Evidence claim

Relevance of GFMBench-API TraitGym Complex, zs-mlm-llr to "Select regulatory variants and genes for functional follow-up"

Use case: Select regulatory variants and genes for functional follow-up
Assessed by: GFMBench-API TraitGym Complex, zs-mlm-llr
Relevance: Proxy evidence
Endpoint: Zero-shot AUROC and AUPRC of masked log-likelihood ratio for masked genomic language models (DNA-BERT, DNABERT-2, NTv3, Caduceus-Ps) on TraitGym Complex

GFMBench-API zero-shot masked log-likelihood ratio scores on TraitGym Complex as evidence for choosing noncoding variants to edit.

4 reviewed evaluations

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.

19 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-22-1b7cf027e4f6
Property and statement	Original source and location	Review and provenance
Citation locations 1 values source id lit-genomics-20261011-gfmbench-source-larey2026 locator Table 4, task 'TraitGym Complex'; appendix task description Context-only references	GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models Original source ↗ lit-genomics-20261011-gfmbench-source-larey2026: Table 4, task 'TraitGym Complex'; appendix task description Version: bioRxiv preprint version 2, posted 2026-08-11 Retrieved: 2026-10-11T00:44:58Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.citation_locators` Source artifact SHA-256: `df9934c88ee245b1e19e155174169d6b6da57ae07c1a04bbea7115423facdf72` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison group gfmbench-traitgym Context-only references	GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models Original source ↗ lit-genomics-20261011-gfmbench-source-larey2026: Table 4, task 'TraitGym Complex'; appendix task description Version: bioRxiv preprint version 2, posted 2026-08-11 Retrieved: 2026-10-11T00:44:58Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.comparison_group` Source artifact SHA-256: `df9934c88ee245b1e19e155174169d6b6da57ae07c1a04bbea7115423facdf72` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison title GFMBench-API zero-shot scores on TraitGym Context-only references	GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models Original source ↗ lit-genomics-20261011-gfmbench-source-larey2026: Table 4, task 'TraitGym Complex'; appendix task description Version: bioRxiv preprint version 2, posted 2026-08-11 Retrieved: 2026-10-11T00:44:58Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.comparison_title` Source artifact SHA-256: `df9934c88ee245b1e19e155174169d6b6da57ae07c1a04bbea7115423facdf72` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Constraints 3 values Inspect every linked evaluation's source locator before citing a result. Do not combine this mapping's evaluations with any other protocol's results. Compare only with other rows of the same GFMBench-API table; TraitGym's own paper uses different context lengths and scoring. Context-only references	GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models Original source ↗ lit-genomics-20261011-gfmbench-source-larey2026: Table 4, task 'TraitGym Complex'; appendix task description Version: bioRxiv preprint version 2, posted 2026-08-11 Retrieved: 2026-10-11T00:44:58Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.constraints` Source artifact SHA-256: `df9934c88ee245b1e19e155174169d6b6da57ae07c1a04bbea7115423facdf72` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Endpoint Zero-shot AUROC and AUPRC of masked log-likelihood ratio for masked genomic language models (DNA-BERT, DNABERT-2, NTv3, Caduceus-Ps) on TraitGym Complex Context-only references	GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models Original source ↗ lit-genomics-20261011-gfmbench-source-larey2026: Table 4, task 'TraitGym Complex'; appendix task description Version: bioRxiv preprint version 2, posted 2026-08-11 Retrieved: 2026-10-11T00:44:58Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.endpoint` Source artifact SHA-256: `df9934c88ee245b1e19e155174169d6b6da57ae07c1a04bbea7115423facdf72` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Claimed field links:assessed_by:lit-genomics-20261011-gfmbench-protocol-traitgym-complex-zs-mlm-llr Context-only references	GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models Original source ↗ lit-genomics-20261011-gfmbench-source-larey2026: Table 4, task 'TraitGym Complex'; appendix task description Version: bioRxiv preprint version 2, posted 2026-08-11 Retrieved: 2026-10-11T00:44:58Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.field` Source artifact SHA-256: `df9934c88ee245b1e19e155174169d6b6da57ae07c1a04bbea7115423facdf72` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Headline metric auroc Context-only references	GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models Original source ↗ lit-genomics-20261011-gfmbench-source-larey2026: Table 4, task 'TraitGym Complex'; appendix task description Version: bioRxiv preprint version 2, posted 2026-08-11 Retrieved: 2026-10-11T00:44:58Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.headline_metric` Source artifact SHA-256: `df9934c88ee245b1e19e155174169d6b6da57ae07c1a04bbea7115423facdf72` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Limitations 3 values Preprint, not peer reviewed. Complex-trait AUROCs are all close to 0.5; differences between models are small and no uncertainty is printed. Fine-mapping labels, not experimental allele effects. Context-only references	GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models Original source ↗ lit-genomics-20261011-gfmbench-source-larey2026: Table 4, task 'TraitGym Complex'; appendix