rewire.it
Protocol

TF-cell-type binding on held-out chromosomes8and9 (transcription-factor DNA binding-site prediction)

TF-cell-type binding on held-out chromosomes8and9 · Table 2.. Per-label AUROC/AUPR macro-averaged over 690 labels. Same Table 2 test cohort; methods differ in additional protein/dynamics inputs. DeepSEA-derived 690 TF-cell-type labels; chr 7 validation; remaining autosomes+X training; chr 8/9 test.

Integrating protein and DNA embeddings for improving genome-wide transcription factor binding site prediction · Table 2.: AUROC, TF-cell-type binding on held-out chromosomes8and9

6 evaluations · 12 metric rows

At a glance

Explanatory profile: limited source coverage · Automated source review, 2026-09-17. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.

How it works

Evaluation in this paper

Per-label AUROC/AUPR macro-averaged over 690 labels. Same Table 2 test cohort; methods differ in additional protein/dynamics inputs. DeepSEA-derived 690 TF-cell-type labels; chr 7 validation; remaining autosomes+X training; chr 8/9 test.

Integrating protein and DNA embeddings for improving genome-wide transcription factor binding site prediction · Table 2.: AUROC, TF-cell-type binding on held-out chromosomes8and9

Evaluation design

Benchmarks bring together tasks and protocols. A task describes the biological question; a protocol defines a particular test.

These source-backed links do not make different protocols or scores interchangeable.

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Published comparisons

Explore the results reported under one evaluation protocol. Each figure keeps its source, dataset and metric together; it is not a ranking across studies.

TF-cell-type binding on held-out chromosomes8and9 · Table 2.

AUROC (fraction) · Higher values are better for this metric.

Per-label AUROC/AUPR macro-averaged over 690 labels. Same Table 2 test cohort; methods differ in additional protein/dynamics inputs. DeepSEA-derived 690 TF-cell-type labels; chr 7 validation; remaining autosomes+X training; chr 8/9 test.

Evaluation protocol · genome-wide TF binding sites

  1. DeepSEA · Configuration · Independent external evaluation0.8934
  2. DanQ · Configuration · Independent external evaluation0.9254
  3. TBiNet · Configuration · Independent external evaluation0.9402
  4. finetuned DNABERT-2 · Configuration · Independent external evaluation0.9180
  5. EPBDXDNABERT-2 · Configuration · Result quoted from another source0.9490
  6. TransBind · Configuration · Author-reported evaluation0.9508

Source order is preserved. Plotted marks show point estimates; uncertainty, where reported, is retained in the printed values and table. Differences do not establish statistical significance.

Integrating protein and DNA embeddings for improving genome-wide transcription factor binding site prediction · Table 2.: AUROC, TF-cell-type binding on held-out chromosomes8and9
Values, uncertainty and evidence
AUROC: original source values
Tested entityPrinted valueUncertaintyEvidence
DeepSEA · Configuration0.8934 fractionNot reportedIndependent external evaluation · source checkedIntegrating protein and DNA embeddings for improving genome-wide transcription factor binding site prediction · Table 2., row DeepSEA, column AUROC; XML row2 column2
DanQ · Configuration0.9254 fractionNot reportedIndependent external evaluation · source checkedIntegrating protein and DNA embeddings for improving genome-wide transcription factor binding site prediction · Table 2., row DanQ, column AUROC; XML row3 column2
TBiNet · Configuration0.9402 fractionNot reportedIndependent external evaluation · source checkedIntegrating protein and DNA embeddings for improving genome-wide transcription factor binding site prediction · Table 2., row TBiNet, column AUROC; XML row4 column2
finetuned DNABERT-2 · Configuration0.9180 fractionNot reportedIndependent external evaluation · source checkedIntegrating protein and DNA embeddings for improving genome-wide transcription factor binding site prediction · Table 2., row finetuned DNABERT-2, column AUROC; XML row5 column2
EPBDXDNABERT-2 · Configuration0.9490 fractionNot reportedResult quoted from another source · source checkedIntegrating protein and DNA embeddings for improving genome-wide transcription factor binding site prediction · Table 2., row EPBDXDNABERT-2, column AUROC; XML row6 column2
TransBind · Configuration0.9508 fractionNot reportedAuthor-reported evaluation · source checkedIntegrating protein and DNA embeddings for improving genome-wide transcription factor binding site prediction; Integrating protein and DNA embeddings for improving genome-wide transcription factor binding site prediction · Table 2, TransBind row, AUROC column
Scope and limitations
  • Chromosome separation does not itself eliminate pretraining overlap.
  • Within-paper aggregate only; do not compare against different label sets.
  • EPBDXDNABERT-2 values are quoted from its original publication because retraining code/data were unavailable; its predictions were not available for paired testing.
  • No interval assigned unless printed in source cell.

