rewirebio.iobenchmarks
Dataset

TraitGym Mendelian traits, matched 9 controls

TraitGym mendelian_traits_matched_9: causal variants with nine matched negative controls each.

Evaluation results

81 evaluations · 81 results. Different protocols are not a single leaderboard.

Filter evaluations

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configurationProtocol and datasetFindingEvidence and details
Configuration: AIDO.DNA_absLLR.plus.score (TraitGym)Protocol: TraitGym Mendelian traits, zero-shot, AUPRC by chromosome weighted average
Dataset: TraitGym Mendelian traits, matched 9 controls
0.115 AUPRC (weighted average over chromosomes of per-chromosome AUPRC; subset 'all')
unitless · higher

Uncertainty: SE 0.008869491282593147

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

AIDO.DNA_absLLR.plus.score on TraitGym mendelian_traits_matched_9

lit-genomics-20261011-traitgym-protocol-mendelian-traits-matched-9-zero-shot

Aggregation: Not reported

TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym) · mendelian_traits_matched_9/AUPRC_by_chrom_weighted_average/all/AIDO.DNA_absLLR.plus.score.csv, column 'score' (standard error in column 'se')
Configuration: AIDO.DNA_Embeddings.minus.inner_product (TraitGym)Protocol: TraitGym Mendelian traits, zero-shot, AUPRC by chromosome weighted average
Dataset: TraitGym Mendelian traits, matched 9 controls
0.173 AUPRC (weighted average over chromosomes of per-chromosome AUPRC; subset 'all')
unitless · higher

Uncertainty: SE 0.016767200388829374

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

AIDO.DNA_Embeddings.minus.inner_product on TraitGym mendelian_traits_matched_9

lit-genomics-20261011-traitgym-protocol-mendelian-traits-matched-9-zero-shot

Aggregation: Not reported

TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym) · mendelian_traits_matched_9/AUPRC_by_chrom_weighted_average/all/AIDO.DNA_Embeddings.minus.inner_product.csv, column 'score' (standard error in column 'se')
Configuration: AIDO.DNA_Embeddings.plus.cosine_distance (TraitGym)Protocol: TraitGym Mendelian traits, zero-shot, AUPRC by chromosome weighted average
Dataset: TraitGym Mendelian traits, matched 9 controls
0.146 AUPRC (weighted average over chromosomes of per-chromosome AUPRC; subset 'all')
unitless · higher

Uncertainty: SE 0.016225199774343134

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

AIDO.DNA_Embeddings.plus.cosine_distance on TraitGym mendelian_traits_matched_9

lit-genomics-20261011-traitgym-protocol-mendelian-traits-matched-9-zero-shot

Aggregation: Not reported

TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym) · mendelian_traits_matched_9/AUPRC_by_chrom_weighted_average/all/AIDO.DNA_Embeddings.plus.cosine_distance.csv, column 'score' (standard error in column 'se')
Configuration: AIDO.DNA_Embeddings.plus.euclidean_distance (TraitGym)Protocol: TraitGym Mendelian traits, zero-shot, AUPRC by chromosome weighted average
Dataset: TraitGym Mendelian traits, matched 9 controls
0.148 AUPRC (weighted average over chromosomes of per-chromosome AUPRC; subset 'all')
unitless · higher

Uncertainty: SE 0.016830422431299015

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

AIDO.DNA_Embeddings.plus.euclidean_distance on TraitGym mendelian_traits_matched_9

lit-genomics-20261011-traitgym-protocol-mendelian-traits-matched-9-zero-shot

Aggregation: Not reported

TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym) · mendelian_traits_matched_9/AUPRC_by_chrom_weighted_average/all/AIDO.DNA_Embeddings.plus.euclidean_distance.csv, column 'score' (standard error in column 'se')
Configuration: AIDO.DNA_LLR.minus.score (TraitGym)Protocol: TraitGym Mendelian traits, zero-shot, AUPRC by chromosome weighted average
Dataset: TraitGym Mendelian traits, matched 9 controls
0.135 AUPRC (weighted average over chromosomes of per-chromosome AUPRC; subset 'all')
unitless · higher

