yeolab/eCLIP
收藏Hugging Face2026-02-02 更新2026-03-29 收录
下载链接:
https://hf-mirror.com/datasets/yeolab/eCLIP
下载链接
链接失效反馈官方服务:
资源简介:
---
dataset_info:
- config_name: AARS_K562_ENCSR825SVO
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 3080006415
num_examples: 491247
- name: validation
num_bytes: 973841934
num_examples: 155332
- name: test
num_bytes: 761112864
num_examples: 121398
download_size: 166562585
dataset_size: 4814961213
- config_name: AATF_K562_ENCSR819XBT
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2287947088
num_examples: 364918
- name: validation
num_bytes: 708424784
num_examples: 112997
- name: test
num_bytes: 544316670
num_examples: 86819
download_size: 125169700
dataset_size: 3540688542
- config_name: ABCF1_K562_ENCSR089BXO
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 404439101
num_examples: 64505
- name: validation
num_bytes: 114647973
num_examples: 18287
- name: test
num_bytes: 97656669
num_examples: 15576
download_size: 23764135
dataset_size: 616743743
- config_name: AGGF1_HepG2_ENCSR543TPH
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2837315422
num_examples: 452530
- name: validation
num_bytes: 569363413
num_examples: 90816
- name: test
num_bytes: 1040110378
num_examples: 165897
download_size: 159687808
dataset_size: 4446789213
- config_name: AGGF1_K562_ENCSR725ARB
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 3493892829
num_examples: 557259
- name: validation
num_bytes: 1049312567
num_examples: 167370
- name: test
num_bytes: 875517157
num_examples: 139645
download_size: 192550404
dataset_size: 5418722553
- config_name: AGO2_K562_4116
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1332839501
num_examples: 212580
- name: validation
num_bytes: 396207674
num_examples: 63197
- name: test
num_bytes: 326802386
num_examples: 52125
download_size: 81715503
dataset_size: 2055849561
- config_name: AKAP1_K562_ENCSR177QQY
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 894159593
num_examples: 142613
- name: validation
num_bytes: 254976093
num_examples: 40670
- name: test
num_bytes: 222335032
num_examples: 35462
download_size: 50924439
dataset_size: 1371470718
- config_name: AKAP8L_K562_ENCSR206RXT
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2558168813
num_examples: 408014
- name: validation
num_bytes: 744003704
num_examples: 118672
- name: test
num_bytes: 635915712
num_examples: 101428
download_size: 140594993
dataset_size: 3938088229
- config_name: APEX1_HepG2_4081
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 926896778
num_examples: 147834
- name: validation
num_bytes: 197285385
num_examples: 31468
- name: test
num_bytes: 342467013
num_examples: 54624
download_size: 55475747
dataset_size: 1466649176
- config_name: APEX1_K562_4028
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 298176188
num_examples: 47557
- name: validation
num_bytes: 84856081
num_examples: 13535
- name: test
num_bytes: 74001277
num_examples: 11803
download_size: 19217669
dataset_size: 457033546
- config_name: APOBEC3C_K562_ENCSR739VVT
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 423931724
num_examples: 67614
- name: validation
num_bytes: 116491125
num_examples: 18581
- name: test
num_bytes: 96440108
num_examples: 15382
download_size: 24849008
dataset_size: 636862957
- config_name: BCCIP_HepG2_ENCSR485QCG
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 721129641
num_examples: 115014
- name: validation
num_bytes: 134572730
num_examples: 21465
- name: test
num_bytes: 255905091
num_examples: 40816
download_size: 41102015
dataset_size: 1111607462
- config_name: BCLAF1_HepG2_ENCSR876EYA
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 4680550921
num_examples: 746516
- name: validation
num_bytes: 1068619711
num_examples: 170449
- name: test
num_bytes: 1636178385
num_examples: 260972
download_size: 264539459
dataset_size: 7385349017
- config_name: BUD13_HepG2_ENCSR830BSQ
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 4381948792
num_examples: 698889
- name: validation
num_bytes: 922370665
num_examples: 147122
- name: test
num_bytes: 1550011172
num_examples: 247227
download_size: 243519811
dataset_size: 6854330629
- config_name: CACTIN_HepG2_4190
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 3825524807
num_examples: 610146
- name: validation
num_bytes: 788704933
num_examples: 125802
- name: test
num_bytes: 1341882279
num_examples: 214031
download_size: 213825214
dataset_size: 5956112019
- config_name: CACTIN_K562_4158
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1045224535
num_examples: 166708
- name: validation
num_bytes: 309043883
num_examples: 49294
- name: test
num_bytes: 243824654
num_examples: 38890
download_size: 60422420
dataset_size: 1598093072
- config_name: CDC40_HepG2_ENCSR815VVI
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2722546022
num_examples: 434228
- name: validation
num_bytes: 542260514
num_examples: 86493
- name: test
num_bytes: 1052402737
num_examples: 167859
download_size: 151866585
dataset_size: 4317209273
- config_name: CDC40_K562_5006
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 5460518343
num_examples: 870918
- name: validation
num_bytes: 1631945658
num_examples: 260302
- name: test
num_bytes: 1386213478
num_examples: 221101
download_size: 307321681
dataset_size: 8478677479
- config_name: CDK9_HepG2_5063
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 453086927
num_examples: 72264
- name: validation
num_bytes: 96492482
num_examples: 15391
- name: test
num_bytes: 142307484
num_examples: 22698
download_size: 26415299
dataset_size: 691886893
- config_name: CNOT2_HepG2_4191
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 3242367356
num_examples: 517135
- name: validation
num_bytes: 692363096
num_examples: 110435
- name: test
num_bytes: 1146280903
num_examples: 182832
download_size: 185670496
dataset_size: 5081011355
- config_name: CPEB4_K562_ENCSR046JHH
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 585192947
num_examples: 93335
- name: validation
num_bytes: 165054061
num_examples: 26327
- name: test
num_bytes: 136377412
num_examples: 21752
download_size: 33496394
dataset_size: 886624420
- config_name: CPSF6_K562_ENCSR532VUB
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 785549756
num_examples: 125290
- name: validation
num_bytes: 221253208
num_examples: 35291
- name: test
num_bytes: 187983446
num_examples: 29983
download_size: 44808635
dataset_size: 1194786410
- config_name: CSTF2_HepG2_ENCSR384MWO
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 3196738072
num_examples: 509860
- name: validation
num_bytes: 617269408
num_examples: 98457
- name: test
num_bytes: 1108071095
num_examples: 176739
download_size: 170420300
dataset_size: 4922078575
- config_name: CXXC1_K562_4088
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1197556369
num_examples: 191002
- name: validation
num_bytes: 349507642
num_examples: 55748
- name: test
num_bytes: 299871126
num_examples: 47829
download_size: 71449510
dataset_size: 1846935137
- config_name: DDX21_K562_ENCSR040QLV
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 624968015
num_examples: 99678
- name: validation
num_bytes: 166671678
num_examples: 26585
- name: test
num_bytes: 152641942
num_examples: 24346
download_size: 35857620
dataset_size: 944281635
- config_name: DDX3X_HepG2_ENCSR648LAH
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1953906382
num_examples: 311634
- name: validation
num_bytes: 387750428
num_examples: 61848
- name: test
num_bytes: 713036040
num_examples: 113729
download_size: 111427776
dataset_size: 3054692850
- config_name: DDX3X_K562_ENCSR930BZL
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1244099781
num_examples: 198427
- name: validation
num_bytes: 371593158
num_examples: 59271
- name: test
num_bytes: 308690723
num_examples: 49236
download_size: 72083572
dataset_size: 1924383662
- config_name: DDX41_K562_5081
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2160440588
num_examples: 344577
- name: validation
num_bytes: 622803683
num_examples: 99340
- name: test
num_bytes: 533464712
num_examples: 85087
download_size: 124426220
dataset_size: 3316708983
- config_name: DDX42_K562_ENCSR576SHT
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 981169940
num_examples: 156490
- name: validation
num_bytes: 275320335
num_examples: 43915
- name: test
num_bytes: 259196071
num_examples: 41341
download_size: 55999331
dataset_size: 1515686346
- config_name: DDX51_K562_ENCSR145NLR
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1181367249
num_examples: 188422
- name: validation
num_bytes: 354208372
num_examples: 56498
- name: test
num_bytes: 283737036
num_examples: 45256
download_size: 65660159
dataset_size: 1819312657
- config_name: DDX52_HepG2_ENCSR970FEW
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2147425333
num_examples: 342499
- name: validation
num_bytes: 438024760
num_examples: 69867
- name: test
num_bytes: 815203721
num_examples: 130025
download_size: 121495510
dataset_size: 3400653814
- config_name: DDX52_K562_ENCSR154CSN
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1909905942
num_examples: 304621
- name: validation
num_bytes: 583963680
num_examples: 93145
- name: test
num_bytes: 465961655
num_examples: 74321
download_size: 105438832
dataset_size: 2959831277
- config_name: DDX55_HepG2_ENCSR845VGB
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1385740110
num_examples: 221015
- name: validation
num_bytes: 284298621
num_examples: 45347
- name: test
num_bytes: 520096716
num_examples: 82955
download_size: 79978208
dataset_size: 2190135447
- config_name: DDX55_K562_ENCSR923NKN
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1457804372
num_examples: 232511
- name: validation
num_bytes: 439252933
num_examples: 70063
- name: test
num_bytes: 348809776
num_examples: 55635
download_size: 82825319
dataset_size: 2245867081
- config_name: DDX59_HepG2_ENCSR214BZA
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2388806214
num_examples: 380997
- name: validation
num_bytes: 463358719
num_examples: 73908
- name: test
num_bytes: 890955518
num_examples: 142107
download_size: 133075796
dataset_size: 3743120451
- config_name: DDX5_K562_5094
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 3086192253
num_examples: 492232
- name: validation
num_bytes: 897597609
num_examples: 143171
- name: test
num_bytes: 778660268
num_examples: 124196
download_size: 171415485
dataset_size: 4762450130
- config_name: DDX6_HepG2_ENCSR141OIM
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 669387399
num_examples: 106762
- name: validation
num_bytes: 132033434
num_examples: 21060
- name: test
num_bytes: 251042952
num_examples: 40041
download_size: 38888647
dataset_size: 1052463785
- config_name: DDX6_K562_ENCSR893EFU
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1362541380
num_examples: 217318
- name: validation
num_bytes: 409836997
num_examples: 65371
- name: test
num_bytes: 333925968
num_examples: 53261
download_size: 77108381
dataset_size: 2106304345
- config_name: DEK_HepG2_4020
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 508782959
num_examples: 81147
- name: validation
num_bytes: 105746054
num_examples: 16867
- name: test
num_bytes: 179291510
num_examples: 28597
download_size: 31151404
dataset_size: 793820523
- config_name: DEK_HepG2_4146
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1209496450
num_examples: 192906
- name: validation
num_bytes: 227836045
num_examples: 36341
- name: test
num_bytes: 447671157
num_examples: 71403
download_size: 69222286
dataset_size: 1885003652
- config_name: DGCR8_HepG2_ENCSR061SZV
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2322753035
num_examples: 370462
- name: validation
num_bytes: 447730061
num_examples: 71415
- name: test
num_bytes: 877961852
num_examples: 140035
download_size: 128644673
dataset_size: 3648444948
- config_name: DGCR8_K562_ENCSR947JVR
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 681726252
num_examples: 108731
- name: validation
num_bytes: 180557739
num_examples: 28800
- name: test
num_bytes: 185834629
num_examples: 29640
download_size: 39085530
dataset_size: 1048118620
- config_name: DHX30_HepG2_ENCSR565DGW
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2657563657
num_examples: 423864
- name: validation
num_bytes: 561244358
num_examples: 89521
- name: test
num_bytes: 989542345
num_examples: 157833
download_size: 148932486
dataset_size: 4208350360
- config_name: DHX30_K562_ENCSR529GSJ
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2572478567
num_examples: 410300
- name: validation
num_bytes: 801738148
num_examples: 127881
- name: test
num_bytes: 623262326
num_examples: 99411
download_size: 140321552
dataset_size: 3997479041
- config_name: DHX38_HepG2_4202
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 942457994
num_examples: 150315
- name: validation
num_bytes: 207461576
num_examples: 33091
- name: test
num_bytes: 302188223
num_examples: 48199
download_size: 54985294
dataset_size: 1452107793
- config_name: DKC1_HepG2_ENCSR301TFY
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1907702119
num_examples: 304264
- name: validation
num_bytes: 381744184
num_examples: 60890
- name: test
num_bytes: 706128514
num_examples: 112627
download_size: 107909164
dataset_size: 2995574817
- config_name: DNAJC2_K562_5084
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2767557561
num_examples: 441411
- name: validation
num_bytes: 836853773
num_examples: 133482
- name: test
num_bytes: 686232614
num_examples: 109454
download_size: 158200160
dataset_size: 4290643948
- config_name: DROSHA_HepG2_ENCSR834YLD
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 3266941905
num_examples: 521054
- name: validation
num_bytes: 659002959
num_examples: 105114
- name: test
num_bytes: 1212729794
num_examples: 193431
download_size: 181693917
dataset_size: 5138674658
- config_name: DROSHA_K562_ENCSR653HQC
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 4568044322
num_examples: 728583
- name: validation
num_bytes: 1431975053
num_examples: 228406
- name: test
num_bytes: 1112717764
num_examples: 177480
download_size: 249254828
dataset_size: 7112737139
- config_name: EFTUD2_HepG2_ENCSR527DXF
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2507797279
num_examples: 399975
- name: validation
num_bytes: 524881271
num_examples: 83721
- name: test
num_bytes: 928840574
num_examples: 148150
download_size: 140500234
dataset_size: 3961519124
- config_name: EFTUD2_K562_ENCSR844RVX
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2137634282
num_examples: 340941
- name: validation
num_bytes: 654507163
num_examples: 104397
- name: test
num_bytes: 535682539
num_examples: 85441
download_size: 118847344
dataset_size: 3327823984
- config_name: EIF2B4_K562_5019
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1744833694
num_examples: 278293
- name: validation
num_bytes: 524492144
num_examples: 83659
- name: test
num_bytes: 417729795
num_examples: 66628
download_size: 99441002
dataset_size: 2687055633
