Method

ChromBPNet (ab initio)

Convolutional network with dilated residual layers that predicts base-resolution chromatin accessibility profiles and total read counts from 2,114 bp of one-hot DNA sequence.

14 evaluations · 14 results

Overview

An explanatory profile has not yet been reviewed for this record.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

Evaluations and results

14 evaluations · 14 results. Different protocols are not a single leaderboard.

Sorted by AUROC (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.

Tested configuration	Protocol and dataset	AUROC	Spearman	Pearson
ChromBPNet (ab initio)Evaluation	DART-Eval CA-AUROC-IMR90: Chromatin activity prediction, IMR90, positives against negatives, ENCODE chromatin accessibility peaks in five cell lines (DART-Eval split)	0.975 (best in column)	Not reported	Not reported
ChromBPNet (ab initio)Evaluation	DART-Eval CA-AUROC-H1ESC: Chromatin activity prediction, H1ESC, positives against negatives, ENCODE chromatin accessibility peaks in five cell lines (DART-Eval split)	0.952	Not reported	Not reported
ChromBPNet (ab initio)Evaluation	DART-Eval CA-AUROC-GM12878: Chromatin activity prediction, GM12878, positives against negatives, ENCODE chromatin accessibility peaks in five cell lines (DART-Eval split)	0.94	Not reported	Not reported
ChromBPNet (ab initio)Evaluation	DART-Eval CA-AUROC-K562: Chromatin activity prediction, K562, positives against negatives, ENCODE chromatin accessibility peaks in five cell lines (DART-Eval split)	0.917	Not reported	Not reported
ChromBPNet (ab initio)Evaluation	DART-Eval CA-AUROC-HEPG2: Chromatin activity prediction, HEPG2, positives against negatives, ENCODE chromatin accessibility peaks in five cell lines (DART-Eval split)	0.91	Not reported	Not reported
ChromBPNet (ab initio)Evaluation	DART-Eval VS-YORUBAN-AUROC: Variant scoring on DNase QTLs in Yoruban LCLs, AUROC, DNase QTLs in Yoruban LCLs (DART-Eval split)	0.892	Not reported	Not reported
ChromBPNet (ab initio)Evaluation	DART-Eval VS-AFRICAN-AUROC: Variant scoring on Chromatin QTLs in African LCLs, AUROC, Chromatin QTLs in African LCLs (DART-Eval split)	0.772	Not reported	Not reported
ChromBPNet (ab initio)Evaluation	DART-Eval CA-SPEARMAN-GM12878: Chromatin activity prediction, GM12878, positives only, ENCODE chromatin accessibility peaks in five cell lines (DART-Eval split)	Not reported	0.54	Not reported
ChromBPNet (ab initio)Evaluation	DART-Eval CA-SPEARMAN-H1ESC: Chromatin activity prediction, H1ESC, positives only, ENCODE chromatin accessibility peaks in five cell lines (DART-Eval split)	Not reported	0.754 (best in column)	Not reported
ChromBPNet (ab initio)Evaluation	DART-Eval CA-SPEARMAN-HEPG2: Chromatin activity prediction, HEPG2, positives only, ENCODE chromatin accessibility peaks in five cell lines (DART-Eval split)	Not reported	0.534	Not reported
ChromBPNet (ab initio)Evaluation	DART-Eval CA-SPEARMAN-IMR90: Chromatin activity prediction, IMR90, positives only, ENCODE chromatin accessibility peaks in five cell lines (DART-Eval split)	Not reported	0.549	Not reported
ChromBPNet (ab initio)Evaluation	DART-Eval CA-SPEARMAN-K562: Chromatin activity prediction, K562, positives only, ENCODE chromatin accessibility peaks in five cell lines (DART-Eval split)	Not reported	0.574	Not reported
ChromBPNet (ab initio)Evaluation	DART-Eval VS-AFRICAN-PEARSON_R: Variant scoring on Chromatin QTLs in African LCLs, Pearson r, Chromatin QTLs in African LCLs (DART-Eval split)	Not reported	Not reported	0.671
ChromBPNet (ab initio)Evaluation	DART-Eval VS-YORUBAN-PEARSON_R: Variant scoring on DNase QTLs in Yoruban LCLs, Pearson r, DNase QTLs in Yoruban LCLs (DART-Eval split)	Not reported	Not reported	0.738 (best in column)