Uncertainty: SE 0.012742124387199684

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

AIDO.DNA_LLR.minus.score on TraitGym mendelian_traits_matched_9

lit-genomics-20261011-traitgym-protocol-mendelian-traits-matched-9-zero-shot

Aggregation: Not reported

TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym) · mendelian_traits_matched_9/AUPRC_by_chrom_weighted_average/all/AIDO.DNA_LLR.minus.score.csv, column 'score' (standard error in column 'se')
Configuration: AIDO.DNA.LogisticRegression.chrom (TraitGym)Protocol: TraitGym Mendelian traits, linear-probing, AUPRC by chromosome weighted average
Dataset: TraitGym Mendelian traits, matched 9 controls
0.179 AUPRC (weighted average over chromosomes of per-chromosome AUPRC; subset 'all')
unitless · higher

Uncertainty: SE 0.039616777374824476

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

AIDO.DNA.LogisticRegression.chrom on TraitGym mendelian_traits_matched_9

lit-genomics-20261011-traitgym-protocol-mendelian-traits-matched-9-linear-probing

Aggregation: Not reported

TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym) · mendelian_traits_matched_9/AUPRC_by_chrom_weighted_average/all/AIDO.DNA.LogisticRegression.chrom.csv, column 'score' (standard error in column 'se')
Configuration: Borzoi_L2_L2.plus.all (TraitGym)Protocol: TraitGym Mendelian traits, zero-shot, AUPRC by chromosome weighted average
Dataset: TraitGym Mendelian traits, matched 9 controls
0.436 AUPRC (weighted average over chromosomes of per-chromosome AUPRC; subset 'all')
unitless · higher

Uncertainty: SE 0.051597004283321764

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

Borzoi_L2_L2.plus.all on TraitGym mendelian_traits_matched_9

lit-genomics-20261011-traitgym-protocol-mendelian-traits-matched-9-zero-shot

Aggregation: Not reported

TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym) · mendelian_traits_matched_9/AUPRC_by_chrom_weighted_average/all/Borzoi_L2_L2.plus.all.csv, column 'score' (standard error in column 'se')
Configuration: Borzoi.LogisticRegression.chrom (TraitGym)Protocol: TraitGym Mendelian traits, linear-probing, AUPRC by chromosome weighted average
Dataset: TraitGym Mendelian traits, matched 9 controls
0.493 AUPRC (weighted average over chromosomes of per-chromosome AUPRC; subset 'all')
unitless · higher

Uncertainty: SE 0.03387962392290682

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

Borzoi.LogisticRegression.chrom on TraitGym mendelian_traits_matched_9

lit-genomics-20261011-traitgym-protocol-mendelian-traits-matched-9-linear-probing

Aggregation: Not reported

TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym) · mendelian_traits_matched_9/AUPRC_by_chrom_weighted_average/all/Borzoi.LogisticRegression.chrom.csv, column 'score' (standard error in column 'se')
Configuration: CADD.LogisticRegression.chrom (TraitGym)Protocol: TraitGym Mendelian traits, linear-probing, AUPRC by chromosome weighted average
Dataset: TraitGym Mendelian traits, matched 9 controls
0.875 AUPRC (weighted average over chromosomes of per-chromosome AUPRC; subset 'all')
unitless · higher

Uncertainty: SE 0.03053334830628915

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

CADD.LogisticRegression.chrom on TraitGym mendelian_traits_matched_9

lit-genomics-20261011-traitgym-protocol-mendelian-traits-matched-9-linear-probing

Aggregation: Not reported

TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym) · mendelian_traits_matched_9/AUPRC_by_chrom_weighted_average/all/CADD.LogisticRegression.chrom.csv, column 'score' (standard error in column 'se')
Configuration: CADD+Borzoi.LogisticRegression.chrom (TraitGym)Protocol: TraitGym Mendelian traits, linear-probing, AUPRC by chromosome weighted average
Dataset: TraitGym Mendelian traits, matched 9 controls
0.757 AUPRC (weighted average over chromosomes of per-chromosome AUPRC; subset 'all')
unitless · higher

