Protocol

NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4)

Classification of splice sites on the Nucleotide Transformer benchmark dataset, with every method given the same train/test split.

11 evaluations · 44 results

Overview

An explanatory profile has not yet been reviewed for this record.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

11 recorded evaluations, 44 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.

View coverage and remaining gaps across all benchmarks

Results

Results are available, but no reviewed comparison panel is linked in this release.

All evaluations

11 evaluations · 44 results. Different protocols are not a single leaderboard.

Protocol: NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4) · Dataset: Nucleotide Transformer benchmark splice-site dataset, donors

Sorted by Accuracy (NT-splice-sites-donors, fine-tuned) (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.

Tested configuration	Accuracy (NT-splice-sites-donors, fine-tuned)	F1 (NT-splice-sites-donors, fine-tuned)	Precision (NT-splice-sites-donors, fine-tuned)	Recall (NT-splice-sites-donors, fine-tuned)
SpliceBERT fine-tuned with an appended convolutional layer (You et al. 2026)Evaluation	0.9915(0.0010) (best in column)	0.9915(0.0010) (best in column)	0.9915(0.0009) (best in column)	0.9915(0.0010) (best in column)
NucleotideTransformer fine-tuned with an appended convolutional layer (You et al. 2026)Evaluation	0.9913(0.0008)	0.9913(0.0008)	0.9914(0.0008)	0.9913(0.0008)
DNABERT fine-tuned with an appended convolutional layer (You et al. 2026)Evaluation	0.9851(0.0007)	0.9851(0.0007)	0.9851(0.0007)	0.9851(0.0007)
RNAFM fine-tuned with an appended convolutional layer (You et al. 2026)Evaluation	0.9841(0.0018)	0.9841(0.0018)	0.9842(0.0017)	0.9841(0.0019)
RNAErnie fine-tuned with an appended convolutional layer (You et al. 2026)Evaluation	0.9832(0.0020)	0.9832(0.0020)	0.9832(0.0020)	0.9832(0.0020)
UTRLM fine-tuned with an appended convolutional layer (You et al. 2026)Evaluation	0.9741(0.0000)	0.9741(0.0000)	0.9741(0.0000)	0.9741(0.0000)
RNAMSM fine-tuned with an appended convolutional layer (You et al. 2026)Evaluation	0.9735(0.0005)	0.9735(0.0005)	0.9735(0.0005)	0.9735(0.0005)
DNABERT2 fine-tuned with an appended convolutional layer (You et al. 2026)Evaluation	0.9677(0.0029)	0.9677(0.0029)	0.9678(0.0028)	0.9677(0.0029)
RNABERT fine-tuned with an appended convolutional layer (You et al. 2026)Evaluation	0.9673(0.0008)	0.9673(0.0008)	0.9673(0.0008)	0.9673(0.0008)
GENA-LM-large fine-tuned with an appended convolutional layer (You et al. 2026)Evaluation	0.9595(0.0005)	0.9595(0.0005)	0.9596(0.0005)	0.9595(0.0005)
GENA-LM-base fine-tuned with an appended convolutional layer (You et al. 2026)Evaluation	0.9472(0.0016)	0.9472(0.0016)	0.9477(0.0012)	0.9472(0.0016)

