ClinVar variant classification assesses whether zero-shot allele scores distinguish pathogenic from benign annotations.
Explanatory profile: limited source coverage · Automated source review, 2026-09-16. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.
| Property | Description and evidence |
|---|---|
| Datasets | ClinVar variants meeting a review-status filter, with pathogenic/likely-pathogenic positives and benign/likely-benign negatives; the catalogue retains the 3-prime UTR subset.SourcesA Phylogenetic Approach to Genomic Language Modeling · Results: Log Likelihood Ratio Evaluation; ClinVar and OMIM tests; cached text lines 46–48, 52, 56 |
| Splits | Zero-shot evaluation, distinct from supervised embedding tasks elsewhere in the paper.SourcesA Phylogenetic Approach to Genomic Language Modeling · Results: Log Likelihood Ratio Evaluation; ClinVar and OMIM tests; cached text lines 46–48, 52, 56 |
| Metrics | ROC-based assessment for ClinVar; AUPRC described for the separate imbalanced OMIM comparison must not be imported automatically.SourcesA Phylogenetic Approach to Genomic Language Modeling · Results: Log Likelihood Ratio Evaluation; ClinVar and OMIM tests; cached text lines 46–48, 52, 56 |
| Baselines | Nucleotide Transformer, HyenaDNA, Caduceus and GPN-MSA comparisons.SourcesA Phylogenetic Approach to Genomic Language Modeling · Results: Log Likelihood Ratio Evaluation; ClinVar and OMIM tests; cached text lines 46–48, 52, 56 |
| Leakage controls | ClinVar variants are selected by review status and pathogenic/benign labels for zero-shot scoring. The main ClinVar experiment does not report exclusion of those loci from genome pretraining. The odd/even chromosome held-out experiment is a separate ablation, not the stated split of the main ClinVar result. · Not reported in inspected sourcesSourcesA Phylogenetic Approach to Genomic Language Modeling · Classifying ClinVar variants and Table 1; held-out-human-sequence ablation; cached paragraphs 36,51–53,72 |
| Uncertainty | The cited text-accessible evaluation sections give no confidence-interval, resampling or repeat-run error-bar specification. Image-only tables and uninspected supplements are outside this absence claim. · Not reported in inspected sourcesSourcesA Phylogenetic Approach to Genomic Language Modeling · Results: Log Likelihood Ratio Evaluation; ClinVar and OMIM tests; cached text lines 46–48, 52, 56 |
| Entity type | Paper-specific computational evaluation protocol.SourcesA Phylogenetic Approach to Genomic Language Modeling · Results: Log Likelihood Ratio Evaluation; ClinVar and OMIM tests; cached text lines 46–48, 52, 56 |
| Organisms | Human ClinVar variants.SourcesA Phylogenetic Approach to Genomic Language Modeling · Results: Log Likelihood Ratio Evaluation; ClinVar and OMIM tests; cached text lines 46–48, 52, 56 |
| Assays | Clinical pathogenic/benign assertions meeting a review-status filter.SourcesA Phylogenetic Approach to Genomic Language Modeling · Results: Log Likelihood Ratio Evaluation; ClinVar and OMIM tests; cached text lines 46–48, 52, 56 |
| Allowed inputs | Reference/alternate genomic sequences for the 3-prime UTR subset.SourcesA Phylogenetic Approach to Genomic Language Modeling · Results: Log Likelihood Ratio Evaluation; ClinVar and OMIM tests; cached text lines 46–48, 52, 56 |
| Adaptation | Zero-shot variant scoring; supervised embedding experiments elsewhere are not this protocol.SourcesA Phylogenetic Approach to Genomic Language Modeling · Results: Log Likelihood Ratio Evaluation; ClinVar and OMIM tests; cached text lines 46–48, 52, 56 |
Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol.
ClinVar variants meeting a review-status filter, with pathogenic/likely-pathogenic positives and benign/likely-benign negatives; the catalogue retains the 3-prime UTR subset. Zero-shot evaluation, distinct from supervised embedding tasks elsewhere in the paper. ROC-based assessment for ClinVar; AUPRC described for the separate imbalanced OMIM comparison must not be imported automatically. Nucleotide Transformer, HyenaDNA, Caduceus and GPN-MSA comparisons. The cited text-accessible evaluation sections give no confidence-interval, resampling or repeat-run error-bar specification. Image-only tables and uninspected supplements are outside this absence claim.
Each evaluation records what was tested and under which conditions.
