rewire.it
Task

DART-Eval VS-AFRICAN-PEARSON_R: Variant scoring on Chromatin QTLs in African LCLs, Pearson r

Variant scoring on Chromatin QTLs in African LCLs, Pearson r. Scored with Pearson r on Chromatin QTLs in African LCLs. Score the effect of a variant on chromatin accessibility, against the measured QTL call.

13 evaluations · 13 metric rows

Overview

Variant scoring on Chromatin QTLs in African LCLs, Pearson r. Scored with Pearson r on Chromatin QTLs in African LCLs. Score the effect of a variant on chromatin accessibility, against the measured QTL call.

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

Evaluation design

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

Benchmarks

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

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Explore all linked results

Run instructions

No runnable recipe has been reviewed for this task. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.

A task describes a biological question. Choose a linked protocol to obtain concrete split and scoring instructions.

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. The pooled view gathers every source table that reports the same metric and names what it does not hold constant.

DART-Eval VS-AFRICAN-PEARSON_R: Variant scoring on Chromatin QTLs in African LCLs, Pearson r

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

Every method DART-Eval reports on Variant scoring on Chromatin QTLs in African LCLs, Pearson r, scored with Pearson r on Chromatin QTLs in African LCLs.

Evaluation protocol · Chromatin QTLs in African LCLs (DART-Eval split)

  1. Caduceus (probed) · Configuration · Author-reported evaluation-0.004
  2. Caduceus (fine-tuned) · Configuration · Author-reported evaluation0.259
  3. DNABERT-2 (probed) · Configuration · Author-reported evaluation0.007
  4. DNABERT-2 (fine-tuned) · Configuration · Author-reported evaluation0.184
  5. GENA-LM (probed) · Configuration · Author-reported evaluation-0.007
  6. GENA-LM (fine-tuned) · Configuration · Author-reported evaluation0.201
  7. HyenaDNA (probed) · Configuration · Author-reported evaluation0.012
  8. HyenaDNA (fine-tuned) · Configuration · Author-reported evaluation0.265
  9. Mistral-DNA (probed) · Configuration · Author-reported evaluation0.018
  10. ChromBPNet (ab initio) · Method · Author-reported evaluation0.671

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.

DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 6, row group(AFRICAN), column(Pearson r)
Values, uncertainty and evidence
pearson_r: original source values
Tested entityPrinted valueUncertaintyEvidence
Caduceus (probed) · Configuration-0.004 fractionNot reportedAuthor-reported evaluation · source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 6, row(African Caduceus), column(probed pearson_r)
Caduceus (fine-tuned) · Configuration0.259 fractionNot reportedAuthor-reported evaluation · source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 6, row(African Caduceus), column(fine-tuned pearson_r)
DNABERT-2 (probed) · Configuration0.007 fractionNot reportedAuthor-reported evaluation · source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 6, row(African DNABERT-2), column(probed pearson_r)
DNABERT-2 (fine-tuned) · Configuration0.184 fractionNot reportedAuthor-reported evaluation · source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 6, row(African DNABERT-2), column(fine-tuned pearson_r)
GENA-LM (probed) · Configuration-0.007 fractionNot reportedAuthor-reported evaluation · source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 6, row(African GENA-LM), column(probed pearson_r)
GENA-LM (fine-tuned) · Configuration0.201 fractionNot reportedAuthor-reported evaluation · source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 6, row(African GENA-LM), column(fine-tuned pearson_r)
HyenaDNA (probed) · Configuration0.012 fractionNot reportedAuthor-reported evaluation · source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 6, row(African HyenaDNA), column(probed pearson_r)
HyenaDNA (fine-tuned) · Configuration0.265 fractionNot reportedAuthor-reported evaluation · source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 6, row(African HyenaDNA), column(fine-tuned pearson_r)
Mistral-DNA (probed) · Configuration0.018 fractionNot reportedAuthor-reported evaluation · source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 6, row(African Mistral-DNA), column(probed pearson_r)
Mistral-DNA (fine-tuned) · Configuration0.085 fractionNot reportedAuthor-reported evaluation · source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 6, row(African Mistral-DNA), column(fine-tuned pearson_r)
Nucleotide Transformer (probed) · Configuration0.006 fractionNot reportedAuthor-reported evaluation · source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 6, row(African NT), column(probed pearson_r)
Nucleotide Transformer (fine-tuned) · Configuration0.230 fractionNot reportedAuthor-reported evaluation · source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 6, row(African NT), column(fine-tuned pearson_r)
ChromBPNet (ab initio) · Method0.671 fractionNot reportedAuthor-reported evaluation · source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 6, row(African ChromBPNet), column(ab initio pearson_r)
Scope and limitations
  • Author-reported numbers, source checked but not independently reproduced.
  • The evaluation setting is part of the method name: a zero-shot, probed and fine-tuned run of the same model are different entries.
  • Metrics and datasets differ between tasks, so these figures cannot be averaged into one score.