All 44 result rows with coverage, uncertainty and sources

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: DNABERT fine-tuned with an appended convolutional layer (You et al. 2026)	Protocol: NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4) Dataset: Nucleotide Transformer benchmark splice-site dataset, donors	0.9851(0.0007) Accuracy (NT-splice-sites-donors, fine-tuned) fraction · higher Uncertainty: SD 0.0007 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DNABERT on NT-splice-sites-donors gfm2-20261011-you2026-protocol-nt-splice-donors Aggregation: Not reported Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary Information · Supplementary Table 4, block 'NT-splice-sites-donors', row 'DNABERT', column 'Accuracy'
Configuration: DNABERT fine-tuned with an appended convolutional layer (You et al. 2026)	Protocol: NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4) Dataset: Nucleotide Transformer benchmark splice-site dataset, donors	0.9851(0.0007) F1 (NT-splice-sites-donors, fine-tuned) fraction · higher Uncertainty: SD 0.0007 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DNABERT on NT-splice-sites-donors gfm2-20261011-you2026-protocol-nt-splice-donors Aggregation: Not reported Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary Information · Supplementary Table 4, block 'NT-splice-sites-donors', row 'DNABERT', column 'F1 Score'
Configuration: DNABERT fine-tuned with an appended convolutional layer (You et al. 2026)	Protocol: NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4) Dataset: Nucleotide Transformer benchmark splice-site dataset, donors	0.9851(0.0007) Precision (NT-splice-sites-donors, fine-tuned) fraction · higher Uncertainty: SD 0.0007 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DNABERT on NT-splice-sites-donors gfm2-20261011-you2026-protocol-nt-splice-donors Aggregation: Not reported Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary Information · Supplementary Table 4, block 'NT-splice-sites-donors', row 'DNABERT', column 'Precision'
Configuration: DNABERT fine-tuned with an appended convolutional layer (You et al. 2026)	Protocol: NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4) Dataset: Nucleotide Transformer benchmark splice-site dataset, donors	0.9851(0.0007) Recall (NT-splice-sites-donors, fine-tuned) fraction · higher Uncertainty: SD 0.0007 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DNABERT on NT-splice-sites-donors gfm2-20261011-you2026-protocol-nt-splice-donors Aggregation: Not reported Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary Information · Supplementary Table 4, block 'NT-splice-sites-donors', row 'DNABERT', column 'Recall'
Configuration: DNABERT2 fine-tuned with an appended convolutional layer (You et al. 2026)	Protocol: NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4) Dataset: Nucleotide Transformer benchmark splice-site dataset, donors	0.9677(0.0029) Accuracy (NT-splice-sites-donors, fine-tuned) fraction · higher Uncertainty: SD 0.0029 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DNABERT2 on NT-splice-sites-donors gfm2-20261011-you2026-protocol-nt-splice-donors Aggregation: Not reported Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary Information · Supplementary Table 4, block 'NT-splice-sites-donors', row 'DNABERT2', column 'Accuracy'
Configuration: DNABERT2 fine-tuned with an appended convolutional layer (You et al. 2026)	Protocol: NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4) Dataset: Nucleotide Transformer benchmark splice-site dataset, donors	0.9677(0.0029) F1 (NT-splice-sites-donors, fine-tuned) fraction · higher Uncertainty: SD 0.0029 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DNABERT2 on NT-splice-sites-donors gfm2-20261011-you2026-protocol-nt-splice-donors Aggregation: Not reported Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary Information · Supplementary Table 4, block 'NT-splice-sites-donors', row 'DNABERT2', column 'F1 Score'
Configuration: DNABERT2 fine-tuned with an appended convolutional layer (You et al. 2026)	Protocol: NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4) Dataset: Nucleotide Transformer benchmark splice-site dataset, donors	0.9678(0.0028) Precision (NT-splice-sites-donors, fine-tuned) fraction · higher Uncertainty: SD 0.0028 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DNABERT2 on NT-splice-sites-donors gfm2-20261011-you2026-protocol-nt-splice-donors Aggregation: Not reported Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary Information · Supplementary Table 4, block 'NT-splice-sites-donors', row 'DNABERT2', column 'Precision'
Configuration: DNABERT2 fine-tuned with an appended convolutional layer (You et al. 2026)	Protocol: NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4) Dataset: Nucleotide Transformer benchmark splice-site dataset, donors	0.9677(0.0029) Recall (NT-splice-sites-donors, fine-tuned) fraction · higher Uncertainty: SD 0.0029 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DNABERT2 on NT-splice-sites-donors gfm2-20261011-you2026-protocol-nt-splice-donors Aggregation: Not reported Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary Information · Supplementary Table 4, block 'NT-splice-sites-donors', row 'DNABERT2', column 'Recall'