Source transcription and grouping reviewed by automated source review on 2026-09-17. These experiments were not independently reproduced by rewire.

Tested entities and results

Release 2026-09-17-d277315f7d76 · 6 evaluations · 12 metric rows. Different protocols are not a single leaderboard.

Results grouped by the exact reported evaluation
Metric and findingCoverage and uncertaintyEvidence
TransBind: transcription-factor DNA binding-site prediction

Per-label AUROC/AUPR macro-averaged over 690 labels. Same Table 2 test cohort; methods differ in additional protein/dynamics inputs. DeepSEA-derived 690 TF-cell-type labels; chr 7 validation; remaining autosomes+X training; chr 8/9 test.

Author-reported evaluation · Evaluation metadata: needs review

0.9508 AUROC

Unit: fraction · Direction: higher

Uncertainty: not reported in legacy extract

Scored: Not reported · Eligible: Not reported

source checkedIntegrating protein and DNA embeddings for improving genome-wide transcription factor binding site prediction; Integrating protein and DNA embeddings for improving genome-wide transcription factor binding site prediction · Table 2, TransBind row, AUROC column

Source checking is not independent reproduction.

0.3741 AUPR

Unit: fraction · Direction: higher

Uncertainty: unreported

Scored: Not reported · Eligible: Not reported

source checkedIntegrating protein and DNA embeddings for improving genome-wide transcription factor binding site prediction · Table 2., row TransBind, column AUPR; XML row7 column3

Source checking is not independent reproduction.

DeepSEA: TF-cell-type binding on held-out chromosomes8and9

Per-label AUROC/AUPR macro-averaged over 690 labels. Same Table 2 test cohort; methods differ in additional protein/dynamics inputs. DeepSEA-derived 690 TF-cell-type labels; chr 7 validation; remaining autosomes+X training; chr 8/9 test.

Independent external evaluation · Evaluation metadata: needs review

0.2509 AUPR

Unit: fraction · Direction: higher

Uncertainty: unreported

Scored: Not reported · Eligible: Not reported

source checkedIntegrating protein and DNA embeddings for improving genome-wide transcription factor binding site prediction · Table 2., row DeepSEA, column AUPR; XML row2 column3

Source checking is not independent reproduction.

0.8934 AUROC

Unit: fraction · Direction: higher

Uncertainty: unreported

Scored: Not reported · Eligible: Not reported

source checkedIntegrating protein and DNA embeddings for improving genome-wide transcription factor binding site prediction · Table 2., row DeepSEA, column AUROC; XML row2 column2

Source checking is not independent reproduction.

TBiNet: TF-cell-type binding on held-out chromosomes8and9

Per-label AUROC/AUPR macro-averaged over 690 labels. Same Table 2 test cohort; methods differ in additional protein/dynamics inputs. DeepSEA-derived 690 TF-cell-type labels; chr 7 validation; remaining autosomes+X training; chr 8/9 test.

