Source

Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications

Nat Commun 17:223, published online 2025-12-07; PMC12780105 full-text XML · Peer-reviewed

What this source contributed

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

7 models
13 configurations
6 protocols
4 datasets
55 evaluations
154 results
1 evidence claim

Results

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

Value	Metric	Model or configuration	Dataset	Evaluation
0.9832(0.0011) fraction	Accuracy (NT-splice-sites-acceptors, fine-tuned)	DNABERT fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, acceptors	DNABERT on NT-splice-sites-acceptors
0.9832(0.0011) fraction	F1 (NT-splice-sites-acceptors, fine-tuned)	DNABERT fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, acceptors	DNABERT on NT-splice-sites-acceptors
0.9832(0.0011) fraction	Precision (NT-splice-sites-acceptors, fine-tuned)	DNABERT fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, acceptors	DNABERT on NT-splice-sites-acceptors
0.9832(0.0011) fraction	Recall (NT-splice-sites-acceptors, fine-tuned)	DNABERT fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, acceptors	DNABERT on NT-splice-sites-acceptors
0.9833(0.0004) fraction	Accuracy (NT-splice-sites-all, fine-tuned)	DNABERT fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, all sites	DNABERT on NT-splice-sites-all
0.9834(0.0004) fraction	F1 (NT-splice-sites-all, fine-tuned)	DNABERT fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, all sites	DNABERT on NT-splice-sites-all
0.9834(0.0003) fraction	Precision (NT-splice-sites-all, fine-tuned)	DNABERT fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, all sites	DNABERT on NT-splice-sites-all
0.9833(0.0004) fraction	Recall (NT-splice-sites-all, fine-tuned)	DNABERT fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, all sites	DNABERT on NT-splice-sites-all
0.9851(0.0007) fraction	Accuracy (NT-splice-sites-donors, fine-tuned)	DNABERT fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, donors	DNABERT on NT-splice-sites-donors
0.9851(0.0007) fraction	F1 (NT-splice-sites-donors, fine-tuned)	DNABERT fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, donors	DNABERT on NT-splice-sites-donors
0.9851(0.0007) fraction	Precision (NT-splice-sites-donors, fine-tuned)	DNABERT fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, donors	DNABERT on NT-splice-sites-donors
0.9851(0.0007) fraction	Recall (NT-splice-sites-donors, fine-tuned)	DNABERT fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, donors	DNABERT on NT-splice-sites-donors
0.9776(0.0005) fraction	Accuracy (NT-splice-sites-acceptors, fine-tuned)	DNABERT2 fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, acceptors	DNABERT2 on NT-splice-sites-acceptors
0.9776(0.0005) fraction	F1 (NT-splice-sites-acceptors, fine-tuned)	DNABERT2 fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, acceptors	DNABERT2 on NT-splice-sites-acceptors
0.9777(0.0005) fraction	Precision (NT-splice-sites-acceptors, fine-tuned)	DNABERT2 fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, acceptors	DNABERT2 on NT-splice-sites-acceptors
0.9776(0.0006) fraction	Recall (NT-splice-sites-acceptors, fine-tuned)	DNABERT2 fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, acceptors	DNABERT2 on NT-splice-sites-acceptors
0.9499(0.0037) fraction	Accuracy (NT-splice-sites-all, fine-tuned)	DNABERT2 fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, all sites	DNABERT2 on NT-splice-sites-all
0.9500(0.0036) fraction	F1 (NT-splice-sites-all, fine-tuned)	DNABERT2 fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, all sites	DNABERT2 on NT-splice-sites-all
0.9503(0.0034) fraction	Precision (NT-splice-sites-all, fine-tuned)	DNABERT2 fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, all sites	DNABERT2 on NT-splice-sites-all
0.9499(0.0037) fraction	Recall (NT-splice-sites-all, fine-tuned)	DNABERT2 fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, all sites	DNABERT2 on NT-splice-sites-all
0.9677(0.0029) fraction	Accuracy (NT-splice-sites-donors, fine-tuned)	DNABERT2 fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, donors	DNABERT2 on NT-splice-sites-donors
0.9677(0.0029) fraction	F1 (NT-splice-sites-donors, fine-tuned)	DNABERT2 fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, donors	DNABERT2 on NT-splice-sites-donors
0.9678(0.0028) fraction	Precision (NT-splice-sites-donors, fine-tuned)	DNABERT2 fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, donors	DNABERT2 on NT-splice-sites-donors
0.9677(0.0029) fraction	Recall (NT-splice-sites-donors, fine-tuned)	DNABERT2 fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, donors	DNABERT2 on NT-splice-sites-donors
0.9545(0.0028) fraction	Accuracy (NT-splice-sites-acceptors, fine-tuned)	GENA-LM-base fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, acceptors	GENA-LM-base on NT-splice-sites-acceptors
