Subject-specific phased sequences (TSS +/- 3,000 bp) and covariate-corrected whole-blood expression for GTEx v8; Feng et al. 2025.
5 evaluations · 10 results. Different protocols are not a single leaderboard.
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: Caduceus-Ph (GTEx whole-blood expression prediction) | Protocol: Feng GTEx whole-blood expression prediction, all genes, 6 kb input Dataset: Feng GTEx v8 whole-blood expression, TSS +/- 3 kb | 0.234 MSE (mean across genes of per-gene MSE of covariate-corrected expression) unit-unreported · lower Uncertainty: Not reported by the source: Table 4 prints averages only; per-gene spread is shown only as a histogram (Fig. 3). Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCaduceus-Ph GTEx whole-blood expression evaluation Table 4, frozen embeddings + per-gene random forest regression Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 4, row 'Caduceus-Ph', column 'Average Prediction MSE' |
| Configuration: Caduceus-Ph (GTEx whole-blood expression prediction) | Protocol: Feng GTEx whole-blood expression prediction, all genes, 6 kb input Dataset: Feng GTEx v8 whole-blood expression, TSS +/- 3 kb | 0.123 Pearson (mean across genes of per-gene Pearson correlation between predicted and observed expression) unitless · higher Uncertainty: Not reported by the source: Table 4 prints averages only; per-gene spread is shown only as a histogram (Fig. 3). Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCaduceus-Ph GTEx whole-blood expression evaluation Table 4, frozen embeddings + per-gene random forest regression Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 4, row 'Caduceus-Ph', column 'Average Prediction Correlation' |
| Configuration: DNABERT-2 (GTEx whole-blood expression prediction) | Protocol: Feng GTEx whole-blood expression prediction, all genes, 6 kb input Dataset: Feng GTEx v8 whole-blood expression, TSS +/- 3 kb | 0.236 MSE (mean across genes of per-gene MSE of covariate-corrected expression) unit-unreported · lower Uncertainty: Not reported by the source: Table 4 prints averages only; per-gene spread is shown only as a histogram (Fig. 3). Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceDNABERT-2 GTEx whole-blood expression evaluation Table 4, frozen embeddings + per-gene random forest regression Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 4, row 'DNABERT-2', column 'Average Prediction MSE' |
| Configuration: DNABERT-2 (GTEx whole-blood expression prediction) | Protocol: Feng GTEx whole-blood expression prediction, all genes, 6 kb input Dataset: Feng GTEx v8 whole-blood expression, TSS +/- 3 kb | 0.121 Pearson (mean across genes of per-gene Pearson correlation between predicted and observed expression) unitless · higher Uncertainty: Not reported by the source: Table 4 prints averages only; per-gene spread is shown only as a histogram (Fig. 3). Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceDNABERT-2 GTEx whole-blood expression evaluation Table 4, frozen embeddings + per-gene random forest regression Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 4, row 'DNABERT-2', column 'Average Prediction Correlation' |
| Configuration: GROVER (GTEx whole-blood expression prediction) | Protocol: Feng GTEx whole-blood expression prediction, all genes, 6 kb input Dataset: Feng GTEx v8 whole-blood expression, TSS +/- 3 kb | 0.233 MSE (mean across genes of per-gene MSE of covariate-corrected expression) unit-unreported · lower Uncertainty: Not reported by the source: Table 4 prints averages only; per-gene spread is shown only as a histogram (Fig. 3). Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceGROVER GTEx whole-blood expression evaluation Table 4, frozen embeddings + per-gene random forest regression Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 4, row 'GROVER', column 'Average Prediction MSE' |
| Configuration: GROVER (GTEx whole-blood expression prediction) | Protocol: Feng GTEx whole-blood expression prediction, all genes, 6 kb input Dataset: Feng GTEx v8 whole-blood expression, TSS +/- 3 kb | 0.114 Pearson (mean across genes of per-gene Pearson correlation between predicted and observed expression) unitless · higher Uncertainty: Not reported by the source: Table 4 prints averages only; per-gene spread is shown only as a histogram (Fig. 3). Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceGROVER GTEx whole-blood expression evaluation Table 4, frozen embeddings + per-gene random forest regression Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 4, row 'GROVER', column 'Average Prediction Correlation' |
| Configuration: HyenaDNA (GTEx whole-blood expression prediction) | Protocol: Feng GTEx whole-blood expression prediction, all genes, 6 kb input Dataset: Feng GTEx v8 whole-blood expression, TSS +/- 3 kb | 0.235 MSE (mean across genes of per-gene MSE of covariate-corrected expression) unit-unreported · lower Uncertainty: Not reported by the source: Table 4 prints averages only; per-gene spread is shown only as a histogram (Fig. 3). Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceHyenaDNA GTEx whole-blood expression evaluation Table 4, frozen embeddings + per-gene random forest regression Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 4, row 'HyenaDNA', column 'Average Prediction MSE' |
| Configuration: HyenaDNA (GTEx whole-blood expression prediction) | Protocol: Feng GTEx whole-blood expression prediction, all genes, 6 kb input Dataset: Feng GTEx v8 whole-blood expression, TSS +/- 3 kb | 0.122 Pearson (mean across genes of per-gene Pearson correlation between predicted and observed expression) unitless · higher Uncertainty: Not reported by the source: Table 4 prints averages only; per-gene spread is shown only as a histogram (Fig. 3). Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceHyenaDNA GTEx whole-blood expression evaluation Table 4, frozen embeddings + per-gene random forest regression Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 4, row 'HyenaDNA', column 'Average Prediction Correlation' |
| Configuration: NT-v2 (GTEx whole-blood expression prediction) | Protocol: Feng GTEx whole-blood expression prediction, all genes, 6 kb input Dataset: Feng GTEx v8 whole-blood expression, TSS +/- 3 kb | 0.236 MSE (mean across genes of per-gene MSE of covariate-corrected expression) unit-unreported · lower Uncertainty: Not reported by the source: Table 4 prints averages only; per-gene spread is shown only as a histogram (Fig. 3). Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceNT-v2 GTEx whole-blood expression evaluation Table 4, frozen embeddings + per-gene random forest regression Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 4, row 'NT-v2', column 'Average Prediction MSE' |
| Configuration: NT-v2 (GTEx whole-blood expression prediction) | Protocol: Feng GTEx whole-blood expression prediction, all genes, 6 kb input Dataset: Feng GTEx v8 whole-blood expression, TSS +/- 3 kb | 0.122 Pearson (mean across genes of per-gene Pearson correlation between predicted and observed expression) unitless · higher Uncertainty: Not reported by the source: Table 4 prints averages only; per-gene spread is shown only as a histogram (Fig. 3). Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceNT-v2 GTEx whole-blood expression evaluation Table 4, frozen embeddings + per-gene random forest regression Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 4, row 'NT-v2', column 'Average Prediction Correlation' |
Source checking is not independent reproduction. Release 2026-11-02-a7f03c9e55a5.