- config_name: EIF2B5_K562_5020
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 948938887
num_examples: 151349
- name: validation
num_bytes: 279014102
num_examples: 44504
- name: test
num_bytes: 227763650
num_examples: 36328
download_size: 55765170
dataset_size: 1455716639
- config_name: EIF2S2_K562_5023
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 96399366
num_examples: 15375
- name: validation
num_bytes: 24199725
num_examples: 3860
- name: test
num_bytes: 18338588
num_examples: 2925
download_size: 6518556
dataset_size: 138937679
- config_name: EIF3B_K562_5061
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 487485481
num_examples: 77751
- name: validation
num_bytes: 136315342
num_examples: 21743
- name: test
num_bytes: 115737858
num_examples: 18460
download_size: 29085083
dataset_size: 739538681
- config_name: EIF3C_K562_5060
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 318425400
num_examples: 50787
- name: validation
num_bytes: 89288705
num_examples: 14242
- name: test
num_bytes: 71360932
num_examples: 11382
download_size: 19442519
dataset_size: 479075037
- config_name: EIF3D_HepG2_ENCSR041NUV
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 5366030514
num_examples: 855844
- name: validation
num_bytes: 1146760149
num_examples: 182913
- name: test
num_bytes: 1868508210
num_examples: 298028
download_size: 294475791
dataset_size: 8381298873
- config_name: EIF3G_K562_ENCSR023PKW
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 195544416
num_examples: 31188
- name: validation
num_bytes: 54468372
num_examples: 8688
- name: test
num_bytes: 43197696
num_examples: 6890
download_size: 12024275
dataset_size: 293210484
- config_name: EIF3H_HepG2_ENCSR916XIV
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1265372849
num_examples: 201817
- name: validation
num_bytes: 270093130
num_examples: 43081
- name: test
num_bytes: 471734917
num_examples: 75241
download_size: 74012070
dataset_size: 2007200896
- config_name: EIF4E_HepG2_4082
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 883511056
num_examples: 140914
- name: validation
num_bytes: 188922076
num_examples: 30134
- name: test
num_bytes: 311897494
num_examples: 49748
download_size: 52894067
dataset_size: 1384330626
- config_name: EIF4G2_K562_5065
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2001499791
num_examples: 319224
- name: validation
num_bytes: 574429791
num_examples: 91624
- name: test
num_bytes: 517370907
num_examples: 82520
download_size: 121853495
dataset_size: 3093300489
- config_name: EIF4G2_K562_ENCSR307YIW
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 969151286
num_examples: 154572
- name: validation
num_bytes: 250010772
num_examples: 39878
- name: test
num_bytes: 275870033
num_examples: 44000
download_size: 55345646
dataset_size: 1495032091
- config_name: ELAVL1_HepG2_4083
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 4050675086
num_examples: 646062
- name: validation
num_bytes: 951028651
num_examples: 151693
- name: test
num_bytes: 1351103728
num_examples: 215505
download_size: 229453752
dataset_size: 6352807465
- config_name: EXOSC5_HepG2_ENCSR693JWP
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 122507494
num_examples: 19539
- name: validation
num_bytes: 24018235
num_examples: 3831
- name: test
num_bytes: 40288376
num_examples: 6426
download_size: 7197503
dataset_size: 186814105
- config_name: FAM120A_HepG2_ENCSR987NYS
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2493945731
num_examples: 397763
- name: validation
num_bytes: 478380953
num_examples: 76304
- name: test
num_bytes: 865192887
num_examples: 137997
download_size: 139283900
dataset_size: 3837519571
- config_name: FASTKD2_HepG2_ENCSR023UHL
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 3124150473
num_examples: 498279
- name: validation
num_bytes: 674151064
num_examples: 107530
- name: test
num_bytes: 1129867224
num_examples: 180214
download_size: 176712539
dataset_size: 4928168761
- config_name: FASTKD2_K562_ENCSR887FHF
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 3121624243
num_examples: 497886
- name: validation
num_bytes: 975370922
num_examples: 155576
- name: test
num_bytes: 749185420
num_examples: 119496
download_size: 169533954
dataset_size: 4846180585
- config_name: FKBP4_HepG2_ENCSR018ZUE
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 768639841
num_examples: 122592
- name: validation
num_bytes: 129506307
num_examples: 20657
- name: test
num_bytes: 299897634
num_examples: 47833
download_size: 43791495
dataset_size: 1198043782
- config_name: FMR1_K562_ENCSR331VNX
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 725725804
num_examples: 115748
- name: validation
num_bytes: 207912466
num_examples: 33163
- name: test
num_bytes: 163681395
num_examples: 26107
download_size: 40861013
dataset_size: 1097319665
- config_name: FMRP_K562_4030
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1077468227
num_examples: 171849
- name: validation
num_bytes: 319288988
num_examples: 50928
- name: test
num_bytes: 276334818
num_examples: 44075
download_size: 63232771
dataset_size: 1673092033
- config_name: FTO_HepG2_ENCSR903PRV
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 151989586
num_examples: 24241
- name: validation
num_bytes: 28249890
num_examples: 4506
- name: test
num_bytes: 50940819
num_examples: 8125
download_size: 8786806
dataset_size: 231180295
- config_name: FTO_K562_ENCSR989SMC
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1495912772
num_examples: 238590
- name: validation
num_bytes: 434744930
num_examples: 69344
- name: test
num_bytes: 368328435
num_examples: 58748
download_size: 84010038
dataset_size: 2298986137
- config_name: FUBP3_HepG2_ENCSR486YGP
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 619171901
num_examples: 98754
- name: validation
num_bytes: 122535792
num_examples: 19545
- name: test
num_bytes: 221860300
num_examples: 35387
download_size: 35450891
dataset_size: 963567993
- config_name: FUS_K562_ENCSR069EVH
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 4192793254
num_examples: 668724
- name: validation
num_bytes: 1173744433
num_examples: 187217
- name: test
num_bytes: 1113720512
num_examples: 177637
download_size: 226976001
dataset_size: 6480258199
- config_name: FXR1_K562_4036
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 584237180
num_examples: 93182
- name: validation
num_bytes: 173536728
num_examples: 27680
- name: test
num_bytes: 149825938
num_examples: 23897
download_size: 35574682
dataset_size: 907599846
- config_name: FXR1_K562_ENCSR774RFN
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 906128515
num_examples: 144522
- name: validation
num_bytes: 281986394
num_examples: 44978
- name: test
num_bytes: 222953215
num_examples: 35561
download_size: 50712514
dataset_size: 1411068124
- config_name: FXR2_HepG2_4098
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2802824691
num_examples: 447032
- name: validation
num_bytes: 631136739
num_examples: 100669
- name: test
num_bytes: 984783612
num_examples: 157074
download_size: 161158650
dataset_size: 4418745042
- config_name: FXR2_HepG2_ENCSR973HOJ
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 942784465
num_examples: 150367
- name: validation
num_bytes: 211969119
num_examples: 33810
- name: test
num_bytes: 331831644
num_examples: 52927
download_size: 55436443
dataset_size: 1486585228
- config_name: FXR2_K562_4002
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1393397798
num_examples: 222239
- name: validation
num_bytes: 416627090
num_examples: 66454
- name: test
num_bytes: 349268581
num_examples: 55708
download_size: 81565335
dataset_size: 2159293469
- config_name: FXR2_K562_ENCSR224QWC
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 796650916
num_examples: 127060
- name: validation
num_bytes: 232971351
num_examples: 37160
- name: test
num_bytes: 184352670
num_examples: 29404
download_size: 45160082
dataset_size: 1213974937
- config_name: G3BP1_HepG2_ENCSR721HPX
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1094855515
num_examples: 174621
- name: validation
num_bytes: 247052645
num_examples: 39406
- name: test
num_bytes: 350727626
num_examples: 55941
download_size: 62781926
dataset_size: 1692635786
- config_name: GARS_HepG2_4108
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 959433400
num_examples: 153023
- name: validation
num_bytes: 196439108
num_examples: 31333
- name: test
num_bytes: 359817156
num_examples: 57391
download_size: 56968226
dataset_size: 1515689664
- config_name: GEMIN5_K562_ENCSR238CLX
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 4467025837
num_examples: 712472
- name: validation
num_bytes: 1439780165
num_examples: 229651
- name: test
num_bytes: 1101542311
num_examples: 175698
download_size: 242966702
dataset_size: 7008348313
- config_name: GNL3_K562_ENCSR301UQM
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 918426723
num_examples: 146484
- name: validation
num_bytes: 269690230
num_examples: 43017
- name: test
num_bytes: 227864213
num_examples: 36344
download_size: 51956286
dataset_size: 1415981166
- config_name: GPKOW_K562_ENCSR647CLF
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2140648077
num_examples: 341424
- name: validation
num_bytes: 663742477
num_examples: 105870
- name: test
num_bytes: 510944611
num_examples: 81496
download_size: 118831398
dataset_size: 3315335165
- config_name: GRSF1_HepG2_ENCSR668MJX
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 692054413
num_examples: 110377
- name: validation
num_bytes: 134095886
num_examples: 21389
- name: test
num_bytes: 256886457
num_examples: 40973
download_size: 40340936
dataset_size: 1083036756
- config_name: GTF2F1_HepG2_ENCSR265ZIS
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1534440490
num_examples: 244731
- name: validation
num_bytes: 286404854
num_examples: 45683
- name: test
num_bytes: 566880363
num_examples: 90417
download_size: 85212764
dataset_size: 2387725707
- config_name: GTF2F1_K562_ENCSR736AAG
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1263270539
num_examples: 201483
- name: validation
num_bytes: 337581248
num_examples: 53846
- name: test
num_bytes: 354879573
num_examples: 56602
download_size: 71003585
dataset_size: 1955731360
- config_name: HLTF_HepG2_ENCSR647HOX
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 5621889660
num_examples: 896656
- name: validation
num_bytes: 1220464930
num_examples: 194669
- name: test
num_bytes: 1946526674
num_examples: 310474
download_size: 308214950
dataset_size: 8788881264
- config_name: HLTF_K562_ENCSR589YHM
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1213381112
num_examples: 193528
- name: validation
num_bytes: 370336250
num_examples: 59070
- name: test
num_bytes: 287589987
num_examples: 45871
download_size: 69350354
dataset_size: 1871307349
- config_name: HNRNPA1_HepG2_ENCSR769UEW
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 3120420204
num_examples: 497688
- name: validation
num_bytes: 630171385
num_examples: 100515
- name: test
num_bytes: 1077058103
num_examples: 171792
download_size: 168254648
dataset_size: 4827649692
- config_name: HNRNPA1_K562_ENCSR154HRN
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1700377494
num_examples: 271201
- name: validation
num_bytes: 502104936
num_examples: 80088
- name: test
num_bytes: 414402395
num_examples: 66097
download_size: 93757528
dataset_size: 2616884825
- config_name: HNRNPC_HepG2_ENCSR550DVK
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 4004587113
num_examples: 638706
- name: validation
num_bytes: 823081745
num_examples: 131285
- name: test
num_bytes: 1403798643
num_examples: 223907
download_size: 218867476
dataset_size: 6231467501
- config_name: HNRNPC_K562_ENCSR249ROI
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 5333719990
num_examples: 850703
- name: validation
num_bytes: 1675620872
num_examples: 267268
- name: test
num_bytes: 1347563491
num_examples: 214938
download_size: 283423745
dataset_size: 8356904353
- config_name: HNRNPK_HepG2_ENCSR828ZID
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 933340372
num_examples: 148860
- name: validation
num_bytes: 161794297
num_examples: 25807
- name: test
num_bytes: 319710925
num_examples: 50993
download_size: 51194227
dataset_size: 1414845594
- config_name: HNRNPK_K562_ENCSR268ETU
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 648273288
num_examples: 103395
- name: validation
num_bytes: 164684497
num_examples: 26268
- name: test
num_bytes: 162993540
num_examples: 25997
download_size: 35856604
dataset_size: 975951325
- config_name: HNRNPL_HepG2_ENCSR724RDN
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2910847319
num_examples: 464263
- name: validation
num_bytes: 582517008
num_examples: 92914
- name: test
num_bytes: 1035743284
num_examples: 165203
download_size: 164243496
dataset_size: 4529107611
- config_name: HNRNPM_HepG2_ENCSR267UCX
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1968329495
num_examples: 313936
- name: validation
num_bytes: 389124744
num_examples: 62067
- name: test
num_bytes: 693314562
num_examples: 110584
download_size: 107568988
dataset_size: 3050768801
- config_name: HNRNPUL1_HepG2_ENCSR755TJC
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 3663917823
num_examples: 584372
- name: validation
num_bytes: 705034184
num_examples: 112456
- name: test
num_bytes: 1362001413
num_examples: 217241
download_size: 199252966
dataset_size: 5730953420
- config_name: HNRNPUL1_K562_ENCSR571VHI
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1110211577
num_examples: 177072
- name: validation
num_bytes: 287025343
num_examples: 45782
- name: test
num_bytes: 284254931
num_examples: 45338
download_size: 60996661
dataset_size: 1681491851
- config_name: HNRNPU_HepG2_ENCSR240MVJ
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2851974500
num_examples: 454871
- name: validation
num_bytes: 553389878
num_examples: 88268
- name: test
num_bytes: 979352523
num_examples: 156207
download_size: 152644717
dataset_size: 4384716901
- config_name: HNRNPU_K562_ENCSR520BZQ
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 6894830561
num_examples: 1099691
- name: validation
num_bytes: 2084877583
num_examples: 332546
- name: test
num_bytes: 1741394857
num_examples: 277754
download_size: 364879362
dataset_size: 10721103001
- config_name: IGF2BP1_HepG2_ENCSR744GEU
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 909828660
num_examples: 145110
- name: validation
num_bytes: 178865832
num_examples: 28530
- name: test
num_bytes: 315453274
num_examples: 50314
download_size: 50599174
dataset_size: 1404147766
- config_name: IGF2BP1_K562_5093
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2002893569
num_examples: 319451
- name: validation
num_bytes: 601204658
num_examples: 95895
- name: test
num_bytes: 485033907
num_examples: 77363
download_size: 115255195
dataset_size: 3089132134
- config_name: IGF2BP2_K562_ENCSR062NNB
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 993941563