Uncertainty: SE 0.02800090306412582

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

CADD+Borzoi.LogisticRegression.chrom on TraitGym mendelian_traits_matched_9

lit-genomics-20261011-traitgym-protocol-mendelian-traits-matched-9-linear-probing

Aggregation: Not reported

TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym) · mendelian_traits_matched_9/AUPRC_by_chrom_weighted_average/all/CADD+Borzoi.LogisticRegression.chrom.csv, column 'score' (standard error in column 'se')
Configuration: CADD+GPN-MSA.LogisticRegression.chrom (TraitGym)Protocol: TraitGym Mendelian traits, linear-probing, AUPRC by chromosome weighted average
Dataset: TraitGym Mendelian traits, matched 9 controls
0.846 AUPRC (weighted average over chromosomes of per-chromosome AUPRC; subset 'all')
unitless · higher

Uncertainty: SE 0.03343976192415707

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

CADD+GPN-MSA.LogisticRegression.chrom on TraitGym mendelian_traits_matched_9

lit-genomics-20261011-traitgym-protocol-mendelian-traits-matched-9-linear-probing

Aggregation: Not reported

TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym) · mendelian_traits_matched_9/AUPRC_by_chrom_weighted_average/all/CADD+GPN-MSA.LogisticRegression.chrom.csv, column 'score' (standard error in column 'se')
Configuration: CADD+GPN-MSA+Borzoi.LogisticRegression.chrom (TraitGym)Protocol: TraitGym Mendelian traits, linear-probing, AUPRC by chromosome weighted average
Dataset: TraitGym Mendelian traits, matched 9 controls
0.74 AUPRC (weighted average over chromosomes of per-chromosome AUPRC; subset 'all')
unitless · higher

Uncertainty: SE 0.03341660529784681

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

CADD+GPN-MSA+Borzoi.LogisticRegression.chrom on TraitGym mendelian_traits_matched_9

lit-genomics-20261011-traitgym-protocol-mendelian-traits-matched-9-linear-probing

Aggregation: Not reported

TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym) · mendelian_traits_matched_9/AUPRC_by_chrom_weighted_average/all/CADD+GPN-MSA+Borzoi.LogisticRegression.chrom.csv, column 'score' (standard error in column 'se')
Configuration: CADD.plus.RawScore (TraitGym)Protocol: TraitGym Mendelian traits, zero-shot, AUPRC by chromosome weighted average
Dataset: TraitGym Mendelian traits, matched 9 controls
0.712 AUPRC (weighted average over chromosomes of per-chromosome AUPRC; subset 'all')
unitless · higher

Uncertainty: SE 0.038447877158699226

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

CADD.plus.RawScore on TraitGym mendelian_traits_matched_9

lit-genomics-20261011-traitgym-protocol-mendelian-traits-matched-9-zero-shot

Aggregation: Not reported

TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym) · mendelian_traits_matched_9/AUPRC_by_chrom_weighted_average/all/CADD.plus.RawScore.csv, column 'score' (standard error in column 'se')
Configuration: Caduceus_absLLR.plus.score (TraitGym)Protocol: TraitGym Mendelian traits, zero-shot, AUPRC by chromosome weighted average
Dataset: TraitGym Mendelian traits, matched 9 controls
0.0878 AUPRC (weighted average over chromosomes of per-chromosome AUPRC; subset 'all')
unitless · higher

Uncertainty: SE 0.005565988958549242

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

Caduceus_absLLR.plus.score on TraitGym mendelian_traits_matched_9

lit-genomics-20261011-traitgym-protocol-mendelian-traits-matched-9-zero-shot

Aggregation: Not reported

TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym) · mendelian_traits_matched_9/AUPRC_by_chrom_weighted_average/all/Caduceus_absLLR.plus.score.csv, column 'score' (standard error in column 'se')
Configuration: Caduceus_Embeddings.minus.inner_product (TraitGym)Protocol: TraitGym Mendelian traits, zero-shot, AUPRC by chromosome weighted average
Dataset: TraitGym Mendelian traits, matched 9 controls
0.131 AUPRC (weighted average over chromosomes of per-chromosome AUPRC; subset 'all')
unitless · higher