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.
Release 2026-11-02-a7f03c9e55a5 · Evidence verified: Not verified
Exact outcomes, predictions, identifiers and evaluator are connected.
Missing or unresolved evidence
Verified: Not verified
Replay evidence includes annotations and an assessment of dependence. Unknown independence permits descriptive analysis only.
Missing or unresolved evidence
Verified: Not verified
A pinned recipe describes the inputs, environment and resource requirements.
Missing or unresolved evidence
Verified: Not verified
Separate data and exposure records support an independent test.
Missing or unresolved evidence
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.
No verified artifact manifest is connected to this record yet. The gaps above identify what is needed before analysis can begin.
A dataset supplies biological observations. The evaluation protocol defines how those observations are split, used and scored.
Source checking verifies the cited claim or transcription. It does not establish independent reproduction.
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.
8 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Access Individual-level GTEx v8 whole-genome sequences and expression are protected human-participant data: per the Data availability statement, raw individual WGS must be requested through the GTEx Protected Data Access portal, and the processed expression benchmark is not deposited with the other processed datasets on Hugging Face. Only aggregated GTEx releases are public. Context-only references | Benchmarking DNA foundation models for genomic and genetic tasks Methods, 'Gene expression prediction datasets' (paragraphs 1 and 3) and 'Gene expression prediction benchmark'; Data availability 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. |
| Population GTEx v8 whole blood: 610 subjects, 21,004 genes. Each subject's phased SNVs and indels from WGS VCFs are inserted into GRCh38 to give both alleles of a ~6,000 bp window centred on the TSS. Context-only references | Benchmarking DNA foundation models for genomic and genetic tasks Methods, 'Gene expression prediction datasets' (paragraphs 1 and 3) and 'Gene expression prediction benchmark'; Data availability 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. |
| Private data not included true Context-only references | Benchmarking DNA foundation models for genomic and genetic tasks Methods, 'Gene expression prediction datasets' (paragraphs 1 and 3) and 'Gene expression prediction benchmark'; Data availability 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. |
| Source location Methods, 'Gene expression prediction datasets' (paragraphs 1 and 3) and 'Gene expression prediction benchmark'; Data availability Context-only references | Benchmarking DNA foundation models for genomic and genetic tasks Methods, 'Gene expression prediction datasets' (paragraphs 1 and 3) and 'Gene expression prediction benchmark'; Data availability 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. |
| Species Homo sapiens Context-only references | Benchmarking DNA foundation models for genomic and genetic tasks Methods, 'Gene expression prediction datasets' (paragraphs 1 and 3) and 'Gene expression prediction benchmark'; Data availability 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. |
| Split Per gene, subjects split 75:25 into training and test; fivefold cross-validation within training for tuning. Context-only references | Benchmarking DNA foundation models for genomic and genetic tasks Methods, 'Gene expression prediction datasets' (paragraphs 1 and 3) and 'Gene expression prediction benchmark'; Data availability 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. |
| Description Subject-specific phased sequences (TSS +/- 3,000 bp) and covariate-corrected whole-blood expression for GTEx v8; Feng et al. 2025. Context-only references | Benchmarking DNA foundation models for genomic and genetic tasks Methods, 'Gene expression prediction datasets' (paragraphs 1 and 3) and 'Gene expression prediction benchmark'; Data availability 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. |
| Name Feng GTEx v8 whole-blood expression, TSS +/- 3 kb Context-only references | Benchmarking DNA foundation models for genomic and genetic tasks Methods, 'Gene expression prediction datasets' (paragraphs 1 and 3) and 'Gene expression prediction benchmark'; Data availability 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. |
Release 2026-11-02-a7f03c9e55a5 · Record review: source checked
Stable ID: feng-dna-fm-20261013-dataset-gtex-wb-expression-6kb