What this source contributed
Records in this release that cite this source. A record can cite several sources.
Results
Values as the source printed them. Compare results only under compatible protocols, datasets and metrics.
Claims
Statements this source supports, each with where in the source it was checked.
- AlphaGenome, output tracks* (eQTL discrimination): facets.method_types: Facets: method types ["supervised_machine_learning"] (The store's Enformer and Sei model records (regulatory-variant-20261009-model-enformer, regulatory-variant-20261009-model-sei) are supervised_machine_learning)
- AlphaGenome, output tracks* (ipaQTL discrimination): facets.method_types: Facets: method types ["supervised_machine_learning"] (The store's Enformer and Sei model records (regulatory-variant-20261009-model-enformer, regulatory-variant-20261009-model-sei) are supervised_machine_learning)
- AlphaGenome, output tracks* (paQTL discrimination): facets.method_types: Facets: method types ["supervised_machine_learning"] (The store's Enformer and Sei model records (regulatory-variant-20261009-model-enformer, regulatory-variant-20261009-model-sei) are supervised_machine_learning)
- AlphaGenome, output tracks* (sQTL discrimination): facets.method_types: Facets: method types ["supervised_machine_learning"] (The store's Enformer and Sei model records (regulatory-variant-20261009-model-enformer, regulatory-variant-20261009-model-sei) are supervised_machine_learning)
- Enformer, hidden states* (eQTL discrimination): facets.method_types: Facets: method types ["supervised_machine_learning"] (The store's Enformer and Sei model records (regulatory-variant-20261009-model-enformer, regulatory-variant-20261009-model-sei) are supervised_machine_learning)
- Enformer, hidden states* (ipaQTL discrimination): facets.method_types: Facets: method types ["supervised_machine_learning"] (The store's Enformer and Sei model records (regulatory-variant-20261009-model-enformer, regulatory-variant-20261009-model-sei) are supervised_machine_learning)
- Enformer, hidden states* (paQTL discrimination): facets.method_types: Facets: method types ["supervised_machine_learning"] (The store's Enformer and Sei model records (regulatory-variant-20261009-model-enformer, regulatory-variant-20261009-model-sei) are supervised_machine_learning)
- Enformer, hidden states* (pathogenic/common SNP classification): facets.method_types: Facets: method types ["supervised_machine_learning"] (The store's Enformer and Sei model records (regulatory-variant-20261009-model-enformer, regulatory-variant-20261009-model-sei) are supervised_machine_learning)
- Enformer, hidden states* (sQTL discrimination): facets.method_types: Facets: method types ["supervised_machine_learning"] (The store's Enformer and Sei model records (regulatory-variant-20261009-model-enformer, regulatory-variant-20261009-model-sei) are supervised_machine_learning)
- Enformer, output tracks* (eQTL discrimination): facets.method_types: Facets: method types ["supervised_machine_learning"] (The store's Enformer and Sei model records (regulatory-variant-20261009-model-enformer, regulatory-variant-20261009-model-sei) are supervised_machine_learning)
- Enformer, output tracks* (ipaQTL discrimination): facets.method_types: Facets: method types ["supervised_machine_learning"] (The store's Enformer and Sei model records (regulatory-variant-20261009-model-enformer, regulatory-variant-20261009-model-sei) are supervised_machine_learning)
- Enformer, output tracks* (paQTL discrimination): facets.method_types: Facets: method types ["supervised_machine_learning"] (The store's Enformer and Sei model records (regulatory-variant-20261009-model-enformer, regulatory-variant-20261009-model-sei) are supervised_machine_learning)
- Enformer, output tracks* (pathogenic/common SNP classification): facets.method_types: Facets: method types ["supervised_machine_learning"] (The store's Enformer and Sei model records (regulatory-variant-20261009-model-enformer, regulatory-variant-20261009-model-sei) are supervised_machine_learning)
