GPN-MSA.LogisticRegression.chrom (TraitGym)
GPN-MSA scored as 'ridge logistic regression on extracted features (chromosome folds)' in TraitGym.
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
2 evaluations · 2 results. Different protocols are not a single leaderboard.
Sorted by AUPRC (weighted average over chromosomes of per-chromosome AUPRC; subset 'all') (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 | AUPRC (weighted average over chromosomes of per-chromosome AUPRC; subset 'all') |
|---|---|---|
| GPN-MSA.LogisticRegression.chrom (TraitGym)Evaluation | TraitGym Mendelian traits, linear-probing, AUPRC by chromosome weighted average, TraitGym Mendelian traits, matched 9 controls | 0.685 (best in column) |
| GPN-MSA.LogisticRegression.chrom (TraitGym)Evaluation | TraitGym Complex traits, linear-probing, AUPRC by chromosome weighted average, TraitGym Complex traits, matched 9 controls | 0.269 |
All 2 result rows with coverage, uncertainty and sources
Filter evaluations
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: GPN-MSA.LogisticRegression.chrom (TraitGym) | Protocol: TraitGym Complex traits, linear-probing, AUPRC by chromosome weighted average Dataset: TraitGym Complex traits, matched 9 controls | 0.269 AUPRC (weighted average over chromosomes of per-chromosome AUPRC; subset 'all') unitless · higher Uncertainty: SE 0.011520107088937664 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGPN-MSA.LogisticRegression.chrom on TraitGym complex_traits_matched_9 lit-genomics-20261011-traitgym-protocol-complex-traits-matched-9-linear-probing Aggregation: Not reported TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym) · complex_traits_matched_9/AUPRC_by_chrom_weighted_average/all/GPN-MSA.LogisticRegression.chrom.csv, column 'score' (standard error in column 'se') |
| Configuration: GPN-MSA.LogisticRegression.chrom (TraitGym) | Protocol: TraitGym Mendelian traits, linear-probing, AUPRC by chromosome weighted average Dataset: TraitGym Mendelian traits, matched 9 controls | 0.685 AUPRC (weighted average over chromosomes of per-chromosome AUPRC; subset 'all') unitless · higher Uncertainty: SE 0.0674501053545171 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGPN-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/GPN-MSA.LogisticRegression.chrom.csv, column 'score' (standard error in column 'se') |
Source checking is not independent reproduction. Release 2026-10-22-1b7cf027e4f6.
Use this configuration
How it works, versions and access
Related profile: GPN-MSA. This page retains the exact record and its evaluation context.
Strengths, limitations and unresolved questions
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.
2 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Relationship: configuration of gfm-guides-20261014-gpnmsa-model-gpn-msa Individual claims | GPN-MSA: an alignment-based DNA language model for genome-wide variant effect prediction (bioRxiv v2) Configuration name as printed in its source (GPN-MSA.LogisticRegression.chrom); GPN-MSA identity from gfm-guides-20261014-gpnmsa-source-biorxiv-v2 (Abstract) and gfm-guides-20261014-gpnmsa-source-gpn-msa-doc Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: bioRxiv v2, posted 2024-04-06 | source checked ["scope-review"] · 2026-10-14 Audit detailsAccepted in the independent review of 2026-10-14. See docs/reviews/2026-10-14-gfm-guide-evidence-review.md. Field: Claim: identity-20261014-4ecd5e1f197a495a744d Source artifact SHA-256: Hash scope: SHA-256 of the PDF bytes as downloaded 2026-10-14T12:02:16Z. bioRxiv rewrites the XMP dates and document IDs, the Info ModDate and the trailer /ID on download, so a re-download does not reproduce the hash; the review found a fresh copy of the same length differing only in those 51 bytes, with an identical pdftotext -layout text layer. |
| Relationship: configuration of gfm-guides-20261014-gpnmsa-model-gpn-msa Individual claims | TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym) Configuration name as printed in its source (GPN-MSA.LogisticRegression.chrom); GPN-MSA identity from gfm-guides-20261014-gpnmsa-source-biorxiv-v2 (Abstract) and gfm-guides-20261014-gpnmsa-source-gpn-msa-doc Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Hugging Face dataset revision 1fde19555fe8c0a55b1382bdf4c6f7082209f566 (last modified 2025-03-25); 156 metric CSVs under {dataset}/AUPRC_by_chrom_weighted_average/all/ | source checked ["scope-review"] · 2026-10-14 Audit detailsAccepted in the independent review of 2026-10-14. See docs/reviews/2026-10-14-gfm-guide-evidence-review.md. Field: Claim: identity-20261014-4ecd5e1f197a495a744d Source artifact SHA-256: 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) |
Sources and history
Release 2026-10-22-1b7cf027e4f6 · Record review: source checked
1 source record and release history
- TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym) · Original source · Hugging Face dataset revision 1fde19555fe8c0a55b1382bdf4c6f7082209f566 (last modified 2025-03-25); 156 metric CSVs under {dataset}/AUPRC_by_chrom_weighted_average/all/
Technical metadata and extraction receipts
Stable ID: lit-genomics-20261011-traitgym-config-gpn-msa-logisticregression-chrom
- areas
- dna-genomes
- contexts
- research
- method types
- foundation_model
- reported name
- GPN-MSA.LogisticRegression.chrom
- foundation model eligible
- true
- parameters
- songlab/gpn-msa-sapiens; ridge logistic regression on extracted features (chromosome folds)
- access reuse
- Public weights or score files (paper Appendix B.1)
- source locator
- File name 'GPN-MSA.LogisticRegression.chrom.csv'; config/models.csv; paper Table S5
- version
- songlab/gpn-msa-sapiens