DeepVRegulome

462 fine-tuned DNABERT models for regulatory variant effect prediction

DeepVRegulome is an end-to-end framework for predicting the functional impact of small somatic variants in non-coding regulatory regions using fine-tuned DNABERT models. It covers 458 transcription factors and 4 histone modifications from ENCODE ChIP-seq data.

๐Ÿ“„ Paper: arXiv:2511.09026 ๐Ÿ’ป Code: GitHub ๐ŸŒ Web App: deepvregulome.streamlit.app

Quick Start

from transformers import AutoModelForSequenceClassification, AutoTokenizer
import torch

# Load any model using subfolder
model_name = "CTCFL"  # or "SP1", "MYC", "H3K27ac", etc.
tokenizer = AutoTokenizer.from_pretrained(
    "duttaprat/DeepVRegulome", subfolder=f"models/{model_name}"
)
model = AutoModelForSequenceClassification.from_pretrained(
    "duttaprat/DeepVRegulome", subfolder=f"models/{model_name}"
)
model.eval()

# Convert DNA to 6-mer representation
def to_kmer(seq, k=6):
    return " ".join([seq[i:i+k] for i in range(len(seq) - k + 1)])

# Predict binding probability
sequence = "ATCGATCG..."  # 301bp DNA sequence
inputs = tokenizer(to_kmer(sequence), return_tensors="pt",
                   max_length=512, truncation=True, padding=True)
with torch.no_grad():
    prob = torch.softmax(model(**inputs).logits, dim=-1)[0][1].item()
print(f"{model_name} binding probability: {prob:.4f}")

Variant Effect Scoring

import math

def score_variant(model, tokenizer, ref_seq, alt_seq):
    probs = {}
    for name, seq in [("REF", ref_seq), ("ALT", alt_seq)]:
        inputs = tokenizer(to_kmer(seq), return_tensors="pt",
                           max_length=512, truncation=True, padding=True)
        with torch.no_grad():
            probs[name] = torch.softmax(model(**inputs).logits, dim=-1)[0][1].item()

    eps = 1e-7
    lo_ref = math.log((probs["REF"] + eps) / (1 - probs["REF"] + eps))
    lo_alt = math.log((probs["ALT"] + eps) / (1 - probs["ALT"] + eps))
    return {
        "prob_ref": probs["REF"],
        "prob_alt": probs["ALT"],
        "log_odds_change": lo_alt - lo_ref,
        "disrupted": abs(lo_alt - lo_ref) > 2.0,
    }

Available Models (462)

Each model is in models/<NAME>/ subfolder. Load with:

AutoModel.from_pretrained("duttaprat/DeepVRegulome", subfolder="models/<NAME>")
# Model Type Accuracy F1 ROC-AUC PR-AUC Peaks
1 CTCFL TF 98.39 98.4 99.71 99.7 12743
2 ZNF426 TF 97.09 96.64 98.08 98.65 7915
3 SAFB TF 97.02 96.81 98.38 98.57 5361
4 RBM34 TF 97 96.53 98.18 98.44 928
5 TAF15 TF 96.74 96.41 99.02 98.58 17900
6 PCBP1 TF 96.7 95.94 99.19 98.66 16229
7 SRSF3 TF 96.6 96.52 98.2 95.53 1610
8 RBM14 TF 96.57 95.73 98.8 98.4 2463
9 KDM4A TF 96.07 95.99 99.08 98.72 25968
10 NFYA TF 95.91 95.19 96.88 93.73 4313
11 SPI1 TF 95.79 95.78 98.75 98.38 104150
12 HLF TF 95.71 95.83 98.88 98.74 66792
13 EGR2 TF 95.68 99.22 99.75 99.6 57610
14 HNRNPLL TF 95.43 93.73 98.77 97.88 25270
15 HNRNPK TF 95.41 94.27 97.05 96.06 24014
16 FIP1L1 TF 95.35 94.16 98.25 98.13 10123
17 ZNF654 TF 95.31 95.28 97.93 98.17 33357
18 ZNF146 TF 95.23 94.66 97.57 97.69 38167
19 E2F6 TF 95.14 93.71 98.25 96.91 30723
20 C11orf30 TF 95.13 94.98 98.63 98.61 58686
21 FUS TF 95.03 93.76 94.87 93.76 7495
22 USF1 TF 94.95 94.93 98.05 97.78 60863
23 ZNF770 TF 94.91 95.01 98.04 97.28 57572
24 AGO1 TF 94.81 92.98 97.19 96.16 16201
25 MAFG TF 94.74 94.7 97.91 97.78 44030
26 ZFHX2 TF 94.73 99.21 99.82 99.74 61052
27 THAP1 TF 94.7 94.48 98.22 97.82 5210
28 HES2 TF 94.55 84.34 97.15 84.39 6520
29 SRSF1 TF 94.49 93.59 98.34 97.9 9933
30 NFE2 TF 94.22 99.19 99.76 99.72 53717
31 MITF TF 94.14 93.57 98.35 98.12 36171
32 MAFF TF 93.91 93.91 97.86 97.17 65684
33 PCBP2 TF 93.89 93.23 96.53 96.61 5328
34 ZIC2 TF 93.77 93.9 97.82 96.94 56766
35 GLIS2 TF 93.74 93.14 98.22 97.8 33566
36 ZNF121 TF 93.64 98.86 99.34 99.26 35805
37 SP2 TF 93.6 93.13 96.81 95.36 27956
38 SCRT2 TF 93.59 98.97 99.56 99.17 59462
39 BATF TF 93.58 93.82 98.16 97.93 36658
40 HNRNPL TF 93.57 92.29 97.59 96.88 24447
41 NFE2L2 TF 93.53 91.27 97.24 96.09 26392
42 ZNF585B TF 93.43 93.4 97.78 98 7381
43 NFYB TF 93.31 91.7 96.3 95.22 14696
44 ZSCAN4 TF 93.25 92.72 97.64 97.75 23997
45 ZNF316 TF 93.22 93.43 97.42 97.55 97518
46 ZNF140 TF 93.19 92.79 96.45 96.93 7623
47 ZNF777 TF 93.12 92.58 97.24 97.07 7181
48 CBFA2T2 TF 93.06 93.09 97.31 97.25 32239
49 TFAP4 TF 93 92.84 96.79 94.97 27035
50 ATF4 TF 93 92.84 97.72 97.64 39441
51 CTBP2 TF 92.98 92.36 96.78 94.11 7351
52 MXD3 TF 92.88 92.08 98.24 97.87 14677
53 E2F1 TF 92.88 86.4 95.25 91.61 18927
54 ZNF202 TF 92.87 92.87 96.29 96.5 6476
55 ZNF266 TF 92.84 92.56 96.93 96.93 5097
56 ZNF263 TF 92.83 91.44 97.39 96.16 35011
57 ZNF433 TF 92.77 92.49 96.97 97.7 3530
58 RBM39 TF 92.73 91.61 97.44 96.77 29478
59 ZNF680 TF 92.69 92.24 97.36 97.68 10483
60 ZNF341 TF 92.66 92.24 97.24 96.26 33413
61 E2F4 TF 92.64 90.76 97.32 97.07 11270
62 CBFA2T3 TF 92.59 92.67 96.97 96.03 51994
63 ZNF555 TF 92.57 92.23 94.78 96.56 6664
64 RBM25 TF 92.56 92.48 96.96 97.05 47193
65 MAFK TF 92.55 92.65 97.36 97.6 121216
66 ZNF623 TF 92.53 92.19 96.77 97.51 14353
67 KAT2A TF 92.45 91.3 92.39 92.84 171
68 SIN3B TF 92.45 90.29 97.21 96.89 11700