Source transcription and grouping reviewed by automated source review on 2026-09-18. These experiments were not independently reproduced by rewire.

Tested entities and results

Release 2026-09-17-134cd1815de8 · 13 evaluations · 13 metric rows. Different protocols are not a single leaderboard. Where several source tables report the same metric, the published comparisons above offer a pooled view that names what it does not hold constant.

Results grouped by the exact reported evaluation
Metric and findingCoverage and uncertaintyEvidence
Caduceus (fine-tuned) 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.

Author-reported evaluation · Evaluation metadata: source checked

0.259 pearson_r

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 6, row(African Caduceus), column(fine-tuned pearson_r)

Source checking is not independent reproduction.

Caduceus (probed) 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.

Author-reported evaluation · Evaluation metadata: source checked

-0.004 pearson_r

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 6, row(African Caduceus), column(probed pearson_r)

Source checking is not independent reproduction.

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.

Author-reported evaluation · Evaluation metadata: source checked

0.671 pearson_r

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 6, row(African ChromBPNet), column(ab initio pearson_r)

Source checking is not independent reproduction.

DNABERT-2 (fine-tuned) 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.

Author-reported evaluation · Evaluation metadata: source checked

0.184 pearson_r

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 6, row(African DNABERT-2), column(fine-tuned pearson_r)

Source checking is not independent reproduction.

DNABERT-2 (probed) 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.

Author-reported evaluation · Evaluation metadata: source checked

0.007 pearson_r

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 6, row(African DNABERT-2), column(probed pearson_r)

Source checking is not independent reproduction.

GENA-LM (fine-tuned) 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.

Author-reported evaluation · Evaluation metadata: source checked

0.201 pearson_r

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 6, row(African GENA-LM), column(fine-tuned pearson_r)

Source checking is not independent reproduction.

GENA-LM (probed) 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.

Author-reported evaluation · Evaluation metadata: source checked

-0.007 pearson_r

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 6, row(African GENA-LM), column(probed pearson_r)

Source checking is not independent reproduction.

HyenaDNA (fine-tuned) 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.

Author-reported evaluation · Evaluation metadata: source checked

0.265 pearson_r

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 6, row(African HyenaDNA), column(fine-tuned pearson_r)

Source checking is not independent reproduction.

HyenaDNA (probed) 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.

Author-reported evaluation · Evaluation metadata: source checked

0.012 pearson_r

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 6, row(African HyenaDNA), column(probed pearson_r)

Source checking is not independent reproduction.

Mistral-DNA (fine-tuned) 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.

Author-reported evaluation · Evaluation metadata: source checked

0.085 pearson_r

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 6, row(African Mistral-DNA), column(fine-tuned pearson_r)

Source checking is not independent reproduction.

Mistral-DNA (probed) 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.

Author-reported evaluation · Evaluation metadata: source checked

0.018 pearson_r

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 6, row(African Mistral-DNA), column(probed pearson_r)

Source checking is not independent reproduction.

Nucleotide Transformer (fine-tuned) 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.

Author-reported evaluation · Evaluation metadata: source checked

0.230 pearson_r

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 6, row(African NT), column(fine-tuned pearson_r)

Source checking is not independent reproduction.