Uncertainty: SE 0.016254752195469967

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

Caduceus_Embeddings.minus.inner_product on TraitGym mendelian_traits_matched_9

lit-genomics-20261011-traitgym-protocol-mendelian-traits-matched-9-zero-shot

Aggregation: Not reported

TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym) · mendelian_traits_matched_9/AUPRC_by_chrom_weighted_average/all/Caduceus_Embeddings.minus.inner_product.csv, column 'score' (standard error in column 'se')
Configuration: Caduceus_Embeddings.plus.cosine_distance (TraitGym)Protocol: TraitGym Mendelian traits, zero-shot, AUPRC by chromosome weighted average
Dataset: TraitGym Mendelian traits, matched 9 controls
0.135 AUPRC (weighted average over chromosomes of per-chromosome AUPRC; subset 'all')
unitless · higher

Uncertainty: SE 0.010093335540829028

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

Caduceus_Embeddings.plus.cosine_distance on TraitGym mendelian_traits_matched_9

lit-genomics-20261011-traitgym-protocol-mendelian-traits-matched-9-zero-shot

Aggregation: Not reported

TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym) · mendelian_traits_matched_9/AUPRC_by_chrom_weighted_average/all/Caduceus_Embeddings.plus.cosine_distance.csv, column 'score' (standard error in column 'se')
Configuration: Caduceus_Embeddings.plus.euclidean_distance (TraitGym)Protocol: TraitGym Mendelian traits, zero-shot, AUPRC by chromosome weighted average
Dataset: TraitGym Mendelian traits, matched 9 controls
0.135 AUPRC (weighted average over chromosomes of per-chromosome AUPRC; subset 'all')
unitless · higher

Uncertainty: SE 0.009044707575175105

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

Caduceus_Embeddings.plus.euclidean_distance on TraitGym mendelian_traits_matched_9

lit-genomics-20261011-traitgym-protocol-mendelian-traits-matched-9-zero-shot

Aggregation: Not reported

TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym) · mendelian_traits_matched_9/AUPRC_by_chrom_weighted_average/all/Caduceus_Embeddings.plus.euclidean_distance.csv, column 'score' (standard error in column 'se')
Configuration: Caduceus_InnerProduct.minus.score (TraitGym)Protocol: TraitGym Mendelian traits, zero-shot, AUPRC by chromosome weighted average
Dataset: TraitGym Mendelian traits, matched 9 controls
0.131 AUPRC (weighted average over chromosomes of per-chromosome AUPRC; subset 'all')
unitless · higher

Uncertainty: SE 0.01625459735416025

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

Caduceus_InnerProduct.minus.score on TraitGym mendelian_traits_matched_9

lit-genomics-20261011-traitgym-protocol-mendelian-traits-matched-9-zero-shot

Aggregation: Not reported

TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym) · mendelian_traits_matched_9/AUPRC_by_chrom_weighted_average/all/Caduceus_InnerProduct.minus.score.csv, column 'score' (standard error in column 'se')
Configuration: Caduceus_LLR.minus.score (TraitGym)Protocol: TraitGym Mendelian traits, zero-shot, AUPRC by chromosome weighted average
Dataset: TraitGym Mendelian traits, matched 9 controls
0.108 AUPRC (weighted average over chromosomes of per-chromosome AUPRC; subset 'all')
unitless · higher

Uncertainty: SE 0.005420533606407098

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

Caduceus_LLR.minus.score on TraitGym mendelian_traits_matched_9

lit-genomics-20261011-traitgym-protocol-mendelian-traits-matched-9-zero-shot

Aggregation: Not reported

TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym) · mendelian_traits_matched_9/AUPRC_by_chrom_weighted_average/all/Caduceus_LLR.minus.score.csv, column 'score' (standard error in column 'se')
Configuration: Caduceus.LogisticRegression.chrom (TraitGym)Protocol: TraitGym Mendelian traits, linear-probing, AUPRC by chromosome weighted average
Dataset: TraitGym Mendelian traits, matched 9 controls
0.237 AUPRC (weighted average over chromosomes of per-chromosome AUPRC; subset 'all')
unitless · higher