69 CEBPA TF 92.39 98.89 99.7 99.6 57842
70 U2AF2 TF 92.37 91.72 96.2 94.8 2777
71 ZBTB10 TF 92.27 91.31 96.02 94.41 15441
72 PBX3 TF 92.25 92.23 96.51 95.35 12981
73 SAP30 TF 92.08 90.13 96.21 92.3 15727
74 PHF8 TF 92.03 88.66 96.25 95.67 30275
75 PAX5 TF 92.02 90.77 96.81 94.42 36090
76 ZNF785 TF 92.01 91.35 97.35 97.16 6605
77 ZNF76 TF 92 90.95 93.83 89.14 11676
78 HNF4G TF 91.93 90.87 96.43 95.82 35204
79 AHR TF 91.82 91.39 97.21 96.43 10611
80 ZC3H11A TF 91.8 91.33 96.31 97.12 9905
81 RFX1 TF 91.79 90.4 96.44 96.43 38873
82 SMAD4 TF 91.75 91.7 96.19 94.92 43342
83 UBTF TF 91.73 89.06 94.72 91.45 19173
84 ZNF704 TF 91.71 90.84 94.66 94.52 1834
85 TAL1 TF 91.69 90.15 96.07 95.03 36574
86 ZBTB7A TF 91.69 90.22 97.14 95.99 37497
87 CEBPB TF 91.69 98.47 99.54 99.42 148540
88 NFIL3 TF 91.67 91.52 96.42 96 38852
89 XRCC5 TF 91.61 90.04 95.9 93.22 32847
90 U2AF1 TF 91.6 89.92 96.08 96 8379
91 ZNF34 TF 91.58 91.34 95.28 96.71 9650
92 FOXP2 TF 91.57 90.78 96.14 93.84 24150
93 AGO2 TF 91.55 89.26 95.16 94.66 33079
94 RUNX3 TF 91.53 98.64 99.5 99.27 69903
95 ZBED5 TF 91.49 91.43 97.14 96.94 5100
96 RARA TF 91.46 91.59 95.97 94.89 42489
97 FOS TF 91.45 98.69 99.62 99.63 169317
98 SP3 TF 91.44 90.22 95.27 94.77 23619
99 NANOG TF 91.43 90.45 95.72 94.36 15681
100 USF2 TF 91.39 89.66 96.88 96.27 37240
101 SP5 TF 91.37 91.12 95.54 94.28 23155
102 HNF4A TF 91.37 91.63 96.12 95.11 89892
103 ZNF354C TF 91.37 90.59 95.08 96.39 1640
104 ZNF444 TF 91.35 90.8 95.64 94.38 25366
105 GMEB2 TF 91.33 90.21 95.76 95.89 4800
106 ZNF677 TF 91.33 91.35 94.68 94.52 5777
107 IRF4 TF 91.18 91.14 96.12 95.26 21810
108 ETV5 TF 91.18 90.89 96.55 95.11 29604
109 PRPF4 TF 91.14 89.78 96.21 95.93 8605
110 FOXA3 TF 91.12 91.46 96.8 96.6 45297
111 ZNF292 TF 91.11 90.59 94.63 96.11 1900
112 GLIS1 TF 91.07 90.1 96.04 95.32 58506
113 FOXA2 TF 91.05 91.28 96.39 96.06 99343
114 KLF9 TF 90.99 87.95 95.59 94.68 32290
115 SOX5 TF 90.98 90.85 95.23 93.77 37979
116 BCL6 TF 90.97 90.9 96.3 95.48 38142
117 IRF3 TF 90.97 87.65 96.01 95.01 5726
118 ZNF223 TF 90.97 90.6 95.52 95.63 5176
119 HCFC1 TF 90.96 85.32 94.4 91.32 19700
120 HNRNPH1 TF 90.85 89.75 96.02 95.65 2446
121 DEAF1 TF 90.85 90.18 94.68 95.53 3170
122 CEBPZ TF 90.82 86.79 89.86 85.64 1971
123 PTBP1 TF 90.8 89.88 94.48 89.35 8063
124 STAT3 TF 90.79 90.81 96.82 96.85 65231
125 KAT2B TF 90.77 90.48 96.6 96.8 3106
126 SOX13 TF 90.76 90.83 96.32 95.69 48796
127 ZNF423 TF 90.75 90.32 94.63 93.05 11299
128 STAT2 TF 90.73 89.46 95.84 93.72 4303
129 MEIS2 TF 90.71 90.78 96.27 96.07 52199
130 ATF2 TF 90.69 90.57 94.77 94.25 110897
131 NFIA TF 90.67 90.58 95.6 95.07 27816
132 PATZ1 TF 90.67 89.53 96.62 95.93 35416
133 ZNF398 TF 90.66 89.94 94.96 92.96 26224
134 KLF1 TF 90.65 89.32 94.52 92.79 40024
135 SCRT1 TF 90.65 90.42 94.93 94.54 25487
136 NFIB TF 90.65 87.93 96.05 95.1 27982
137 PLRG1 TF 90.64 90.06 96.68 96.85 2256
138 PRDM1 TF 90.62 95.17 98.83 98.73 50489