0.9544(0.0028) fraction	F1 (NT-splice-sites-acceptors, fine-tuned)	GENA-LM-base fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, acceptors	GENA-LM-base on NT-splice-sites-acceptors
0.9555(0.0023) fraction	Precision (NT-splice-sites-acceptors, fine-tuned)	GENA-LM-base fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, acceptors	GENA-LM-base on NT-splice-sites-acceptors
0.9543(0.0029) fraction	Recall (NT-splice-sites-acceptors, fine-tuned)	GENA-LM-base fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, acceptors	GENA-LM-base on NT-splice-sites-acceptors
0.9336(0.0021) fraction	Accuracy (NT-splice-sites-all, fine-tuned)	GENA-LM-base fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, all sites	GENA-LM-base on NT-splice-sites-all
0.9337(0.0023) fraction	F1 (NT-splice-sites-all, fine-tuned)	GENA-LM-base fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, all sites	GENA-LM-base on NT-splice-sites-all
0.9341(0.0026) fraction	Precision (NT-splice-sites-all, fine-tuned)	GENA-LM-base fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, all sites	GENA-LM-base on NT-splice-sites-all
0.9336(0.0021) fraction	Recall (NT-splice-sites-all, fine-tuned)	GENA-LM-base fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, all sites	GENA-LM-base on NT-splice-sites-all
0.9472(0.0016) fraction	Accuracy (NT-splice-sites-donors, fine-tuned)	GENA-LM-base fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, donors	GENA-LM-base on NT-splice-sites-donors
0.9472(0.0016) fraction	F1 (NT-splice-sites-donors, fine-tuned)	GENA-LM-base fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, donors	GENA-LM-base on NT-splice-sites-donors
0.9477(0.0012) fraction	Precision (NT-splice-sites-donors, fine-tuned)	GENA-LM-base fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, donors	GENA-LM-base on NT-splice-sites-donors
0.9472(0.0016) fraction	Recall (NT-splice-sites-donors, fine-tuned)	GENA-LM-base fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, donors	GENA-LM-base on NT-splice-sites-donors
0.9618(0.0011) fraction	Accuracy (NT-splice-sites-acceptors, fine-tuned)	GENA-LM-large fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, acceptors	GENA-LM-large on NT-splice-sites-acceptors
0.9618(0.0011) fraction	F1 (NT-splice-sites-acceptors, fine-tuned)	GENA-LM-large fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, acceptors	GENA-LM-large on NT-splice-sites-acceptors
0.9621(0.0011) fraction	Precision (NT-splice-sites-acceptors, fine-tuned)	GENA-LM-large fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, acceptors	GENA-LM-large on NT-splice-sites-acceptors
0.9618(0.0012) fraction	Recall (NT-splice-sites-acceptors, fine-tuned)	GENA-LM-large fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, acceptors	GENA-LM-large on NT-splice-sites-acceptors
0.9482(0.0032) fraction	Accuracy (NT-splice-sites-all, fine-tuned)	GENA-LM-large fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, all sites	GENA-LM-large on NT-splice-sites-all
0.9483(0.0030) fraction	F1 (NT-splice-sites-all, fine-tuned)	GENA-LM-large fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, all sites	GENA-LM-large on NT-splice-sites-all
0.9488(0.0025) fraction	Precision (NT-splice-sites-all, fine-tuned)	GENA-LM-large fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, all sites	GENA-LM-large on NT-splice-sites-all
0.9482(0.0032) fraction	Recall (NT-splice-sites-all, fine-tuned)	GENA-LM-large fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, all sites	GENA-LM-large on NT-splice-sites-all
0.9595(0.0005) fraction	Accuracy (NT-splice-sites-donors, fine-tuned)	GENA-LM-large fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, donors	GENA-LM-large on NT-splice-sites-donors
0.9595(0.0005) fraction	F1 (NT-splice-sites-donors, fine-tuned)	GENA-LM-large fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, donors	GENA-LM-large on NT-splice-sites-donors
0.9596(0.0005) fraction	Precision (NT-splice-sites-donors, fine-tuned)	GENA-LM-large fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, donors	GENA-LM-large on NT-splice-sites-donors
0.9595(0.0005) fraction	Recall (NT-splice-sites-donors, fine-tuned)	GENA-LM-large fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, donors	GENA-LM-large on NT-splice-sites-donors
0.9899(0.0014) fraction	Accuracy (NT-splice-sites-acceptors, fine-tuned)	NucleotideTransformer fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, acceptors	NucleotideTransformer on NT-splice-sites-acceptors
0.9899(0.0014) fraction	F1 (NT-splice-sites-acceptors, fine-tuned)	NucleotideTransformer fine-tuned with an appended convolutional layer (You et al. 2026)	Nucleotide Transformer benchmark splice-site dataset, acceptors	NucleotideTransformer on NT-splice-sites-acceptors

