Source

DNALONGBENCH: a benchmark suite for long-range DNA prediction tasks

Nature Communications 16, published 2025-11-18; PMC12627797 full-text XML · Peer-reviewed

What this source contributed

Records in this release that cite this source. A record can cite several sources.

3 models
13 configurations
1 benchmark
5 protocols
5 datasets
25 evaluations
135 results
1 evidence claim

Results

Values as the source printed them. Compare results only under compatible protocols, datasets and metrics.

Model or configuration	Metric	Value	Dataset	Evaluation
Caduceus-Ph (DNALONGBENCH)	Stratum adjusted correlation coefficient (average over CMP conditions as printed)	0.133 unitless	DNALONGBENCH Contact map prediction test set	Caduceus-Ph on DNALONGBENCH CMP
Caduceus-Ph (DNALONGBENCH)	Stratum adjusted correlation coefficient (GM12878)	0.101 unitless	DNALONGBENCH Contact map prediction test set	Caduceus-Ph on DNALONGBENCH CMP
Caduceus-Ph (DNALONGBENCH)	Stratum adjusted correlation coefficient (H1hESC)	0.130 unitless	DNALONGBENCH Contact map prediction test set	Caduceus-Ph on DNALONGBENCH CMP
Caduceus-Ph (DNALONGBENCH)	Stratum adjusted correlation coefficient (HCT116)	0.145 unitless	DNALONGBENCH Contact map prediction test set	Caduceus-Ph on DNALONGBENCH CMP
Caduceus-Ph (DNALONGBENCH)	Stratum adjusted correlation coefficient (HFF)	0.153 unitless	DNALONGBENCH Contact map prediction test set	Caduceus-Ph on DNALONGBENCH CMP
Caduceus-Ph (DNALONGBENCH)	Stratum adjusted correlation coefficient (IMR90)	0.138 unitless	DNALONGBENCH Contact map prediction test set	Caduceus-Ph on DNALONGBENCH CMP
Caduceus-Ph (DNALONGBENCH)	AUROC (AS (Adipose_Subcutaneous))	0.541 unitless	DNALONGBENCH Expression quantitative trait loci prediction test set	Caduceus-Ph on DNALONGBENCH eQTLP
Caduceus-Ph (DNALONGBENCH)	AUROC (AT (Artery_Tibial))	0.547 unitless	DNALONGBENCH Expression quantitative trait loci prediction test set	Caduceus-Ph on DNALONGBENCH eQTLP
Caduceus-Ph (DNALONGBENCH)	AUROC (average over eQTLP conditions as printed)	0.565 unitless	DNALONGBENCH Expression quantitative trait loci prediction test set	Caduceus-Ph on DNALONGBENCH eQTLP
Caduceus-Ph (DNALONGBENCH)	AUROC (CCF (Cells_Cultured_fibroblasts))	0.597 unitless	DNALONGBENCH Expression quantitative trait loci prediction test set	Caduceus-Ph on DNALONGBENCH eQTLP
Caduceus-Ph (DNALONGBENCH)	AUROC (MS (Muscle Skeletal))	0.538 unitless	DNALONGBENCH Expression quantitative trait loci prediction test set	Caduceus-Ph on DNALONGBENCH eQTLP
Caduceus-Ph (DNALONGBENCH)	AUROC (NT (Nerve Tibial))	0.588 unitless	DNALONGBENCH Expression quantitative trait loci prediction test set	Caduceus-Ph on DNALONGBENCH eQTLP
Caduceus-Ph (DNALONGBENCH)	AUROC (SNSES (Skin_Not_Sun_Exposed_Suprapubic))	0.586 unitless	DNALONGBENCH Expression quantitative trait loci prediction test set	Caduceus-Ph on DNALONGBENCH eQTLP
Caduceus-Ph (DNALONGBENCH)	AUROC (SSELL (Skin_Sun_Exposed_Lower_leg))	0.574 unitless	DNALONGBENCH Expression quantitative trait loci prediction test set	Caduceus-Ph on DNALONGBENCH eQTLP
