 2-(3,4-methylenedioxy-6-nitrophenyl)propyloxycarbonyl_count: int64
- 9-(4-bromophenyl)-9-fluorenyl_count: int64
- azidomethoxycarbonyl_count: int64
- hexafluoroacetone_count: int64
- Z_count: int64
- alloc_count: int64
- o-nbs_count: int64
- d-nbs_count: int64
- bts_count: int64
- troc_count: int64
- dts_count: int64
- pnz_count: int64
- poc_count: int64
- onz_count: int64
- nvoc_count: int64
- nppoc_count: int64
- mnppoc_count: int64
- brphf_count: int64
- azoc_count: int64
- hfa_count: int64
- 2-chlorobenzyloxycarbonyl_count: int64
- 4-methyltrityl_count: int64
- cl-z_count: int64
- mtt_count: int64
- 1-(4,4-dimethyl-2,6-dioxocylohex-1-ylidene)-3-methylbutyl_count: int64
- trifluoroacetyl_count: int64
- 2-(methylsulfonyl)ethoxycarbonyl_count: int64
- tfa_count: int64
- msc_count: int64
- phenyldisulphanylethyloxycarbonyl_count: int64
- 2-pyridyldisulphanylethyloxycarbonyl_count: int64
- phdec_count: int64
- pydec_count: int64
- tert-butyl_count: int64
- 2-chlorotrityl_count: int64
- 2-4-dimethyoxybenzyl_count: int64
- 2-phenylisopropyl_count: int64
- 5-phenyl-3,4-ethylenedioxythenyl_count: int64
- bu_count: int64
- 2-cl-trt_count: int64
- dmb_count: int64
- 2-ph-pr_count: int64
- phenyl-edotn_count: int64
- 9-fluorenylmethyl_count: int64
- 4-(N-[1-(4,4-dimethyl-2,6-dioxocylocheylidene)-3-methylbutyl]-amino)benzyl_count: int64
- methyl_count: int64
- ethyl_count: int64
- carbamoylmethyl_count: int64
- fm_count: int64
- dmab_count: int64
- me_count: int64
- et_count: int64
- cam_count: int64
- allyl_count: int64
- benzyl_count: int64
- phenacyl_count: int64
- p-nitrobenzyl_count: int64
- 2-trimethylsilyethyl_count: int64
- (2-phenyl-2-trimethylsilyl)ethyl_count: int64
- 2-(trimethylsilyl)isopropyl_count: int64
- 2,2,2-trichloroethyl_count: int64
- p-hydroxyphenacyl_count: int64
- 4,5-dimethyoxy-2-nitrobenzyl_count: int64
- 1,1-dimethylallyl_count: int64
- pentaaminecobalt_III_count: int64
- al_count: int64
- bn_count: int64
- pac_count: int64
- pnb_count: int64
- tmse_count: int64
- ptmse_count: int64
- tmsi_count: int64
- tce_count: int64
- php_count: int64
- dmnb_count: int64
- dma_count: int64
- cyclohexyl_count: int64
- b-menthyl_count: int64
- b-3-methylpent-3-yl_count: int64
- 4-(3,6,9-trioxadecyl)oxybenzyl_count: int64
- chx_count: int64
- men_count: int64
- mpe_count: int64
- tegbz_count: int64
- 9-fluoroenylmethyl_count: int64
- 4-(N-[1-(4,4-dimethyl-2,6-dioxocyclohexylidene)-3-methyl-butyl]-amino)benzyl_count: int64
- trimethylsilylethyl_count: int64
- 4,5-dimethoxy-2-nitrobenzyloxycarbonyl_count: int64
- pseudoprolines_count: int64
- 2-hydroxy-4-methoxybenzyl_count: int64
- 2,4-dimethoxybenzyl_count: int64
- 2,4,6-trimethoxybenzyl_count: int64
- 1-methyl-3-indolylmethyl_count: int64
- 3,4-ethylene-dioxy-2-thenyl_count: int64
- hmb_count: int64
- tmob_count: int64
- mim_count: int64
- edot_count: int64
- 4-methoxy-2-nitro-benzyl_count: int64
- (6-hydroxy-3-oxido-1,3-benz[d]oxathiol-5-yl)methyl_count: int64
- 2-hydroxy-4-methoxy-5-(methylsulfinyl)benzyl_count: int64
- n-boc-n-methyl[2-(methylamino)ethyl]carbamoyl-hmb_count: int64
- 9-xanthenyl_count: int64
- cyclopropyldimethylcarbinyl_count: int64
- 4,4-dimethoxybenzhydryl_count: int64
- xan_count: int64
- cpd_count: int64
- mbh_count: int64
- p-toluenesulfonyl_count: int64
- 2,2,5,7,8-pentamethylchroman-6-sulfonyl_count: int64
- 2,2,4,6,7-pentamethyl-2,3-dihydrobenzofuran-5-sulfonyl_count: int64
- mesityl-2-sulfonyl_count: int64
- 4-methoxy-2,3,6-trimethylphenylsulfonyl_count: int64
- 1,2-dimethylindole-3-sulfonyl_count: int64
- w,w-bis-tert-butyloxycarbonyl_count: int64
- 5-dibenzosuberenyl_count: int64
- 5-dibenzosuberyl_count: int64
- 2-methoxy-5-dibenzosuberyl_count: int64
- nitro_count: int64
- tos_count: int64
- pmc_count: int64
- pbf_count: int64
- mts_count: int64
- mtr_count: int64
- mis_count: int64
- bis-boc_count: int64
- suben_count: int64
- sub_count: int64
- mesub_count: int64
- no2_count: int64
- w,w-bis-benzyloxycarbonyl_count: int64
- w,w-bis-allyloxycarbonyl_count: int64
- z-small_count: int64
- p-methylbenzyl_count: int64
- p-methoxybenzyl_count: int64
- monomethoxytrityl_count: int64
- trimethoxybenzyl_count: int64



