Protocol

GUANinE v1.1 cons30, Spearman rho x100 (Table 2)

GUANinE v1.1 task cons30: Sequence conservation, 30-way.

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.

32 recorded evaluations, 32 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

32 evaluations · 32 results. Different protocols are not a single leaderboard.

Protocol: GUANinE v1.1 cons30, Spearman rho x100 (Table 2) · Dataset: GUANinE cons30 test set

Sorted by Spearman (GUANinE v1.1 test set) (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	Spearman (GUANinE v1.1 test set)
Evo2_7B (1% eval (evaluated with 1% of the training set), GUANinE v1.1)Evaluation	76.7 (best in column)
NTv2-500m (1% eval (evaluated with 1% of the training set), GUANinE v1.1)Evaluation	75.6
Enformer (Pre-output) (1% eval (evaluated with 1% of the training set), GUANinE v1.1)Evaluation	74.7
Enformer (1% eval (evaluated with 1% of the training set), GUANinE v1.1)Evaluation	74.4
Caduceus-PS (1% eval (evaluated with 1% of the training set), GUANinE v1.1)Evaluation	74.4
Evo2_7B_base (1% eval (evaluated with 1% of the training set), GUANinE v1.1)Evaluation	74.1
GENA-LM-bigbird-base-t2t (1% eval (evaluated with 1% of the training set), GUANinE v1.1)Evaluation	73.6
NTv3-650m-post (1% eval (evaluated with 1% of the training set), GUANinE v1.1)Evaluation	73.3
NTv3-100m-post (1% eval (evaluated with 1% of the training set), GUANinE v1.1)Evaluation	72
GENA-LM-bert-large-t2t (1% eval (evaluated with 1% of the training set), GUANinE v1.1)Evaluation	71.6
Borzoi (1% eval (evaluated with 1% of the training set), GUANinE v1.1)Evaluation	71.5
NTv2-100m (1% eval (evaluated with 1% of the training set), GUANinE v1.1)Evaluation	69.2
Evo2_1B_base (1% eval (evaluated with 1% of the training set), GUANinE v1.1)Evaluation	68.5
GENA-LM-bert-base-t2t-enf (1% eval (evaluated with 1% of the training set), GUANinE v1.1)Evaluation	68.2
GENA-LM-bert-base-t2t (1% eval (evaluated with 1% of the training set), GUANinE v1.1)Evaluation	66.7
NTv3-100m-pre (1% eval (evaluated with 1% of the training set), GUANinE v1.1)Evaluation	65.8
Sei (1% eval (evaluated with 1% of the training set), GUANinE v1.1)Evaluation	63.2
Enigma-Distilled (1% eval (evaluated with 1% of the training set), GUANinE v1.1)Evaluation	63
AIDO.DNA_300m (1% eval (evaluated with 1% of the training set), GUANinE v1.1)Evaluation	61
DNABERT-2 (1% eval (evaluated with 1% of the training set), GUANinE v1.1)Evaluation	60.6
Mistral-DNA-422m-hg38 (1% eval (evaluated with 1% of the training set), GUANinE v1.1)Evaluation	60.5
hgT5-8195 (fine-tuned, GUANinE v1.1)Evaluation	59.4
PhyloGPN (1% eval (evaluated with 1% of the training set), GUANinE v1.1)Evaluation	53.2
5-mer kNN (fine-tuned, GUANinE v1.1)Evaluation	52.6
⋆ T5 (fine-tuned, GUANinE v1.1)Evaluation	52.6
DeepSEA (1% eval (evaluated with 1% of the training set), GUANinE v1.1)Evaluation	49.6
5-mer LinSVR (fine-tuned, GUANinE v1.1)Evaluation	49.4
ChromBPNet-ATAC-F0 (1% eval (evaluated with 1% of the training set), GUANinE v1.1)Evaluation	47.8
ChromBPNet-ATAC-F3 (1% eval (evaluated with 1% of the training set), GUANinE v1.1)Evaluation	47.4
ESA-dna2vec (1% eval (evaluated with 1% of the training set), GUANinE v1.1)Evaluation	44.1
GC-content (zero-shot, GUANinE v1.1)Evaluation	38.1
ENCFF180XQC (zero-shot, GUANinE v1.1)Evaluation	4.09