num_examples: 158526
- name: validation
num_bytes: 276499036
num_examples: 44103
- name: test
num_bytes: 267490925
num_examples: 42664
download_size: 56667593
dataset_size: 1537931524
- config_name: IGF2BP3_HepG2_ENCSR993OLA
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1213520310
num_examples: 193546
- name: validation
num_bytes: 241873191
num_examples: 38580
- name: test
num_bytes: 419468792
num_examples: 66904
download_size: 67207382
dataset_size: 1874862293
- config_name: ILF3_HepG2_ENCSR786TSC
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2550057645
num_examples: 406714
- name: validation
num_bytes: 527215147
num_examples: 84093
- name: test
num_bytes: 856965826
num_examples: 136685
download_size: 137105259
dataset_size: 3934238618
- config_name: ILF3_K562_ENCSR438KWZ
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 3465163455
num_examples: 552673
- name: validation
num_bytes: 1030396695
num_examples: 164353
- name: test
num_bytes: 891213798
num_examples: 142147
download_size: 188737617
dataset_size: 5386773948
- config_name: KHDRBS1_K562_ENCSR628IDK
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 3041124932
num_examples: 485050
- name: validation
num_bytes: 963768852
num_examples: 153725
- name: test
num_bytes: 733483760
num_examples: 116992
download_size: 164248516
dataset_size: 4738377544
- config_name: KHSRP_HepG2_ENCSR366DGX
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 4138098450
num_examples: 660004
- name: validation
num_bytes: 878861327
num_examples: 140182
- name: test
num_bytes: 1529265336
num_examples: 243922
download_size: 228435826
dataset_size: 6546225113
- config_name: KHSRP_K562_5001
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 4016421731
num_examples: 640605
- name: validation
num_bytes: 1288305120
num_examples: 205490
- name: test
num_bytes: 991868815
num_examples: 158206
download_size: 232942025
dataset_size: 6296595666
- config_name: LARP4_K562_ENCSR888YTT
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1212364594
num_examples: 193367
- name: validation
num_bytes: 358453430
num_examples: 57175
- name: test
num_bytes: 273089534
num_examples: 43558
download_size: 67364260
dataset_size: 1843907558
- config_name: LARP7_K562_ENCSR456KXI
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 427367752
num_examples: 68162
- name: validation
num_bytes: 115005372
num_examples: 18344
- name: test
num_bytes: 113394638
num_examples: 18086
download_size: 25157384
dataset_size: 655767762
- config_name: LIN28B_HepG2_ENCSR861GYE
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 639528377
num_examples: 102000
- name: validation
num_bytes: 136096504
num_examples: 21708
- name: test
num_bytes: 213937731
num_examples: 34123
download_size: 37501139
dataset_size: 989562612
- config_name: LIN28B_K562_ENCSR970NKP
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 772945299
num_examples: 123280
- name: validation
num_bytes: 230407027
num_examples: 36751
- name: test
num_bytes: 180218779
num_examples: 28745
download_size: 45059169
dataset_size: 1183571105
- config_name: LSM11_HepG2_ENCSR135VMS
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2233424289
num_examples: 356213
- name: validation
num_bytes: 477566333
num_examples: 76174
- name: test
num_bytes: 811197556
num_examples: 129385
download_size: 127261959
dataset_size: 3522188178
- config_name: LSM11_K562_ENCSR022BVV
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1868991160
num_examples: 298093
- name: validation
num_bytes: 522347612
num_examples: 83317
- name: test
num_bytes: 477246934
num_examples: 76120
download_size: 102698740
dataset_size: 2868585706
- config_name: MATR3_HepG2_ENCSR290VLT
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1800307262
num_examples: 287139
- name: validation
num_bytes: 362585630
num_examples: 57834
- name: test
num_bytes: 633502039
num_examples: 101045
download_size: 98703841
dataset_size: 2796394931
- config_name: MBNL1_K562_4056
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1898566423
num_examples: 302811
- name: validation
num_bytes: 551439532
num_examples: 87957
- name: test
num_bytes: 501705109
num_examples: 80021
download_size: 109351919
dataset_size: 2951711064
- config_name: METAP2_K562_ENCSR303OQD
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1183272665
num_examples: 188725
- name: validation
num_bytes: 340415701
num_examples: 54298
- name: test
num_bytes: 286322869
num_examples: 45668
download_size: 67265241
dataset_size: 1810011235
- config_name: MTPAP_K562_ENCSR200DKE
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 3013179850
num_examples: 480585
- name: validation
num_bytes: 882313263
num_examples: 140733
- name: test
num_bytes: 765391271
num_examples: 122079
download_size: 166192530
dataset_size: 4660884384
- config_name: NCBP2_HepG2_ENCSR018RVZ
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1323546312
num_examples: 211095
- name: validation
num_bytes: 264637684
num_examples: 42211
- name: test
num_bytes: 493032295
num_examples: 78638
download_size: 76165413
dataset_size: 2081216291
- config_name: NCBP2_K562_ENCSR484LTQ
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 559747786
num_examples: 89276
- name: validation
num_bytes: 159894681
num_examples: 25504
- name: test
num_bytes: 136284218
num_examples: 21737
download_size: 32664891
dataset_size: 855926685
- config_name: NCL_K562_5086
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1306647702
num_examples: 208404
- name: validation
num_bytes: 384859635
num_examples: 61387
- name: test
num_bytes: 315234880
num_examples: 50280
download_size: 74435689
dataset_size: 2006742217
- config_name: NIP7_HepG2_ENCSR361OCV
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 168573615
num_examples: 26886
- name: validation
num_bytes: 31961374
num_examples: 5098
- name: test
num_bytes: 54220172
num_examples: 8648
download_size: 10386557
dataset_size: 254755161
- config_name: NIPBL_K562_ENCSR891RIC
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2536791591
num_examples: 404606
- name: validation
num_bytes: 798178793
num_examples: 127313
- name: test
num_bytes: 654822444
num_examples: 104444
download_size: 141058431
dataset_size: 3989792828
- config_name: NKRF_HepG2_ENCSR277DEO
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 3437283807
num_examples: 548219
- name: validation
num_bytes: 691015173
num_examples: 110220
- name: test
num_bytes: 1216483057
num_examples: 194028
download_size: 190042526
dataset_size: 5344782037
- config_name: NKRF_K562_5005
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 4196882713
num_examples: 669376
- name: validation
num_bytes: 1207339137
num_examples: 192576
- name: test
num_bytes: 1092334449
num_examples: 174226
download_size: 236353847
dataset_size: 6496556299
- config_name: NOL12_HepG2_ENCSR820DQJ
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 843939049
num_examples: 134602
- name: validation
num_bytes: 161950964
num_examples: 25832
- name: test
num_bytes: 315080399
num_examples: 50255
download_size: 49122575
dataset_size: 1320970412
- config_name: NOLC1_HepG2_ENCSR194HZU
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1297367375
num_examples: 206920
- name: validation
num_bytes: 259760213
num_examples: 41433
- name: test
num_bytes: 483289422
num_examples: 77084
download_size: 75032512
dataset_size: 2040417010
- config_name: NONO_K562_4001
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 807976140
num_examples: 128865
- name: validation
num_bytes: 161166758
num_examples: 25707
- name: test
num_bytes: 263106336
num_examples: 41964
download_size: 45008540
dataset_size: 1232249234
- config_name: NPM1_K562_ENCSR867DSZ
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 338841222
num_examples: 54043
- name: validation
num_bytes: 94579642
num_examples: 15086
- name: test
num_bytes: 76301502
num_examples: 12170
download_size: 20016252
dataset_size: 509722366
- config_name: NSUN2_HepG2_4215
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 3694550455
num_examples: 589258
- name: validation
num_bytes: 822198425
num_examples: 131144
- name: test
num_bytes: 1190155775
num_examples: 189832
download_size: 208172801
dataset_size: 5706904655
- config_name: NSUN2_K562_ENCSR081JYH
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 861068454
num_examples: 137336
- name: validation
num_bytes: 251954365
num_examples: 40188
- name: test
num_bytes: 200063366
num_examples: 31910
download_size: 48725399
dataset_size: 1313086185
- config_name: PABPC4_K562_ENCSR958FKZ
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1413084170
num_examples: 225379
- name: validation
num_bytes: 414638977
num_examples: 66137
- name: test
num_bytes: 353394196
num_examples: 56366
download_size: 81050514
dataset_size: 2181117343
- config_name: PABPN1_HepG2_5062
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 3041230391
num_examples: 485053
- name: validation
num_bytes: 699887542
num_examples: 111635
- name: test
num_bytes: 963063913
num_examples: 153608
download_size: 169949564
dataset_size: 4704181846
- config_name: PABPN1_HepG2_ENCSR820UYE
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1089803335
num_examples: 173815
- name: validation
num_bytes: 234908129
num_examples: 37469
- name: test
num_bytes: 377337416
num_examples: 60185
download_size: 62696883
dataset_size: 1702048880
- config_name: PARP_HepG2_4214
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2066371464
num_examples: 329572
- name: validation
num_bytes: 445097963
num_examples: 70995
- name: test
num_bytes: 681695884
num_examples: 108731
download_size: 118932140
dataset_size: 3193165311
- config_name: PCBP1_K562_ENCSR922WJV
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 595283658
num_examples: 94944
- name: validation
num_bytes: 166652771
num_examples: 26582
- name: test
num_bytes: 137832104
num_examples: 21984
download_size: 34338965
dataset_size: 899768533
- config_name: PHF6_K562_ENCSR001KKZ
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 784910427
num_examples: 125189
- name: validation
num_bytes: 229208779
num_examples: 36560
- name: test
num_bytes: 185060226
num_examples: 29517
download_size: 44580835
dataset_size: 1199179432
- config_name: PPIG_HepG2_ENCSR097NEE
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2714992089
num_examples: 433020
- name: validation
num_bytes: 594097206
num_examples: 94761
- name: test
num_bytes: 926631348
num_examples: 147797
download_size: 154953661
dataset_size: 4235720643
- config_name: PPIL4_K562_ENCSR197INS
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1985132507
num_examples: 316619
- name: validation
num_bytes: 577206991
num_examples: 92067
- name: test
num_bytes: 460989091
num_examples: 73528
download_size: 107176743
dataset_size: 3023328589
- config_name: PPP1R10_HepG2_4148
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 4348000171
num_examples: 693477
- name: validation
num_bytes: 853073771
num_examples: 136069
- name: test
num_bytes: 1479863058
num_examples: 236039
download_size: 238847958
dataset_size: 6680937000
- config_name: PRK2_K562_5064
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1480186500
num_examples: 236079
- name: validation
num_bytes: 430382443
num_examples: 68648
- name: test
num_bytes: 401905082
num_examples: 64103
download_size: 87200030
dataset_size: 2312474025
- config_name: PRKRA_K562_5068
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1463150870
num_examples: 233361
- name: validation
num_bytes: 410733552
num_examples: 65514
- name: test
num_bytes: 380226477
num_examples: 60645
download_size: 83093213
dataset_size: 2254110899
- config_name: PRPF39_HepG2_4114
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2331683357
num_examples: 371887
- name: validation
num_bytes: 494367999
num_examples: 78854
- name: test
num_bytes: 826139701
num_examples: 131770
download_size: 135614315
dataset_size: 3652191057
- config_name: PRPF39_HepG2_4149
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 3369057184
num_examples: 537340
- name: validation
num_bytes: 659391431
num_examples: 105176
- name: test
num_bytes: 1162133624
num_examples: 185360
download_size: 188994410
dataset_size: 5190582239
- config_name: PRPF39_K562_4068
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 613173061
num_examples: 97797
- name: validation
num_bytes: 164251579
num_examples: 26199
- name: test
num_bytes: 151325311
num_examples: 24136
download_size: 36579237
dataset_size: 928749951
- config_name: PRPF4_HepG2_ENCSR977OXG
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1877731567
num_examples: 299482
- name: validation
num_bytes: 399348629
num_examples: 63698
- name: test
num_bytes: 627246687
num_examples: 100045
download_size: 104850899
dataset_size: 2904326883
- config_name: PRPF8_HepG2_ENCSR121NVA
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2849153239
num_examples: 454416
- name: validation
num_bytes: 581945696
num_examples: 92823
- name: test
num_bytes: 969451257
num_examples: 154626
download_size: 157601253
dataset_size: 4400550192
- config_name: PTBP1_HepG2_ENCSR384KAN
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1443931254
num_examples: 230297
- name: validation
num_bytes: 291564947
num_examples: 46506
- name: test
num_bytes: 530262329
num_examples: 84577
download_size: 82957538
dataset_size: 2265758530
- config_name: PTBP1_K562_5015
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 3743061694
num_examples: 597002
- name: validation
num_bytes: 1174214858
num_examples: 187292
- name: test
num_bytes: 923577588
num_examples: 147312
download_size: 214118046
dataset_size: 5840854140
- config_name: PTBP1_K562_ENCSR981WKN
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1497511147
num_examples: 238845
- name: validation
num_bytes: 442563046
num_examples: 70591
- name: test
num_bytes: 379828232
num_examples: 60582
download_size: 84699069
dataset_size: 2319902425
- config_name: PUM1_K562_ENCSR308YNT
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 849401523
num_examples: 135474
- name: validation
num_bytes: 248688634
num_examples: 39667
- name: test
num_bytes: 202371490
num_examples: 32278
download_size: 49315026
dataset_size: 1300461647
- config_name: PUS1_K562_ENCSR291XPT
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 827262370
num_examples: 131943
- name: validation
num_bytes: 239146042
num_examples: 38145
- name: test
num_bytes: 204108841
num_examples: 32555
download_size: 47530391
dataset_size: 1270517253
- config_name: QKI_HepG2_ENCSR570WLM
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2186056593
num_examples: 348663
- name: validation
num_bytes: 437811784
num_examples: 69833
- name: test
num_bytes: 788117469
num_examples: 125706
download_size: 122748373
dataset_size: 3411985846
- config_name: QKI_K562_5007
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2016794378
num_examples: 321670
- name: validation
num_bytes: 640840879
num_examples: 102217
- name: test
num_bytes: 486635529
num_examples: 77619
download_size: 117403402