- Enformer, output tracks* (sQTL discrimination): facets.method_types: Facets: method types ["supervised_machine_learning"] (The store's Enformer and Sei model records (regulatory-variant-20261009-model-enformer, regulatory-variant-20261009-model-sei) are supervised_machine_learning)
- Evidence summary: Compare methods for plant promoter experiments: Summary AgroNT scored above the task-specific CNN in all six assay-by-species comparisons, but by 0.02 to 0.05 R-squared, with no uncertainty reported. On STARR-seq core-promoter strength, AgroNT reached R-squared 0.62 to 0.75 and the CNN from Jores et al. 0.57 to 0.73, across maize protoplasts and tobacco leaves for Arabidopsis thaliana, Sorghum bicolor and Zea mays sequences. In the earlier Jores study, which pools the three species, the CNN reached a squared Pearson correlation of 0.67 in maize protoplasts and 0.71 in tobacco leaves, against 0.45 and 0.51 for a GC and motif linear model. In an independent benchmark, five DNA foundation models separate Arabidopsis TATA and non-TATA promoter sequences from similar non-promoter sequences at AUC 0.937 to 0.961, but that is sequence classification, not reporter strength, and it uses a different dataset. The AgroNT and Jores values are reported by the authors of those studies, the six AgroNT comparisons all come from one figure of the AgroNT paper, and no value has a confidence interval or run variability. Nothing here covers stable transformed plants, tissue specificity or newly designed promoters. (agront-2024-fig3e-source: Figures/Fig3_panele.txt, R2 column, all six assay-by-species rows for AgroNT and the CNN; uc20260930-source-jores-2021: Figure 8b, maize-protoplasts and tobacco-leaves panels; evidence-expansion-dna-foundation-models-2025-5d8ca9bc: Table 2, Promoter Arabidopsis TATA and NonTATA rows)
- Relevance of Feng Acceptor sequence classification to "Prioritise variants for splicing experiments": Assessed by Feng Acceptor sequence classification (evidence-expansion-dna-foundation-models-2025-5d8ca9bc: See clinical/claims.csv and clinical/sources.md in data/omics/use-case-coverage-amp-20261007/)
- Relevance of Feng Donor sequence classification to "Prioritise variants for splicing experiments": Assessed by Feng Donor sequence classification (evidence-expansion-dna-foundation-models-2025-5d8ca9bc: See clinical/claims.csv and clinical/sources.md in data/omics/use-case-coverage-amp-20261007/)
- Relevance of Feng eQTL discrimination to "Select regulatory variants and genes for functional follow-up": Assessed by Feng eQTL discrimination (evidence-expansion-dna-foundation-models-2025-5d8ca9bc: See clinical/claims.csv and clinical/sources.md in data/omics/use-case-coverage-amp-20261007/)
- Relevance of Feng ipaQTL discrimination to "Select regulatory variants and genes for functional follow-up": Assessed by Feng ipaQTL discrimination (evidence-expansion-dna-foundation-models-2025-5d8ca9bc: See clinical/claims.csv and clinical/sources.md in data/omics/use-case-coverage-amp-20261007/)
- Relevance of Feng paQTL discrimination to "Select regulatory variants and genes for functional follow-up": Assessed by Feng paQTL discrimination (evidence-expansion-dna-foundation-models-2025-5d8ca9bc: See clinical/claims.csv and clinical/sources.md in data/omics/use-case-coverage-amp-20261007/)
- Relevance of Feng pathogenic-versus-common SNP classification to "Rank rare-disease variants for review": Assessed by Feng pathogenic-versus-common SNP classification (evidence-expansion-dna-foundation-models-2025-5d8ca9bc: See clinical/claims.csv and clinical/sources.md in data/omics/use-case-coverage-amp-20261007/)
- Relevance of Feng Promoter Arabidopsis NonTATA sequence classification to "Compare methods for plant promoter experiments": Assessed by Feng Promoter Arabidopsis NonTATA sequence classification (evidence-expansion-dna-foundation-models-2025-5d8ca9bc: See clinical/claims.csv and clinical/sources.md in data/omics/use-case-coverage-amp-20261007/)
- Relevance of Feng Promoter Arabidopsis TATA sequence classification to "Compare methods for plant promoter experiments": Assessed by Feng Promoter Arabidopsis TATA sequence classification (evidence-expansion-dna-foundation-models-2025-5d8ca9bc: See clinical/claims.csv and clinical/sources.md in data/omics/use-case-coverage-amp-20261007/)