Uncertainty: SE 0.0659529424131491

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

Caduceus.LogisticRegression.chrom on TraitGym mendelian_traits_matched_9

lit-genomics-20261011-traitgym-protocol-mendelian-traits-matched-9-linear-probing

Aggregation: Not reported

TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym) · mendelian_traits_matched_9/AUPRC_by_chrom_weighted_average/all/Caduceus.LogisticRegression.chrom.csv, column 'score' (standard error in column 'se')
Configuration: Enformer_L2_L2.plus.all (TraitGym)Protocol: TraitGym Mendelian traits, zero-shot, AUPRC by chromosome weighted average
Dataset: TraitGym Mendelian traits, matched 9 controls
0.418 AUPRC (weighted average over chromosomes of per-chromosome AUPRC; subset 'all')
unitless · higher

Uncertainty: SE 0.03675225375188307

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

Enformer_L2_L2.plus.all on TraitGym mendelian_traits_matched_9

lit-genomics-20261011-traitgym-protocol-mendelian-traits-matched-9-zero-shot

Aggregation: Not reported

TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym) · mendelian_traits_matched_9/AUPRC_by_chrom_weighted_average/all/Enformer_L2_L2.plus.all.csv, column 'score' (standard error in column 'se')
Configuration: Enformer.LogisticRegression.chrom (TraitGym)Protocol: TraitGym Mendelian traits, linear-probing, AUPRC by chromosome weighted average
Dataset: TraitGym Mendelian traits, matched 9 controls
0.446 AUPRC (weighted average over chromosomes of per-chromosome AUPRC; subset 'all')
unitless · higher

Uncertainty: SE 0.037976767408547156

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

Enformer.LogisticRegression.chrom on TraitGym mendelian_traits_matched_9

lit-genomics-20261011-traitgym-protocol-mendelian-traits-matched-9-linear-probing

Aggregation: Not reported

TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym) · mendelian_traits_matched_9/AUPRC_by_chrom_weighted_average/all/Enformer.LogisticRegression.chrom.csv, column 'score' (standard error in column 'se')
Configuration: evo2_1b_base_absLLR.plus.score (TraitGym)Protocol: TraitGym Mendelian traits, zero-shot, AUPRC by chromosome weighted average
Dataset: TraitGym Mendelian traits, matched 9 controls
0.159 AUPRC (weighted average over chromosomes of per-chromosome AUPRC; subset 'all')
unitless · higher

Uncertainty: SE 0.031111541939277777

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

evo2_1b_base_absLLR.plus.score on TraitGym mendelian_traits_matched_9

lit-genomics-20261011-traitgym-protocol-mendelian-traits-matched-9-zero-shot

Aggregation: Not reported

TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym) · mendelian_traits_matched_9/AUPRC_by_chrom_weighted_average/all/evo2_1b_base_absLLR.plus.score.csv, column 'score' (standard error in column 'se')
Configuration: evo2_1b_base_Embeddings.minus.inner_product (TraitGym)Protocol: TraitGym Mendelian traits, zero-shot, AUPRC by chromosome weighted average
Dataset: TraitGym Mendelian traits, matched 9 controls
0.165 AUPRC (weighted average over chromosomes of per-chromosome AUPRC; subset 'all')
unitless · higher

Uncertainty: SE 0.03484037341338302

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

evo2_1b_base_Embeddings.minus.inner_product on TraitGym mendelian_traits_matched_9

lit-genomics-20261011-traitgym-protocol-mendelian-traits-matched-9-zero-shot

Aggregation: Not reported

TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym) · mendelian_traits_matched_9/AUPRC_by_chrom_weighted_average/all/evo2_1b_base_Embeddings.minus.inner_product.csv, column 'score' (standard error in column 'se')
Configuration: evo2_1b_base_Embeddings.plus.cosine_distance (TraitGym)Protocol: TraitGym Mendelian traits, zero-shot, AUPRC by chromosome weighted average
Dataset: TraitGym Mendelian traits, matched 9 controls
0.118 AUPRC (weighted average over chromosomes of per-chromosome AUPRC; subset 'all')
unitless · higher