task description Version: bioRxiv preprint version 2, posted 2026-08-11 Retrieved: 2026-10-11T00:44:58Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.limitations` Source artifact SHA-256: `df9934c88ee245b1e19e155174169d6b6da57ae07c1a04bbea7115423facdf72` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Pinned records 15 values record id lit-genomics-20261011-gfmbench-eval-caduceus-ps-zero-shot-traitgym-complex-zs-mlm-llr fields status links attributes.origin attributes.comparison sha256 8e1684afc02cec0487cedbaebddbdea14ea7243b35141a4d4d1d60bce69cdef3 record id lit-genomics-20261011-gfmbench-eval-dna-bert-zero-shot-traitgym-complex-zs-mlm-llr fields status links attributes.origin attributes.comparison sha256 a3956e2cc52030de7c0cc2574a0af80e2e6a066f4326304d4953fae817c11366 record id lit-genomics-20261011-gfmbench-eval-dnabert-2-zero-shot-traitgym-complex-zs-mlm-llr fields status links attributes.origin attributes.comparison sha256 dcdd1351212f29879096f642a402bc2fc12aeeab2ea3821fa446fdb0fbd42c16 record id lit-genomics-20261011-gfmbench-eval-ntv3-zero-shot-traitgym-complex-zs-mlm-llr fields status links attributes.origin attributes.comparison sha256 66193bc6910fd56ff5d597918e0608994bc15280501ad5098d1fb61c5dc975bb record id lit-genomics-20261011-gfmbench-protocol-traitgym-complex-zs-mlm-llr fields status name description facets source_ids links attributes sha256 beb572aec582c2bc358955ff69a7b56df98b17dee3448b0a181a35e91669e384 record id lit-genomics-20261011-gfmbench-result-caduceus-ps-zero-shot-traitgym-complex-zs-mlm-llr-msk-llr-prc fields status attributes.metric attributes.metric_qualifier attributes.printed_value attributes.numeric_value sha256 d19b43990f1dda0b9fb268c763d0ad2aea8573cfdb55982e1276f51be0f86344 record id lit-genomics-20261011-gfmbench-result-caduceus-ps-zero-shot-traitgym-complex-zs-mlm-llr-msk-llr-roc fields status attributes.metric attributes.metric_qualifier attributes.printed_value attributes.numeric_value sha256 f8ea923154ec78156e447fb7a317d17701a93502d8eaf770640308d57a74134d record id lit-genomics-20261011-gfmbench-result-dna-bert-zero-shot-traitgym-complex-zs-mlm-llr-msk-llr-prc fields status attributes.metric attributes.metric_qualifier attributes.printed_value attributes.numeric_value sha256 afd5ce1127333caf40903eb4156c1aaf1cf9c979c700efa3bab96801d9eaa964 record id lit-genomics-20261011-gfmbench-result-dna-bert-zero-shot-traitgym-complex-zs-mlm-llr-msk-llr-roc fields status attributes.metric attributes.metric_qualifier attributes.printed_value attributes.numeric_value sha256 ddfcfaf3794355c0725492c2555b0d5c586b8d85eee7e5d5edfbfa083ce60140 record id lit-genomics-20261011-gfmbench-result-dnabert-2-zero-shot-traitgym-complex-zs-mlm-llr-msk-llr-prc fields status attributes.metric attributes.metric_qualifier attributes.printed_value attributes.numeric_value sha256 6279689625916795c0d3b2c31f6abafd652637003e2e375290977819d52692ba record id lit-genomics-20261011-gfmbench-result-dnabert-2-zero-shot-traitgym-complex-zs-mlm-llr-msk-llr-roc fields status attributes.metric attributes.metric_qualifier attributes.printed_value attributes.numeric_value sha256 47a3cf4d78d3810fb9d34ee28a1207cba21faca4790e4aad04a9cec172d988d0 record id lit-genomics-20261011-gfmbench-result-ntv3-zero-shot-traitgym-complex-zs-mlm-llr-msk-llr-prc fields status attributes.metric attributes.metric_qualifier attributes.printed_value attributes.numeric_value sha256 912dfb00d9ffae3ff0e621457c5b8d2ed99f3f5d3c5ebae6f173bcfdd8e6a962 record id lit-genomics-20261011-gfmbench-result-ntv3-zero-shot-traitgym-complex-zs-mlm-llr-msk-llr-roc fields status attributes.metric attributes.metric_qualifier attributes.printed_value attributes.numeric_value sha256 3ad399f17a03a80aceeeeedddb2deb509547753795273873dfac2ad9db606d05 record id lit-genomics-20261011-gfmbench-source-larey2026 fields status attributes.artifact_sha256 sha256 a461e55e4db9e70efca0dd40a686ae239e2e254757de72623099c721fd6eb0fc record id use-case-regulatory-variant-gene-follow-up fields status name description facets attributes.question attributes.decision attributes.inputs attributes.output attributes.exclusions attributes.setting attributes.clinical_scope attributes.intended_users sha256 0071547e01ccaec30238aea9e4882dd92e6f51be9c967c7fb88bc61d2788b870 Context-only references	GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models Original source ↗ lit-genomics-20261011-gfmbench-source-larey2026: Table 4, task 'TraitGym Complex'; appendix task description Version: bioRxiv preprint version 2, posted 2026-08-11 Retrieved: 2026-10-11T00:44:58Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.pins` Source artifact SHA-256: `df9934c88ee245b1e19e155174169d6b6da57ae07c1a04bbea7115423facdf72` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Rationale Proxy, not direct: the protocol ranks candidate noncoding variants by zero-shot model scores, which matches the first step of choosing allele edits, but it gives no element-gene link and no effect direction, and it is scored on the GFMBench-API re-implementation of TraitGym rather than on perturbation data. Context-only references	GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models Original source ↗ lit-genomics-20261011-gfmbench-source-larey2026: Table 4, task 'TraitGym Complex'; appendix task description Version: bioRxiv preprint version 2, posted 2026-08-11 Retrieved: 2026-10-11T00:44:58Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.rationale` Source artifact SHA-256: `df9934c88ee245b1e19e155174169d6b6da57ae07c1a04bbea7115423facdf72` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact

How to read the evidence

Sources and history

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

1 source record and release history

GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models · Original source · bioRxiv preprint version 2, posted 2026-08-11

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: use-case-mapping-lit-genomics-20261011-gfmbench-traitgym-complex-zs-mlm-llr

field: links:assessed_by:lit-genomics-20261011-gfmbench-protocol-traitgym-complex-zs-mlm-llr
value: lit-genomics-20261011-gfmbench-protocol-traitgym-complex-zs-mlm-llr
relevance: proxy
endpoint: Zero-shot AUROC and AUPRC of masked log-likelihood ratio for masked genomic language models (DNA-BERT, DNABERT-2, NTv3, Caduceus-Ps) on TraitGym Complex
rationale: Proxy, not direct: the protocol ranks candidate noncoding variants by zero-shot model scores, which matches the first step of choosing allele edits, but it gives no element-gene link and no effect direction, and it is scored on the GFMBench-API re-implementation of TraitGym rather than on perturbation data.
constraints: Inspect every linked evaluation's source locator before citing a result.; Do not combine this mapping's evaluations with any other protocol's results.; Compare only with other rows of the same GFMBench-API table; TraitGym's own paper uses different context lengths and scoring.
limitations: Preprint, not peer reviewed.; Complex-trait AUROCs are all close to 0.5; differences between models are small and no uncertainty is printed.; Fine-mapping labels, not experimental allele effects.
citation locators: source id: lit-genomics-20261011-gfmbench-source-larey2026; locator: Table 4, task 'TraitGym Complex'; appendix task description
source locator: lit-genomics-20261011-gfmbench-source-larey2026: Table 4, task 'TraitGym Complex'; appendix task description
headline metric: auroc
reason: Add a relevance judgement for a genomic foundation model benchmark protocol from the 2026-10-11 genomics suite pass, reviewed in docs/reviews/2026-10-11-genomics-gfm-suites.md.
comparison group: gfmbench-traitgym
comparison title: GFMBench-API zero-shot scores on TraitGym
stratum label: TraitGym Complex, masked log-likelihood ratio
stratum order: 5
reviewed evaluations: lit-genomics-20261011-gfmbench-eval-caduceus-ps-zero-shot-traitgym-complex-zs-mlm-llr; lit-genomics-20261011-gfmbench-eval-dna-bert-zero-shot-traitgym-complex-zs-mlm-llr; lit-genomics-20261011-gfmbench-eval-dnabert-2-zero-shot-traitgym-complex-zs-mlm-llr; lit-genomics-20261011-gfmbench-eval-ntv3-zero-shot-traitgym-complex-zs-mlm-llr
review: method: ai-assisted-source-review; scope-review; method note: Reviewer checked the endpoint against the use case's inputs and output, the proxy rating and the limitations; every evaluation on the protocol had its values checked in the batch review. Corrections listed in review.md were applied by the extractor.; reviewer: claude; reviewer note: Claude review agent reviewer-gen-3, independent of the extractor lit-genomics; no human review claimed; reviewed at: 2026-10-11T14:40:00Z; note: Automated review; not human scientific review.