dataset_size: 3144270786
- config_name: QKI_K562_ENCSR366YOG
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 963677504
num_examples: 153702
- name: validation
num_bytes: 286141275
num_examples: 45641
- name: test
num_bytes: 224338246
num_examples: 35782
download_size: 54799751
dataset_size: 1474157025
- config_name: RBFOX2_HepG2_ENCSR987FTF
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1334568368
num_examples: 212852
- name: validation
num_bytes: 241591199
num_examples: 38535
- name: test
num_bytes: 469500190
num_examples: 74884
download_size: 75237236
dataset_size: 2045659757
- config_name: RBFOX2_K562_ENCSR756CKJ
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 3446849617
num_examples: 549753
- name: validation
num_bytes: 1010155195
num_examples: 161124
- name: test
num_bytes: 874396966
num_examples: 139466
download_size: 188775626
dataset_size: 5331401778
- config_name: RBM15_HepG2_ENCSR754NDA
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1559244261
num_examples: 248687
- name: validation
num_bytes: 318417363
num_examples: 50789
- name: test
num_bytes: 573955809
num_examples: 91545
download_size: 88287722
dataset_size: 2451617433
- config_name: RBM15_K562_5008
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 4904989312
num_examples: 782317
- name: validation
num_bytes: 1465667621
num_examples: 233780
- name: test
num_bytes: 1247931562
num_examples: 199045
download_size: 282709273
dataset_size: 7618588495
- config_name: RBM22_HepG2_ENCSR456JJQ
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2398416571
num_examples: 382529
- name: validation
num_bytes: 470331339
num_examples: 75020
- name: test
num_bytes: 883754152
num_examples: 140958
download_size: 134738979
dataset_size: 3752502062
- config_name: RBM22_K562_ENCSR295OKT
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 342070561
num_examples: 54558
- name: validation
num_bytes: 97156296
num_examples: 15497
- name: test
num_bytes: 81611876
num_examples: 13017
download_size: 20433052
dataset_size: 520838733
- config_name: RBM5_HepG2_ENCSR489ABS
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2070540476
num_examples: 330237
- name: validation
num_bytes: 399574281
num_examples: 63734
- name: test
num_bytes: 802619242
num_examples: 128018
download_size: 116344110
dataset_size: 3272733999
- config_name: RBM5_K562_5018
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 3271711976
num_examples: 521821
- name: validation
num_bytes: 993420438
num_examples: 158455
- name: test
num_bytes: 820828616
num_examples: 130922
download_size: 186814045
dataset_size: 5085961030
- config_name: RECQ1_K562_4049
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 384756880
num_examples: 61366
- name: validation
num_bytes: 106453785
num_examples: 16980
- name: test
num_bytes: 96609942
num_examples: 15409
download_size: 23332580
dataset_size: 587820607
- config_name: RPS11_K562_ENCSR269AJF
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 312659281
num_examples: 49867
- name: validation
num_bytes: 86931133
num_examples: 13866
- name: test
num_bytes: 69900178
num_examples: 11149
download_size: 18796880
dataset_size: 469490592
- config_name: RPS3_HepG2_ENCSR766FAC
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 986064781
num_examples: 157270
- name: validation
num_bytes: 190539290
num_examples: 30392
- name: test
num_bytes: 351462321
num_examples: 56058
download_size: 57205084
dataset_size: 1528066392
- config_name: RPS3_K562_ENCSR120EAR
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1565882489
num_examples: 249751
- name: validation
num_bytes: 468186142
num_examples: 74678
- name: test
num_bytes: 355233299
num_examples: 56660
download_size: 86304109
dataset_size: 2389301930
- config_name: SAFB_HepG2_ENCSR337XGI
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 3445132892
num_examples: 549479
- name: validation
num_bytes: 718419622
num_examples: 114591
- name: test
num_bytes: 1214611936
num_examples: 193733
download_size: 187143457
dataset_size: 5378164450
- config_name: SAFB_K562_ENCSR484LAB
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 3601691031
num_examples: 574455
- name: validation
num_bytes: 1116228958
num_examples: 178043
- name: test
num_bytes: 900088348
num_examples: 143565
download_size: 195036921
dataset_size: 5618008337
- config_name: SBDS_K562_ENCSR059CWF
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 128777566
num_examples: 20539
- name: validation
num_bytes: 33058334
num_examples: 5273
- name: test
num_bytes: 26527028
num_examples: 4231
download_size: 8111775
dataset_size: 188362928
- config_name: SDAD1_HepG2_ENCSR050BDZ
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 602256782
num_examples: 96055
- name: validation
num_bytes: 114911606
num_examples: 18329
- name: test
num_bytes: 221840156
num_examples: 35383
download_size: 35287059
dataset_size: 939008544
- config_name: SERBP1_K562_ENCSR121GQH
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 247663135
num_examples: 39501
- name: validation
num_bytes: 71659124
num_examples: 11430
- name: test
num_bytes: 51786608
num_examples: 8260
download_size: 14699545
dataset_size: 371108867
- config_name: SF3A1_HepG2_4117
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1845268851
num_examples: 294308
- name: validation
num_bytes: 399913076
num_examples: 63788
- name: test
num_bytes: 662120388
num_examples: 105609
download_size: 108256367
dataset_size: 2907302315
- config_name: SF3A1_K562_4048
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 481760316
num_examples: 76837
- name: validation
num_bytes: 128985952
num_examples: 20574
- name: test
num_bytes: 129094007
num_examples: 20590
download_size: 29134314
dataset_size: 739840275
- config_name: SF3A3_HepG2_ENCSR331MIC
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1692115967
num_examples: 269880
- name: validation
num_bytes: 323319053
num_examples: 51571
- name: test
num_bytes: 643481910
num_examples: 102635
download_size: 95565389
dataset_size: 2658916930
- config_name: SF3B1_K562_ENCSR133QEA
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 3402870651
num_examples: 542745
- name: validation
num_bytes: 1091073874
num_examples: 174031
- name: test
num_bytes: 804923844
num_examples: 128387
download_size: 181990141
dataset_size: 5298868369
- config_name: SF3B4_HepG2_ENCSR279UJF
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 650741614
num_examples: 103787
- name: validation
num_bytes: 119281398
num_examples: 19026
- name: test
num_bytes: 218758525
num_examples: 34891
download_size: 36577459
dataset_size: 988781537
- config_name: SFPQ_HepG2_ENCSR965DLL
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2832988926
num_examples: 451844
- name: validation
num_bytes: 532405522
num_examples: 84921
- name: test
num_bytes: 1031811058
num_examples: 164575
download_size: 150182051
dataset_size: 4397205506
- config_name: SLBP_K562_ENCSR483NOP
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 116833582
num_examples: 18634
- name: validation
num_bytes: 27848569
num_examples: 4442
- name: test
num_bytes: 24176064
num_examples: 3856
download_size: 7149218
dataset_size: 168858215
- config_name: SLTM_HepG2_ENCSR351PVI
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1752215375
num_examples: 279465
- name: validation
num_bytes: 312573156
num_examples: 49857
- name: test
num_bytes: 657673582
num_examples: 104898
download_size: 96660130
dataset_size: 2722462113
- config_name: SLTM_K562_ENCSR000SSH
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1434240601
num_examples: 228751
- name: validation
num_bytes: 371279901
num_examples: 59221
- name: test
num_bytes: 408461341
num_examples: 65148
download_size: 80101393
dataset_size: 2213981843
- config_name: SMNDC1_K562_ENCSR658IQB
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1418609098
num_examples: 226258
- name: validation
num_bytes: 388150313
num_examples: 61912
- name: test
num_bytes: 379568091
num_examples: 60540
download_size: 79052893
dataset_size: 2186327502
- config_name: SND1_HepG2_ENCSR061EVO
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 926390334
num_examples: 147752
- name: validation
num_bytes: 178872097
num_examples: 28531
- name: test
num_bytes: 329498011
num_examples: 52554
download_size: 54211058
dataset_size: 1434760442
- config_name: SND1_K562_ENCSR128VXC
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2773046011
num_examples: 442287
- name: validation
num_bytes: 848502295
num_examples: 135340
- name: test
num_bytes: 688403123
num_examples: 109800
download_size: 155365058
dataset_size: 4309951429
- config_name: SNRNP200_HepG2_4212
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2282160015
num_examples: 363990
- name: validation
num_bytes: 486262552
num_examples: 77561
- name: test
num_bytes: 800143259
num_examples: 127624
download_size: 130395476
dataset_size: 3568565826
- config_name: SNRPA1_HepG2_4203
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1059498635
num_examples: 168982
- name: validation
num_bytes: 235680395
num_examples: 37592
- name: test
num_bytes: 341956299
num_examples: 54542
download_size: 63240844
dataset_size: 1637135329
- config_name: SNRPC_HepG2_4187
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1550806204
num_examples: 247342
- name: validation
num_bytes: 318749426
num_examples: 50842
- name: test
num_bytes: 543131153
num_examples: 86629
download_size: 90584176
dataset_size: 2412686783
- config_name: SNRPC_K562_4164
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1738571203
num_examples: 277292
- name: validation
num_bytes: 515922875
num_examples: 82292
- name: test
num_bytes: 435950314
num_examples: 69534
download_size: 100214371
dataset_size: 2690444392
- config_name: SNRPD3_HepG2_4204
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 977213254
num_examples: 155858
- name: validation
num_bytes: 216652496
num_examples: 34557
- name: test
num_bytes: 318577842
num_examples: 50813
download_size: 59386744
dataset_size: 1512443592
- config_name: SRSF1_HepG2_ENCSR989VIY
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1495853265
num_examples: 238576
- name: validation
num_bytes: 305859743
num_examples: 48786
- name: test
num_bytes: 514333353
num_examples: 82035
download_size: 83884021
dataset_size: 2316046361
- config_name: SRSF1_K562_ENCSR432XUP
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1346531551
num_examples: 214763
- name: validation
num_bytes: 379374300
num_examples: 60512
- name: test
num_bytes: 346706994
num_examples: 55299
download_size: 75637273
dataset_size: 2072612845
- config_name: SRSF7_K562_ENCSR468FSW
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 458677782
num_examples: 73156
- name: validation
num_bytes: 134441051
num_examples: 21444
- name: test
num_bytes: 111900948
num_examples: 17848
download_size: 26828585
dataset_size: 705019781
- config_name: SRSF9_HepG2_ENCSR773KRC
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 734434167
num_examples: 117136
- name: validation
num_bytes: 135663578
num_examples: 21639
- name: test
num_bytes: 269773045
num_examples: 43028
download_size: 41448442
dataset_size: 1139870790
- config_name: SSB_HepG2_ENCSR352STY
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1087598644
num_examples: 173463
- name: validation
num_bytes: 221798775
num_examples: 35378
- name: test
num_bytes: 405128081
num_examples: 64617
download_size: 63013003
dataset_size: 1714525500
- config_name: SSB_K562_ENCSR356MSW
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 202322089
num_examples: 32269
- name: validation
num_bytes: 57716019
num_examples: 9206
- name: test
num_bytes: 45448707
num_examples: 7249
download_size: 12850809
dataset_size: 305486815
- config_name: STAU2_HepG2_ENCSR979EWD
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 4076276773
num_examples: 650135
- name: validation
num_bytes: 824001825
num_examples: 131432
- name: test
num_bytes: 1449082807
num_examples: 231128
download_size: 220027262
dataset_size: 6349361405
- config_name: SUB1_HepG2_ENCSR406OOZ
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 267071793
num_examples: 42596
- name: validation
num_bytes: 82191820
num_examples: 13110
- name: test
num_bytes: 66847444
num_examples: 10662
download_size: 16189010
dataset_size: 416111057
- config_name: SUGP2_HepG2_ENCSR506UPY
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 6763959004
num_examples: 1078814
- name: validation
num_bytes: 1511780482
num_examples: 241135
- name: test
num_bytes: 2209387040
num_examples: 352403
download_size: 360278576
dataset_size: 10485126526
- config_name: SUPV3L1_HepG2_ENCSR580MFX
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1521052487
num_examples: 242597
- name: validation
num_bytes: 308310292
num_examples: 49177
- name: test
num_bytes: 582890478
num_examples: 92971
download_size: 86390797
dataset_size: 2412253257
- config_name: SUPV3L1_K562_ENCSR580OFI
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 5341065841
num_examples: 851874
- name: validation
num_bytes: 1682917420
num_examples: 268432
- name: test
num_bytes: 1342561595
num_examples: 214140
download_size: 287509214
dataset_size: 8366544856
- config_name: TAF15_HepG2_ENCSR841EQA
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 4015148734
num_examples: 640391
- name: validation
num_bytes: 797953848
num_examples: 127277
- name: test
num_bytes: 1436876891
num_examples: 229184
download_size: 214350530
dataset_size: 6249979473
- config_name: TAF15_K562_5013
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 3494725194
num_examples: 557392
- name: validation
num_bytes: 1035576825
num_examples: 165179
- name: test
num_bytes: 885172957
num_examples: 141185
download_size: 193051903
dataset_size: 5415474976
- config_name: TAF15_K562_ENCSR568DZW
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2017919023
num_examples: 321848
- name: validation
num_bytes: 592433900
num_examples: 94496
- name: test
num_bytes: 542907413
num_examples: 86593
download_size: 111484222
dataset_size: 3153260336
- config_name: TARDBP_K562_ENCSR584TCR
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 662971162
num_examples: 105740
- name: validation
num_bytes: 196382936
num_examples: 31324
- name: test
num_bytes: 163730530
num_examples: 26115
download_size: 38257435
dataset_size: 1023084628
- config_name: TBRG4_K562_ENCSR506OTC
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1274305990
num_examples: 203245
- name: validation
num_bytes: 374960219
num_examples: 59808
- name: test
num_bytes: 314791924
num_examples: 50209
download_size: 71557529
dataset_size: 1964058133
- config_name: TFAM_K562_5069
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 871339203
num_examples: 138972
- name: validation
num_bytes: 254318079
num_examples: 40565
- name: test
num_bytes: 217368978
num_examples: 34670
download_size: 52048514
dataset_size: 1343026260
- config_name: TIA1_HepG2_ENCSR623VEQ
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1000721859
num_examples: 159608