Caduceus-Ph (DNALONGBENCH)	AUROC (Thyroid)	0.527 unitless	DNALONGBENCH Expression quantitative trait loci prediction test set	Caduceus-Ph on DNALONGBENCH eQTLP
Caduceus-Ph (DNALONGBENCH)	AUROC (WB (Whole_Blood))	0.594 unitless	DNALONGBENCH Expression quantitative trait loci prediction test set	Caduceus-Ph on DNALONGBENCH eQTLP
Caduceus-Ph (DNALONGBENCH)	AUPRC	0.380 unitless	DNALONGBENCH Enhancer-target gene prediction test set	Caduceus-Ph on DNALONGBENCH ETGP
Caduceus-Ph (DNALONGBENCH)	AUROC	0.826 unitless	DNALONGBENCH Enhancer-target gene prediction test set	Caduceus-Ph on DNALONGBENCH ETGP
Caduceus-Ph (DNALONGBENCH)	Pearson (average over RSAP conditions as printed)	0.349 unitless	DNALONGBENCH Regulatory sequence activity prediction test set	Caduceus-Ph on DNALONGBENCH RSAP
Caduceus-Ph (DNALONGBENCH)	Pearson (Human)	0.301 unitless	DNALONGBENCH Regulatory sequence activity prediction test set	Caduceus-Ph on DNALONGBENCH RSAP
Caduceus-Ph (DNALONGBENCH)	Pearson (Mouse)	0.400 unitless	DNALONGBENCH Regulatory sequence activity prediction test set	Caduceus-Ph on DNALONGBENCH RSAP
Caduceus-Ph (DNALONGBENCH)	Pearson (average over TISP conditions as printed)	0.109 unitless	DNALONGBENCH Transcription initiation signal prediction test set	Caduceus-Ph on DNALONGBENCH TISP
Caduceus-Ph (DNALONGBENCH)	Pearson (EC (ENCODE CAGE))	0.088 unitless	DNALONGBENCH Transcription initiation signal prediction test set	Caduceus-Ph on DNALONGBENCH TISP
Caduceus-Ph (DNALONGBENCH)	Pearson (ER (ENCODE RAMPAGE))	0.088 unitless	DNALONGBENCH Transcription initiation signal prediction test set	Caduceus-Ph on DNALONGBENCH TISP
Caduceus-Ph (DNALONGBENCH)	Pearson (FC (FANTOM CAGE))	0.114 unitless	DNALONGBENCH Transcription initiation signal prediction test set	Caduceus-Ph on DNALONGBENCH TISP
Caduceus-Ph (DNALONGBENCH)	Pearson (GC (GRO-cap))	0.097 unitless	DNALONGBENCH Transcription initiation signal prediction test set	Caduceus-Ph on DNALONGBENCH TISP
Caduceus-Ph (DNALONGBENCH)	Pearson (PC (PRO-cap))	0.154 unitless	DNALONGBENCH Transcription initiation signal prediction test set	Caduceus-Ph on DNALONGBENCH TISP
Caduceus-PS (DNALONGBENCH)	Stratum adjusted correlation coefficient (average over CMP conditions as printed)	0.127 unitless	DNALONGBENCH Contact map prediction test set	Caduceus-PS on DNALONGBENCH CMP
Caduceus-PS (DNALONGBENCH)	Stratum adjusted correlation coefficient (GM12878)	0.097 unitless	DNALONGBENCH Contact map prediction test set	Caduceus-PS on DNALONGBENCH CMP
Caduceus-PS (DNALONGBENCH)	Stratum adjusted correlation coefficient (H1hESC)	0.123 unitless	DNALONGBENCH Contact map prediction test set	Caduceus-PS on DNALONGBENCH CMP
Caduceus-PS (DNALONGBENCH)	Stratum adjusted correlation coefficient (HCT116)	0.139 unitless	DNALONGBENCH Contact map prediction test set	Caduceus-PS on DNALONGBENCH CMP
Caduceus-PS (DNALONGBENCH)	Stratum adjusted correlation coefficient (HFF)	0.142 unitless	DNALONGBENCH Contact map prediction test set	Caduceus-PS on DNALONGBENCH CMP