Independent external evaluation · Evaluation metadata: needs review

0.9402 AUROC

Unit: fraction · Direction: higher

Uncertainty: unreported

Scored: Not reported · Eligible: Not reported

source checkedIntegrating protein and DNA embeddings for improving genome-wide transcription factor binding site prediction · Table 2., row TBiNet, column AUROC; XML row4 column2

Source checking is not independent reproduction.

0.3346 AUPR

Unit: fraction · Direction: higher

Uncertainty: unreported

Scored: Not reported · Eligible: Not reported

source checkedIntegrating protein and DNA embeddings for improving genome-wide transcription factor binding site prediction · Table 2., row TBiNet, column AUPR; XML row4 column3

Source checking is not independent reproduction.

DanQ: TF-cell-type binding on held-out chromosomes8and9

Per-label AUROC/AUPR macro-averaged over 690 labels. Same Table 2 test cohort; methods differ in additional protein/dynamics inputs. DeepSEA-derived 690 TF-cell-type labels; chr 7 validation; remaining autosomes+X training; chr 8/9 test.

Independent external evaluation · Evaluation metadata: needs review

0.9254 AUROC

Unit: fraction · Direction: higher

Uncertainty: unreported

Scored: Not reported · Eligible: Not reported

source checkedIntegrating protein and DNA embeddings for improving genome-wide transcription factor binding site prediction · Table 2., row DanQ, column AUROC; XML row3 column2

Source checking is not independent reproduction.

0.3065 AUPR

Unit: fraction · Direction: higher

Uncertainty: unreported

Scored: Not reported · Eligible: Not reported

source checkedIntegrating protein and DNA embeddings for improving genome-wide transcription factor binding site prediction · Table 2., row DanQ, column AUPR; XML row3 column3

Source checking is not independent reproduction.

EPBDXDNABERT-2: TF-cell-type binding on held-out chromosomes8and9

Per-label AUROC/AUPR macro-averaged over 690 labels. Same Table 2 test cohort; methods differ in additional protein/dynamics inputs. DeepSEA-derived 690 TF-cell-type labels; chr 7 validation; remaining autosomes+X training; chr 8/9 test.

Result quoted from another source · Evaluation metadata: needs review

0.9490 AUROC

Unit: fraction · Direction: higher

Uncertainty: unreported

Scored: Not reported · Eligible: Not reported

source checkedIntegrating protein and DNA embeddings for improving genome-wide transcription factor binding site prediction · Table 2., row EPBDXDNABERT-2, column AUROC; XML row6 column2

Source checking is not independent reproduction.

0.3260 AUPR

Unit: fraction · Direction: higher

Uncertainty: unreported

Scored: Not reported · Eligible: Not reported

source checkedIntegrating protein and DNA embeddings for improving genome-wide transcription factor binding site prediction · Table 2., row EPBDXDNABERT-2, column AUPR; XML row6 column3

Source checking is not independent reproduction.

finetuned DNABERT-2: TF-cell-type binding on held-out chromosomes8and9

Per-label AUROC/AUPR macro-averaged over 690 labels. Same Table 2 test cohort; methods differ in additional protein/dynamics inputs. DeepSEA-derived 690 TF-cell-type labels; chr 7 validation; remaining autosomes+X training; chr 8/9 test.

Independent external evaluation · Evaluation metadata: needs review

0.9180 AUROC

Unit: fraction · Direction: higher

Uncertainty: unreported

Scored: Not reported · Eligible: Not reported

source checkedIntegrating protein and DNA embeddings for improving genome-wide transcription factor binding site prediction · Table 2., row finetuned DNABERT-2, column AUROC; XML row5 column2

Source checking is not independent reproduction.

0.2960 AUPR

Unit: fraction · Direction: higher

Uncertainty: unreported

Scored: Not reported · Eligible: Not reported

source checkedIntegrating protein and DNA embeddings for improving genome-wide transcription factor binding site prediction · Table 2., row finetuned DNABERT-2, column AUPR; XML row5 column3

Source checking is not independent reproduction.

Papers and result coverage

Last literature check: 2026-09-17. Primary-source discovery and table/protocol screening; source checked is not independently reproduced. Raw acquisitions not automatically numerical publication approval.