- name: validation
num_bytes: 194890902
num_examples: 31086
- name: test
num_bytes: 376157603
num_examples: 59997
download_size: 56266973
dataset_size: 1571770364
- config_name: TIAL1_HepG2_ENCSR322HHA
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 527477655
num_examples: 84129
- name: validation
num_bytes: 109087550
num_examples: 17400
- name: test
num_bytes: 193278090
num_examples: 30828
download_size: 31070376
dataset_size: 829843295
- config_name: TRA2A_HepG2_ENCSR314UMJ
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 248224949
num_examples: 39590
- name: validation
num_bytes: 45929661
num_examples: 7326
- name: test
num_bytes: 88972236
num_examples: 14191
download_size: 14670424
dataset_size: 383126846
- config_name: TRA2A_K562_ENCSR365NVO
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 726715888
num_examples: 115906
- name: validation
num_bytes: 206978368
num_examples: 33014
- name: test
num_bytes: 165519297
num_examples: 26400
download_size: 41679835
dataset_size: 1099213553
- config_name: TROVE2_HepG2_ENCSR993FMY
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 3023543750
num_examples: 482236
- name: validation
num_bytes: 605575292
num_examples: 96592
- name: test
num_bytes: 1120681271
num_examples: 178750
download_size: 167530460
dataset_size: 4749800313
- config_name: TROVE2_K562_ENCSR539ZTS
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2757395291
num_examples: 439792
- name: validation
num_bytes: 847009859
num_examples: 135102
- name: test
num_bytes: 669195881
num_examples: 106737
download_size: 151380517
dataset_size: 4273601031
- config_name: U2AF1_K562_ENCSR862QCH
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 733635846
num_examples: 117010
- name: validation
num_bytes: 203028128
num_examples: 32384
- name: test
num_bytes: 164163851
num_examples: 26184
download_size: 41406480
dataset_size: 1100827825
- config_name: U2AF2_HepG2_ENCSR202BFN
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 3561395753
num_examples: 568021
- name: validation
num_bytes: 716412835
num_examples: 114271
- name: test
num_bytes: 1310921776
num_examples: 209094
download_size: 198382533
dataset_size: 5588730364
- config_name: U2AF2_K562_ENCSR893RAV
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1690382370
num_examples: 269606
- name: validation
num_bytes: 493716712
num_examples: 78750
- name: test
num_bytes: 406418668
num_examples: 64824
download_size: 92442867
dataset_size: 2590517750
- config_name: UBAP2L_K562_5090
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 4380554108
num_examples: 698676
- name: validation
num_bytes: 1350121536
num_examples: 215350
- name: test
num_bytes: 1103982820
num_examples: 176086
download_size: 251770297
dataset_size: 6834658464
- config_name: UCHL5_HepG2_ENCSR490IEE
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 3334910252
num_examples: 531892
- name: validation
num_bytes: 756463939
num_examples: 120659
- name: test
num_bytes: 1121965383
num_examples: 178953
download_size: 184699531
dataset_size: 5213339574
- config_name: UPF1_HepG2_ENCSR539BEV
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 651834360
num_examples: 103962
- name: validation
num_bytes: 140898747
num_examples: 22474
- name: test
num_bytes: 215105107
num_examples: 34309
download_size: 39363320
dataset_size: 1007838214
- config_name: UPF1_K562_5002
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 5015691881
num_examples: 799977
- name: validation
num_bytes: 1569032161
num_examples: 250267
- name: test
num_bytes: 1257555476
num_examples: 200581
download_size: 302678603
dataset_size: 7842279518
- config_name: USP10_K562_5089
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
sequence: float64
- name: control
sequence: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 3120930835
num_examples: 497773
- name: validation
num_bytes: 968481190
num_examples: 154477
- name: test
num_bytes: 769871269
num_examples: 122795
download_size: 179752765
dataset_size: 4859283294
- config_name: UTP18_HepG2_ENCSR488JKQ
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1134172218
num_examples: 180892
- name: validation
num_bytes: 224356616
num_examples: 35786
- name: test
num_bytes: 433023731
num_examples: 69067
download_size: 65271067
dataset_size: 1791552565
- config_name: UTP18_K562_ENCSR964VOX
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 499398553
num_examples: 79651
- name: validation
num_bytes: 140998569
num_examples: 22490
- name: test
num_bytes: 124177150
num_examples: 19806
download_size: 29304214
dataset_size: 764574272
- config_name: UTP3_K562_ENCSR734ZHL
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1748508177
num_examples: 278879
- name: validation
num_bytes: 529206451
num_examples: 84411
- name: test
num_bytes: 409835538
num_examples: 65369
download_size: 93480888
dataset_size: 2687550166
- config_name: WDR3_K562_ENCSR202HKN
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1004237328
num_examples: 160171
- name: validation
num_bytes: 302818230
num_examples: 48301
- name: test
num_bytes: 239210457
num_examples: 38154
download_size: 56314049
dataset_size: 1546266015
- config_name: WDR43_HepG2_ENCSR085JPB
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 501923912
num_examples: 80053
- name: validation
num_bytes: 91332396
num_examples: 14568
- name: test
num_bytes: 197118332
num_examples: 31440
download_size: 29571252
dataset_size: 790374640
- config_name: WDR43_K562_ENCSR349CMI
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1082929154
num_examples: 172722
- name: validation
num_bytes: 311952746
num_examples: 49758
- name: test
num_bytes: 247574470
num_examples: 39488
download_size: 60395934
dataset_size: 1642456370
- config_name: WRN_K562_ENCSR038JME
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2036474967
num_examples: 324809
- name: validation
num_bytes: 627191466
num_examples: 100040
- name: test
num_bytes: 508432348
num_examples: 81095
download_size: 113371855
dataset_size: 3172098781
- config_name: XPO5_HepG2_ENCSR921SXC
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 2658459159
num_examples: 424005
- name: validation
num_bytes: 546874472
num_examples: 87229
- name: test
num_bytes: 991354288
num_examples: 158121
download_size: 149064572
dataset_size: 4196687919
- config_name: XRCC6_HepG2_ENCSR571ROL
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 886615211
num_examples: 141408
- name: validation
num_bytes: 158001143
num_examples: 25202
- name: test
num_bytes: 355721719
num_examples: 56737
download_size: 51273520
dataset_size: 1400338073
- config_name: XRCC6_K562_ENCSR258QKO
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 3131293405
num_examples: 499427
- name: validation
num_bytes: 978957717
num_examples: 156148
- name: test
num_bytes: 754178179
num_examples: 120292
download_size: 172693694
dataset_size: 4864429301
- config_name: XRN2_K562_ENCSR657TZB
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1038079027
num_examples: 165566
- name: validation
num_bytes: 274191647
num_examples: 43735
- name: test
num_bytes: 285611839
num_examples: 45554
download_size: 58338795
dataset_size: 1597882513
- config_name: YWHAG_K562_ENCSR867ZVK
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 579295278
num_examples: 92393
- name: validation
num_bytes: 144232939
num_examples: 23006
- name: test
num_bytes: 172707606
num_examples: 27546
download_size: 33058535
dataset_size: 896235823
- config_name: ZC3H11A_HepG2_ENCSR907GUB
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 3834381587
num_examples: 611560
- name: validation
num_bytes: 818548410
num_examples: 130562
- name: test
num_bytes: 1386219757
num_examples: 221104
download_size: 212608924
dataset_size: 6039149754
- config_name: ZC3H11A_K562_ENCSR712IAG
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 1579504788
num_examples: 251923
- name: validation
num_bytes: 472995483
num_examples: 75445
- name: test
num_bytes: 389481220
num_examples: 62122
download_size: 88255864
dataset_size: 2441981491
- config_name: ZC3H8_K562_ENCSR181NRW
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 121053411
num_examples: 19307
- name: validation
num_bytes: 29071141
num_examples: 4637
- name: test
num_bytes: 29881655
num_examples: 4766
download_size: 7856025
dataset_size: 180006207
- config_name: ZNF800_HepG2_ENCSR685AUR
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 949670101
num_examples: 151465
- name: validation
num_bytes: 197241886
num_examples: 31461
- name: test
num_bytes: 341105655
num_examples: 54406
download_size: 55322743
dataset_size: 1488017642
- config_name: ZNF800_K562_ENCSR586DGV
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 695865807
num_examples: 110986
- name: validation
num_bytes: 200959604
num_examples: 32054
- name: test
num_bytes: 170095555
num_examples: 27130
download_size: 41089194
dataset_size: 1066920966
- config_name: ZRANB2_K562_ENCSR663NRA
features:
- name: chrom
dtype: string
- name: chromStart
dtype: int64
- name: chromEnd
dtype: int64
- name: strand
dtype: string
- name: name
dtype: int64
- name: rep
dtype: int64
- name: gc_fraction
dtype: float64
- name: n_IP
dtype: int64
- name: n_IN
dtype: int64
- name: train_test
dtype: bool
- name: train_val
dtype: bool
- name: signal
list: float64
- name: control
list: float64
- name: seq
dtype: string
splits:
- name: train
num_bytes: 520222143
num_examples: 82972
- name: validation
num_bytes: 145543645
num_examples: 23215
- name: test
num_bytes: 124439994
num_examples: 19848
download_size: 30176574
dataset_size: 790205782
configs:
- config_name: AARS_K562_ENCSR825SVO
data_files:
- split: train
path: AARS_K562_ENCSR825SVO/train-*
- split: validation
path: AARS_K562_ENCSR825SVO/validation-*
- split: test
path: AARS_K562_ENCSR825SVO/test-*
- config_name: AATF_K562_ENCSR819XBT
data_files:
- split: train
path: AATF_K562_ENCSR819XBT/train-*
- split: validation
path: AATF_K562_ENCSR819XBT/validation-*
- split: test
path: AATF_K562_ENCSR819XBT/test-*
- config_name: ABCF1_K562_ENCSR089BXO
data_files:
- split: train
path: ABCF1_K562_ENCSR089BXO/train-*
- split: validation
path: ABCF1_K562_ENCSR089BXO/validation-*
- split: test
path: ABCF1_K562_ENCSR089BXO/test-*
- config_name: AGGF1_HepG2_ENCSR543TPH
data_files:
- split: train
path: AGGF1_HepG2_ENCSR543TPH/train-*
- split: validation
path: AGGF1_HepG2_ENCSR543TPH/validation-*
- split: test
path: AGGF1_HepG2_ENCSR543TPH/test-*
- config_name: AGGF1_K562_ENCSR725ARB
data_files:
- split: train
path: AGGF1_K562_ENCSR725ARB/train-*
- split: validation
path: AGGF1_K562_ENCSR725ARB/validation-*
- split: test
path: AGGF1_K562_ENCSR725ARB/test-*
- config_name: AGO2_K562_4116
data_files:
- split: train
path: AGO2_K562_4116/train-*
- split: validation
path: AGO2_K562_4116/validation-*
- split: test
path: AGO2_K562_4116/test-*
- config_name: AKAP1_K562_ENCSR177QQY
data_files:
- split: train
path: AKAP1_K562_ENCSR177QQY/train-*
- split: validation
path: AKAP1_K562_ENCSR177QQY/validation-*
- split: test
path: AKAP1_K562_ENCSR177QQY/test-*
- config_name: AKAP8L_K562_ENCSR206RXT
data_files:
- split: train
path: AKAP8L_K562_ENCSR206RXT/train-*
- split: validation
path: AKAP8L_K562_ENCSR206RXT/validation-*
- split: test
path: AKAP8L_K562_ENCSR206RXT/test-*
- config_name: APEX1_HepG2_4081
data_files:
- split: train
path: APEX1_HepG2_4081/train-*
- split: validation
path: APEX1_HepG2_4081/validation-*
- split: test
path: APEX1_HepG2_4081/test-*
- config_name: APEX1_K562_4028
data_files:
- split: train
path: APEX1_K562_4028/train-*
- split: validation
path: APEX1_K562_4028/validation-*
- split: test
path: APEX1_K562_4028/test-*
- config_name: APOBEC3C_K562_ENCSR739VVT
data_files:
- split: train
path: APOBEC3C_K562_ENCSR739VVT/train-*
- split: validation
path: APOBEC3C_K562_ENCSR739VVT/validation-*
- split: test
path: APOBEC3C_K562_ENCSR739VVT/test-*
- config_name: BCCIP_HepG2_ENCSR485QCG
data_files:
- split: train
path: BCCIP_HepG2_ENCSR485QCG/train-*
- split: validation
path: BCCIP_HepG2_ENCSR485QCG/validation-*
- split: test
path: BCCIP_HepG2_ENCSR485QCG/test-*
- config_name: BCLAF1_HepG2_ENCSR876EYA
data_files:
- split: train
path: BCLAF1_HepG2_ENCSR876EYA/train-*
- split: validation
path: BCLAF1_HepG2_ENCSR876EYA/validation-*
- split: test
path: BCLAF1_HepG2_ENCSR876EYA/test-*
- config_name: BUD13_HepG2_ENCSR830BSQ
data_files:
- split: train
path: BUD13_HepG2_ENCSR830BSQ/train-*
- split: validation
path: BUD13_HepG2_ENCSR830BSQ/validation-*
- split: test
path: BUD13_HepG2_ENCSR830BSQ/test-*
- config_name: CACTIN_HepG2_4190
data_files:
- split: train
path: CACTIN_HepG2_4190/train-*
- split: validation
path: CACTIN_HepG2_4190/validation-*
- split: test
path: CACTIN_HepG2_4190/test-*
- config_name: CACTIN_K562_4158
data_files:
- split: train
path: CACTIN_K562_4158/train-*
- split: validation
path: CACTIN_K562_4158/validation-*
- split: test
path: CACTIN_K562_4158/test-*
- config_name: CDC40_HepG2_ENCSR815VVI
data_files:
- split: train
path: CDC40_HepG2_ENCSR815VVI/train-*
- split: validation
path: CDC40_HepG2_ENCSR815VVI/validation-*
- split: test
path: CDC40_HepG2_ENCSR815VVI/test-*
- config_name: CDC40_K562_5006
data_files:
- split: train
path: CDC40_K562_5006/train-*
- split: validation
path: CDC40_K562_5006/validation-*
- split: test
path: CDC40_K562_5006/test-*
- config_name: CDK9_HepG2_5063
data_files:
- split: train
path: CDK9_HepG2_5063/train-*
- split: validation
path: CDK9_HepG2_5063/validation-*
- split: test
path: CDK9_HepG2_5063/test-*
- config_name: CNOT2_HepG2_4191
data_files:
- split: train
path: CNOT2_HepG2_4191/train-*
- split: validation
path: CNOT2_HepG2_4191/validation-*
- split: test
path: CNOT2_HepG2_4191/test-*
- config_name: CPEB4_K562_ENCSR046JHH
data_files:
- split: train
path: CPEB4_K562_ENCSR046JHH/train-*
- split: validation
path: CPEB4_K562_ENCSR046JHH/validation-*
- split: test
path: CPEB4_K562_ENCSR046JHH/test-*
- config_name: CPSF6_K562_ENCSR532VUB
data_files:
- split: train
path: CPSF6_K562_ENCSR532VUB/train-*
- split: validation
path: CPSF6_K562_ENCSR532VUB/validation-*
- split: test
path: CPSF6_K562_ENCSR532VUB/test-*
- config_name: CSTF2_HepG2_ENCSR384MWO
data_files:
- split: train
path: CSTF2_HepG2_ENCSR384MWO/train-*
- split: validation
path: CSTF2_HepG2_ENCSR384MWO/validation-*
- split: test
path: CSTF2_HepG2_ENCSR384MWO/test-*
- config_name: CXXC1_K562_4088
data_files:
- split: train
path: CXXC1_K562_4088/train-*
- split: validation
path: CXXC1_K562_4088/validation-*
- split: test
path: CXXC1_K562_4088/test-*
- config_name: DDX21_K562_ENCSR040QLV
data_files:
- split: train
path: DDX21_K562_ENCSR040QLV/train-*
- split: validation
path: DDX21_K562_ENCSR040QLV/validation-*
- split: test
path: DDX21_K562_ENCSR040QLV/test-*
- config_name: DDX3X_HepG2_ENCSR648LAH
data_files:
- split: train
path: DDX3X_HepG2_ENCSR648LAH/train-*
- split: validation
path: DDX3X_HepG2_ENCSR648LAH/validation-*
- split: test
path: DDX3X_HepG2_ENCSR648LAH/test-*
- config_name: DDX3X_K562_ENCSR930BZL
data_files:
- split: train