Caduceus-PS (DNALONGBENCH)	Stratum adjusted correlation coefficient (IMR90)	0.132 unitless	DNALONGBENCH Contact map prediction test set	Caduceus-PS on DNALONGBENCH CMP
Caduceus-PS (DNALONGBENCH)	AUROC (AS (Adipose_Subcutaneous))	0.519 unitless	DNALONGBENCH Expression quantitative trait loci prediction test set	Caduceus-PS on DNALONGBENCH eQTLP
Caduceus-PS (DNALONGBENCH)	AUROC (AT (Artery_Tibial))	0.536 unitless	DNALONGBENCH Expression quantitative trait loci prediction test set	Caduceus-PS on DNALONGBENCH eQTLP
Caduceus-PS (DNALONGBENCH)	AUROC (average over eQTLP conditions as printed)	0.537 unitless	DNALONGBENCH Expression quantitative trait loci prediction test set	Caduceus-PS on DNALONGBENCH eQTLP
Caduceus-PS (DNALONGBENCH)	AUROC (CCF (Cells_Cultured_fibroblasts))	0.549 unitless	DNALONGBENCH Expression quantitative trait loci prediction test set	Caduceus-PS on DNALONGBENCH eQTLP
Caduceus-PS (DNALONGBENCH)	AUROC (MS (Muscle Skeletal))	0.523 unitless	DNALONGBENCH Expression quantitative trait loci prediction test set	Caduceus-PS on DNALONGBENCH eQTLP
Caduceus-PS (DNALONGBENCH)	AUROC (NT (Nerve Tibial))	0.552 unitless	DNALONGBENCH Expression quantitative trait loci prediction test set	Caduceus-PS on DNALONGBENCH eQTLP
Caduceus-PS (DNALONGBENCH)	AUROC (SNSES (Skin_Not_Sun_Exposed_Suprapubic))	0.529 unitless	DNALONGBENCH Expression quantitative trait loci prediction test set	Caduceus-PS on DNALONGBENCH eQTLP
Caduceus-PS (DNALONGBENCH)	AUROC (SSELL (Skin_Sun_Exposed_Lower_leg))	0.541 unitless	DNALONGBENCH Expression quantitative trait loci prediction test set	Caduceus-PS on DNALONGBENCH eQTLP
Caduceus-PS (DNALONGBENCH)	AUROC (Thyroid)	0.547 unitless	DNALONGBENCH Expression quantitative trait loci prediction test set	Caduceus-PS on DNALONGBENCH eQTLP
Caduceus-PS (DNALONGBENCH)	AUROC (WB (Whole_Blood))	0.542 unitless	DNALONGBENCH Expression quantitative trait loci prediction test set	Caduceus-PS on DNALONGBENCH eQTLP
Caduceus-PS (DNALONGBENCH)	AUPRC	0.376 unitless	DNALONGBENCH Enhancer-target gene prediction test set	Caduceus-PS on DNALONGBENCH ETGP
Caduceus-PS (DNALONGBENCH)	AUROC	0.821 unitless	DNALONGBENCH Enhancer-target gene prediction test set	Caduceus-PS on DNALONGBENCH ETGP
Caduceus-PS (DNALONGBENCH)	Pearson (average over RSAP conditions as printed)	0.344 unitless	DNALONGBENCH Regulatory sequence activity prediction test set	Caduceus-PS on DNALONGBENCH RSAP
Caduceus-PS (DNALONGBENCH)	Pearson (Human)	0.301 unitless	DNALONGBENCH Regulatory sequence activity prediction test set	Caduceus-PS on DNALONGBENCH RSAP
Caduceus-PS (DNALONGBENCH)	Pearson (Mouse)	0.387 unitless	DNALONGBENCH Regulatory sequence activity prediction test set	Caduceus-PS on DNALONGBENCH RSAP
Caduceus-PS (DNALONGBENCH)	Pearson (average over TISP conditions as printed)	0.108 unitless	DNALONGBENCH Transcription initiation signal prediction test set	Caduceus-PS on DNALONGBENCH TISP
Caduceus-PS (DNALONGBENCH)	Pearson (EC (ENCODE CAGE))	0.088 unitless	DNALONGBENCH Transcription initiation signal prediction test set	Caduceus-PS on DNALONGBENCH TISP

