ScrambleBench: A Workflow for Comparative Assessment of Structure-based de novo Generative Models

Data Availability for ScrambleBench The zipped file contained all of the information needed to reproduce the main and supplementary figure of the manuscript: ScrambleBench: A Workflow for Comparative Assessment of Structure-based de novo Generative Models (Updated as of 12 Feb 2026) You can explore the folders which contains the README.md for further information. Main Figure Figure 1 directory: output_analysis_supporting/diversity_resultfile: SixProtein_Benchmark_DiversityAnalysis_HamDivMCES.csv Figure 2-7 (Distribution Figure shown in Raincloud plot) directory: output_scramblebench_data_warehousefile: data_warehouse_without_molblock.csv (Docking Figure of Generated Ligand) directory: output_virtual_hitsfile: best_compound_23dec_*.sdf (Docking Figure of Native Complex) directory: input_proteinfile: [protein_name]_complex_autoprepared.pdb Main Table Table 3 directory: output_generation/Docking/phase_score/hypofile: all files inside Table 4-5, 8-9, 12-13 (Time) directory: output_generation/generation_logfile: all files inside (Generated Ligand) directory_1: output_generation/*nov_*/summaryfile_1: all files inside directory_2: output_generation/*nov_*/cheminformatics_input_preparedfile_2: all files inside Table 6-7, 10-11, 14-15 directory: output_virtual_hitsfile: virtual_hits*.csv Supplementary Figure All Docking Figure containing Native Complex is available here:directory: input_proteinfile: [protein_name]_complex_autoprepared.pdb Figure 1 directory: input_external_data/SuppFig1file: SupplementaryFigure1.xlsx Figure 2 directory: output_analysis_supporting/diversity_resultfile: ThreeProtein_Benchmark_DiversityAnalysis_RASCALConfig_HamDivMCES.csv Figure 3 directory: output_analysis_supporting/GenBench3D_finetunefile: data.yaml Figure 4 directory: output_generation/Docking/Glide/generated_ligandfile: kinase_gsk3b_glide-dock_SP_nonforce_planar_lib.sdfgz (ligand ID: control_36) Figure 5 directory: output_generation/Docking/phase_score/hypofile: all files inside Figure 6 directory: output_analysis_supporting/diversity_resultfile: SixProteinBenchmark_DiversityAnalysis_HamDivECFP.csv Figure 7 directory: output_analysis_supporting/diversity_resultfile: SixProteinBenchmark_DiversityAnalysis_Average_Tanimoto.csv Figure 8 directory: output_scramblebench_data_warehousefile: data_warehouse_without_molblock.csv Figure 9 directory: output_generation/*nov_*/genbench_analysis/output_jsonfile: all json files Figure 10 directory: output_generation/Docking/Vina/output_generated_ligandfile: gpcr_5ht2c_input_docking_vina.sdf (ligand ID: Pocket2Mol_num500_444) Figure 11 directory: input_external_data/SuppFig11file: 1Q3D_prepared.pdb directory: output_virtual_hitsfile: best_compound_23dec_DiffSBDD.sdf Figure 12 directory: input_external_data/SuppFig12file: crossdocked_set_ids.txt and uniprot_protein_family_list.txt Figure 13 directory: output_generation/Docking/Glide/generated_ligandfile: /kinase_cdk2_glide-dock_SP_nonforce_planar_lib.sdfgz (ligand_ID: PMDM_num100_10) Figure 14 directory: input_external_data/SuppFig12file: wu-04_docking_pose.sdf (4th pose) Figure 15-20 directory: output_virtual_hitsfile: best_compound_23dec_*.sdf