All 32 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: 5-mer kNN (fine-tuned, GUANinE v1.1)	Protocol: GUANinE v1.1 cons30, Spearman rho x100 (Table 2) Dataset: GUANinE cons30 test set	52.6 Spearman (GUANinE v1.1 test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source 5-mer kNN on GUANinE cons30 lit-genomics-20261011-guanine-protocol-cons30 Aggregation: Not reported GUANinE v1.1 reveals complementarity of supervised and genomic language models · Table 2, row '5-mer kNN', column 'cons30' (ρ)
Configuration: 5-mer LinSVR (fine-tuned, GUANinE v1.1)	Protocol: GUANinE v1.1 cons30, Spearman rho x100 (Table 2) Dataset: GUANinE cons30 test set	49.4 Spearman (GUANinE v1.1 test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source 5-mer LinSVR on GUANinE cons30 lit-genomics-20261011-guanine-protocol-cons30 Aggregation: Not reported GUANinE v1.1 reveals complementarity of supervised and genomic language models · Table 2, row '5-mer LinSVR', column 'cons30' (ρ)
Configuration: AIDO.DNA_300m (1% eval (evaluated with 1% of the training set), GUANinE v1.1)	Protocol: GUANinE v1.1 cons30, Spearman rho x100 (Table 2) Dataset: GUANinE cons30 test set	61 Spearman (GUANinE v1.1 test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source AIDO.DNA_300m on GUANinE cons30 lit-genomics-20261011-guanine-protocol-cons30 Aggregation: Not reported GUANinE v1.1 reveals complementarity of supervised and genomic language models · Table 2, row 'AIDO.DNA_300m', column 'cons30' (ρ)
Configuration: Borzoi (1% eval (evaluated with 1% of the training set), GUANinE v1.1)	Protocol: GUANinE v1.1 cons30, Spearman rho x100 (Table 2) Dataset: GUANinE cons30 test set	71.5 Spearman (GUANinE v1.1 test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Borzoi on GUANinE cons30 lit-genomics-20261011-guanine-protocol-cons30 Aggregation: Not reported GUANinE v1.1 reveals complementarity of supervised and genomic language models · Table 2, row 'Borzoi', column 'cons30' (ρ)
Configuration: Caduceus-PS (1% eval (evaluated with 1% of the training set), GUANinE v1.1)	Protocol: GUANinE v1.1 cons30, Spearman rho x100 (Table 2) Dataset: GUANinE cons30 test set	74.4 Spearman (GUANinE v1.1 test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Caduceus-PS on GUANinE cons30 lit-genomics-20261011-guanine-protocol-cons30 Aggregation: Not reported GUANinE v1.1 reveals complementarity of supervised and genomic language models · Table 2, row 'Caduceus-PS', column 'cons30' (ρ)
Configuration: ChromBPNet-ATAC-F0 (1% eval (evaluated with 1% of the training set), GUANinE v1.1)	Protocol: GUANinE v1.1 cons30, Spearman rho x100 (Table 2) Dataset: GUANinE cons30 test set	47.8 Spearman (GUANinE v1.1 test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ChromBPNet-ATAC-F0 on GUANinE cons30 lit-genomics-20261011-guanine-protocol-cons30 Aggregation: Not reported GUANinE v1.1 reveals complementarity of supervised and genomic language models · Table 2, row 'ChromBPNet-ATAC-F0', column 'cons30' (ρ)
Configuration: ChromBPNet-ATAC-F3 (1% eval (evaluated with 1% of the training set), GUANinE v1.1)	Protocol: GUANinE v1.1 cons30, Spearman rho x100 (Table 2) Dataset: GUANinE cons30 test set	47.4 Spearman (GUANinE v1.1 test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ChromBPNet-ATAC-F3 on GUANinE cons30 lit-genomics-20261011-guanine-protocol-cons30 Aggregation: Not reported GUANinE v1.1 reveals complementarity of supervised and genomic language models · Table 2, row 'ChromBPNet-ATAC-F3', column 'cons30' (ρ)