- Relevance of Feng sQTL discrimination to "Select regulatory variants and genes for functional follow-up": Assessed by Feng sQTL discrimination (evidence-expansion-dna-foundation-models-2025-5d8ca9bc: See clinical/claims.csv and clinical/sources.md in data/omics/use-case-coverage-amp-20261007/)
- Relevance of feng-dna-fm-20261013-protocol-gtex-wb-expression-6kb to "Select regulatory variants and genes for functional follow-up": Assessed by Feng GTEx whole-blood expression prediction, all genes, 6 kb input (evidence-expansion-dna-foundation-models-2025-5d8ca9bc: Table 4)
Models, benchmarks and other records
Configurations (325)
- AlphaGenome, output tracks* (eQTL discrimination)
- AlphaGenome, output tracks* (ipaQTL discrimination)
- AlphaGenome, output tracks* (paQTL discrimination)
- AlphaGenome, output tracks* (sQTL discrimination)
- Caduceus-Ph (A.Thaliana 4mC classification)
- Caduceus-Ph (Acceptor classification)
- Caduceus-Ph (C.Elegans 4mC classification)
- Caduceus-Ph (Coding classification)
- Caduceus-Ph (D.Melanogaster 4mC classification)
- Caduceus-Ph (DNase I Hypersensitive classification)
- Caduceus-Ph (Donor classification)
- Caduceus-Ph (E.Coli 4mC classification)
- Caduceus-Ph (Enhancer classification)
- Caduceus-Ph (Enhancer Cohn classification)
- Caduceus-Ph (Enhancer Ensembl classification)
- Caduceus-Ph (eQTL discrimination)
- Caduceus-Ph (G.Pickeringii 4mC classification)
- Caduceus-Ph (G.Subterraneus 4mC classification)
- Caduceus-Ph (GTEx whole-blood expression prediction)
- Caduceus-Ph (Human 6 mA classification)
- Caduceus-Ph (Human TFBS 1 classification)
- Caduceus-Ph (Human TFBS 2 classification)
- Caduceus-Ph (Human TFBS 3 classification)
- Caduceus-Ph (Human TFBS 4 classification)
- Caduceus-Ph (Human TFBS 5 classification)
Tasks (1)
Protocols (60)
- Feng A.Thaliana 4mC sequence classification
- Feng Acceptor sequence classification
- Feng C.Elegans 4mC sequence classification
- Feng Coding sequence classification
- Feng D.Melanogaster 4mC sequence classification
- Feng DNase I Hypersensitive sequence classification
- Feng Donor sequence classification
- Feng E.Coli 4mC sequence classification
- Feng Enhancer Cohn sequence classification
- Feng Enhancer Ensembl sequence classification
- Feng Enhancer sequence classification
- Feng eQTL discrimination
- Feng G.Pickeringii 4mC sequence classification
- Feng G.Subterraneus 4mC sequence classification
- Feng GTEx whole-blood expression prediction, 768 genes, long input
- Feng GTEx whole-blood expression prediction, all genes, 6 kb input
- Feng Human 5mC sequence classification
- Feng Human 6 mA sequence classification
- Feng Human TFBS 1 sequence classification
- Feng Human TFBS 2 sequence classification
- Feng Human TFBS 3 sequence classification
- Feng Human TFBS 4 sequence classification
- Feng Human TFBS 5 sequence classification
- Feng Human vs worm sequence classification
- Feng ipaQTL discrimination
Datasets (64)
- Feng A.Thaliana 4mC dataset
- Feng Acceptor dataset
- Feng C.Elegans 4mC dataset
- Feng Coding dataset
- Feng D.Melanogaster 4mC dataset
- Feng DNase I Hypersensitive dataset
- Feng Donor dataset
- Feng E.Coli 4mC dataset
- Feng Enhancer Cohn dataset
- Feng Enhancer dataset
- Feng Enhancer Ensembl dataset
- Feng eQTL discrimination long-window dataset
- Feng eQTL discrimination short-window dataset
- Feng G.Pickeringii 4mC dataset
- Feng G.Subterraneus 4mC dataset
- Feng GTEx v8 whole-blood expression, TSS +/- 3 kb
- Feng GTEx v8 whole-blood expression, TSS +/- 98 kb, 768 genes
- Feng Human 6 mA dataset
- Feng Human TFBS 1 dataset
- Feng Human TFBS 2 dataset
- Feng Human TFBS 3 dataset
- Feng Human TFBS 4 dataset
- Feng Human TFBS 5 dataset
- Feng Human vs worm dataset
- Feng IMR90 TAD-centred and background sequences
Evaluations (384)
- AlphaGenome, output tracks eQTL per-test-group evaluation
- AlphaGenome, output tracks ipaQTL per-test-group evaluation
- AlphaGenome, output tracks paQTL per-test-group evaluation
- AlphaGenome, output tracks sQTL per-test-group evaluation
- AlphaGenome, output tracks* eQTL discrimination evaluation
- AlphaGenome, output tracks* ipaQTL discrimination evaluation