Paper or primary resourceVersionReference
Integrating protein and DNA embeddings for improving genome-wide transcription factor binding site predictionversion of recordRead source
DOI: 10.1093/nargab/lqag047

What is still missing

  • Independent batch review before import; preserve existing observation identities.
Search and extraction details

complete comparison tables extracted pending publication review

Searches

  • Integrating protein and DNA embeddings for improving genome-wide transcription factor binding site prediction primary paper benchmark results

Evidence locations

  • Table 2.: AUROC, TF-cell-type binding on held-out chromosomes8and9

Strengths and limitations

Strengths and considerations

No source-reviewed explanatory claims are recorded here yet.

Limitations and conditions

No source-reviewed explanatory claims are recorded here yet.

Profile review details

Primary-source transcription and separate automated review. No human sign-off or experimental reproduction.

Stable record: paper-protocol-6821afc366eb11d0c6

Evidence table

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.

3 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-09-17-d277315f7d76
Property and statementOriginal source and locationReview and provenance
Evaluation in this paper

Per-label AUROC/AUPR macro-averaged over 690 labels. Same Table 2 test cohort; methods differ in additional protein/dynamics inputs. DeepSEA-derived 690 TF-cell-type labels; chr 7 validation; remaining autosomes+X training; chr 8/9 test.

Individual claims
Integrating protein and DNA embeddings for improving genome-wide transcription factor binding site prediction

Original source ↗

Table 2.: AUROC, TF-cell-type binding on held-out chromosomes8and9

Version: version of record
Retrieved: 2026-09-17T07:56:18.711445+00:00

source checked

automated source review · 2026-09-17

Audit details

Primary-source transcription and separate automated review. No human sign-off or experimental reproduction.

Field: attributes.profile.sections.0.body

Source artifact SHA-256: 5d777f5925e941b7d087035d5d87e79ef75ae8d6456a770ffe8c527da566fee0

Hash scope: Exact retrieved primary paper artifact bytes.

Inspected artifact

Introduction

TF-cell-type binding on held-out chromosomes8and9 · Table 2.. Per-label AUROC/AUPR macro-averaged over 690 labels. Same Table 2 test cohort; methods differ in additional protein/dynamics inputs. DeepSEA-derived 690 TF-cell-type labels; chr 7 validation; remaining autosomes+X training; chr 8/9 test.

Individual claims
Integrating protein and DNA embeddings for improving genome-wide transcription factor binding site prediction

Original source ↗

Table 2.: AUROC, TF-cell-type binding on held-out chromosomes8and9

Version: version of record
Retrieved: 2026-09-17T07:56:18.711445+00:00

source checked

automated source review · 2026-09-17

Audit details

Primary-source transcription and separate automated review. No human sign-off or experimental reproduction.

Field: attributes.profile.summary

Source artifact SHA-256: 5d777f5925e941b7d087035d5d87e79ef75ae8d6456a770ffe8c527da566fee0

Hash scope: Exact retrieved primary paper artifact bytes.

Inspected artifact

Relationship: evaluates task

reported-task-ac191e878dff5e

Individual claims
Integrating protein and DNA embeddings for improving genome-wide transcription factor binding site prediction

Original source ↗

Table 2.: AUROC, TF-cell-type binding on held-out chromosomes8and9

Version: version of record
Retrieved: 2026-09-17T07:56:18.711445+00:00

source checked

automated source review · 2026-09-17

Audit details

Field: links:evaluates_task:reported-task-ac191e878dff5e

Claim: paper-claim-dbec0ecce4f8d58b1e

Source artifact SHA-256: 5d777f5925e941b7d087035d5d87e79ef75ae8d6456a770ffe8c527da566fee0

Hash scope: Exact retrieved primary paper artifact bytes.