Configuration: DeepSEA (1% eval (evaluated with 1% of the training set), GUANinE v1.1)	Protocol: GUANinE v1.1 cons30, Spearman rho x100 (Table 2) Dataset: GUANinE cons30 test set	49.6 Spearman (GUANinE v1.1 test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DeepSEA on GUANinE cons30 lit-genomics-20261011-guanine-protocol-cons30 Aggregation: Not reported GUANinE v1.1 reveals complementarity of supervised and genomic language models · Table 2, row 'DeepSEA', column 'cons30' (ρ)
Configuration: DNABERT-2 (1% eval (evaluated with 1% of the training set), GUANinE v1.1)	Protocol: GUANinE v1.1 cons30, Spearman rho x100 (Table 2) Dataset: GUANinE cons30 test set	60.6 Spearman (GUANinE v1.1 test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DNABERT-2 on GUANinE cons30 lit-genomics-20261011-guanine-protocol-cons30 Aggregation: Not reported GUANinE v1.1 reveals complementarity of supervised and genomic language models · Table 2, row 'DNABERT-2', column 'cons30' (ρ)
Configuration: ENCFF180XQC (zero-shot, GUANinE v1.1)	Protocol: GUANinE v1.1 cons30, Spearman rho x100 (Table 2) Dataset: GUANinE cons30 test set	4.09 Spearman (GUANinE v1.1 test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ENCFF180XQC on GUANinE cons30 lit-genomics-20261011-guanine-protocol-cons30 Aggregation: Not reported GUANinE v1.1 reveals complementarity of supervised and genomic language models · Table 2, row 'ENCFF180XQC', column 'cons30' (ρ)
Configuration: Enformer (1% eval (evaluated with 1% of the training set), GUANinE v1.1)	Protocol: GUANinE v1.1 cons30, Spearman rho x100 (Table 2) Dataset: GUANinE cons30 test set	74.4 Spearman (GUANinE v1.1 test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Enformer on GUANinE cons30 lit-genomics-20261011-guanine-protocol-cons30 Aggregation: Not reported GUANinE v1.1 reveals complementarity of supervised and genomic language models · Table 2, row 'Enformer', column 'cons30' (ρ)
Configuration: Enformer (Pre-output) (1% eval (evaluated with 1% of the training set), GUANinE v1.1)	Protocol: GUANinE v1.1 cons30, Spearman rho x100 (Table 2) Dataset: GUANinE cons30 test set	74.7 Spearman (GUANinE v1.1 test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Enformer (Pre-output) on GUANinE cons30 lit-genomics-20261011-guanine-protocol-cons30 Aggregation: Not reported GUANinE v1.1 reveals complementarity of supervised and genomic language models · Table 2, row 'Enformer (Pre-output)', column 'cons30' (ρ)
Configuration: Enigma-Distilled (1% eval (evaluated with 1% of the training set), GUANinE v1.1)	Protocol: GUANinE v1.1 cons30, Spearman rho x100 (Table 2) Dataset: GUANinE cons30 test set	63 Spearman (GUANinE v1.1 test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Enigma-Distilled on GUANinE cons30 lit-genomics-20261011-guanine-protocol-cons30 Aggregation: Not reported GUANinE v1.1 reveals complementarity of supervised and genomic language models · Table 2, row 'Enigma-Distilled', column 'cons30' (ρ)
Configuration: ESA-dna2vec (1% eval (evaluated with 1% of the training set), GUANinE v1.1)	Protocol: GUANinE v1.1 cons30, Spearman rho x100 (Table 2) Dataset: GUANinE cons30 test set	44.1 Spearman (GUANinE v1.1 test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ESA-dna2vec on GUANinE cons30 lit-genomics-20261011-guanine-protocol-cons30 Aggregation: Not reported GUANinE v1.1 reveals complementarity of supervised and genomic language models · Table 2, row 'ESA-dna2vec', column 'cons30' (ρ)