Claims

Statements this source supports, each with where in the source it was checked.

ABC (DNALONGBENCH): facets.method_types: Facets: method types ["conventional_pipeline"] (DNALongBench Results: the expert model is ABC, "which incorporates DNase-seq, H3K27ac ChIP-seq data, and a Hi-C matrix"; MPRAbc Introduction: ABC is "a mathematical framework" combining activity and contact)

Models, benchmarks and other records

Models (3)

Configurations (13)

Benchmarks (1)

DNALONGBENCH

Protocols (5)

Datasets (5)

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.

23 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-23-5347695500ed
Property and statement	Original source and location	Review and provenance
Artifact SHA-256 0d7db21f2a843dda3ba703c53cd0abad12c9c795cfbcf4fd1bdc6c4a863fe41b Source metadata	DNALONGBENCH: a benchmark suite for long-range DNA prediction tasks Original source ↗ No field-specific location recorded Version: Nature Communications 16, published 2025-11-18; PMC12627797 full-text XML Retrieved: 2026-10-11T01:34:19Z	catalogued No individual claim review recorded Audit details Field: `attributes.artifact_sha256` Source artifact SHA-256: `0d7db21f2a843dda3ba703c53cd0abad12c9c795cfbcf4fd1bdc6c4a863fe41b` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Artifact url https://www.ebi.ac.uk/europepmc/webservices/rest/PMC12627797/fullTextXML Source metadata	DNALONGBENCH: a benchmark suite for long-range DNA prediction tasks Original source ↗ No field-specific location recorded Version: Nature Communications 16, published 2025-11-18; PMC12627797 full-text XML Retrieved: 2026-10-11T01:34:19Z	catalogued No individual claim review recorded Audit details Field: `attributes.artifact_url` Source artifact SHA-256: `0d7db21f2a843dda3ba703c53cd0abad12c9c795cfbcf4fd1bdc6c4a863fe41b` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Doi 10.1038/s41467-025-65077-4 Source metadata	DNALONGBENCH: a benchmark suite for long-range DNA prediction tasks Original source ↗ No field-specific location recorded Version: Nature Communications 16, published 2025-11-18; PMC12627797 full-text XML Retrieved: 2026-10-11T01:34:19Z	catalogued No individual claim review recorded Audit details Field: `attributes.doi` Source artifact SHA-256: `0d7db21f2a843dda3ba703c53cd0abad12c9c795cfbcf4fd1bdc6c4a863fe41b` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Licence CC-BY-NC-ND-4.0 Source metadata	DNALONGBENCH: a benchmark suite for long-range DNA prediction tasks Original source ↗ No field-specific location recorded Version: Nature Communications 16, published 2025-11-18; PMC12627797 full-text XML Retrieved: 2026-10-11T01:34:19Z	catalogued No individual claim review recorded Audit details Field: `attributes.licence` Source artifact SHA-256: `0d7db21f2a843dda3ba703c53cd0abad12c9c795cfbcf4fd1bdc6c4a863fe41b` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Limitations 2 values Journal version of the bioRxiv preprint already in the store as dnalongbench-2025 (2 results from Table 3). The two overlapping cells (HyenaDNA and Caduceus-Ph ETGP AUROC) agree with this version. Supplementary Information (Table S1 and per-task details) was not read. Source metadata	DNALONGBENCH: a benchmark suite for long-range DNA prediction tasks Original source ↗ No field-specific location recorded Version: Nature Communications 16, published 2025-11-18; PMC12627797 full-text XML Retrieved: 2026-10-11T01:34:19Z	catalogued No individual claim review recorded Audit details Field: `attributes.limitations` Source artifact SHA-256: `0d7db21f2a843dda3ba703c53cd0abad12c9c795cfbcf4fd1bdc6c4a863fe41b` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Media type application/xml Source metadata	DNALONGBENCH: a benchmark suite for long-range DNA prediction tasks Original source ↗ No field-specific location recorded Version: Nature Communications 16, published 2025-11-18; PMC12627797 full-text XML Retrieved: 2026-10-11T01:34:19Z	catalogued No individual claim review recorded Audit details Field: `attributes.media_type` Source artifact SHA-256: `0d7db21f2a843dda3ba703c53cd0abad12c9c795cfbcf4fd1bdc6c4a863fe41b` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Publication status peer_reviewed Source metadata	DNALONGBENCH: a benchmark suite for long-range DNA prediction tasks Original source ↗ No field-specific location recorded Version: Nature Communications 16, published 2025-11-18; PMC12627797 full-text XML Retrieved: 2026-10-11T01:34:19Z	catalogued No individual claim review recorded Audit details Field: `attributes.publication_status` Source artifact SHA-256: `0d7db21f2a843dda3ba703c53cd0abad12c9c795cfbcf4fd1bdc6c4a863fe41b` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Retrieved at 2026-10-11T01:34:19Z Source metadata	DNALONGBENCH: a benchmark suite for long-range DNA prediction tasks Original source ↗ No field-specific location recorded Version: Nature Communications 16, published 2025-11-18; PMC12627797 full-text XML Retrieved: 2026-10-11T01:34:19Z	catalogued No individual claim review recorded Audit details Field: `attributes.retrieved_at` Source artifact SHA-256: `0d7db21f2a843dda3ba703c53cd0abad12c9c795cfbcf4fd1bdc6c4a863fe41b` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Review: date 2026-10-11 Source metadata	DNALONGBENCH: a benchmark suite for long-range DNA prediction tasks Original source ↗ No field-specific location recorded Version: Nature Communications 16, published 2025-11-18; PMC12627797 full-text XML Retrieved: 2026-10-11T01:34:19Z	catalogued No individual claim review recorded Audit details Field: `attributes.review.date` Source artifact SHA-256: `0d7db21f2a843dda3ba703c53cd0abad12c9c795cfbcf4fd1bdc6c4a863fe41b` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Review: method note Artifact re-retrieved or unpacked and SHA-256 matched. Source metadata	DNALONGBENCH: a benchmark suite for long-range DNA prediction tasks Original source ↗ No field-specific location recorded Version: Nature Communications 16, published 2025-11-18; PMC12627797 full-text XML Retrieved: 2026-10-11T01:34:19Z	catalogued No individual claim review recorded Audit details Field: `attributes.review.method_note` Source artifact SHA-256: `0d7db21f2a843dda3ba703c53cd0abad12c9c795cfbcf4fd1bdc6c4a863fe41b` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact

How to read the evidence

Sources and history

Release 2026-10-23-5347695500ed · Record review: source checked

Primary source retrieved and hashed for the 2026-10-11 genomics literature pass.

Release history

No supporting source is linked yet.

Read original source

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: lit-genomics-20261011-dnalongbench-source-cheng2025

areas: dna-genomes
contexts: research
url: https://doi.org/10.1038/s41467-025-65077-4
artifact url: https://www.ebi.ac.uk/europepmc/webservices/rest/PMC12627797/fullTextXML
version: Nature Communications 16, published 2025-11-18; PMC12627797 full-text XML
retrieved at: 2026-10-11T01:34:19Z
artifact sha256: 0d7db21f2a843dda3ba703c53cd0abad12c9c795cfbcf4fd1bdc6c4a863fe41b
doi: 10.1038/s41467-025-65077-4
publication status: peer_reviewed
licence: CC-BY-NC-ND-4.0
media type: application/xml
limitations: Journal version of the bioRxiv preprint already in the store as dnalongbench-2025 (2 results from Table 3). The two overlapping cells (HyenaDNA and Caduceus-Ph ETGP AUROC) agree with this version.; Supplementary Information (Table S1 and per-task details) was not read.
review: method: source-hash-verification; method note: Artifact re-retrieved or unpacked and SHA-256 matched.; reviewer: claude; reviewer note: Claude review agent reviewer-gen-3, independent of the extractor lit-genomics; no human review claimed; date: 2026-10-11

Related records

Suggest a correction