Release 2026-09-17-d277315f7d76 · 1 evaluation · 1 metric row. Different protocols are not a single leaderboard.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| PhyloGPN: ClinVar 3-prime UTR variant classification Configuration: PhyloGPNTask: ClinVar 3-prime UTR variant classificationDataset: ClinVar 3-prime UTR variants log-likelihood-ratio scoring Author-reported evaluation · Evaluation metadata: needs review | ||
| 0.94 AUROC Unit: fraction · Direction: unknown | Uncertainty: not reported in legacy extract Scored: Not reported · Eligible: Not reported | source checkedA Phylogenetic Approach to Genomic Language Modeling · Table 1, 3-prime UTR row, PhyloGPN AUROC column Source checking is not independent reproduction. |
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 resource | Version | Reference |
|---|---|---|
| A Phylogenetic Approach to Genomic Language Modeling | preprint version in PMC | Read source |
source found structured extraction pending
Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged.
Stable record: reported-task-ed3dd3b83c4505Trace 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.
18 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Diagram caption Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol. Individual claims | A Phylogenetic Approach to Genomic Language Modeling Results: Log Likelihood Ratio Evaluation; ClinVar and OMIM tests; cached text lines 46–48, 52, 56 Version: preprint version in PMC | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram steps ["Input: Reference/alternate genomic sequences for the 3-prime UTR subset.","Evaluation: Zero-shot variant scoring; supervised embedding experiments elsewhere are not this protocol.","Readout: ROC-based assessment for ClinVar; AUPRC described for the separate imbalanced OMIM comparison must not be imported automatically."] Individual claims | A Phylogenetic Approach to Genomic Language Modeling Results: Log Likelihood Ratio Evaluation; ClinVar and OMIM tests; cached text lines 46–48, 52, 56 Version: preprint version in PMC | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram title Computational evaluation flow Individual claims | A Phylogenetic Approach to Genomic Language Modeling Results: Log Likelihood Ratio Evaluation; ClinVar and OMIM tests; cached text lines 46–48, 52, 56 Version: preprint version in PMC | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Datasets ClinVar variants meeting a review-status filter, with pathogenic/likely-pathogenic positives and benign/likely-benign negatives; the catalogue retains the 3-prime UTR subset. Individual claims | A Phylogenetic Approach to Genomic Language Modeling Results: Log Likelihood Ratio Evaluation; ClinVar and OMIM tests; cached text lines 46–48, 52, 56 Version: preprint version in PMC | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Splits Zero-shot evaluation, distinct from supervised embedding tasks elsewhere in the paper. Individual claims | A Phylogenetic Approach to Genomic Language Modeling Results: Log Likelihood Ratio Evaluation; ClinVar and OMIM tests; cached text lines 46–48, 52, 56 Version: preprint version in PMC | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Adaptation Zero-shot variant scoring; supervised embedding experiments elsewhere are not this protocol. Individual claims | A Phylogenetic Approach to Genomic Language Modeling Results: Log Likelihood Ratio Evaluation; ClinVar and OMIM tests; cached text lines 46–48, 52, 56 Version: preprint version in PMC | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Metrics ROC-based assessment for ClinVar; AUPRC described for the separate imbalanced OMIM comparison must not be imported automatically. Individual claims | A Phylogenetic Approach to Genomic Language Modeling Results: Log Likelihood Ratio Evaluation; ClinVar and OMIM tests; cached text lines 46–48, 52, 56 Version: preprint version in PMC | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Baselines Nucleotide Transformer, HyenaDNA, Caduceus and GPN-MSA comparisons. Individual claims | A Phylogenetic Approach to Genomic Language Modeling Results: Log Likelihood Ratio Evaluation; ClinVar and OMIM tests; cached text lines 46–48, 52, 56 Version: preprint version in PMC | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Leakage controls ClinVar variants are selected by review status and pathogenic/benign labels for zero-shot scoring. The main ClinVar experiment does not report exclusion of those loci from genome pretraining. The odd/even chromosome held-out experiment is a separate ablation, not the stated split of the main ClinVar result. Individual claims | A Phylogenetic Approach to Genomic Language Modeling Classifying ClinVar variants and Table 1; held-out-human-sequence ablation; cached paragraphs 36,51–53,72 Version: preprint version in PMC | unreported automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Uncertainty The cited text-accessible evaluation sections give no confidence-interval, resampling or repeat-run error-bar specification. Image-only tables and uninspected supplements are outside this absence claim. Individual claims | A Phylogenetic Approach to Genomic Language Modeling Results: Log Likelihood Ratio Evaluation; ClinVar and OMIM tests; cached text lines 46–48, 52, 56 Version: preprint version in PMC | unreported automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Release 2026-09-17-d277315f7d76 · Record review: needs review
Stable ID: reported-task-ed3dd3b83c4505