Configuration: Evo2_1B_base (1% eval (evaluated with 1% of the training set), GUANinE v1.1)	Protocol: GUANinE v1.1 cons30, Spearman rho x100 (Table 2) Dataset: GUANinE cons30 test set	68.5 Spearman (GUANinE v1.1 test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Evo2_1B_base on GUANinE cons30 lit-genomics-20261011-guanine-protocol-cons30 Aggregation: Not reported GUANinE v1.1 reveals complementarity of supervised and genomic language models · Table 2, row 'Evo2_1B_base', column 'cons30' (ρ)
Configuration: Evo2_7B (1% eval (evaluated with 1% of the training set), GUANinE v1.1)	Protocol: GUANinE v1.1 cons30, Spearman rho x100 (Table 2) Dataset: GUANinE cons30 test set	76.7 Spearman (GUANinE v1.1 test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Evo2_7B on GUANinE cons30 lit-genomics-20261011-guanine-protocol-cons30 Aggregation: Not reported GUANinE v1.1 reveals complementarity of supervised and genomic language models · Table 2, row 'Evo2_7B', column 'cons30' (ρ)
Configuration: Evo2_7B_base (1% eval (evaluated with 1% of the training set), GUANinE v1.1)	Protocol: GUANinE v1.1 cons30, Spearman rho x100 (Table 2) Dataset: GUANinE cons30 test set	74.1 Spearman (GUANinE v1.1 test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Evo2_7B_base on GUANinE cons30 lit-genomics-20261011-guanine-protocol-cons30 Aggregation: Not reported GUANinE v1.1 reveals complementarity of supervised and genomic language models · Table 2, row 'Evo2_7B_base', column 'cons30' (ρ)
Configuration: GC-content (zero-shot, GUANinE v1.1)	Protocol: GUANinE v1.1 cons30, Spearman rho x100 (Table 2) Dataset: GUANinE cons30 test set	38.1 Spearman (GUANinE v1.1 test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source GC-content on GUANinE cons30 lit-genomics-20261011-guanine-protocol-cons30 Aggregation: Not reported GUANinE v1.1 reveals complementarity of supervised and genomic language models · Table 2, row 'GC-content', column 'cons30' (ρ)
Configuration: GENA-LM-bert-base-t2t (1% eval (evaluated with 1% of the training set), GUANinE v1.1)	Protocol: GUANinE v1.1 cons30, Spearman rho x100 (Table 2) Dataset: GUANinE cons30 test set	66.7 Spearman (GUANinE v1.1 test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source GENA-LM-bert-base-t2t on GUANinE cons30 lit-genomics-20261011-guanine-protocol-cons30 Aggregation: Not reported GUANinE v1.1 reveals complementarity of supervised and genomic language models · Table 2, row 'GENA-LM-bert-base-t2t', column 'cons30' (ρ)
Configuration: GENA-LM-bert-base-t2t-enf (1% eval (evaluated with 1% of the training set), GUANinE v1.1)	Protocol: GUANinE v1.1 cons30, Spearman rho x100 (Table 2) Dataset: GUANinE cons30 test set	68.2 Spearman (GUANinE v1.1 test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source GENA-LM-bert-base-t2t-enf on GUANinE cons30 lit-genomics-20261011-guanine-protocol-cons30 Aggregation: Not reported GUANinE v1.1 reveals complementarity of supervised and genomic language models · Table 2, row 'GENA-LM-bert-base-t2t-enf', column 'cons30' (ρ)
Configuration: GENA-LM-bert-large-t2t (1% eval (evaluated with 1% of the training set), GUANinE v1.1)	Protocol: GUANinE v1.1 cons30, Spearman rho x100 (Table 2) Dataset: GUANinE cons30 test set	71.6 Spearman (GUANinE v1.1 test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source GENA-LM-bert-large-t2t on GUANinE cons30 lit-genomics-20261011-guanine-protocol-cons30 Aggregation: Not reported GUANinE v1.1 reveals complementarity of supervised and genomic language models · Table 2, row 'GENA-LM-bert-large-t2t', column 'cons30' (ρ)