139 ZNF133 TF 90.61 90.22 95.36 94.71 8423
140 SREBF2 TF 90.59 89.11 96.2 95.55 4933
141 EBF1 TF 90.59 90.64 95.31 94.3 56947
142 THAP11 TF 90.57 89.79 94.85 93.4 31698
143 ZNF48 TF 90.56 89.58 94.31 91 28840
144 POU5F1 TF 90.56 89.71 96.35 95.35 7870
145 RB1 TF 90.5 87.95 94 91.78 31314
146 ZBTB6 TF 90.44 90.06 95.43 95.01 13955
147 HNF1A TF 90.44 90.13 93.47 91.12 12818
148 KDM5B TF 90.43 88.75 96.53 95.91 18356
149 ZNF521 TF 90.37 90.04 96.17 96.82 1585
150 GLI4 TF 90.37 90.04 96.45 96.57 6130
151 RERE TF 90.37 89.28 95.15 93.11 11849
152 ZBTB26 TF 90.33 87.38 93.76 90.92 32837
153 FOXP1 TF 90.33 89.44 95.14 93.99 31380
154 ZNF596 TF 90.31 89.88 95.56 95.65 14087
155 ZBTB21 TF 90.29 89.52 96.14 95.86 18547
156 HMGXB4 TF 90.27 89.5 93.94 91.67 25984
157 TEAD1 TF 90.27 90.29 95.53 94.84 33326
158 ZNF660 TF 90.18 89.77 94.75 94.22 29821
159 SFPQ TF 90.18 90.09 91.7 90.66 335
160 ZNF658 TF 90.14 88.6 93.92 94.54 1325
161 SKI TF 90.12 89.27 95.47 93.65 30460
162 SRF TF 90.12 87.92 96 94.95 27692
163 CEBPG TF 90.11 90.14 96.25 96.42 87912
164 ZHX1 TF 90.1 88.61 94.55 92.57 5512
165 RUNX1 TF 90.07 89.3 94.29 91.85 7554
166 RXRB TF 90.07 89.83 94.62 92.92 38236
167 ZBTB48 TF 90.05 89.29 96.26 95.22 24899
168 ZNF747 TF 90.02 88.84 95.87 95.94 1427
169 VEZF1 TF 90.01 88.14 94.32 93.48 35726
170 GATA1 TF 89.96 87.31 93.39 91.08 33326
171 ZNF670 TF 89.95 88.3 95.12 95.63 1288
172 ARID4B TF 89.94 88.99 94.05 92.27 42648
173 ZNF449 TF 89.94 89.32 94.61 94.5 18374
174 KLF17 TF 89.93 89.05 96.18 95.48 25375
175 ZBTB20 TF 89.91 88.23 95.2 92.94 31889
176 ELF3 TF 89.85 89.43 95.06 93.86 35966
177 ZNF16 TF 89.85 89.14 95.41 95.27 2784
178 ZMIZ1 TF 89.85 90.09 95.22 95.28 1077
179 ZSCAN5A TF 89.84 89.2 93.59 90.92 8202
180 ZNF143 TF 89.84 98.49 99.48 99.5 66295
181 ZNF513 TF 89.78 88.85 94.49 95.41 11211
182 PPARG TF 89.77 89.47 94.59 93.53 23903
183 ZBTB8A TF 89.73 88.24 94 92.72 32420
184 IRF5 TF 89.71 89.41 93.56 94.62 2755
185 ZMYM3 TF 89.71 89.32 95.52 95.45 43157
186 DEK TF 89.7 88.82 95.38 93.29 8490
187 GABPB1 TF 89.7 89.12 94.29 92.92 47437
188 ZNF629 TF 89.69 88.91 94.14 92.43 37813
189 ETV1 TF 89.68 89.39 95.3 95.09 20672
190 ZNF394 TF 89.67 88.63 94.54 94.01 28297
191 TEAD4 TF 89.66 89.49 95.4 94.56 34189
192 PHF20 TF 89.63 88.59 94.4 91.57 13930
193 RBBP5 TF 89.59 85.4 96.01 94.46 30322
194 NFYC TF 89.59 89.07 95.3 95.46 15080
195 ELK1 TF 89.58 84.66 91.33 89.55 12298
196 H4K12ac HISTONE 89.57 89.53 96.1 95.46 42837
197 HMBOX1 TF 89.55 88.79 95.65 94.82 24883
198 KDM5A TF 89.53 82.52 92.86 90.18 13023
199 WHSC1 TF 89.51 89.25 94.42 89.89 1801
200 ZNF692 TF 89.51 88.62 94.15 92.63 30183
201 MEF2B TF 89.51 88.5 94.65 93.45 34822
202 TCF7L2 TF 89.46 86.81 94.06 91.99 28567
203 SAP130 TF 89.46 89.63 93.52 92.26 58021
204 SETDB1 TF 89.45 87.69 96.29 95.41 4903
205 ZKSCAN1 TF 89.45 87.61 94.37 92.44 20226
206 GATA4 TF 89.43 88.99 94.52 91.79 12156
207 EGR1 TF 89.43 89.26 93.84 93.58 67451