Inspected artifact

Sources and history

Release 2026-09-17-d277315f7d76 · Record review: needs review

Download this release
Technical metadata and extraction receipts

Stable ID: paper-protocol-6821afc366eb11d0c6

areas
molecular-interactions
tasks
transcription-factor DNA binding-site prediction
entity level
protocol
protocol
Per-label AUROC/AUPR macro-averaged over 690 labels. Same Table 2 test cohort; methods differ in additional protein/dynamics inputs. DeepSEA-derived 690 TF-cell-type labels; chr 7 validation; remaining autosomes+X training; chr 8/9 test.
comparison panels
id: part2-transbind-2026-tbl2-06294a7ed9; title: TF-cell-type binding on held-out chromosomes8and9 · Table 2.; protocol id: paper-protocol-6821afc366eb11d0c6; dataset id: reported-dataset-034c60a2dabc73; metric: AUROC; unit: fraction; direction: higher; result ids: paper-result-8e4b88567c025003ed; paper-result-5c446c8d7902f5ff2b; paper-result-1d4fe2cf1475e26a45; paper-result-ced903b7d93ba17186; paper-result-684ff8c686809c84b0; lit-b4-023; source ids: part2-transbind-2026; source locator: Table 2.: AUROC, TF-cell-type binding on held-out chromosomes8and9; context: Per-label AUROC/AUPR macro-averaged over 690 labels. Same Table 2 test cohort; methods differ in additional protein/dynamics inputs. DeepSEA-derived 690 TF-cell-type labels; chr 7 validation; remaining autosomes+X training; chr 8/9 test.; caveats: Chromosome separation does not itself eliminate pretraining overlap.; Within-paper aggregate only; do not compare against different label sets.; EPBDXDNABERT-2 values are quoted from its original publication because retraining code/data were unavailable; its predictions were not available for paired testing.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17; id: part2-transbind-2026-tbl2-fe3d7b6ab2; title: TF-cell-type binding on held-out chromosomes8and9 · Table 2.; protocol id: paper-protocol-6821afc366eb11d0c6; dataset id: reported-dataset-034c60a2dabc73; metric: AUPR; unit: fraction; direction: higher; result ids: paper-result-0f2759fe5b6ccce7e1; paper-result-d386eaf35eb25ef60a; paper-result-a2922906b449e8d5c5; paper-result-ec2a592fbd35502a5b; paper-result-afd5bc7f082f6ab7e4; paper-result-1237415199f36ae278; source ids: part2-transbind-2026; source locator: Table 2.: AUPR, TF-cell-type binding on held-out chromosomes8and9; context: Per-label AUROC/AUPR macro-averaged over 690 labels. Same Table 2 test cohort; methods differ in additional protein/dynamics inputs. DeepSEA-derived 690 TF-cell-type labels; chr 7 validation; remaining autosomes+X training; chr 8/9 test.; caveats: Chromosome separation does not itself eliminate pretraining overlap.; Within-paper aggregate only; do not compare against different label sets.; EPBDXDNABERT-2 values are quoted from its original publication because retraining code/data were unavailable; its predictions were not available for paired testing.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17
benchmark research
review date: 2026-09-17; status: complete_comparison_tables_extracted_pending_publication_review; primary sources: part2-transbind-2026; inspected locators: Table 2.: AUROC, TF-cell-type binding on held-out chromosomes8and9; searched queries: Integrating protein and DNA embeddings for improving genome-wide transcription factor binding site prediction primary paper benchmark results; gaps: Independent batch review before import; preserve existing observation identities.; claim scope: Primary-source discovery and table/protocol screening; source checked is not independently reproduced. Raw acquisitions not automatically numerical publication approval.
legacy kinds
benchmark
entity classification
review date: 2026-09-17; rationale: The source-backed record identifies a specified evaluated procedure and its dataset/split/scoring context. Classify it as a protocol while preserving version and comparison restrictions.; source ids: part2-transbind-2026; source locator: Table 2.: AUROC, TF-cell-type binding on held-out chromosomes8and9; ambiguities: None recorded
Related records

Suggest a correction