Uncertainty: SE 0.006145116728818818

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

evo2_1b_base_Embeddings.plus.cosine_distance on TraitGym mendelian_traits_matched_9

lit-genomics-20261011-traitgym-protocol-mendelian-traits-matched-9-zero-shot

Aggregation: Not reported

TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym) · mendelian_traits_matched_9/AUPRC_by_chrom_weighted_average/all/evo2_1b_base_Embeddings.plus.cosine_distance.csv, column 'score' (standard error in column 'se')

Source checking is not independent reproduction. Release 2026-10-22-1b7cf027e4f6.

Research readiness

0 of 4 readiness checks met. These checks assess whether the evidence supports a reproducible investigation; a source-checked score alone does not meet them.

Readiness checks, gaps and artifacts

Release 2026-10-22-1b7cf027e4f6 · Evidence verified: Not verified

Evidence incomplete

Replay metrics

Exact outcomes, predictions, identifiers and evaluator are connected.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • Metrics are recomputed from the saved predictions: not yet verified

Verified: Not verified

Evidence incomplete

Investigate discrepancies

Replay evidence includes annotations and an assessment of dependence. Unknown independence permits descriptive analysis only.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • Metrics are recomputed from the saved predictions: not yet verified
  • Sample annotations are recorded: not yet verified
  • Dependence between samples is assessed: not yet verified

Verified: Not verified

Evidence incomplete

Run locally

A pinned recipe describes the inputs, environment and resource requirements.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • A pinned run recipe exists: not yet verified
  • Compute requirements are estimated: not yet verified

Verified: Not verified

Evidence incomplete

Validate independently

Separate data and exposure records support an independent test.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • Independent validation data exist: not yet verified
  • Overlap with training data is checked: not yet verified

Verified: Not verified

Readiness describes the evidence in this release. Availability on your computer is checked separately when an investigation runs. Existing data exposure can prevent independent validation even when files are available.

Artifacts and reproduction

No verified artifact manifest is connected to this record yet. The gaps above identify what is needed before analysis can begin.

Dataset and evaluation context

A dataset supplies biological observations. The evaluation protocol defines how those observations are split, used and scored.

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.

6 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-22-1b7cf027e4f6
Property and statementOriginal source and locationReview and provenance
Population
Mendelian traits; nine matched controls per causal variant (baseline AUPRC 0.1)
Context-only references
TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym)

Original source ↗

mendelian_traits_matched_9/test.parquet (not downloaded); README

Version: Hugging Face dataset revision 1fde19555fe8c0a55b1382bdf4c6f7082209f566 (last modified 2025-03-25); 156 metric CSVs under {dataset}/AUPRC_by_chrom_weighted_average/all/
Retrieved: 2026-10-11T01:40:33Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.population

Source artifact SHA-256: 44dfedc00ac5c7918b188af2a5a200f08da3b641f73d7d5327e26f94a7d0372e

Hash scope: SHA-256 of a JSON bundle listing every retrieved CSV with its path, its own SHA-256 and its bytes (artifacts/traitgym-metrics-bundle.json.gz)

Inspected artifact

Source location
mendelian_traits_matched_9/test.parquet (not downloaded); README
Context-only references
TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym)

Original source ↗

mendelian_traits_matched_9/test.parquet (not downloaded); README

Version: Hugging Face dataset revision 1fde19555fe8c0a55b1382bdf4c6f7082209f566 (last modified 2025-03-25); 156 metric CSVs under {dataset}/AUPRC_by_chrom_weighted_average/all/
Retrieved: 2026-10-11T01:40:33Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.source_locator

Source artifact SHA-256: 44dfedc00ac5c7918b188af2a5a200f08da3b641f73d7d5327e26f94a7d0372e

Hash scope: SHA-256 of a JSON bundle listing every retrieved CSV with its path, its own SHA-256 and its bytes (artifacts/traitgym-metrics-bundle.json.gz)

