Relevance of feng-dna-fm-20261013-protocol-gtex-wb-expression-long-768 to "Select regulatory variants and genes for functional follow-up"
- Use case
- Select regulatory variants and genes for functional follow-up
- Assessed by
- Feng GTEx whole-blood expression prediction, 768 genes, long input
- Relevance
- Proxy evidence
- Endpoint
- Average per-gene Pearson correlation and MSE between predicted and observed whole-blood expression across GTEx subjects, from frozen embeddings of each subject's phased TSS-centred sequence plus a per-gene random forest
Descriptive fact transcribed from the pinned source.
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
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
Citation locations1 values
| Benchmarking DNA foundation models for genomic and genetic tasks evidence-expansion-dna-foundation-models-2025-5d8ca9bc: Table 4 Version: PMC12663285.1 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| Comparison group feng-gtex-expression Context-only references | Benchmarking DNA foundation models for genomic and genetic tasks evidence-expansion-dna-foundation-models-2025-5d8ca9bc: Table 4 Version: PMC12663285.1 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| Comparison title Feng et al. GTEx whole-blood expression prediction Context-only references | Benchmarking DNA foundation models for genomic and genetic tasks evidence-expansion-dna-foundation-models-2025-5d8ca9bc: Table 4 Version: PMC12663285.1 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
Constraints3 values
| Benchmarking DNA foundation models for genomic and genetic tasks evidence-expansion-dna-foundation-models-2025-5d8ca9bc: Table 4 Version: PMC12663285.1 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| Endpoint Average per-gene Pearson correlation and MSE between predicted and observed whole-blood expression across GTEx subjects, from frozen embeddings of each subject's phased TSS-centred sequence plus a per-gene random forest Context-only references | Benchmarking DNA foundation models for genomic and genetic tasks evidence-expansion-dna-foundation-models-2025-5d8ca9bc: Table 4 Version: PMC12663285.1 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| Claimed field links:assessed_by:feng-dna-fm-20261013-protocol-gtex-wb-expression-long-768 Context-only references | Benchmarking DNA foundation models for genomic and genetic tasks evidence-expansion-dna-foundation-models-2025-5d8ca9bc: Table 4 Version: PMC12663285.1 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| Headline metric pearson-correlation Context-only references | Benchmarking DNA foundation models for genomic and genetic tasks evidence-expansion-dna-foundation-models-2025-5d8ca9bc: Table 4 Version: PMC12663285.1 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
Limitations9 values
| Benchmarking DNA foundation models for genomic and genetic tasks evidence-expansion-dna-foundation-models-2025-5d8ca9bc: Table 4 Version: PMC12663285.1 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
Pinned records15 values
| Benchmarking DNA foundation models for genomic and genetic tasks evidence-expansion-dna-foundation-models-2025-5d8ca9bc: Table 4 Version: PMC12663285.1 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| Rationale Proxy: tests whether a model's sequence representation captures inter-individual cis-sequence effects on expression, which bears on allele-effect prediction for a locus. It does not score individual variants, link elements to genes or measure perturbation outcomes, which the use case needs. Context-only references | Benchmarking DNA foundation models for genomic and genetic tasks evidence-expansion-dna-foundation-models-2025-5d8ca9bc: Table 4 Version: PMC12663285.1 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
Sources and history
Release 2026-11-02-a7f03c9e55a5 · Record review: source checked
1 source record and release history
Download this release (gzip)Technical metadata and extraction receipts
Stable ID: use-case-mapping-feng-dna-fm-20261013-gtex-wb-expression-long-768
- field
- links:assessed_by:feng-dna-fm-20261013-protocol-gtex-wb-expression-long-768
- value
- feng-dna-fm-20261013-protocol-gtex-wb-expression-long-768
- relevance
- proxy
- endpoint
- Average per-gene Pearson correlation and MSE between predicted and observed whole-blood expression across GTEx subjects, from frozen embeddings of each subject's phased TSS-centred sequence plus a per-gene random forest
- rationale
- Proxy: tests whether a model's sequence representation captures inter-individual cis-sequence effects on expression, which bears on allele-effect prediction for a locus. It does not score individual variants, link elements to genes or measure perturbation outcomes, which the use case needs.
- 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 rows only within this protocol.
- limitations
- Labels are covariate-corrected whole-blood expression of GTEx subjects, not allele-specific or endogenous perturbation effects, and not in the user's cell type.; Each model's representation is frozen; a random forest is fitted per gene on expression labels, so this measures how much expression variation the embedding plus a supervised head explains, not a label-free variant-effect score.; Individual-level GTEx data are protected (GTEx Protected Data Access application); the benchmark cannot be rerun from public data.; Transcribed from the paper; Feng et al. did not develop the models (independent_paper). No reproduction by Rewire and no human scientific review.; The authors call overall performance modest and say the findings should be considered preliminary indicators (Results, Gene expression prediction, last paragraph).; Subjects are split 75:25 within each gene; no loci, genes or studies are held out, which the use case's validation requirements ask for.; 768 randomly selected genes only; not comparable with the all-gene rows.; Enformer is a supervised expression model used as a comparator.; Caduceus-Ph used the central 131 kb; HyenaDNA-450K and Enformer used the 196 kb window (Methods).