208 SUZ12 TF 89.36 82.88 94.21 91.33 24316
209 HDAC6 TF 89.35 87.38 95.07 94.75 5762
210 TEAD3 TF 89.35 89.2 95.32 93.94 42854
211 SRSF9 TF 89.34 87.07 96.1 95.7 846
212 MLX TF 89.33 88.85 93.58 91.33 14640
213 ARID1B TF 89.32 88.77 95.17 94.59 45992
214 ZSCAN30 TF 89.31 88.65 94.12 92.49 24704
215 ZFP36 TF 89.3 86.44 94.32 92.7 32993
216 ZFP64 TF 89.3 88.8 94.25 93.12 9433
217 ZNF518A TF 89.3 88.1 94.68 95.04 16690
218 ZNF512 TF 89.29 87.52 95.55 95.6 17500
219 MEF2C TF 89.25 89.19 94.66 93.88 11421
220 ARID2 TF 89.24 88.78 93.47 91.82 11585
221 IKZF5 TF 89.21 88.59 94.7 92.99 25386
222 PRDM2 TF 89.19 88.58 93.29 91.23 3824
223 KDM6A TF 89.17 88.82 95.31 94.56 12193
224 RXRA TF 89.17 89.44 94.78 93.82 85611
225 NRF1 TF 89.15 87.63 93.52 92.27 41391
226 MEF2A TF 89.15 89.07 95.08 95.07 22725
227 SREBF1 TF 89.15 87.65 95.62 95.11 13518
228 BCOR TF 89.08 88.74 95.34 94.44 41985
229 FOSL1 TF 89.06 88.05 94.11 93.96 43596
230 ZFP69B TF 89.05 88.39 94.54 93.79 21782
231 ZNF837 TF 89 88.53 94.06 94.52 2332
232 CREB1 TF 88.96 89.04 95.48 96.05 89914
233 KDM3A TF 88.94 88.07 92.68 88.4 15970
234 POU2F2 TF 88.92 88.77 93.25 89.71 19963
235 RBPJ TF 88.92 87.6 94.85 93.61 24864
236 H2AK9ac HISTONE 88.91 89.24 94.58 92.7 129243
237 IRF2 TF 88.9 87.49 93.77 92.14 31753
238 EED TF 88.9 88.18 94.22 92.87 33175
239 CBFB TF 88.89 87.72 93.81 91.26 18476
240 ZNF362 TF 88.88 87.44 94.25 92.46 20426
241 HMG20A TF 88.87 88.31 94.68 93.45 24288
242 NR2F6 TF 88.87 88.87 93.72 92 59262
243 MIXL1 TF 88.8 88.4 94.17 93.38 25659
244 ZNF768 TF 88.79 88.37 92.77 94.22 7605
245 ZNF791 TF 88.77 87.99 94.79 95.45 3900
246 ZNF652 TF 88.76 88.46 95.01 94.59 15412
247 GTF2B TF 88.76 86.89 94.01 94.5 1890
248 CBX1 TF 88.75 87.21 94.69 92.62 12838
249 KLF4 TF 88.72 86.04 92.03 91.82 6883
250 HHEX TF 88.7 88.36 95.48 94.32 7808
251 ZFP91 TF 88.7 87.92 93.44 93.1 12862
252 ETS1 TF 88.69 84.7 94.07 90.02 30554
253 FOSL2 TF 88.66 88.52 92.87 91.8 54934
254 GMEB1 TF 88.61 86.89 94.78 94.21 22958
255 MYRF TF 88.61 88.08 92.66 88.81 6038
256 CREB3L1 TF 88.6 86.11 93.55 91.45 16274
257 MBD2 TF 88.6 85.96 94.29 92.38 20596
258 ZNF384 TF 88.58 88.42 94.86 94.74 49451
259 ZNF664 TF 88.58 88.58 94.23 93.8 26774
260 SP7 TF 88.58 87.43 93.73 92.33 43425
261 AEBP2 TF 88.57 88.27 92.65 93.95 2439
262 HOMEZ TF 88.57 88.43 94.49 93.05 25047
263 ZNF514 TF 88.55 88.75 93.62 94.15 1637
264 DRAP1 TF 88.55 87.7 93.04 91.43 23241
265 HSF1 TF 88.53 86.77 93.77 93.41 3588
266 FOXA1 TF 88.52 88.77 94.82 94.45 144475
267 KLF10 TF 88.52 87.13 93.65 91.19 18933
268 ZNF18 TF 88.49 87.85 93.25 92.44 18879
269 GATAD1 TF 88.45 87.54 92.76 90.62 22354
270 BRCA1 TF 88.43 84.43 91.88 90.63 4271
271 GATA3 TF 88.41 88.76 93.95 93.68 89323
272 TBX3 TF 88.37 86.69 92.33 87.32 16097
273 HIC1 TF 88.34 87.87 95.07 94.7 24393
274 ELF4 TF 88.29 85.91 91.81 90.4 19552
275 KLF7 TF 88.28 87.47 95.07 95.1 11741
276 MAZ TF 88.25 88.01 93.3 92.34 57653