All 14 result rows with coverage, uncertainty and sources

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Method: ChromBPNet (ab initio)	Task: DART-Eval CA-AUROC-GM12878: Chromatin activity prediction, GM12878, positives against negatives Dataset subset: ENCODE chromatin accessibility peaks in five cell lines (DART-Eval split)	0.94 AUROC unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ChromBPNet (ab initio) on DART-Eval CA-AUROC-GM12878: Chromatin activity prediction, GM12878, positives against negatives Separating positive GM12878 peaks from matched negatives. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 5, row(Ab initio ChromBPNet), column(CA-AUROC-GM12878)
Method: ChromBPNet (ab initio)	Task: DART-Eval CA-AUROC-H1ESC: Chromatin activity prediction, H1ESC, positives against negatives Dataset subset: ENCODE chromatin accessibility peaks in five cell lines (DART-Eval split)	0.952 AUROC unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ChromBPNet (ab initio) on DART-Eval CA-AUROC-H1ESC: Chromatin activity prediction, H1ESC, positives against negatives Separating positive H1ESC peaks from matched negatives. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 5, row(Ab initio ChromBPNet), column(CA-AUROC-H1ESC)
Method: ChromBPNet (ab initio)	Task: DART-Eval CA-AUROC-HEPG2: Chromatin activity prediction, HEPG2, positives against negatives Dataset subset: ENCODE chromatin accessibility peaks in five cell lines (DART-Eval split)	0.91 AUROC unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ChromBPNet (ab initio) on DART-Eval CA-AUROC-HEPG2: Chromatin activity prediction, HEPG2, positives against negatives Separating positive HEPG2 peaks from matched negatives. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 5, row(Ab initio ChromBPNet), column(CA-AUROC-HEPG2)
Method: ChromBPNet (ab initio)	Task: DART-Eval CA-AUROC-IMR90: Chromatin activity prediction, IMR90, positives against negatives Dataset subset: ENCODE chromatin accessibility peaks in five cell lines (DART-Eval split)	0.975 AUROC unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ChromBPNet (ab initio) on DART-Eval CA-AUROC-IMR90: Chromatin activity prediction, IMR90, positives against negatives Separating positive IMR90 peaks from matched negatives. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 5, row(Ab initio ChromBPNet), column(CA-AUROC-IMR90)
Method: ChromBPNet (ab initio)	Task: DART-Eval CA-AUROC-K562: Chromatin activity prediction, K562, positives against negatives Dataset subset: ENCODE chromatin accessibility peaks in five cell lines (DART-Eval split)	0.917 AUROC unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ChromBPNet (ab initio) on DART-Eval CA-AUROC-K562: Chromatin activity prediction, K562, positives against negatives Separating positive K562 peaks from matched negatives. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 5, row(Ab initio ChromBPNet), column(CA-AUROC-K562)
Method: ChromBPNet (ab initio)	Task: DART-Eval CA-SPEARMAN-GM12878: Chromatin activity prediction, GM12878, positives only Dataset subset: ENCODE chromatin accessibility peaks in five cell lines (DART-Eval split)	0.54 Spearman unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ChromBPNet (ab initio) on DART-Eval CA-SPEARMAN-GM12878: Chromatin activity prediction, GM12878, positives only Rank correlation with measured accessibility among positive GM12878 peaks. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 5, row(Ab initio ChromBPNet), column(CA-SPEARMAN-GM12878)
Method: ChromBPNet (ab initio)	Task: DART-Eval CA-SPEARMAN-H1ESC: Chromatin activity prediction, H1ESC, positives only Dataset subset: ENCODE chromatin accessibility peaks in five cell lines (DART-Eval split)	0.754 Spearman unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ChromBPNet (ab initio) on DART-Eval CA-SPEARMAN-H1ESC: Chromatin activity prediction, H1ESC, positives only Rank correlation with measured accessibility among positive H1ESC peaks. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 5, row(Ab initio ChromBPNet), column(CA-SPEARMAN-H1ESC)
Method: ChromBPNet (ab initio)	Task: DART-Eval CA-SPEARMAN-HEPG2: Chromatin activity prediction, HEPG2, positives only Dataset subset: ENCODE chromatin accessibility peaks in five cell lines (DART-Eval split)	0.534 Spearman unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ChromBPNet (ab initio) on DART-Eval CA-SPEARMAN-HEPG2: Chromatin activity prediction, HEPG2, positives only Rank correlation with measured accessibility among positive HEPG2 peaks. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 5, row(Ab initio ChromBPNet), column(CA-SPEARMAN-HEPG2)