Configuration: GENA-LM-base fine-tuned with an appended convolutional layer (You et al. 2026)	Protocol: NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4) Dataset: Nucleotide Transformer benchmark splice-site dataset, donors	0.9472(0.0016) Accuracy (NT-splice-sites-donors, fine-tuned) fraction · higher Uncertainty: SD 0.0016 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source GENA-LM-base on NT-splice-sites-donors gfm2-20261011-you2026-protocol-nt-splice-donors Aggregation: Not reported Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary Information · Supplementary Table 4, block 'NT-splice-sites-donors', row 'GENA-LM-base', column 'Accuracy'
Configuration: GENA-LM-base fine-tuned with an appended convolutional layer (You et al. 2026)	Protocol: NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4) Dataset: Nucleotide Transformer benchmark splice-site dataset, donors	0.9472(0.0016) F1 (NT-splice-sites-donors, fine-tuned) fraction · higher Uncertainty: SD 0.0016 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source GENA-LM-base on NT-splice-sites-donors gfm2-20261011-you2026-protocol-nt-splice-donors Aggregation: Not reported Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary Information · Supplementary Table 4, block 'NT-splice-sites-donors', row 'GENA-LM-base', column 'F1 Score'
Configuration: GENA-LM-base fine-tuned with an appended convolutional layer (You et al. 2026)	Protocol: NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4) Dataset: Nucleotide Transformer benchmark splice-site dataset, donors	0.9477(0.0012) Precision (NT-splice-sites-donors, fine-tuned) fraction · higher Uncertainty: SD 0.0012 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source GENA-LM-base on NT-splice-sites-donors gfm2-20261011-you2026-protocol-nt-splice-donors Aggregation: Not reported Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary Information · Supplementary Table 4, block 'NT-splice-sites-donors', row 'GENA-LM-base', column 'Precision'
Configuration: GENA-LM-base fine-tuned with an appended convolutional layer (You et al. 2026)	Protocol: NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4) Dataset: Nucleotide Transformer benchmark splice-site dataset, donors	0.9472(0.0016) Recall (NT-splice-sites-donors, fine-tuned) fraction · higher Uncertainty: SD 0.0016 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source GENA-LM-base on NT-splice-sites-donors gfm2-20261011-you2026-protocol-nt-splice-donors Aggregation: Not reported Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary Information · Supplementary Table 4, block 'NT-splice-sites-donors', row 'GENA-LM-base', column 'Recall'
Configuration: GENA-LM-large fine-tuned with an appended convolutional layer (You et al. 2026)	Protocol: NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4) Dataset: Nucleotide Transformer benchmark splice-site dataset, donors	0.9595(0.0005) Accuracy (NT-splice-sites-donors, fine-tuned) fraction · higher Uncertainty: SD 0.0005 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source GENA-LM-large on NT-splice-sites-donors gfm2-20261011-you2026-protocol-nt-splice-donors Aggregation: Not reported Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary Information · Supplementary Table 4, block 'NT-splice-sites-donors', row 'GENA-LM-large', column 'Accuracy'
Configuration: GENA-LM-large fine-tuned with an appended convolutional layer (You et al. 2026)	Protocol: NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4) Dataset: Nucleotide Transformer benchmark splice-site dataset, donors	0.9595(0.0005) F1 (NT-splice-sites-donors, fine-tuned) fraction · higher Uncertainty: SD 0.0005 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source GENA-LM-large on NT-splice-sites-donors gfm2-20261011-you2026-protocol-nt-splice-donors Aggregation: Not reported Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary Information · Supplementary Table 4, block 'NT-splice-sites-donors', row 'GENA-LM-large', column 'F1 Score'
Configuration: GENA-LM-large fine-tuned with an appended convolutional layer (You et al. 2026)	Protocol: NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4) Dataset: Nucleotide Transformer benchmark splice-site dataset, donors	0.9596(0.0005) Precision (NT-splice-sites-donors, fine-tuned) fraction · higher Uncertainty: SD 0.0005 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source GENA-LM-large on NT-splice-sites-donors gfm2-20261011-you2026-protocol-nt-splice-donors Aggregation: Not reported Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary Information · Supplementary Table 4, block 'NT-splice-sites-donors', row 'GENA-LM-large', column 'Precision'
Configuration: GENA-LM-large fine-tuned with an appended convolutional layer (You et al. 2026)	Protocol: NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4) Dataset: Nucleotide Transformer benchmark splice-site dataset, donors	0.9595(0.0005) Recall (NT-splice-sites-donors, fine-tuned) fraction · higher Uncertainty: SD 0.0005 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source GENA-LM-large on NT-splice-sites-donors gfm2-20261011-you2026-protocol-nt-splice-donors Aggregation: Not reported Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary Information · Supplementary Table 4, block 'NT-splice-sites-donors', row 'GENA-LM-large', column 'Recall'
Configuration: NucleotideTransformer fine-tuned with an appended convolutional layer (You et al. 2026)	Protocol: NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4) Dataset: Nucleotide Transformer benchmark splice-site dataset, donors	0.9913(0.0008) Accuracy (NT-splice-sites-donors, fine-tuned) fraction · higher Uncertainty: SD 0.0008 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NucleotideTransformer on NT-splice-sites-donors gfm2-20261011-you2026-protocol-nt-splice-donors Aggregation: Not reported Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary Information · Supplementary Table 4, block 'NT-splice-sites-donors', row 'NucleotideTransformer', column 'Accuracy'