Nucleotide Transformer (probed) 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.

Author-reported evaluation · Evaluation metadata: source checked

0.006 pearson_r

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 6, row(African NT), column(probed pearson_r)

Source checking is not 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.

1 evidence row matching the loaded filters

Claims, original sources and review scope · Release 2026-09-17-134cd1815de8
Property and statementOriginal source and locationReview and provenance
Relationship: part of

discovery-benchmark-dart-eval

Individual claims
DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA

Original source ↗

Table 6, row group(AFRICAN), column(Pearson r)

Version: 2412.05430v1
Retrieved: 2026-09-17T07:56:09.182117+00:00

source checked

automated source review · 2026-09-18

Audit details

Primary-source transcription with no human sign-off and no independent reproduction.

Field: links:part_of:discovery-benchmark-dart-eval

Claim: dart-eval-association-vs-african-pearson-r

Source artifact SHA-256: 4194b137ba55c9a2c269d119a9afec6ae1bb0feaf17d91433ae483c41221a56b

Hash scope: Exact retrieved primary paper artifact bytes.

Inspected artifact

Sources and history

Release 2026-09-17-134cd1815de8 · Record review: source checked

1 source records and release historyDownload this release
Technical metadata and extraction receipts

Stable ID: dart-eval-task-vs-african-pearson-r

areas
dna-genomes
tasks
Variant scoring on Chromatin QTLs in African LCLs, Pearson r
metric
Pearson r
metric direction
higher
dataset
Chromatin QTLs in African LCLs
protocol
Score the effect of a variant on chromatin accessibility, against the measured QTL call.
source locator
Table 6, row group(AFRICAN), column(Pearson r)
comparison panels
id: dart-eval-panel-vs-african-pearson-r; title: DART-Eval VS-AFRICAN-PEARSON_R: Variant scoring on Chromatin QTLs in African LCLs, Pearson r; protocol id: dart-eval-task-vs-african-pearson-r; dataset id: dart-eval-dataset-chromatin-qtls-in-african-lcls; metric: pearson_r; unit: fraction; direction: higher; result ids: dart-eval-result-caduceus-probed-vs-african-pearson-r-pearson-r; dart-eval-result-caduceus-fine-tuned-vs-african-pearson-r-pearson-r; dart-eval-result-dnabert-2-probed-vs-african-pearson-r-pearson-r; dart-eval-result-dnabert-2-fine-tuned-vs-african-pearson-r-pearson-r; dart-eval-result-gena-lm-probed-vs-african-pearson-r-pearson-r; dart-eval-result-gena-lm-fine-tuned-vs-african-pearson-r-pearson-r; dart-eval-result-hyenadna-probed-vs-african-pearson-r-pearson-r; dart-eval-result-hyenadna-fine-tuned-vs-african-pearson-r-pearson-r; dart-eval-result-mistral-dna-probed-vs-african-pearson-r-pearson-r; dart-eval-result-mistral-dna-fine-tuned-vs-african-pearson-r-pearson-r; dart-eval-result-nucleotide-transformer-probed-vs-african-pearson-r-pearson-r; dart-eval-result-nucleotide-transformer-fine-tuned-vs-african-pearson-r-pearson-r; dart-eval-result-chrombpnet-ab-initio-vs-african-pearson-r-pearson-r; source ids: evidence-expansion-p2-evidence-discovery-final-dart-4194b137ba55; source locator: Table 6, row group(AFRICAN), column(Pearson r); context: Every method DART-Eval reports on Variant scoring on Chromatin QTLs in African LCLs, Pearson r, scored with Pearson r on Chromatin QTLs in African LCLs.; caveats: Author-reported numbers, source checked but not independently reproduced.; The evaluation setting is part of the method name: a zero-shot, probed and fine-tuned run of the same model are different entries.; Metrics and datasets differ between tasks, so these figures cannot be averaged into one score.; review: method: automated_source_review; date: 2026-09-18
Related records

Suggest a correction