277 YY2 TF 88.25 87.53 94.5 93.99 9753
278 RLF TF 88.25 87.22 91.97 89.17 9482
279 ZNF561 TF 88.25 87.47 92.52 89.34 21469
280 HBP1 TF 88.25 87.02 94.35 92.31 13101
281 PBX2 TF 88.24 86.87 92.57 90.17 38883
282 GATA2 TF 88.17 88.14 93.72 92.79 71662
283 ESRRA TF 88.17 86.95 93.13 89.98 41619
284 ZNF189 TF 88.17 87.09 93.99 92.74 35323
285 MIER2 TF 88.16 87.72 93.74 92.28 15598
286 TBX21 TF 88.15 87.4 94.73 94.2 38025
287 DMAP1 TF 88.15 86.04 92.88 89.99 21794
288 RFX3 TF 88.14 87.7 92.23 93.25 6180
289 FEZF1 TF 88.12 87.4 94.8 93.99 31350
290 ZNF248 TF 88.12 87.31 92.8 92.85 2499
291 ZNF600 TF 88.11 87.42 93.97 90.88 45001
292 NR2F2 TF 88.09 88 95.03 94.56 55514
293 ZNF560 TF 88.07 87.67 95.15 96.12 3447
294 BHLHE40 TF 88.01 88 92.37 91.72 90623
295 NFKBIZ TF 88 86.89 93.2 90.86 12731
296 SOX6 TF 87.97 87.18 92.97 91.69 36530
297 NCOA1 TF 87.95 83.89 92.56 89.24 26193
298 ZNF2 TF 87.94 86.44 92.68 91 24945
299 JUNB TF 87.93 88.02 92.72 91.19 51972
300 KDM4B TF 87.93 86.42 93.56 94.18 7803
301 ZNF10 TF 87.88 87.16 93.83 93.93 17922
302 MYB TF 87.86 86.65 94.72 93.1 3337
303 MGA TF 87.84 86.5 91.45 85.5 28338
304 ZBTB2 TF 87.82 86.59 94.58 94.15 16341
305 ZEB1 TF 87.82 85.07 94.37 93.15 20733
306 REPIN1 TF 87.81 86.18 94.22 94.58 5721
307 ZNF148 TF 87.79 85.69 92.13 92.12 21902
308 ERF TF 87.78 86.48 92.92 90.58 27611
309 KLF8 TF 87.78 86.2 91.63 88.66 27450
310 MYC TF 87.77 87.53 93.73 92.94 94483
311 TRIM22 TF 87.77 97.99 99.03 99.13 55932
312 RFX5 TF 87.76 81.96 92.33 89.55 24728
313 DACH1 TF 87.72 87.31 92.88 92.63 18904
314 ZNF239 TF 87.71 86.87 92.62 91.05 4689
315 ZNF366 TF 87.69 97.9 99.1 98.73 44505
316 PRDM6 TF 87.65 87.25 94.46 92.98 42954
317 ATF3 TF 87.61 87.36 92.96 92.73 94190
318 RAD51 TF 87.58 84.45 93.59 92.92 36133
319 PRDM4 TF 87.55 87.06 93.45 92.04 20853
320 KAT8 TF 87.54 85.89 92.39 89.64 31059
321 MBD1 TF 87.54 84.57 92.74 88.6 18264
322 PKNOX1 TF 87.54 87.54 94.59 94.36 113107
323 WT1 TF 87.54 86.69 92.85 89.27 26226
324 CHD2 TF 87.52 86.08 93.75 91.52 41627
325 ZXDB TF 87.51 86.1 91.92 88.84 30796
326 HMG20B TF 87.5 86.97 93.22 90.82 12656
327 SIX5 TF 87.49 79.23 89.33 86.03 10595
328 MAX TF 87.44 87.59 92.05 89.23 94496
329 TRIM24 TF 87.42 84.62 93.51 90.72 35639
330 NONO TF 87.4 82.54 89.28 84.68 29192
331 NFE2L1 TF 87.36 83.51 90.34 91.43 10261
332 ZSCAN16 TF 87.36 87.06 92.03 89.65 6915
333 ZNF391 TF 87.36 86.05 92.69 90.97 12610
334 GATAD2A TF 87.27 87.34 92.84 92.14 59253
335 ZNF282 TF 87.23 85.73 92.1 90.4 12994
336 SMC3 TF 87.23 86.92 93.67 94.33 89498
337 SMARCA4 TF 87.23 87.23 92.59 91.47 94655
338 ZNF645 TF 87.19 85.99 93.82 93.71 3597
339 SIRT6 TF 87.18 86.27 91.81 89.63 831
340 ZNF205 TF 87.17 85.68 93.89 92.45 17444
341 ZBTB11 TF 87.17 83.11 93.24 92.37 34307
342 KLF13 TF 87.15 86.93 90.16 85.26 11590
343 NKRF TF 87.15 82.95 93.67 92.25 27626
344 OSR2 TF 87.15 86.49 92.7 90.29 33243
345 CC2D1A TF 87.14 86.24 92.24 91.48 24056
346 NFIC TF 87.14 87.09 92.88 93.61 74803