Configuration: NucleotideTransformer fine-tuned with an appended convolutional layer (You et al. 2026)	Protocol: NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4) Dataset: Nucleotide Transformer benchmark splice-site dataset, donors	0.9913(0.0008) F1 (NT-splice-sites-donors, fine-tuned) fraction · higher Uncertainty: SD 0.0008 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NucleotideTransformer on NT-splice-sites-donors gfm2-20261011-you2026-protocol-nt-splice-donors Aggregation: Not reported Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary Information · Supplementary Table 4, block 'NT-splice-sites-donors', row 'NucleotideTransformer', column 'F1 Score'
Configuration: NucleotideTransformer fine-tuned with an appended convolutional layer (You et al. 2026)	Protocol: NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4) Dataset: Nucleotide Transformer benchmark splice-site dataset, donors	0.9914(0.0008) Precision (NT-splice-sites-donors, fine-tuned) fraction · higher Uncertainty: SD 0.0008 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NucleotideTransformer on NT-splice-sites-donors gfm2-20261011-you2026-protocol-nt-splice-donors Aggregation: Not reported Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary Information · Supplementary Table 4, block 'NT-splice-sites-donors', row 'NucleotideTransformer', column 'Precision'
Configuration: NucleotideTransformer fine-tuned with an appended convolutional layer (You et al. 2026)	Protocol: NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4) Dataset: Nucleotide Transformer benchmark splice-site dataset, donors	0.9913(0.0008) Recall (NT-splice-sites-donors, fine-tuned) fraction · higher Uncertainty: SD 0.0008 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NucleotideTransformer on NT-splice-sites-donors gfm2-20261011-you2026-protocol-nt-splice-donors Aggregation: Not reported Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary Information · Supplementary Table 4, block 'NT-splice-sites-donors', row 'NucleotideTransformer', column 'Recall'
Configuration: RNABERT fine-tuned with an appended convolutional layer (You et al. 2026)	Protocol: NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4) Dataset: Nucleotide Transformer benchmark splice-site dataset, donors	0.9673(0.0008) Accuracy (NT-splice-sites-donors, fine-tuned) fraction · higher Uncertainty: SD 0.0008 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source RNABERT on NT-splice-sites-donors gfm2-20261011-you2026-protocol-nt-splice-donors Aggregation: Not reported Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary Information · Supplementary Table 4, block 'NT-splice-sites-donors', row 'RNABERT', column 'Accuracy'
Configuration: RNABERT fine-tuned with an appended convolutional layer (You et al. 2026)	Protocol: NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4) Dataset: Nucleotide Transformer benchmark splice-site dataset, donors	0.9673(0.0008) F1 (NT-splice-sites-donors, fine-tuned) fraction · higher Uncertainty: SD 0.0008 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source RNABERT on NT-splice-sites-donors gfm2-20261011-you2026-protocol-nt-splice-donors Aggregation: Not reported Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary Information · Supplementary Table 4, block 'NT-splice-sites-donors', row 'RNABERT', column 'F1 Score'
Configuration: RNABERT fine-tuned with an appended convolutional layer (You et al. 2026)	Protocol: NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4) Dataset: Nucleotide Transformer benchmark splice-site dataset, donors	0.9673(0.0008) Precision (NT-splice-sites-donors, fine-tuned) fraction · higher Uncertainty: SD 0.0008 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source RNABERT on NT-splice-sites-donors gfm2-20261011-you2026-protocol-nt-splice-donors Aggregation: Not reported Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary Information · Supplementary Table 4, block 'NT-splice-sites-donors', row 'RNABERT', column 'Precision'
Configuration: RNABERT fine-tuned with an appended convolutional layer (You et al. 2026)	Protocol: NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4) Dataset: Nucleotide Transformer benchmark splice-site dataset, donors	0.9673(0.0008) Recall (NT-splice-sites-donors, fine-tuned) fraction · higher Uncertainty: SD 0.0008 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source RNABERT on NT-splice-sites-donors gfm2-20261011-you2026-protocol-nt-splice-donors Aggregation: Not reported Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary Information · Supplementary Table 4, block 'NT-splice-sites-donors', row 'RNABERT', column 'Recall'
Configuration: RNAErnie fine-tuned with an appended convolutional layer (You et al. 2026)	Protocol: NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4) Dataset: Nucleotide Transformer benchmark splice-site dataset, donors	0.9832(0.0020) Accuracy (NT-splice-sites-donors, fine-tuned) fraction · higher Uncertainty: SD 0.0020 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source RNAErnie on NT-splice-sites-donors gfm2-20261011-you2026-protocol-nt-splice-donors Aggregation: Not reported Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary Information · Supplementary Table 4, block 'NT-splice-sites-donors', row 'RNAErnie', column 'Accuracy'