Method: ChromBPNet (ab initio)	Task: DART-Eval CA-SPEARMAN-IMR90: Chromatin activity prediction, IMR90, positives only Dataset subset: ENCODE chromatin accessibility peaks in five cell lines (DART-Eval split)	0.549 Spearman unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ChromBPNet (ab initio) on DART-Eval CA-SPEARMAN-IMR90: Chromatin activity prediction, IMR90, positives only Rank correlation with measured accessibility among positive IMR90 peaks. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 5, row(Ab initio ChromBPNet), column(CA-SPEARMAN-IMR90)
Method: ChromBPNet (ab initio)	Task: DART-Eval CA-SPEARMAN-K562: Chromatin activity prediction, K562, positives only Dataset subset: ENCODE chromatin accessibility peaks in five cell lines (DART-Eval split)	0.574 Spearman unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ChromBPNet (ab initio) on DART-Eval CA-SPEARMAN-K562: Chromatin activity prediction, K562, positives only Rank correlation with measured accessibility among positive K562 peaks. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 5, row(Ab initio ChromBPNet), column(CA-SPEARMAN-K562)
Method: ChromBPNet (ab initio)	Task: DART-Eval VS-AFRICAN-AUROC: Variant scoring on Chromatin QTLs in African LCLs, AUROC Dataset subset: Chromatin QTLs in African LCLs (DART-Eval split)	0.772 AUROC unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ChromBPNet (ab initio) on DART-Eval VS-AFRICAN-AUROC: Variant scoring on Chromatin QTLs in African LCLs, AUROC Score the effect of a variant on chromatin accessibility, against the measured QTL call. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 6, row(African ChromBPNet), column(ab initio auroc)
Method: ChromBPNet (ab initio)	Task: DART-Eval VS-AFRICAN-PEARSON_R: Variant scoring on Chromatin QTLs in African LCLs, Pearson r Dataset subset: Chromatin QTLs in African LCLs (DART-Eval split)	0.671 Pearson unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ChromBPNet (ab initio) on DART-Eval VS-AFRICAN-PEARSON_R: Variant scoring on Chromatin QTLs in African LCLs, Pearson r Score the effect of a variant on chromatin accessibility, against the measured QTL call. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 6, row(African ChromBPNet), column(ab initio pearson_r)
Method: ChromBPNet (ab initio)	Task: DART-Eval VS-YORUBAN-AUROC: Variant scoring on DNase QTLs in Yoruban LCLs, AUROC Dataset subset: DNase QTLs in Yoruban LCLs (DART-Eval split)	0.892 AUROC unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ChromBPNet (ab initio) on DART-Eval VS-YORUBAN-AUROC: Variant scoring on DNase QTLs in Yoruban LCLs, AUROC Score the effect of a variant on chromatin accessibility, against the measured QTL call. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 6, row(Yoruban ChromBPNet), column(ab initio auroc)
Method: ChromBPNet (ab initio)	Task: DART-Eval VS-YORUBAN-PEARSON_R: Variant scoring on DNase QTLs in Yoruban LCLs, Pearson r Dataset subset: DNase QTLs in Yoruban LCLs (DART-Eval split)	0.738 Pearson unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ChromBPNet (ab initio) on DART-Eval VS-YORUBAN-PEARSON_R: Variant scoring on DNase QTLs in Yoruban LCLs, Pearson r Score the effect of a variant on chromatin accessibility, against the measured QTL call. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 6, row(Yoruban ChromBPNet), column(ab initio pearson_r)

Source checking is not independent reproduction. Release 2026-11-02-a7f03c9e55a5.

Use this method

How it works, versions and access

Additional methodological details, versions and access terms have not yet been extracted into a structured profile for this method. Consult the linked sources and evaluation records below.

Evidence

Source checking verifies the cited claim or transcription. It does not establish independent reproduction.

Evidence table

Inspect claims, sources and review details

Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.

One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.

0 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-11-02-a7f03c9e55a5
Property and statement	Original source and location	Review and provenance

No evidence rows match these filters. Choose another scope or clear the search.

How to read the evidence

Sources and history

Release 2026-11-02-a7f03c9e55a5 · Record review: source checked

1 source record and release history

DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Original source · 2412.05430v1

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: dart-eval-method-chrombpnet-ab-initio

areas: dna-genomes
source locator: Table 1, row(ChromBPNet)
missing metadata: checkpoint revision: reason: unreported; parameters: reason: unextracted
provenance note: Pretrained ChromBPNet models from the ENCODE project, used by the DART-Eval authors as the ab initio baseline; only the count prediction was compared.

Related records

Suggest a correction