347 ZNF138 TF 87.12 86.79 93.04 94.92 1611
348 PHB2 TF 87.11 86.36 93.7 93.49 8362
349 ZHX2 TF 87.11 84.59 92.57 90.95 14751
350 ZNF614 TF 87.09 86.34 92.96 90.43 21841
351 ZBTB44 TF 87.09 86.97 91.7 89.35 19961
352 ZNF501 TF 87.07 84.58 89.56 85.25 18650
353 ZNF547 TF 87.07 87.18 93.08 93.55 4777
354 E4F1 TF 87.05 83.51 91.86 88.4 27783
355 ZNF530 TF 87 86.21 92.54 93.54 2193
356 MYNN TF 86.97 85.32 92.29 90.37 19348
357 INSM2 TF 86.94 86.19 92.8 91.74 16385
358 ZBTB7B TF 86.94 85.85 93.93 93.22 9156
359 BCL11B TF 86.93 86.01 92.01 89.38 11525
360 ZBTB12 TF 86.93 86.23 92.9 91.71 10363
361 PML TF 86.92 85.32 93.87 93.51 18068
362 SALL2 TF 86.9 86.55 93.23 94.22 2489
363 NR2F1 TF 86.87 86.87 93.08 92.05 70026
364 LCORL TF 86.86 86.86 93.26 93.83 10617
365 THRB TF 86.86 86.05 92.7 91.63 14895
366 ZGPAT TF 86.84 85.13 90.76 86.79 33522
367 MIER3 TF 86.83 85.69 92.53 91.2 19565
368 KMT2B TF 86.81 84.82 92.77 91.54 17871
369 TGIF2 TF 86.8 85.45 92.88 90.99 18162
370 IKZF2 TF 86.79 86.64 92.67 91.71 52015
371 ZBTB33 TF 86.78 92.02 97.16 96.92 96111
372 NEUROD1 TF 86.73 85.61 92.99 91.71 19165
373 ATF7 TF 86.72 86.65 92.77 93.41 105695
374 SMARCE1 TF 86.71 86.36 92.37 91.4 48505
375 RELB TF 86.71 84.55 93.6 91.95 36669
376 ELF1 TF 86.71 86.32 93.8 94.5 70684
377 ZNF843 TF 86.68 85.41 92.05 89.55 22911
378 ATM TF 86.67 85.99 93.74 94.31 2162
379 ZNF473 TF 86.67 86.34 92.54 93 2252
380 MXD4 TF 86.63 84.43 91.34 88.33 18180
381 ZNF707 TF 86.61 86.66 93.38 93.31 3329
382 CREM TF 86.61 86.56 92.96 93.26 72466
383 ZNF157 TF 86.6 86.52 89.54 86.21 3778
384 IKZF3 TF 86.59 85.8 91.99 88.04 29535
385 DIDO1 TF 86.58 85.66 92.29 92.48 7186
386 ZSCAN26 TF 86.56 85.08 93.43 94.67 2537
387 MXI1 TF 86.53 86.12 94.05 94.26 52982
388 ZSCAN18 TF 86.51 85.15 92.3 92.92 4130
389 CDC5L TF 86.47 85.08 93.59 93.67 5151
390 KLF5 TF 86.44 85.35 92.7 90.15 11680
391 ZNF512B TF 86.43 83.44 93.26 91.76 8552
392 LARP7 TF 86.42 84.12 93.32 92.81 27160
393 ZNF280C TF 86.42 86.07 92.27 92.66 1292
394 L3MBTL2 TF 86.41 86.23 91.05 89.82 52245
395 MCM2 TF 86.41 85.41 93.45 94.29 4549
396 ZNF404 TF 86.4 85.45 91.88 93.7 2249
397 E2F7 TF 86.4 85.34 91.15 91.4 2985
398 MTA1 TF 86.34 84.24 93.57 92.13 22370
399 ZNF324 TF 86.32 84.57 93.81 93.44 14713
400 GTF2F1 TF 86.32 83.54 92.14 90.16 39350
401 RAD21 TF 86.3 97.92 99.11 98.99 188052
402 NR2C1 TF 86.27 81.88 90.51 85.79 31898
403 RBAK TF 86.25 85.74 92.56 93.16 3642
404 TCF7 TF 86.23 85.39 92.08 90.33 30462
405 ZNF776 TF 86.23 85.19 92.22 92.04 2838
406 ARHGAP35 TF 86.18 85.43 93.57 93.39 4817
407 STAT1 TF 86.15 83.28 92.57 90.18 11457
408 ZNF621 TF 86.14 85.57 92.51 92.93 1976
409 YBX3 TF 86.12 84.54 90.9 90.72 2599
410 ZNF610 TF 86.07 84.35 91.36 89.32 13333
411 OVOL3 TF 86.05 85.14 90.46 88.66 9089
412 GLI2 TF 86.05 86.28 91.17 92.26 5650
413 KLF6 TF 86.05 84.14 91.14 87.94 15409
414 ASH1L TF 85.96 84.17 92.97 93.93 7269
415 NR3C1 TF 85.91 85.89 93.29 93.1 62779