path: DDX3X_K562_ENCSR930BZL/train-*
- split: validation
path: DDX3X_K562_ENCSR930BZL/validation-*
- split: test
path: DDX3X_K562_ENCSR930BZL/test-*
- config_name: DDX41_K562_5081
data_files:
- split: train
path: DDX41_K562_5081/train-*
- split: validation
path: DDX41_K562_5081/validation-*
- split: test
path: DDX41_K562_5081/test-*
- config_name: DDX42_K562_ENCSR576SHT
data_files:
- split: train
path: DDX42_K562_ENCSR576SHT/train-*
- split: validation
path: DDX42_K562_ENCSR576SHT/validation-*
- split: test
path: DDX42_K562_ENCSR576SHT/test-*
- config_name: DDX51_K562_ENCSR145NLR
data_files:
- split: train
path: DDX51_K562_ENCSR145NLR/train-*
- split: validation
path: DDX51_K562_ENCSR145NLR/validation-*
- split: test
path: DDX51_K562_ENCSR145NLR/test-*
- config_name: DDX52_HepG2_ENCSR970FEW
data_files:
- split: train
path: DDX52_HepG2_ENCSR970FEW/train-*
- split: validation
path: DDX52_HepG2_ENCSR970FEW/validation-*
- split: test
path: DDX52_HepG2_ENCSR970FEW/test-*
- config_name: DDX52_K562_ENCSR154CSN
data_files:
- split: train
path: DDX52_K562_ENCSR154CSN/train-*
- split: validation
path: DDX52_K562_ENCSR154CSN/validation-*
- split: test
path: DDX52_K562_ENCSR154CSN/test-*
- config_name: DDX55_HepG2_ENCSR845VGB
data_files:
- split: train
path: DDX55_HepG2_ENCSR845VGB/train-*
- split: validation
path: DDX55_HepG2_ENCSR845VGB/validation-*
- split: test
path: DDX55_HepG2_ENCSR845VGB/test-*
- config_name: DDX55_K562_ENCSR923NKN
data_files:
- split: train
path: DDX55_K562_ENCSR923NKN/train-*
- split: validation
path: DDX55_K562_ENCSR923NKN/validation-*
- split: test
path: DDX55_K562_ENCSR923NKN/test-*
- config_name: DDX59_HepG2_ENCSR214BZA
data_files:
- split: train
path: DDX59_HepG2_ENCSR214BZA/train-*
- split: validation
path: DDX59_HepG2_ENCSR214BZA/validation-*
- split: test
path: DDX59_HepG2_ENCSR214BZA/test-*
- config_name: DDX5_K562_5094
data_files:
- split: train
path: DDX5_K562_5094/train-*
- split: validation
path: DDX5_K562_5094/validation-*
- split: test
path: DDX5_K562_5094/test-*
- config_name: DDX6_HepG2_ENCSR141OIM
data_files:
- split: train
path: DDX6_HepG2_ENCSR141OIM/train-*
- split: validation
path: DDX6_HepG2_ENCSR141OIM/validation-*
- split: test
path: DDX6_HepG2_ENCSR141OIM/test-*
- config_name: DDX6_K562_ENCSR893EFU
data_files:
- split: train
path: DDX6_K562_ENCSR893EFU/train-*
- split: validation
path: DDX6_K562_ENCSR893EFU/validation-*
- split: test
path: DDX6_K562_ENCSR893EFU/test-*
- config_name: DEK_HepG2_4020
data_files:
- split: train
path: DEK_HepG2_4020/train-*
- split: validation
path: DEK_HepG2_4020/validation-*
- split: test
path: DEK_HepG2_4020/test-*
- config_name: DEK_HepG2_4146
data_files:
- split: train
path: DEK_HepG2_4146/train-*
- split: validation
path: DEK_HepG2_4146/validation-*
- split: test
path: DEK_HepG2_4146/test-*
- config_name: DGCR8_HepG2_ENCSR061SZV
data_files:
- split: train
path: DGCR8_HepG2_ENCSR061SZV/train-*
- split: validation
path: DGCR8_HepG2_ENCSR061SZV/validation-*
- split: test
path: DGCR8_HepG2_ENCSR061SZV/test-*
- config_name: DGCR8_K562_ENCSR947JVR
data_files:
- split: train
path: DGCR8_K562_ENCSR947JVR/train-*
- split: validation
path: DGCR8_K562_ENCSR947JVR/validation-*
- split: test
path: DGCR8_K562_ENCSR947JVR/test-*
- config_name: DHX30_HepG2_ENCSR565DGW
data_files:
- split: train
path: DHX30_HepG2_ENCSR565DGW/train-*
- split: validation
path: DHX30_HepG2_ENCSR565DGW/validation-*
- split: test
path: DHX30_HepG2_ENCSR565DGW/test-*
- config_name: DHX30_K562_ENCSR529GSJ
data_files:
- split: train
path: DHX30_K562_ENCSR529GSJ/train-*
- split: validation
path: DHX30_K562_ENCSR529GSJ/validation-*
- split: test
path: DHX30_K562_ENCSR529GSJ/test-*
- config_name: DHX38_HepG2_4202
data_files:
- split: train
path: DHX38_HepG2_4202/train-*
- split: validation
path: DHX38_HepG2_4202/validation-*
- split: test
path: DHX38_HepG2_4202/test-*
- config_name: DKC1_HepG2_ENCSR301TFY
data_files:
- split: train
path: DKC1_HepG2_ENCSR301TFY/train-*
- split: validation
path: DKC1_HepG2_ENCSR301TFY/validation-*
- split: test
path: DKC1_HepG2_ENCSR301TFY/test-*
- config_name: DNAJC2_K562_5084
data_files:
- split: train
path: DNAJC2_K562_5084/train-*
- split: validation
path: DNAJC2_K562_5084/validation-*
- split: test
path: DNAJC2_K562_5084/test-*
- config_name: DROSHA_HepG2_ENCSR834YLD
data_files:
- split: train
path: DROSHA_HepG2_ENCSR834YLD/train-*
- split: validation
path: DROSHA_HepG2_ENCSR834YLD/validation-*
- split: test
path: DROSHA_HepG2_ENCSR834YLD/test-*
- config_name: DROSHA_K562_ENCSR653HQC
data_files:
- split: train
path: DROSHA_K562_ENCSR653HQC/train-*
- split: validation
path: DROSHA_K562_ENCSR653HQC/validation-*
- split: test
path: DROSHA_K562_ENCSR653HQC/test-*
- config_name: EFTUD2_HepG2_ENCSR527DXF
data_files:
- split: train
path: EFTUD2_HepG2_ENCSR527DXF/train-*
- split: validation
path: EFTUD2_HepG2_ENCSR527DXF/validation-*
- split: test
path: EFTUD2_HepG2_ENCSR527DXF/test-*
- config_name: EFTUD2_K562_ENCSR844RVX
data_files:
- split: train
path: EFTUD2_K562_ENCSR844RVX/train-*
- split: validation
path: EFTUD2_K562_ENCSR844RVX/validation-*
- split: test
path: EFTUD2_K562_ENCSR844RVX/test-*
- config_name: EIF2B4_K562_5019
data_files:
- split: train
path: EIF2B4_K562_5019/train-*
- split: validation
path: EIF2B4_K562_5019/validation-*
- split: test
path: EIF2B4_K562_5019/test-*
- config_name: EIF2B5_K562_5020
data_files:
- split: train
path: EIF2B5_K562_5020/train-*
- split: validation
path: EIF2B5_K562_5020/validation-*
- split: test
path: EIF2B5_K562_5020/test-*
- config_name: EIF2S2_K562_5023
data_files:
- split: train
path: EIF2S2_K562_5023/train-*
- split: validation
path: EIF2S2_K562_5023/validation-*
- split: test
path: EIF2S2_K562_5023/test-*
- config_name: EIF3B_K562_5061
data_files:
- split: train
path: EIF3B_K562_5061/train-*
- split: validation
path: EIF3B_K562_5061/validation-*
- split: test
path: EIF3B_K562_5061/test-*
- config_name: EIF3C_K562_5060
data_files:
- split: train
path: EIF3C_K562_5060/train-*
- split: validation
path: EIF3C_K562_5060/validation-*
- split: test
path: EIF3C_K562_5060/test-*
- config_name: EIF3D_HepG2_ENCSR041NUV
data_files:
- split: train
path: EIF3D_HepG2_ENCSR041NUV/train-*
- split: validation
path: EIF3D_HepG2_ENCSR041NUV/validation-*
- split: test
path: EIF3D_HepG2_ENCSR041NUV/test-*
- config_name: EIF3G_K562_ENCSR023PKW
data_files:
- split: train
path: EIF3G_K562_ENCSR023PKW/train-*
- split: validation
path: EIF3G_K562_ENCSR023PKW/validation-*
- split: test
path: EIF3G_K562_ENCSR023PKW/test-*
- config_name: EIF3H_HepG2_ENCSR916XIV
data_files:
- split: train
path: EIF3H_HepG2_ENCSR916XIV/train-*
- split: validation
path: EIF3H_HepG2_ENCSR916XIV/validation-*
- split: test
path: EIF3H_HepG2_ENCSR916XIV/test-*
- config_name: EIF4E_HepG2_4082
data_files:
- split: train
path: EIF4E_HepG2_4082/train-*
- split: validation
path: EIF4E_HepG2_4082/validation-*
- split: test
path: EIF4E_HepG2_4082/test-*
- config_name: EIF4G2_K562_5065
data_files:
- split: train
path: EIF4G2_K562_5065/train-*
- split: validation
path: EIF4G2_K562_5065/validation-*
- split: test
path: EIF4G2_K562_5065/test-*
- config_name: EIF4G2_K562_ENCSR307YIW
data_files:
- split: train
path: EIF4G2_K562_ENCSR307YIW/train-*
- split: validation
path: EIF4G2_K562_ENCSR307YIW/validation-*
- split: test
path: EIF4G2_K562_ENCSR307YIW/test-*
- config_name: ELAVL1_HepG2_4083
data_files:
- split: train
path: ELAVL1_HepG2_4083/train-*
- split: validation
path: ELAVL1_HepG2_4083/validation-*
- split: test
path: ELAVL1_HepG2_4083/test-*
- config_name: EXOSC5_HepG2_ENCSR693JWP
data_files:
- split: train
path: EXOSC5_HepG2_ENCSR693JWP/train-*
- split: validation
path: EXOSC5_HepG2_ENCSR693JWP/validation-*
- split: test
path: EXOSC5_HepG2_ENCSR693JWP/test-*
- config_name: FAM120A_HepG2_ENCSR987NYS
data_files:
- split: train
path: FAM120A_HepG2_ENCSR987NYS/train-*
- split: validation
path: FAM120A_HepG2_ENCSR987NYS/validation-*
- split: test
path: FAM120A_HepG2_ENCSR987NYS/test-*
- config_name: FASTKD2_HepG2_ENCSR023UHL
data_files:
- split: train
path: FASTKD2_HepG2_ENCSR023UHL/train-*
- split: validation
path: FASTKD2_HepG2_ENCSR023UHL/validation-*
- split: test
path: FASTKD2_HepG2_ENCSR023UHL/test-*
- config_name: FASTKD2_K562_ENCSR887FHF
data_files:
- split: train
path: FASTKD2_K562_ENCSR887FHF/train-*
- split: validation
path: FASTKD2_K562_ENCSR887FHF/validation-*
- split: test
path: FASTKD2_K562_ENCSR887FHF/test-*
- config_name: FKBP4_HepG2_ENCSR018ZUE
data_files:
- split: train
path: FKBP4_HepG2_ENCSR018ZUE/train-*
- split: validation
path: FKBP4_HepG2_ENCSR018ZUE/validation-*
- split: test
path: FKBP4_HepG2_ENCSR018ZUE/test-*
- config_name: FMR1_K562_ENCSR331VNX
data_files:
- split: train
path: FMR1_K562_ENCSR331VNX/train-*
- split: validation
path: FMR1_K562_ENCSR331VNX/validation-*
- split: test
path: FMR1_K562_ENCSR331VNX/test-*
- config_name: FMRP_K562_4030
data_files:
- split: train
path: FMRP_K562_4030/train-*
- split: validation
path: FMRP_K562_4030/validation-*
- split: test
path: FMRP_K562_4030/test-*
- config_name: FTO_HepG2_ENCSR903PRV
data_files:
- split: train
path: FTO_HepG2_ENCSR903PRV/train-*
- split: validation
path: FTO_HepG2_ENCSR903PRV/validation-*
- split: test
path: FTO_HepG2_ENCSR903PRV/test-*
- config_name: FTO_K562_ENCSR989SMC
data_files:
- split: train
path: FTO_K562_ENCSR989SMC/train-*
- split: validation
path: FTO_K562_ENCSR989SMC/validation-*
- split: test
path: FTO_K562_ENCSR989SMC/test-*
- config_name: FUBP3_HepG2_ENCSR486YGP
data_files:
- split: train
path: FUBP3_HepG2_ENCSR486YGP/train-*
- split: validation
path: FUBP3_HepG2_ENCSR486YGP/validation-*
- split: test
path: FUBP3_HepG2_ENCSR486YGP/test-*
- config_name: FUS_K562_ENCSR069EVH
data_files:
- split: train
path: FUS_K562_ENCSR069EVH/train-*
- split: validation
path: FUS_K562_ENCSR069EVH/validation-*
- split: test
path: FUS_K562_ENCSR069EVH/test-*
- config_name: FXR1_K562_4036
data_files:
- split: train
path: FXR1_K562_4036/train-*
- split: validation
path: FXR1_K562_4036/validation-*
- split: test
path: FXR1_K562_4036/test-*
- config_name: FXR1_K562_ENCSR774RFN
data_files:
- split: train
path: FXR1_K562_ENCSR774RFN/train-*
- split: validation
path: FXR1_K562_ENCSR774RFN/validation-*
- split: test
path: FXR1_K562_ENCSR774RFN/test-*
- config_name: FXR2_HepG2_4098
data_files:
- split: train
path: FXR2_HepG2_4098/train-*
- split: validation
path: FXR2_HepG2_4098/validation-*
- split: test
path: FXR2_HepG2_4098/test-*
- config_name: FXR2_HepG2_ENCSR973HOJ
data_files:
- split: train
path: FXR2_HepG2_ENCSR973HOJ/train-*
- split: validation
path: FXR2_HepG2_ENCSR973HOJ/validation-*
- split: test
path: FXR2_HepG2_ENCSR973HOJ/test-*
- config_name: FXR2_K562_4002
data_files:
- split: train
path: FXR2_K562_4002/train-*
- split: validation
path: FXR2_K562_4002/validation-*
- split: test
path: FXR2_K562_4002/test-*
- config_name: FXR2_K562_ENCSR224QWC
data_files:
- split: train
path: FXR2_K562_ENCSR224QWC/train-*
- split: validation
path: FXR2_K562_ENCSR224QWC/validation-*
- split: test
path: FXR2_K562_ENCSR224QWC/test-*
- config_name: G3BP1_HepG2_ENCSR721HPX
data_files:
- split: train
path: G3BP1_HepG2_ENCSR721HPX/train-*
- split: validation
path: G3BP1_HepG2_ENCSR721HPX/validation-*
- split: test
path: G3BP1_HepG2_ENCSR721HPX/test-*
- config_name: GARS_HepG2_4108
data_files:
- split: train
path: GARS_HepG2_4108/train-*
- split: validation
path: GARS_HepG2_4108/validation-*
- split: test
path: GARS_HepG2_4108/test-*
- config_name: GEMIN5_K562_ENCSR238CLX
data_files:
- split: train
path: GEMIN5_K562_ENCSR238CLX/train-*
- split: validation
path: GEMIN5_K562_ENCSR238CLX/validation-*
- split: test
path: GEMIN5_K562_ENCSR238CLX/test-*
- config_name: GNL3_K562_ENCSR301UQM
data_files:
- split: train
path: GNL3_K562_ENCSR301UQM/train-*
- split: validation
path: GNL3_K562_ENCSR301UQM/validation-*
- split: test
path: GNL3_K562_ENCSR301UQM/test-*
- config_name: GPKOW_K562_ENCSR647CLF
data_files:
- split: train
path: GPKOW_K562_ENCSR647CLF/train-*
- split: validation
path: GPKOW_K562_ENCSR647CLF/validation-*
- split: test
path: GPKOW_K562_ENCSR647CLF/test-*
- config_name: GRSF1_HepG2_ENCSR668MJX
data_files:
- split: train
path: GRSF1_HepG2_ENCSR668MJX/train-*
- split: validation
path: GRSF1_HepG2_ENCSR668MJX/validation-*
- split: test
path: GRSF1_HepG2_ENCSR668MJX/test-*
- config_name: GTF2F1_HepG2_ENCSR265ZIS
data_files:
- split: train
path: GTF2F1_HepG2_ENCSR265ZIS/train-*
- split: validation
path: GTF2F1_HepG2_ENCSR265ZIS/validation-*
- split: test
path: GTF2F1_HepG2_ENCSR265ZIS/test-*
- config_name: GTF2F1_K562_ENCSR736AAG
data_files:
- split: train
path: GTF2F1_K562_ENCSR736AAG/train-*
- split: validation
path: GTF2F1_K562_ENCSR736AAG/validation-*
- split: test
path: GTF2F1_K562_ENCSR736AAG/test-*
- config_name: HLTF_HepG2_ENCSR647HOX
data_files:
- split: train
path: HLTF_HepG2_ENCSR647HOX/train-*
- split: validation
path: HLTF_HepG2_ENCSR647HOX/validation-*
- split: test
path: HLTF_HepG2_ENCSR647HOX/test-*
- config_name: HLTF_K562_ENCSR589YHM
data_files:
- split: train
path: HLTF_K562_ENCSR589YHM/train-*
- split: validation
path: HLTF_K562_ENCSR589YHM/validation-*
- split: test
path: HLTF_K562_ENCSR589YHM/test-*
- config_name: HNRNPA1_HepG2_ENCSR769UEW
data_files:
- split: train
path: HNRNPA1_HepG2_ENCSR769UEW/train-*
- split: validation
path: HNRNPA1_HepG2_ENCSR769UEW/validation-*
- split: test
path: HNRNPA1_HepG2_ENCSR769UEW/test-*
- config_name: HNRNPA1_K562_ENCSR154HRN
data_files:
- split: train
path: HNRNPA1_K562_ENCSR154HRN/train-*
- split: validation
path: HNRNPA1_K562_ENCSR154HRN/validation-*
- split: test
path: HNRNPA1_K562_ENCSR154HRN/test-*
- config_name: HNRNPC_HepG2_ENCSR550DVK
data_files:
- split: train
path: HNRNPC_HepG2_ENCSR550DVK/train-*
- split: validation
path: HNRNPC_HepG2_ENCSR550DVK/validation-*
- split: test
path: HNRNPC_HepG2_ENCSR550DVK/test-*
- config_name: HNRNPC_K562_ENCSR249ROI
data_files:
- split: train
path: HNRNPC_K562_ENCSR249ROI/train-*
- split: validation
path: HNRNPC_K562_ENCSR249ROI/validation-*
- split: test
path: HNRNPC_K562_ENCSR249ROI/test-*
- config_name: HNRNPK_HepG2_ENCSR828ZID
data_files:
- split: train
path: HNRNPK_HepG2_ENCSR828ZID/train-*
- split: validation
path: HNRNPK_HepG2_ENCSR828ZID/validation-*
- split: test
path: HNRNPK_HepG2_ENCSR828ZID/test-*
- config_name: HNRNPK_K562_ENCSR268ETU
data_files:
- split: train
path: HNRNPK_K562_ENCSR268ETU/train-*
- split: validation
path: HNRNPK_K562_ENCSR268ETU/validation-*
- split: test
path: HNRNPK_K562_ENCSR268ETU/test-*
- config_name: HNRNPL_HepG2_ENCSR724RDN
data_files:
- split: train
path: HNRNPL_HepG2_ENCSR724RDN/train-*
- split: validation
path: HNRNPL_HepG2_ENCSR724RDN/validation-*
- split: test
path: HNRNPL_HepG2_ENCSR724RDN/test-*
- config_name: HNRNPM_HepG2_ENCSR267UCX
data_files:
- split: train
path: HNRNPM_HepG2_ENCSR267UCX/train-*
- split: validation
path: HNRNPM_HepG2_ENCSR267UCX/validation-*
- split: test
path: HNRNPM_HepG2_ENCSR267UCX/test-*
- config_name: HNRNPUL1_HepG2_ENCSR755TJC