Inspected artifact

Split
Leave-one-chromosome-out for linear probing; all variants scored for zero-shot
Context-only references
TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym)

Original source ↗

mendelian_traits_matched_9/test.parquet (not downloaded); README

Version: Hugging Face dataset revision 1fde19555fe8c0a55b1382bdf4c6f7082209f566 (last modified 2025-03-25); 156 metric CSVs under {dataset}/AUPRC_by_chrom_weighted_average/all/
Retrieved: 2026-10-11T01:40:33Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.split

Source artifact SHA-256: 44dfedc00ac5c7918b188af2a5a200f08da3b641f73d7d5327e26f94a7d0372e

Hash scope: SHA-256 of a JSON bundle listing every retrieved CSV with its path, its own SHA-256 and its bytes (artifacts/traitgym-metrics-bundle.json.gz)

Inspected artifact

Version
Hugging Face revision 1fde19555fe8
Context-only references
TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym)

Original source ↗

mendelian_traits_matched_9/test.parquet (not downloaded); README

Version: Hugging Face dataset revision 1fde19555fe8c0a55b1382bdf4c6f7082209f566 (last modified 2025-03-25); 156 metric CSVs under {dataset}/AUPRC_by_chrom_weighted_average/all/
Retrieved: 2026-10-11T01:40:33Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.version

Source artifact SHA-256: 44dfedc00ac5c7918b188af2a5a200f08da3b641f73d7d5327e26f94a7d0372e

Hash scope: SHA-256 of a JSON bundle listing every retrieved CSV with its path, its own SHA-256 and its bytes (artifacts/traitgym-metrics-bundle.json.gz)

Inspected artifact

Description
TraitGym mendelian_traits_matched_9: causal variants with nine matched negative controls each.
Context-only references
TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym)

Original source ↗

mendelian_traits_matched_9/test.parquet (not downloaded); README

Version: Hugging Face dataset revision 1fde19555fe8c0a55b1382bdf4c6f7082209f566 (last modified 2025-03-25); 156 metric CSVs under {dataset}/AUPRC_by_chrom_weighted_average/all/
Retrieved: 2026-10-11T01:40:33Z

not individually reviewed

No individual claim review recorded

Audit details

Field: description

Source artifact SHA-256: 44dfedc00ac5c7918b188af2a5a200f08da3b641f73d7d5327e26f94a7d0372e

Hash scope: SHA-256 of a JSON bundle listing every retrieved CSV with its path, its own SHA-256 and its bytes (artifacts/traitgym-metrics-bundle.json.gz)

Inspected artifact

Name
TraitGym Mendelian traits, matched 9 controls
Context-only references
TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym)

Original source ↗

mendelian_traits_matched_9/test.parquet (not downloaded); README

Version: Hugging Face dataset revision 1fde19555fe8c0a55b1382bdf4c6f7082209f566 (last modified 2025-03-25); 156 metric CSVs under {dataset}/AUPRC_by_chrom_weighted_average/all/
Retrieved: 2026-10-11T01:40:33Z

not individually reviewed

No individual claim review recorded

Audit details

Field: name

Source artifact SHA-256: 44dfedc00ac5c7918b188af2a5a200f08da3b641f73d7d5327e26f94a7d0372e

Hash scope: SHA-256 of a JSON bundle listing every retrieved CSV with its path, its own SHA-256 and its bytes (artifacts/traitgym-metrics-bundle.json.gz)

Inspected artifact

Sources and history

Release 2026-10-22-1b7cf027e4f6 · Record review: source checked

1 source record and release historyDownload this release (gzip)
Technical metadata and extraction receipts

Stable ID: lit-genomics-20261011-traitgym-data-mendelian-traits-matched-9

areas
dna-genomes
contexts
research
version
Hugging Face revision 1fde19555fe8
split
Leave-one-chromosome-out for linear probing; all variants scored for zero-shot
population
Mendelian traits; nine matched controls per causal variant (baseline AUPRC 0.1)
source locator
mendelian_traits_matched_9/test.parquet (not downloaded); README
Related records

Suggest a correction