- AlphaGenome, output tracks* paQTL discrimination evaluation
- AlphaGenome, output tracks* sQTL discrimination evaluation
- Caduceus-Ph A.Thaliana 4mC evaluation
- Caduceus-Ph Acceptor evaluation
- Caduceus-Ph C.Elegans 4mC evaluation
- Caduceus-Ph Coding evaluation
- Caduceus-Ph D.Melanogaster 4mC evaluation
- Caduceus-Ph DNase I Hypersensitive evaluation
- Caduceus-Ph Donor evaluation
- Caduceus-Ph E.Coli 4mC evaluation
- Caduceus-Ph Enhancer Cohn evaluation
- Caduceus-Ph Enhancer Ensembl evaluation
- Caduceus-Ph Enhancer evaluation
- Caduceus-Ph eQTL discrimination evaluation
- Caduceus-Ph eQTL per-test-group evaluation
- Caduceus-Ph G.Pickeringii 4mC evaluation
- Caduceus-Ph G.Subterraneus 4mC evaluation
- Caduceus-Ph GTEx whole-blood expression evaluation
- Caduceus-Ph Human 6 mA evaluation
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.
15 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Artifact SHA-256 5d8ca9bcf88cc1b38ad667906a2e4699b1aefa6d31c6f49259784930353f3202 Source metadata | Benchmarking DNA foundation models for genomic and genetic tasks No field-specific location recorded Version: PMC12663285.1 | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| Artifact url https://www.ebi.ac.uk/europepmc/webservices/rest/PMC12663285/fullTextXML Source metadata | Benchmarking DNA foundation models for genomic and genetic tasks No field-specific location recorded Version: PMC12663285.1 | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| Hash scope Exact retrieved primary paper artifact bytes. Source metadata | Benchmarking DNA foundation models for genomic and genetic tasks No field-specific location recorded Version: PMC12663285.1 | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| Retrieved at 2026-09-17T07:54:51.004119+00:00 Source metadata | Benchmarking DNA foundation models for genomic and genetic tasks No field-specific location recorded Version: PMC12663285.1 | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
Review method1 values
| Benchmarking DNA foundation models for genomic and genetic tasks No field-specific location recorded Version: PMC12663285.1 | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| Review: scope Source identification and table transcription; no independent experimental reproduction. Source metadata | Benchmarking DNA foundation models for genomic and genetic tasks No field-specific location recorded Version: PMC12663285.1 | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| Url https://pmc.ncbi.nlm.nih.gov/articles/PMC12663285/ Source metadata | Benchmarking DNA foundation models for genomic and genetic tasks No field-specific location recorded Version: PMC12663285.1 | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| Version PMC12663285.1 Source metadata | Benchmarking DNA foundation models for genomic and genetic tasks No field-specific location recorded Version: PMC12663285.1 | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| Description Primary reference; inspect retrieval status and review scope. Source metadata | Benchmarking DNA foundation models for genomic and genetic tasks No field-specific location recorded Version: PMC12663285.1 | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| Search facets None recorded Source metadata | Benchmarking DNA foundation models for genomic and genetic tasks No field-specific location recorded Version: PMC12663285.1 | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
Sources and history
Release 2026-11-21-adc15377fab2 · Record review: source checked
Primary reference; inspect retrieval status and review scope.
Technical metadata and extraction receipts
Stable ID: evidence-expansion-dna-foundation-models-2025-5d8ca9bc
- url
- https://pmc.ncbi.nlm.nih.gov/articles/PMC12663285/
- version
- PMC12663285.1
- retrieved at
- 2026-09-17T07:54:51.004119+00:00
- artifact sha256
- 5d8ca9bcf88cc1b38ad667906a2e4699b1aefa6d31c6f49259784930353f3202
- artifact url
- https://www.ebi.ac.uk/europepmc/webservices/rest/PMC12663285/fullTextXML
- hash scope
- Exact retrieved primary paper artifact bytes.
- review
- scope: Source identification and table transcription; no independent experimental reproduction.; method: automated-source-review