data_files:
- split: train
path: HNRNPUL1_HepG2_ENCSR755TJC/train-*
- split: validation
path: HNRNPUL1_HepG2_ENCSR755TJC/validation-*
- split: test
path: HNRNPUL1_HepG2_ENCSR755TJC/test-*
- config_name: HNRNPUL1_K562_ENCSR571VHI
data_files:
- split: train
path: HNRNPUL1_K562_ENCSR571VHI/train-*
- split: validation
path: HNRNPUL1_K562_ENCSR571VHI/validation-*
- split: test
path: HNRNPUL1_K562_ENCSR571VHI/test-*
- config_name: HNRNPU_HepG2_ENCSR240MVJ
data_files:
- split: train
path: HNRNPU_HepG2_ENCSR240MVJ/train-*
- split: validation
path: HNRNPU_HepG2_ENCSR240MVJ/validation-*
- split: test
path: HNRNPU_HepG2_ENCSR240MVJ/test-*
- config_name: HNRNPU_K562_ENCSR520BZQ
data_files:
- split: train
path: HNRNPU_K562_ENCSR520BZQ/train-*
- split: validation
path: HNRNPU_K562_ENCSR520BZQ/validation-*
- split: test
path: HNRNPU_K562_ENCSR520BZQ/test-*
- config_name: IGF2BP1_HepG2_ENCSR744GEU
data_files:
- split: train
path: IGF2BP1_HepG2_ENCSR744GEU/train-*
- split: validation
path: IGF2BP1_HepG2_ENCSR744GEU/validation-*
- split: test
path: IGF2BP1_HepG2_ENCSR744GEU/test-*
- config_name: IGF2BP1_K562_5093
data_files:
- split: train
path: IGF2BP1_K562_5093/train-*
- split: validation
path: IGF2BP1_K562_5093/validation-*
- split: test
path: IGF2BP1_K562_5093/test-*
- config_name: IGF2BP2_K562_ENCSR062NNB
data_files:
- split: train
path: IGF2BP2_K562_ENCSR062NNB/train-*
- split: validation
path: IGF2BP2_K562_ENCSR062NNB/validation-*
- split: test
path: IGF2BP2_K562_ENCSR062NNB/test-*
- config_name: IGF2BP3_HepG2_ENCSR993OLA
data_files:
- split: train
path: IGF2BP3_HepG2_ENCSR993OLA/train-*
- split: validation
path: IGF2BP3_HepG2_ENCSR993OLA/validation-*
- split: test
path: IGF2BP3_HepG2_ENCSR993OLA/test-*
- config_name: ILF3_HepG2_ENCSR786TSC
data_files:
- split: train
path: ILF3_HepG2_ENCSR786TSC/train-*
- split: validation
path: ILF3_HepG2_ENCSR786TSC/validation-*
- split: test
path: ILF3_HepG2_ENCSR786TSC/test-*
- config_name: ILF3_K562_ENCSR438KWZ
data_files:
- split: train
path: ILF3_K562_ENCSR438KWZ/train-*
- split: validation
path: ILF3_K562_ENCSR438KWZ/validation-*
- split: test
path: ILF3_K562_ENCSR438KWZ/test-*
- config_name: KHDRBS1_K562_ENCSR628IDK
data_files:
- split: train
path: KHDRBS1_K562_ENCSR628IDK/train-*
- split: validation
path: KHDRBS1_K562_ENCSR628IDK/validation-*
- split: test
path: KHDRBS1_K562_ENCSR628IDK/test-*
- config_name: KHSRP_HepG2_ENCSR366DGX
data_files:
- split: train
path: KHSRP_HepG2_ENCSR366DGX/train-*
- split: validation
path: KHSRP_HepG2_ENCSR366DGX/validation-*
- split: test
path: KHSRP_HepG2_ENCSR366DGX/test-*
- config_name: KHSRP_K562_5001
data_files:
- split: train
path: KHSRP_K562_5001/train-*
- split: validation
path: KHSRP_K562_5001/validation-*
- split: test
path: KHSRP_K562_5001/test-*
- config_name: LARP4_K562_ENCSR888YTT
data_files:
- split: train
path: LARP4_K562_ENCSR888YTT/train-*
- split: validation
path: LARP4_K562_ENCSR888YTT/validation-*
- split: test
path: LARP4_K562_ENCSR888YTT/test-*
- config_name: LARP7_K562_ENCSR456KXI
data_files:
- split: train
path: LARP7_K562_ENCSR456KXI/train-*
- split: validation
path: LARP7_K562_ENCSR456KXI/validation-*
- split: test
path: LARP7_K562_ENCSR456KXI/test-*
- config_name: LIN28B_HepG2_ENCSR861GYE
data_files:
- split: train
path: LIN28B_HepG2_ENCSR861GYE/train-*
- split: validation
path: LIN28B_HepG2_ENCSR861GYE/validation-*
- split: test
path: LIN28B_HepG2_ENCSR861GYE/test-*
- config_name: LIN28B_K562_ENCSR970NKP
data_files:
- split: train
path: LIN28B_K562_ENCSR970NKP/train-*
- split: validation
path: LIN28B_K562_ENCSR970NKP/validation-*
- split: test
path: LIN28B_K562_ENCSR970NKP/test-*
- config_name: LSM11_HepG2_ENCSR135VMS
data_files:
- split: train
path: LSM11_HepG2_ENCSR135VMS/train-*
- split: validation
path: LSM11_HepG2_ENCSR135VMS/validation-*
- split: test
path: LSM11_HepG2_ENCSR135VMS/test-*
- config_name: LSM11_K562_ENCSR022BVV
data_files:
- split: train
path: LSM11_K562_ENCSR022BVV/train-*
- split: validation
path: LSM11_K562_ENCSR022BVV/validation-*
- split: test
path: LSM11_K562_ENCSR022BVV/test-*
- config_name: MATR3_HepG2_ENCSR290VLT
data_files:
- split: train
path: MATR3_HepG2_ENCSR290VLT/train-*
- split: validation
path: MATR3_HepG2_ENCSR290VLT/validation-*
- split: test
path: MATR3_HepG2_ENCSR290VLT/test-*
- config_name: MBNL1_K562_4056
data_files:
- split: train
path: MBNL1_K562_4056/train-*
- split: validation
path: MBNL1_K562_4056/validation-*
- split: test
path: MBNL1_K562_4056/test-*
- config_name: METAP2_K562_ENCSR303OQD
data_files:
- split: train
path: METAP2_K562_ENCSR303OQD/train-*
- split: validation
path: METAP2_K562_ENCSR303OQD/validation-*
- split: test
path: METAP2_K562_ENCSR303OQD/test-*
- config_name: MTPAP_K562_ENCSR200DKE
data_files:
- split: train
path: MTPAP_K562_ENCSR200DKE/train-*
- split: validation
path: MTPAP_K562_ENCSR200DKE/validation-*
- split: test
path: MTPAP_K562_ENCSR200DKE/test-*
- config_name: NCBP2_HepG2_ENCSR018RVZ
data_files:
- split: train
path: NCBP2_HepG2_ENCSR018RVZ/train-*
- split: validation
path: NCBP2_HepG2_ENCSR018RVZ/validation-*
- split: test
path: NCBP2_HepG2_ENCSR018RVZ/test-*
- config_name: NCBP2_K562_ENCSR484LTQ
data_files:
- split: train
path: NCBP2_K562_ENCSR484LTQ/train-*
- split: validation
path: NCBP2_K562_ENCSR484LTQ/validation-*
- split: test
path: NCBP2_K562_ENCSR484LTQ/test-*
- config_name: NCL_K562_5086
data_files:
- split: train
path: NCL_K562_5086/train-*
- split: validation
path: NCL_K562_5086/validation-*
- split: test
path: NCL_K562_5086/test-*
- config_name: NIP7_HepG2_ENCSR361OCV
data_files:
- split: train
path: NIP7_HepG2_ENCSR361OCV/train-*
- split: validation
path: NIP7_HepG2_ENCSR361OCV/validation-*
- split: test
path: NIP7_HepG2_ENCSR361OCV/test-*
- config_name: NIPBL_K562_ENCSR891RIC
data_files:
- split: train
path: NIPBL_K562_ENCSR891RIC/train-*
- split: validation
path: NIPBL_K562_ENCSR891RIC/validation-*
- split: test
path: NIPBL_K562_ENCSR891RIC/test-*
- config_name: NKRF_HepG2_ENCSR277DEO
data_files:
- split: train
path: NKRF_HepG2_ENCSR277DEO/train-*
- split: validation
path: NKRF_HepG2_ENCSR277DEO/validation-*
- split: test
path: NKRF_HepG2_ENCSR277DEO/test-*
- config_name: NKRF_K562_5005
data_files:
- split: train
path: NKRF_K562_5005/train-*
- split: validation
path: NKRF_K562_5005/validation-*
- split: test
path: NKRF_K562_5005/test-*
- config_name: NOL12_HepG2_ENCSR820DQJ
data_files:
- split: train
path: NOL12_HepG2_ENCSR820DQJ/train-*
- split: validation
path: NOL12_HepG2_ENCSR820DQJ/validation-*
- split: test
path: NOL12_HepG2_ENCSR820DQJ/test-*
- config_name: NOLC1_HepG2_ENCSR194HZU
data_files:
- split: train
path: NOLC1_HepG2_ENCSR194HZU/train-*
- split: validation
path: NOLC1_HepG2_ENCSR194HZU/validation-*
- split: test
path: NOLC1_HepG2_ENCSR194HZU/test-*
- config_name: NONO_K562_4001
data_files:
- split: train
path: NONO_K562_4001/train-*
- split: validation
path: NONO_K562_4001/validation-*
- split: test
path: NONO_K562_4001/test-*
- config_name: NPM1_K562_ENCSR867DSZ
data_files:
- split: train
path: NPM1_K562_ENCSR867DSZ/train-*
- split: validation
path: NPM1_K562_ENCSR867DSZ/validation-*
- split: test
path: NPM1_K562_ENCSR867DSZ/test-*
- config_name: NSUN2_HepG2_4215
data_files:
- split: train
path: NSUN2_HepG2_4215/train-*
- split: validation
path: NSUN2_HepG2_4215/validation-*
- split: test
path: NSUN2_HepG2_4215/test-*
- config_name: NSUN2_K562_ENCSR081JYH
data_files:
- split: train
path: NSUN2_K562_ENCSR081JYH/train-*
- split: validation
path: NSUN2_K562_ENCSR081JYH/validation-*
- split: test
path: NSUN2_K562_ENCSR081JYH/test-*
- config_name: PABPC4_K562_ENCSR958FKZ
data_files:
- split: train
path: PABPC4_K562_ENCSR958FKZ/train-*
- split: validation
path: PABPC4_K562_ENCSR958FKZ/validation-*
- split: test
path: PABPC4_K562_ENCSR958FKZ/test-*
- config_name: PABPN1_HepG2_5062
data_files:
- split: train
path: PABPN1_HepG2_5062/train-*
- split: validation
path: PABPN1_HepG2_5062/validation-*
- split: test
path: PABPN1_HepG2_5062/test-*
- config_name: PABPN1_HepG2_ENCSR820UYE
data_files:
- split: train
path: PABPN1_HepG2_ENCSR820UYE/train-*
- split: validation
path: PABPN1_HepG2_ENCSR820UYE/validation-*
- split: test
path: PABPN1_HepG2_ENCSR820UYE/test-*
- config_name: PARP_HepG2_4214
data_files:
- split: train
path: PARP_HepG2_4214/train-*
- split: validation
path: PARP_HepG2_4214/validation-*
- split: test
path: PARP_HepG2_4214/test-*
- config_name: PCBP1_K562_ENCSR922WJV
data_files:
- split: train
path: PCBP1_K562_ENCSR922WJV/train-*
- split: validation
path: PCBP1_K562_ENCSR922WJV/validation-*
- split: test
path: PCBP1_K562_ENCSR922WJV/test-*
- config_name: PHF6_K562_ENCSR001KKZ
data_files:
- split: train
path: PHF6_K562_ENCSR001KKZ/train-*
- split: validation
path: PHF6_K562_ENCSR001KKZ/validation-*
- split: test
path: PHF6_K562_ENCSR001KKZ/test-*
- config_name: PPIG_HepG2_ENCSR097NEE
data_files:
- split: train
path: PPIG_HepG2_ENCSR097NEE/train-*
- split: validation
path: PPIG_HepG2_ENCSR097NEE/validation-*
- split: test
path: PPIG_HepG2_ENCSR097NEE/test-*
- config_name: PPIL4_K562_ENCSR197INS
data_files:
- split: train
path: PPIL4_K562_ENCSR197INS/train-*
- split: validation
path: PPIL4_K562_ENCSR197INS/validation-*
- split: test
path: PPIL4_K562_ENCSR197INS/test-*
- config_name: PPP1R10_HepG2_4148
data_files:
- split: train
path: PPP1R10_HepG2_4148/train-*
- split: validation
path: PPP1R10_HepG2_4148/validation-*
- split: test
path: PPP1R10_HepG2_4148/test-*
- config_name: PRK2_K562_5064
data_files:
- split: train
path: PRK2_K562_5064/train-*
- split: validation
path: PRK2_K562_5064/validation-*
- split: test
path: PRK2_K562_5064/test-*
- config_name: PRKRA_K562_5068
data_files:
- split: train
path: PRKRA_K562_5068/train-*
- split: validation
path: PRKRA_K562_5068/validation-*
- split: test
path: PRKRA_K562_5068/test-*
- config_name: PRPF39_HepG2_4114
data_files:
- split: train
path: PRPF39_HepG2_4114/train-*
- split: validation
path: PRPF39_HepG2_4114/validation-*
- split: test
path: PRPF39_HepG2_4114/test-*
- config_name: PRPF39_HepG2_4149
data_files:
- split: train
path: PRPF39_HepG2_4149/train-*
- split: validation
path: PRPF39_HepG2_4149/validation-*
- split: test
path: PRPF39_HepG2_4149/test-*
- config_name: PRPF39_K562_4068
data_files:
- split: train
path: PRPF39_K562_4068/train-*
- split: validation
path: PRPF39_K562_4068/validation-*
- split: test
path: PRPF39_K562_4068/test-*
- config_name: PRPF4_HepG2_ENCSR977OXG
data_files:
- split: train
path: PRPF4_HepG2_ENCSR977OXG/train-*
- split: validation
path: PRPF4_HepG2_ENCSR977OXG/validation-*
- split: test
path: PRPF4_HepG2_ENCSR977OXG/test-*
- config_name: PRPF8_HepG2_ENCSR121NVA
data_files:
- split: train
path: PRPF8_HepG2_ENCSR121NVA/train-*
- split: validation
path: PRPF8_HepG2_ENCSR121NVA/validation-*
- split: test
path: PRPF8_HepG2_ENCSR121NVA/test-*
- config_name: PTBP1_HepG2_ENCSR384KAN
data_files:
- split: train
path: PTBP1_HepG2_ENCSR384KAN/train-*
- split: validation
path: PTBP1_HepG2_ENCSR384KAN/validation-*
- split: test
path: PTBP1_HepG2_ENCSR384KAN/test-*
- config_name: PTBP1_K562_5015
data_files:
- split: train
path: PTBP1_K562_5015/train-*
- split: validation
path: PTBP1_K562_5015/validation-*
- split: test
path: PTBP1_K562_5015/test-*
- config_name: PTBP1_K562_ENCSR981WKN
data_files:
- split: train
path: PTBP1_K562_ENCSR981WKN/train-*
- split: validation
path: PTBP1_K562_ENCSR981WKN/validation-*
- split: test
path: PTBP1_K562_ENCSR981WKN/test-*
- config_name: PUM1_K562_ENCSR308YNT
data_files:
- split: train
path: PUM1_K562_ENCSR308YNT/train-*
- split: validation
path: PUM1_K562_ENCSR308YNT/validation-*
- split: test
path: PUM1_K562_ENCSR308YNT/test-*
- config_name: PUS1_K562_ENCSR291XPT
data_files:
- split: train
path: PUS1_K562_ENCSR291XPT/train-*
- split: validation
path: PUS1_K562_ENCSR291XPT/validation-*
- split: test
path: PUS1_K562_ENCSR291XPT/test-*
- config_name: QKI_HepG2_ENCSR570WLM
data_files:
- split: train
path: QKI_HepG2_ENCSR570WLM/train-*
- split: validation
path: QKI_HepG2_ENCSR570WLM/validation-*
- split: test
path: QKI_HepG2_ENCSR570WLM/test-*
- config_name: QKI_K562_5007
data_files:
- split: train
path: QKI_K562_5007/train-*
- split: validation
path: QKI_K562_5007/validation-*
- split: test
path: QKI_K562_5007/test-*
- config_name: QKI_K562_ENCSR366YOG
data_files:
- split: train
path: QKI_K562_ENCSR366YOG/train-*
- split: validation
path: QKI_K562_ENCSR366YOG/validation-*
- split: test
path: QKI_K562_ENCSR366YOG/test-*
- config_name: RBFOX2_HepG2_ENCSR987FTF
data_files:
- split: train
path: RBFOX2_HepG2_ENCSR987FTF/train-*
- split: validation
path: RBFOX2_HepG2_ENCSR987FTF/validation-*
- split: test
path: RBFOX2_HepG2_ENCSR987FTF/test-*
- config_name: RBFOX2_K562_ENCSR756CKJ
data_files:
- split: train
path: RBFOX2_K562_ENCSR756CKJ/train-*
- split: validation
path: RBFOX2_K562_ENCSR756CKJ/validation-*
- split: test
path: RBFOX2_K562_ENCSR756CKJ/test-*
- config_name: RBM15_HepG2_ENCSR754NDA
data_files:
- split: train
path: RBM15_HepG2_ENCSR754NDA/train-*
- split: validation
path: RBM15_HepG2_ENCSR754NDA/validation-*
- split: test
path: RBM15_HepG2_ENCSR754NDA/test-*
- config_name: RBM15_K562_5008
data_files:
- split: train
path: RBM15_K562_5008/train-*
- split: validation
path: RBM15_K562_5008/validation-*
- split: test
path: RBM15_K562_5008/test-*
- config_name: RBM22_HepG2_ENCSR456JJQ
data_files:
- split: train
path: RBM22_HepG2_ENCSR456JJQ/train-*
- split: validation
path: RBM22_HepG2_ENCSR456JJQ/validation-*
- split: test
path: RBM22_HepG2_ENCSR456JJQ/test-*
- config_name: RBM22_K562_ENCSR295OKT
data_files:
- split: train
path: RBM22_K562_ENCSR295OKT/train-*
- split: validation
path: RBM22_K562_ENCSR295OKT/validation-*
- split: test
path: RBM22_K562_ENCSR295OKT/test-*
- config_name: RBM5_HepG2_ENCSR489ABS
data_files:
- split: train
path: RBM5_HepG2_ENCSR489ABS/train-*
- split: validation
path: RBM5_HepG2_ENCSR489ABS/validation-*
- split: test
path: RBM5_HepG2_ENCSR489ABS/test-*
- config_name: RBM5_K562_5018
data_files:
- split: train
path: RBM5_K562_5018/train-*
- split: validation
path: RBM5_K562_5018/validation-*
- split: test
path: RBM5_K562_5018/test-*
- config_name: RECQ1_K562_4049
data_files:
- split: train
path: RECQ1_K562_4049/train-*
- split: validation
path: RECQ1_K562_4049/validation-*
- split: test
path: RECQ1_K562_4049/test-*
- config_name: RPS11_K562_ENCSR269AJF
data_files:
- split: train
path: RPS11_K562_ENCSR269AJF/train-*
- split: validation
path: RPS11_K562_ENCSR269AJF/validation-*
- split: test
path: RPS11_K562_ENCSR269AJF/test-*
- config_name: RPS3_HepG2_ENCSR766FAC
data_files:
- split: train
path: RPS3_HepG2_ENCSR766FAC/train-*
- split: validation
path: RPS3_HepG2_ENCSR766FAC/validation-*
- split: test
path: RPS3_HepG2_ENCSR766FAC/test-*
- config_name: RPS3_K562_ENCSR120EAR
data_files:
- split: train
path: RPS3_K562_ENCSR120EAR/train-*
- split: validation
path: RPS3_K562_ENCSR120EAR/validation-*
- split: test
path: RPS3_K562_ENCSR120EAR/test-*