- citation locators
- source id: evidence-expansion-dna-foundation-models-2025-5d8ca9bc; locator: Table 4; Methods, 'Gene expression prediction datasets' and 'Gene expression prediction benchmark'; Data availability
- source locator
- evidence-expansion-dna-foundation-models-2025-5d8ca9bc: Table 4
- headline metric
- pearson-correlation
- comparison group
- feng-gtex-expression
- comparison title
- Feng et al. GTEx whole-blood expression prediction
- stratum label
- 768-gene subset, long input
- stratum order
- 2
- reason
- Add a relevance judgement for the Feng et al. gene-expression protocol (rewire-benchmark-data#19).
- reviewed evaluations
- feng-dna-fm-20261013-eval-gtex-caduceus-ph-long-sequence-input; feng-dna-fm-20261013-eval-gtex-enformer; feng-dna-fm-20261013-eval-gtex-hyenadna-450k
- review
- method: ai-assisted-source-review; scope-review; method note: Checked the endpoint against the use case's inputs, output and setting in data/entities/use-cases.jsonl; checked each limitation against Methods, Results, Data availability and Table 4; checked every evaluation on the protocol.; reviewer: claude; reviewer note: Independent Claude (Opus 5.5) review agent, separate from the extraction agent feng-19 that built this batch. Automated review only; no human review claimed. Transcription, not reproduction.; reviewed at: 2026-10-13T14:40:00Z; artifact sha256: 5d8ca9bcf88cc1b38ad667906a2e4699b1aefa6d31c6f49259784930353f3202; retrieval url: https://www.ebi.ac.uk/europepmc/webservices/rest/PMC12663285/fullTextXML; note: Judgement written by the extraction agent. Independent review: proxy is justified because cross-individual expression prediction bears only on allele-effect prediction, which the use case treats as a separate comparison; it does not score variants or link elements to genes.
- pins
- record id: evidence-expansion-dna-foundation-models-2025-5d8ca9bc; fields: status; attributes.artifact_sha256; sha256: 7996f91821054e875cfca234e2e3bca2b25a02af92475d0577cd3dd0a71a8559; record id: evidence-reported-dna-foundation-models-2025-readme-md; fields: status; attributes.artifact_sha256; sha256: 58a64d048abd1fac81c829a001a39a4184741155de8eb41a05f8e8cf3edabea8; record id: feng-dna-fm-20261013-eval-gtex-caduceus-ph-long-sequence-input; fields: status; links; attributes.origin; attributes.comparison; sha256: a511fdbdf507eddd28979b22aa57c75e394295ffc8d50432ff411190cf1b2758; record id: feng-dna-fm-20261013-eval-gtex-enformer; fields: status; links; attributes.origin; attributes.comparison; sha256: 32b152afeabb92ed3bbe177fd646991c6025292abe9353e2647057a0ed187cda; record id: feng-dna-fm-20261013-eval-gtex-hyenadna-450k; fields: status; links; attributes.origin; attributes.comparison; sha256: cd4982965a058168cee3c7603467fb3bb60503368b7ba2c7e83391f25cf07e8e; record id: feng-dna-fm-20261013-protocol-gtex-wb-expression-long-768; fields: status; name; description; facets; source_ids; links; attributes; sha256: 6812e940fc7a9ef179eeee3830e52821a1760e563daa528c59f2e7eab090523d; record id: feng-dna-fm-20261013-result-gtex-caduceus-ph-long-sequence-input-mse; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: df2978024d3148de30dbdcb06edc2de8b0c5800b0c12fd91f892dc6b23e3459b; record id: feng-dna-fm-20261013-result-gtex-caduceus-ph-long-sequence-input-pearson; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 87681065b137de41f1a51f521307c11092cd96c224dc6d1d702dab49b6076476; record id: feng-dna-fm-20261013-result-gtex-enformer-mse; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: df2978024d3148de30dbdcb06edc2de8b0c5800b0c12fd91f892dc6b23e3459b; record id: feng-dna-fm-20261013-result-gtex-enformer-pearson; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 5203f17ef7faf52a3f6ba9da861b9bc190b557a727237919e15cadd079c3b09f; record id: feng-dna-fm-20261013-result-gtex-hyenadna-450k-mse; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: dcc5a64bf299d8b3cec2499afe8dd55c4e40626c0ed7994cbde46085c91832b4; record id: feng-dna-fm-20261013-result-gtex-hyenadna-450k-pearson; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 9d6f0b1a9dd6cc8a606d61ded0cdf9b77060d076fb5800bbcdbf8a9a2b7397b8; record id: feng-dna-fm-20261013-source-gtex-hyena-script; fields: status; attributes.artifact_sha256; sha256: 14826c6e46f84645a24696ddc49fddd5506047571f168932b6e3d7a4ef296f43; record id: feng-dna-fm-20261013-source-supplementary-information; fields: status; attributes.artifact_sha256; sha256: b4b55ba9044d429e526d69c577581951682d9a8668b3e44820badecf3448e42f; 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