Source checking is not independent reproduction. Release 2026-10-22-1b7cf027e4f6.

Methods and evaluation design

Procedure, tasks and evaluated configurations

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Baseline coverage

Reference methods help show what a model adds beyond simple controls. We track a null control and a conventional method for each protocol.

0 of 2 active baseline roles have published Rewire measurements in this release. Measurements on a selected protocol do not establish coverage of an entire suite.

No execution recipe linked to this protocol. Recipe availability does not establish a completed evaluation.

External evaluations: 11

Literature evidence is not a Rewire measurement. Executed but unpublished runs and private review status are not included.

Null control

Proposed control: requires review

Training-set class prior where supervised fitting is permitted

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Conventional reference

Proposed control: requires review

Regularised classifier on simple permitted features, or protocol's conventional reference

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Protocol coverage CSV (gzip) · Model evaluation matrix (gzip) · Source table (gzip) · Release and checksums (gzip)

Coverage is derived from release 2026-10-22-1b7cf027e4f6. Source citations describe the original records; they do not validate an unreviewed baseline proposal. No results have been generated by this audit.

Run instructions

No runnable recipe has been reviewed for this protocol. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.

Strengths, limitations and unresolved questions

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.

0 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

No evidence rows match these filters. Choose another scope or clear the search.

How to read the evidence

Sources and history

Release 2026-10-22-1b7cf027e4f6 · Record review: source checked

1 source record and release history

Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications · Original source · Nat Commun 17:223, published online 2025-12-07; PMC12780105 full-text XML

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: gfm2-20261011-you2026-protocol-nt-splice-donors

areas: dna-genomes
contexts: research
protocol: Fine-tune each model on the dataset's training split with an appended convolutional layer for the language models (sequence-level classification, Methods), then score the held-out test split. Each model is fine-tuned and tested three times with different random initialisations; mean and standard deviation are reported.
version: Supplementary Table 4, block 'NT-splice-sites-donors'
metric direction: higher
unit: fraction
aggregation: Mean over three fine-tuning runs
replicates: Three random initialisations
metric implementation: F1 score, precision, recall and accuracy as defined in Methods
limitations: Fine-tuned and tested three times with different random initialisations; the printed spread is the standard deviation over those three runs (Methods, 'To ensure the reliability of our findings').; Input length for the NT splice-site datasets is not stated in this source; the 500 bp division applies to the GTEx task.; Each language model is fine-tuned with an appended convolution head, so the comparison measures the adapted model, not zero-shot likelihood.; Values are read from the Supplementary Information tables behind the figures; the main-text figures are not read.
source locator: Supplementary Table 4, block 'NT-splice-sites-donors'; Table 1; Methods

Related records

uses data: Nucleotide Transformer benchmark splice-site dataset, donors
assessment: DNABERT on NT-splice-sites-donors
assessment: DNABERT2 on NT-splice-sites-donors
assessment: GENA-LM-base on NT-splice-sites-donors
assessment: GENA-LM-large on NT-splice-sites-donors
assessment: NucleotideTransformer on NT-splice-sites-donors
assessment: RNABERT on NT-splice-sites-donors
assessment: RNAErnie on NT-splice-sites-donors
assessment: RNAFM on NT-splice-sites-donors
assessment: RNAMSM on NT-splice-sites-donors
assessment: SpliceBERT on NT-splice-sites-donors
assessment: UTRLM on NT-splice-sites-donors

Suggest a correction