416 KLF16 TF 85.91 85.24 90.83 90.08 48641
417 ZNF114 TF 85.91 82.83 91.36 91.57 1444
418 PRDM10 TF 85.9 86.39 91.62 88.42 68962
419 ZSCAN29 TF 85.87 82.16 90.3 85.84 21597
420 IRF1 TF 85.84 80.68 89.75 87.82 32357
421 ZSCAN9 TF 85.83 84.87 91.14 89.95 17526
422 ZFP3 TF 85.82 84.76 93.06 93.73 4550
423 TAF7 TF 85.79 81.76 93.28 92.37 21002
424 MNT TF 85.79 85.08 92.76 93.16 83589
425 ZFP37 TF 85.78 83.76 89.27 86.32 16553
426 MZF1 TF 85.78 85.16 91.67 89.93 17643
427 TOE1 TF 85.74 82.45 89.5 89.69 29556
428 PHF21A TF 85.74 85.18 88.24 82.19 8878
429 BACH1 TF 85.62 83.64 90.78 88.15 41151
430 ZNF7 TF 85.61 84.92 92.67 92.68 8038
431 ZNF211 TF 85.59 84.6 91.95 92.44 1919
432 ZSCAN23 TF 85.58 84.31 92.3 91.5 8505
433 FOXM1 TF 85.57 83.72 90.82 89.44 20757
434 SUPT5H TF 85.56 81.99 93.26 92.1 22469
435 BCL3 TF 85.55 83.8 93.27 92.67 43282
436 TFDP1 TF 85.52 80.8 89.14 84.38 30292
437 TAF9B TF 85.46 83.58 87.02 79.88 13069
438 ZNF792 TF 85.46 83.82 92.95 91.81 24699
439 SIN3A TF 85.43 85.07 93.29 93.11 65597
440 JUND TF 85.43 85.33 93.1 93.42 166033
441 H3K9me1 HISTONE 85.43 87.45 93.75 91.95 196657
442 BCL11A TF 85.41 84.36 92.15 91.13 33663
443 POLR2G TF 85.39 84.83 92.98 93.64 59528
444 H3K23me2 HISTONE 85.39 85.45 93.76 93.34 77099
445 NR2C2 TF 85.39 80.24 89.73 86.9 29811
446 ZNF571 TF 85.34 84.53 92.7 93.55 1488
447 ZNF311 TF 85.34 84.08 92.44 93.57 2206
448 EP400 TF 85.29 82.21 89.96 88.24 25324
449 ZFP1 TF 85.26 83.98 91.92 90.8 12129
450 REST TF 85.25 84.97 90.84 91.49 119743
451 RCOR2 TF 85.25 84.38 90.5 88.89 19532
452 SP1 TF 85.24 84.86 91.19 91.14 120925
453 MCM3 TF 85.24 84.32 93 93.26 2561
454 ZNF169 TF 85.23 84.36 91.23 90.6 2873
455 PHF5A TF 85.23 82.4 90.52 88.55 9570
456 TSHZ1 TF 85.17 84.45 92.39 91.76 11804
457 MTA2 TF 85.15 84.91 90.5 89.57 59001
458 GFI1B TF 85.11 84.57 91.26 90.52 10694
459 ZNF558 TF 85.1 84.16 91.1 91.2 13849
460 ZNF19 TF 85.06 84.17 91.34 93.34 1998
461 SMAD5 TF 85.03 79.12 92.23 90.37 22402
462 SNRNP70 TF 85.02 82.87 89.28 89.69 871

Model Details

Property Value
Base model DNABERT (6-mer, k=6)
Architecture BERT-base (~340M parameters)
Task Binary classification (binding/no-binding)
Input 301 bp DNA sequence (6-mer tokenized)
Training data ENCODE ChIP-seq
Species Human (hg38)
License CC-BY-NC-4.0

Citation

@article{deepvregulome2025,
  title={DeepVRegulome: DNABERT-based deep-learning framework for predicting
         the functional impact of short genomic variants on the human regulome},
  author={Dutta, Pratik and Sarkar, Shayan and Sathian, Rekha and Tasnim,
          Taharina and Sibi, Sahanya and Sahanya, Samantha and Ghosal,
          Tirthankar and Ay, Ferhat and Zhong, Zhihan and Han, Jiayu
          and Davuluri, Ramana V.},
  journal={arXiv preprint arXiv:2511.09026},
  year={2025},
  url={https://arxiv.org/abs/2511.09026}
}
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Paper for duttaprat/DeepVRegulome