- config_name: SAFB_HepG2_ENCSR337XGI
data_files:
- split: train
path: SAFB_HepG2_ENCSR337XGI/train-*
- split: validation
path: SAFB_HepG2_ENCSR337XGI/validation-*
- split: test
path: SAFB_HepG2_ENCSR337XGI/test-*
- config_name: SAFB_K562_ENCSR484LAB
data_files:
- split: train
path: SAFB_K562_ENCSR484LAB/train-*
- split: validation
path: SAFB_K562_ENCSR484LAB/validation-*
- split: test
path: SAFB_K562_ENCSR484LAB/test-*
- config_name: SBDS_K562_ENCSR059CWF
data_files:
- split: train
path: SBDS_K562_ENCSR059CWF/train-*
- split: validation
path: SBDS_K562_ENCSR059CWF/validation-*
- split: test
path: SBDS_K562_ENCSR059CWF/test-*
- config_name: SDAD1_HepG2_ENCSR050BDZ
data_files:
- split: train
path: SDAD1_HepG2_ENCSR050BDZ/train-*
- split: validation
path: SDAD1_HepG2_ENCSR050BDZ/validation-*
- split: test
path: SDAD1_HepG2_ENCSR050BDZ/test-*
- config_name: SERBP1_K562_ENCSR121GQH
data_files:
- split: train
path: SERBP1_K562_ENCSR121GQH/train-*
- split: validation
path: SERBP1_K562_ENCSR121GQH/validation-*
- split: test
path: SERBP1_K562_ENCSR121GQH/test-*
- config_name: SF3A1_HepG2_4117
data_files:
- split: train
path: SF3A1_HepG2_4117/train-*
- split: validation
path: SF3A1_HepG2_4117/validation-*
- split: test
path: SF3A1_HepG2_4117/test-*
- config_name: SF3A1_K562_4048
data_files:
- split: train
path: SF3A1_K562_4048/train-*
- split: validation
path: SF3A1_K562_4048/validation-*
- split: test
path: SF3A1_K562_4048/test-*
- config_name: SF3A3_HepG2_ENCSR331MIC
data_files:
- split: train
path: SF3A3_HepG2_ENCSR331MIC/train-*
- split: validation
path: SF3A3_HepG2_ENCSR331MIC/validation-*
- split: test
path: SF3A3_HepG2_ENCSR331MIC/test-*
- config_name: SF3B1_K562_ENCSR133QEA
data_files:
- split: train
path: SF3B1_K562_ENCSR133QEA/train-*
- split: validation
path: SF3B1_K562_ENCSR133QEA/validation-*
- split: test
path: SF3B1_K562_ENCSR133QEA/test-*
- config_name: SF3B4_HepG2_ENCSR279UJF
data_files:
- split: train
path: SF3B4_HepG2_ENCSR279UJF/train-*
- split: validation
path: SF3B4_HepG2_ENCSR279UJF/validation-*
- split: test
path: SF3B4_HepG2_ENCSR279UJF/test-*
- config_name: SFPQ_HepG2_ENCSR965DLL
data_files:
- split: train
path: SFPQ_HepG2_ENCSR965DLL/train-*
- split: validation
path: SFPQ_HepG2_ENCSR965DLL/validation-*
- split: test
path: SFPQ_HepG2_ENCSR965DLL/test-*
- config_name: SLBP_K562_ENCSR483NOP
data_files:
- split: train
path: SLBP_K562_ENCSR483NOP/train-*
- split: validation
path: SLBP_K562_ENCSR483NOP/validation-*
- split: test
path: SLBP_K562_ENCSR483NOP/test-*
- config_name: SLTM_HepG2_ENCSR351PVI
data_files:
- split: train
path: SLTM_HepG2_ENCSR351PVI/train-*
- split: validation
path: SLTM_HepG2_ENCSR351PVI/validation-*
- split: test
path: SLTM_HepG2_ENCSR351PVI/test-*
- config_name: SLTM_K562_ENCSR000SSH
data_files:
- split: train
path: SLTM_K562_ENCSR000SSH/train-*
- split: validation
path: SLTM_K562_ENCSR000SSH/validation-*
- split: test
path: SLTM_K562_ENCSR000SSH/test-*
- config_name: SMNDC1_K562_ENCSR658IQB
data_files:
- split: train
path: SMNDC1_K562_ENCSR658IQB/train-*
- split: validation
path: SMNDC1_K562_ENCSR658IQB/validation-*
- split: test
path: SMNDC1_K562_ENCSR658IQB/test-*
- config_name: SND1_HepG2_ENCSR061EVO
data_files:
- split: train
path: SND1_HepG2_ENCSR061EVO/train-*
- split: validation
path: SND1_HepG2_ENCSR061EVO/validation-*
- split: test
path: SND1_HepG2_ENCSR061EVO/test-*
- config_name: SND1_K562_ENCSR128VXC
data_files:
- split: train
path: SND1_K562_ENCSR128VXC/train-*
- split: validation
path: SND1_K562_ENCSR128VXC/validation-*
- split: test
path: SND1_K562_ENCSR128VXC/test-*
- config_name: SNRNP200_HepG2_4212
data_files:
- split: train
path: SNRNP200_HepG2_4212/train-*
- split: validation
path: SNRNP200_HepG2_4212/validation-*
- split: test
path: SNRNP200_HepG2_4212/test-*
- config_name: SNRPA1_HepG2_4203
data_files:
- split: train
path: SNRPA1_HepG2_4203/train-*
- split: validation
path: SNRPA1_HepG2_4203/validation-*
- split: test
path: SNRPA1_HepG2_4203/test-*
- config_name: SNRPC_HepG2_4187
data_files:
- split: train
path: SNRPC_HepG2_4187/train-*
- split: validation
path: SNRPC_HepG2_4187/validation-*
- split: test
path: SNRPC_HepG2_4187/test-*
- config_name: SNRPC_K562_4164
data_files:
- split: train
path: SNRPC_K562_4164/train-*
- split: validation
path: SNRPC_K562_4164/validation-*
- split: test
path: SNRPC_K562_4164/test-*
- config_name: SNRPD3_HepG2_4204
data_files:
- split: train
path: SNRPD3_HepG2_4204/train-*
- split: validation
path: SNRPD3_HepG2_4204/validation-*
- split: test
path: SNRPD3_HepG2_4204/test-*
- config_name: SRSF1_HepG2_ENCSR989VIY
data_files:
- split: train
path: SRSF1_HepG2_ENCSR989VIY/train-*
- split: validation
path: SRSF1_HepG2_ENCSR989VIY/validation-*
- split: test
path: SRSF1_HepG2_ENCSR989VIY/test-*
- config_name: SRSF1_K562_ENCSR432XUP
data_files:
- split: train
path: SRSF1_K562_ENCSR432XUP/train-*
- split: validation
path: SRSF1_K562_ENCSR432XUP/validation-*
- split: test
path: SRSF1_K562_ENCSR432XUP/test-*
- config_name: SRSF7_K562_ENCSR468FSW
data_files:
- split: train
path: SRSF7_K562_ENCSR468FSW/train-*
- split: validation
path: SRSF7_K562_ENCSR468FSW/validation-*
- split: test
path: SRSF7_K562_ENCSR468FSW/test-*
- config_name: SRSF9_HepG2_ENCSR773KRC
data_files:
- split: train
path: SRSF9_HepG2_ENCSR773KRC/train-*
- split: validation
path: SRSF9_HepG2_ENCSR773KRC/validation-*
- split: test
path: SRSF9_HepG2_ENCSR773KRC/test-*
- config_name: SSB_HepG2_ENCSR352STY
data_files:
- split: train
path: SSB_HepG2_ENCSR352STY/train-*
- split: validation
path: SSB_HepG2_ENCSR352STY/validation-*
- split: test
path: SSB_HepG2_ENCSR352STY/test-*
- config_name: SSB_K562_ENCSR356MSW
data_files:
- split: train
path: SSB_K562_ENCSR356MSW/train-*
- split: validation
path: SSB_K562_ENCSR356MSW/validation-*
- split: test
path: SSB_K562_ENCSR356MSW/test-*
- config_name: STAU2_HepG2_ENCSR979EWD
data_files:
- split: train
path: STAU2_HepG2_ENCSR979EWD/train-*
- split: validation
path: STAU2_HepG2_ENCSR979EWD/validation-*
- split: test
path: STAU2_HepG2_ENCSR979EWD/test-*
- config_name: SUB1_HepG2_ENCSR406OOZ
data_files:
- split: train
path: SUB1_HepG2_ENCSR406OOZ/train-*
- split: validation
path: SUB1_HepG2_ENCSR406OOZ/validation-*
- split: test
path: SUB1_HepG2_ENCSR406OOZ/test-*
- config_name: SUGP2_HepG2_ENCSR506UPY
data_files:
- split: train
path: SUGP2_HepG2_ENCSR506UPY/train-*
- split: validation
path: SUGP2_HepG2_ENCSR506UPY/validation-*
- split: test
path: SUGP2_HepG2_ENCSR506UPY/test-*
- config_name: SUPV3L1_HepG2_ENCSR580MFX
data_files:
- split: train
path: SUPV3L1_HepG2_ENCSR580MFX/train-*
- split: validation
path: SUPV3L1_HepG2_ENCSR580MFX/validation-*
- split: test
path: SUPV3L1_HepG2_ENCSR580MFX/test-*
- config_name: SUPV3L1_K562_ENCSR580OFI
data_files:
- split: train
path: SUPV3L1_K562_ENCSR580OFI/train-*
- split: validation
path: SUPV3L1_K562_ENCSR580OFI/validation-*
- split: test
path: SUPV3L1_K562_ENCSR580OFI/test-*
- config_name: TAF15_HepG2_ENCSR841EQA
data_files:
- split: train
path: TAF15_HepG2_ENCSR841EQA/train-*
- split: validation
path: TAF15_HepG2_ENCSR841EQA/validation-*
- split: test
path: TAF15_HepG2_ENCSR841EQA/test-*
- config_name: TAF15_K562_5013
data_files:
- split: train
path: TAF15_K562_5013/train-*
- split: validation
path: TAF15_K562_5013/validation-*
- split: test
path: TAF15_K562_5013/test-*
- config_name: TAF15_K562_ENCSR568DZW
data_files:
- split: train
path: TAF15_K562_ENCSR568DZW/train-*
- split: validation
path: TAF15_K562_ENCSR568DZW/validation-*
- split: test
path: TAF15_K562_ENCSR568DZW/test-*
- config_name: TARDBP_K562_ENCSR584TCR
data_files:
- split: train
path: TARDBP_K562_ENCSR584TCR/train-*
- split: validation
path: TARDBP_K562_ENCSR584TCR/validation-*
- split: test
path: TARDBP_K562_ENCSR584TCR/test-*
- config_name: TBRG4_K562_ENCSR506OTC
data_files:
- split: train
path: TBRG4_K562_ENCSR506OTC/train-*
- split: validation
path: TBRG4_K562_ENCSR506OTC/validation-*
- split: test
path: TBRG4_K562_ENCSR506OTC/test-*
- config_name: TFAM_K562_5069
data_files:
- split: train
path: TFAM_K562_5069/train-*
- split: validation
path: TFAM_K562_5069/validation-*
- split: test
path: TFAM_K562_5069/test-*
- config_name: TIA1_HepG2_ENCSR623VEQ
data_files:
- split: train
path: TIA1_HepG2_ENCSR623VEQ/train-*
- split: validation
path: TIA1_HepG2_ENCSR623VEQ/validation-*
- split: test
path: TIA1_HepG2_ENCSR623VEQ/test-*
- config_name: TIAL1_HepG2_ENCSR322HHA
data_files:
- split: train
path: TIAL1_HepG2_ENCSR322HHA/train-*
- split: validation
path: TIAL1_HepG2_ENCSR322HHA/validation-*
- split: test
path: TIAL1_HepG2_ENCSR322HHA/test-*
- config_name: TRA2A_HepG2_ENCSR314UMJ
data_files:
- split: train
path: TRA2A_HepG2_ENCSR314UMJ/train-*
- split: validation
path: TRA2A_HepG2_ENCSR314UMJ/validation-*
- split: test
path: TRA2A_HepG2_ENCSR314UMJ/test-*
- config_name: TRA2A_K562_ENCSR365NVO
data_files:
- split: train
path: TRA2A_K562_ENCSR365NVO/train-*
- split: validation
path: TRA2A_K562_ENCSR365NVO/validation-*
- split: test
path: TRA2A_K562_ENCSR365NVO/test-*
- config_name: TROVE2_HepG2_ENCSR993FMY
data_files:
- split: train
path: TROVE2_HepG2_ENCSR993FMY/train-*
- split: validation
path: TROVE2_HepG2_ENCSR993FMY/validation-*
- split: test
path: TROVE2_HepG2_ENCSR993FMY/test-*
- config_name: TROVE2_K562_ENCSR539ZTS
data_files:
- split: train
path: TROVE2_K562_ENCSR539ZTS/train-*
- split: validation
path: TROVE2_K562_ENCSR539ZTS/validation-*
- split: test
path: TROVE2_K562_ENCSR539ZTS/test-*
- config_name: U2AF1_K562_ENCSR862QCH
data_files:
- split: train
path: U2AF1_K562_ENCSR862QCH/train-*
- split: validation
path: U2AF1_K562_ENCSR862QCH/validation-*
- split: test
path: U2AF1_K562_ENCSR862QCH/test-*
- config_name: U2AF2_HepG2_ENCSR202BFN
data_files:
- split: train
path: U2AF2_HepG2_ENCSR202BFN/train-*
- split: validation
path: U2AF2_HepG2_ENCSR202BFN/validation-*
- split: test
path: U2AF2_HepG2_ENCSR202BFN/test-*
- config_name: U2AF2_K562_ENCSR893RAV
data_files:
- split: train
path: U2AF2_K562_ENCSR893RAV/train-*
- split: validation
path: U2AF2_K562_ENCSR893RAV/validation-*
- split: test
path: U2AF2_K562_ENCSR893RAV/test-*
- config_name: UBAP2L_K562_5090
data_files:
- split: train
path: UBAP2L_K562_5090/train-*
- split: validation
path: UBAP2L_K562_5090/validation-*
- split: test
path: UBAP2L_K562_5090/test-*
- config_name: UCHL5_HepG2_ENCSR490IEE
data_files:
- split: train
path: UCHL5_HepG2_ENCSR490IEE/train-*
- split: validation
path: UCHL5_HepG2_ENCSR490IEE/validation-*
- split: test
path: UCHL5_HepG2_ENCSR490IEE/test-*
- config_name: UPF1_HepG2_ENCSR539BEV
data_files:
- split: train
path: UPF1_HepG2_ENCSR539BEV/train-*
- split: validation
path: UPF1_HepG2_ENCSR539BEV/validation-*
- split: test
path: UPF1_HepG2_ENCSR539BEV/test-*
- config_name: UPF1_K562_5002
data_files:
- split: train
path: UPF1_K562_5002/train-*
- split: validation
path: UPF1_K562_5002/validation-*
- split: test
path: UPF1_K562_5002/test-*
- config_name: USP10_K562_5089
data_files:
- split: train
path: USP10_K562_5089/train-*
- split: validation
path: USP10_K562_5089/validation-*
- split: test
path: USP10_K562_5089/test-*
- config_name: UTP18_HepG2_ENCSR488JKQ
data_files:
- split: train
path: UTP18_HepG2_ENCSR488JKQ/train-*
- split: validation
path: UTP18_HepG2_ENCSR488JKQ/validation-*
- split: test
path: UTP18_HepG2_ENCSR488JKQ/test-*
- config_name: UTP18_K562_ENCSR964VOX
data_files:
- split: train
path: UTP18_K562_ENCSR964VOX/train-*
- split: validation
path: UTP18_K562_ENCSR964VOX/validation-*
- split: test
path: UTP18_K562_ENCSR964VOX/test-*
- config_name: UTP3_K562_ENCSR734ZHL
data_files:
- split: train
path: UTP3_K562_ENCSR734ZHL/train-*
- split: validation
path: UTP3_K562_ENCSR734ZHL/validation-*
- split: test
path: UTP3_K562_ENCSR734ZHL/test-*
- config_name: WDR3_K562_ENCSR202HKN
data_files:
- split: train
path: WDR3_K562_ENCSR202HKN/train-*
- split: validation
path: WDR3_K562_ENCSR202HKN/validation-*
- split: test
path: WDR3_K562_ENCSR202HKN/test-*
- config_name: WDR43_HepG2_ENCSR085JPB
data_files:
- split: train
path: WDR43_HepG2_ENCSR085JPB/train-*
- split: validation
path: WDR43_HepG2_ENCSR085JPB/validation-*
- split: test
path: WDR43_HepG2_ENCSR085JPB/test-*
- config_name: WDR43_K562_ENCSR349CMI
data_files:
- split: train
path: WDR43_K562_ENCSR349CMI/train-*
- split: validation
path: WDR43_K562_ENCSR349CMI/validation-*
- split: test
path: WDR43_K562_ENCSR349CMI/test-*
- config_name: WRN_K562_ENCSR038JME
data_files:
- split: train
path: WRN_K562_ENCSR038JME/train-*
- split: validation
path: WRN_K562_ENCSR038JME/validation-*
- split: test
path: WRN_K562_ENCSR038JME/test-*
- config_name: XPO5_HepG2_ENCSR921SXC
data_files:
- split: train
path: XPO5_HepG2_ENCSR921SXC/train-*
- split: validation
path: XPO5_HepG2_ENCSR921SXC/validation-*
- split: test
path: XPO5_HepG2_ENCSR921SXC/test-*
- config_name: XRCC6_HepG2_ENCSR571ROL
data_files:
- split: train
path: XRCC6_HepG2_ENCSR571ROL/train-*
- split: validation
path: XRCC6_HepG2_ENCSR571ROL/validation-*
- split: test
path: XRCC6_HepG2_ENCSR571ROL/test-*
- config_name: XRCC6_K562_ENCSR258QKO
data_files:
- split: train
path: XRCC6_K562_ENCSR258QKO/train-*
- split: validation
path: XRCC6_K562_ENCSR258QKO/validation-*
- split: test
path: XRCC6_K562_ENCSR258QKO/test-*
- config_name: XRN2_K562_ENCSR657TZB
data_files:
- split: train
path: XRN2_K562_ENCSR657TZB/train-*
- split: validation
path: XRN2_K562_ENCSR657TZB/validation-*
- split: test
path: XRN2_K562_ENCSR657TZB/test-*
- config_name: YWHAG_K562_ENCSR867ZVK
data_files:
- split: train
path: YWHAG_K562_ENCSR867ZVK/train-*
- split: validation
path: YWHAG_K562_ENCSR867ZVK/validation-*
- split: test
path: YWHAG_K562_ENCSR867ZVK/test-*
- config_name: ZC3H11A_HepG2_ENCSR907GUB
data_files:
- split: train
path: ZC3H11A_HepG2_ENCSR907GUB/train-*
- split: validation
path: ZC3H11A_HepG2_ENCSR907GUB/validation-*
- split: test
path: ZC3H11A_HepG2_ENCSR907GUB/test-*
- config_name: ZC3H11A_K562_ENCSR712IAG
data_files:
- split: train
path: ZC3H11A_K562_ENCSR712IAG/train-*
- split: validation
path: ZC3H11A_K562_ENCSR712IAG/validation-*
- split: test
path: ZC3H11A_K562_ENCSR712IAG/test-*
- config_name: ZC3H8_K562_ENCSR181NRW
data_files:
- split: train
path: ZC3H8_K562_ENCSR181NRW/train-*
- split: validation
path: ZC3H8_K562_ENCSR181NRW/validation-*
- split: test
path: ZC3H8_K562_ENCSR181NRW/test-*
- config_name: ZNF800_HepG2_ENCSR685AUR
data_files:
- split: train
path: ZNF800_HepG2_ENCSR685AUR/train-*
- split: validation
path: ZNF800_HepG2_ENCSR685AUR/validation-*
- split: test
path: ZNF800_HepG2_ENCSR685AUR/test-*
- config_name: ZNF800_K562_ENCSR586DGV
data_files:
- split: train
path: ZNF800_K562_ENCSR586DGV/train-*
- split: validation
path: ZNF800_K562_ENCSR586DGV/validation-*
- split: test
path: ZNF800_K562_ENCSR586DGV/test-*
- config_name: ZRANB2_K562_ENCSR663NRA
data_files:
- split: train
path: ZRANB2_K562_ENCSR663NRA/train-*
- split: validation
path: ZRANB2_K562_ENCSR663NRA/validation-*
- split: test
path: ZRANB2_K562_ENCSR663NRA/test-*
---
提供机构:
yeolab