Claims

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

tables_not_extracted: gfm2-20261011-you2026-source-supplement: Tables not extracted Supplementary Tables 2 (non-coding RNA classification), 3 (m6A modification), 6 (translation efficiency) and the main-text figures are not extracted in this batch; only the splicing tables 4 and 5 are. (Supplementary Tables 2, 3 and 6)

Models, benchmarks and other records

Models (7)

Configurations (13)

Protocols (6)

Datasets (4)

Evaluations (55)

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.

25 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
attributes.artifact_sha256 2c6b2816846a21296c56b4dd58f3d1e8810e9d96e224d3ab21b5eb8faa9928e4 Source metadata	Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications Original source ↗ No field-specific location recorded Version: Nat Commun 17:223, published online 2025-12-07; PMC12780105 full-text XML Retrieved: 2026-10-11T00:55:34Z	catalogued No individual claim review recorded Audit details Field: `attributes.artifact_sha256` Source artifact SHA-256: `2c6b2816846a21296c56b4dd58f3d1e8810e9d96e224d3ab21b5eb8faa9928e4` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Artifact url https://www.ebi.ac.uk/europepmc/webservices/rest/PMC12780105/fullTextXML Source metadata	Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications Original source ↗ No field-specific location recorded Version: Nat Commun 17:223, published online 2025-12-07; PMC12780105 full-text XML Retrieved: 2026-10-11T00:55:34Z	catalogued No individual claim review recorded Audit details Field: `attributes.artifact_url` Source artifact SHA-256: `2c6b2816846a21296c56b4dd58f3d1e8810e9d96e224d3ab21b5eb8faa9928e4` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Doi 10.1038/s41467-025-66899-y Source metadata	Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications Original source ↗ No field-specific location recorded Version: Nat Commun 17:223, published online 2025-12-07; PMC12780105 full-text XML Retrieved: 2026-10-11T00:55:34Z	catalogued No individual claim review recorded Audit details Field: `attributes.doi` Source artifact SHA-256: `2c6b2816846a21296c56b4dd58f3d1e8810e9d96e224d3ab21b5eb8faa9928e4` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Licence CC-BY-NC-ND-4.0 Source metadata	Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications Original source ↗ No field-specific location recorded Version: Nat Commun 17:223, published online 2025-12-07; PMC12780105 full-text XML Retrieved: 2026-10-11T00:55:34Z	catalogued No individual claim review recorded Audit details Field: `attributes.licence` Source artifact SHA-256: `2c6b2816846a21296c56b4dd58f3d1e8810e9d96e224d3ab21b5eb8faa9928e4` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Media type application/xml Source metadata	Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications Original source ↗ No field-specific location recorded Version: Nat Commun 17:223, published online 2025-12-07; PMC12780105 full-text XML Retrieved: 2026-10-11T00:55:34Z	catalogued No individual claim review recorded Audit details Field: `attributes.media_type` Source artifact SHA-256: `2c6b2816846a21296c56b4dd58f3d1e8810e9d96e224d3ab21b5eb8faa9928e4` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Publication status peer_reviewed Source metadata	Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications Original source ↗ No field-specific location recorded Version: Nat Commun 17:223, published online 2025-12-07; PMC12780105 full-text XML Retrieved: 2026-10-11T00:55:34Z	catalogued No individual claim review recorded Audit details Field: `attributes.publication_status` Source artifact SHA-256: `2c6b2816846a21296c56b4dd58f3d1e8810e9d96e224d3ab21b5eb8faa9928e4` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Retrieved at 2026-10-11T00:55:34Z Source metadata	Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications Original source ↗ No field-specific location recorded Version: Nat Commun 17:223, published online 2025-12-07; PMC12780105 full-text XML Retrieved: 2026-10-11T00:55:34Z	catalogued No individual claim review recorded Audit details Field: `attributes.retrieved_at` Source artifact SHA-256: `2c6b2816846a21296c56b4dd58f3d1e8810e9d96e224d3ab21b5eb8faa9928e4` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
attributes.review.artifact_sha256 2c6b2816846a21296c56b4dd58f3d1e8810e9d96e224d3ab21b5eb8faa9928e4 Source metadata	Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications Original source ↗ No field-specific location recorded Version: Nat Commun 17:223, published online 2025-12-07; PMC12780105 full-text XML Retrieved: 2026-10-11T00:55:34Z	catalogued No individual claim review recorded Audit details Field: `attributes.review.artifact_sha256` Source artifact SHA-256: `2c6b2816846a21296c56b4dd58f3d1e8810e9d96e224d3ab21b5eb8faa9928e4` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Review: date 2026-10-11 Source metadata	Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications Original source ↗ No field-specific location recorded Version: Nat Commun 17:223, published online 2025-12-07; PMC12780105 full-text XML Retrieved: 2026-10-11T00:55:34Z	catalogued No individual claim review recorded Audit details Field: `attributes.review.date` Source artifact SHA-256: `2c6b2816846a21296c56b4dd58f3d1e8810e9d96e224d3ab21b5eb8faa9928e4` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Review method 2 values source-hash-verification ai-assisted-source-review Source metadata	Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications Original source ↗ No field-specific location recorded Version: Nat Commun 17:223, published online 2025-12-07; PMC12780105 full-text XML Retrieved: 2026-10-11T00:55:34Z	catalogued No individual claim review recorded Audit details Field: `attributes.review.method` Source artifact SHA-256: `2c6b2816846a21296c56b4dd58f3d1e8810e9d96e224d3ab21b5eb8faa9928e4` 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

Nature Communications article benchmarking eleven pre-trained genomic language models against task-specific methods on non-coding RNA classification, m6A modification, splice site prediction and translation efficiency.

Release history

No supporting source is linked yet.

Read original source

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: gfm2-20261011-you2026-source

areas: dna-genomes
contexts: research
url: https://doi.org/10.1038/s41467-025-66899-y
doi: 10.1038/s41467-025-66899-y
artifact url: https://www.ebi.ac.uk/europepmc/webservices/rest/PMC12780105/fullTextXML
artifact sha256: 2c6b2816846a21296c56b4dd58f3d1e8810e9d96e224d3ab21b5eb8faa9928e4
retrieved at: 2026-10-11T00:55:34Z
publication status: peer_reviewed
version: Nat Commun 17:223, published online 2025-12-07; PMC12780105 full-text XML
licence: CC-BY-NC-ND-4.0
media type: application/xml
source locator: Methods; Table 1; Supplementary Information
review: method: source-hash-verification; ai-assisted-source-review; reviewer: claude; reviewer note: Claude (Opus 5.5) review agent reviewer-gfm-a, independent of the extractor lit-gfm-2; no human review claimed; date: 2026-10-11; artifact sha256: 2c6b2816846a21296c56b4dd58f3d1e8810e9d96e224d3ab21b5eb8faa9928e4; retrieval url: https://www.ebi.ac.uk/europepmc/webservices/rest/PMC12780105/fullTextXML; note: Fresh retrieval matches the pinned SHA-256. CC BY-NC-ND 4.0; no copy archived.

Related records

Suggest a correction