pins: record id: lit-genomics-20261011-gfmbench-eval-caduceus-ps-zero-shot-traitgym-complex-zs-mlm-llr; fields: status; links; attributes.origin; attributes.comparison; sha256: 8e1684afc02cec0487cedbaebddbdea14ea7243b35141a4d4d1d60bce69cdef3; record id: lit-genomics-20261011-gfmbench-eval-dna-bert-zero-shot-traitgym-complex-zs-mlm-llr; fields: status; links; attributes.origin; attributes.comparison; sha256: a3956e2cc52030de7c0cc2574a0af80e2e6a066f4326304d4953fae817c11366; record id: lit-genomics-20261011-gfmbench-eval-dnabert-2-zero-shot-traitgym-complex-zs-mlm-llr; fields: status; links; attributes.origin; attributes.comparison; sha256: dcdd1351212f29879096f642a402bc2fc12aeeab2ea3821fa446fdb0fbd42c16; record id: lit-genomics-20261011-gfmbench-eval-ntv3-zero-shot-traitgym-complex-zs-mlm-llr; fields: status; links; attributes.origin; attributes.comparison; sha256: 66193bc6910fd56ff5d597918e0608994bc15280501ad5098d1fb61c5dc975bb; record id: lit-genomics-20261011-gfmbench-protocol-traitgym-complex-zs-mlm-llr; fields: status; name; description; facets; source_ids; links; attributes; sha256: beb572aec582c2bc358955ff69a7b56df98b17dee3448b0a181a35e91669e384; record id: lit-genomics-20261011-gfmbench-result-caduceus-ps-zero-shot-traitgym-complex-zs-mlm-llr-msk-llr-prc; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: d19b43990f1dda0b9fb268c763d0ad2aea8573cfdb55982e1276f51be0f86344; record id: lit-genomics-20261011-gfmbench-result-caduceus-ps-zero-shot-traitgym-complex-zs-mlm-llr-msk-llr-roc; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: f8ea923154ec78156e447fb7a317d17701a93502d8eaf770640308d57a74134d; record id: lit-genomics-20261011-gfmbench-result-dna-bert-zero-shot-traitgym-complex-zs-mlm-llr-msk-llr-prc; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: afd5ce1127333caf40903eb4156c1aaf1cf9c979c700efa3bab96801d9eaa964; record id: lit-genomics-20261011-gfmbench-result-dna-bert-zero-shot-traitgym-complex-zs-mlm-llr-msk-llr-roc; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: ddfcfaf3794355c0725492c2555b0d5c586b8d85eee7e5d5edfbfa083ce60140; record id: lit-genomics-20261011-gfmbench-result-dnabert-2-zero-shot-traitgym-complex-zs-mlm-llr-msk-llr-prc; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 6279689625916795c0d3b2c31f6abafd652637003e2e375290977819d52692ba; record id: lit-genomics-20261011-gfmbench-result-dnabert-2-zero-shot-traitgym-complex-zs-mlm-llr-msk-llr-roc; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 47a3cf4d78d3810fb9d34ee28a1207cba21faca4790e4aad04a9cec172d988d0; record id: lit-genomics-20261011-gfmbench-result-ntv3-zero-shot-traitgym-complex-zs-mlm-llr-msk-llr-prc; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 912dfb00d9ffae3ff0e621457c5b8d2ed99f3f5d3c5ebae6f173bcfdd8e6a962; record id: lit-genomics-20261011-gfmbench-result-ntv3-zero-shot-traitgym-complex-zs-mlm-llr-msk-llr-roc; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 3ad399f17a03a80aceeeeedddb2deb509547753795273873dfac2ad9db606d05; record id: lit-genomics-20261011-gfmbench-source-larey2026; fields: status; attributes.artifact_sha256; sha256: a461e55e4db9e70efca0dd40a686ae239e2e254757de72623099c721fd6eb0fc; record id: use-case-regulatory-variant-gene-follow-up; fields: status; name; description; facets; attributes.question; attributes.decision; attributes.inputs; attributes.output; attributes.exclusions; attributes.setting; attributes.clinical_scope; attributes.intended_users; sha256: 0071547e01ccaec30238aea9e4882dd92e6f51be9c967c7fb88bc61d2788b870

Related records

subject: Select regulatory variants and genes for functional follow-up

Suggest a correction