Configuration: GENA-LM-bigbird-base-t2t (1% eval (evaluated with 1% of the training set), GUANinE v1.1)	Protocol: GUANinE v1.1 cons30, Spearman rho x100 (Table 2) Dataset: GUANinE cons30 test set	73.6 Spearman (GUANinE v1.1 test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source GENA-LM-bigbird-base-t2t on GUANinE cons30 lit-genomics-20261011-guanine-protocol-cons30 Aggregation: Not reported GUANinE v1.1 reveals complementarity of supervised and genomic language models · Table 2, row 'GENA-LM-bigbird-base-t2t', column 'cons30' (ρ)
Configuration: hgT5-8195 (fine-tuned, GUANinE v1.1)	Protocol: GUANinE v1.1 cons30, Spearman rho x100 (Table 2) Dataset: GUANinE cons30 test set	59.4 Spearman (GUANinE v1.1 test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source hgT5-8195 on GUANinE cons30 lit-genomics-20261011-guanine-protocol-cons30 Aggregation: Not reported GUANinE v1.1 reveals complementarity of supervised and genomic language models · Table 2, row 'hgT5-8195', column 'cons30' (ρ)
Configuration: Mistral-DNA-422m-hg38 (1% eval (evaluated with 1% of the training set), GUANinE v1.1)	Protocol: GUANinE v1.1 cons30, Spearman rho x100 (Table 2) Dataset: GUANinE cons30 test set	60.5 Spearman (GUANinE v1.1 test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Mistral-DNA-422m-hg38 on GUANinE cons30 lit-genomics-20261011-guanine-protocol-cons30 Aggregation: Not reported GUANinE v1.1 reveals complementarity of supervised and genomic language models · Table 2, row 'Mistral-DNA-422m-hg38', column 'cons30' (ρ)
Configuration: NTv2-100m (1% eval (evaluated with 1% of the training set), GUANinE v1.1)	Protocol: GUANinE v1.1 cons30, Spearman rho x100 (Table 2) Dataset: GUANinE cons30 test set	69.2 Spearman (GUANinE v1.1 test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NTv2-100m on GUANinE cons30 lit-genomics-20261011-guanine-protocol-cons30 Aggregation: Not reported GUANinE v1.1 reveals complementarity of supervised and genomic language models · Table 2, row 'NTv2-100m', column 'cons30' (ρ)

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.

Explore all linked results

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.

Author-reported evaluations: 5
External evaluations: 27

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

Null control

Proposed control: requires review

Select a task-valid null control after reviewing inputs and metric

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

Select an upstream conventional reference after reviewing the full protocol

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

GUANinE v1.1 reveals complementarity of supervised and genomic language models · Original source · Bioinformatics 2026, btag427 (issue date 2026-08-01); PMC13501288 full-text XML

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: lit-genomics-20261011-guanine-protocol-cons30

areas: dna-genomes
contexts: research
protocol: GUANinE v1.1 cons30 test set; score is the printed column 'ρ'
version: GUANinE v1.1
metric: spearman-correlation
metric direction: higher
unit: unitless
unit detail: Printed as Spearman rho multiplied by 100
limitations: The benchmark authors evaluated the models; GUANinE v1.1 is by the developers of hgT5 and the T5 baseline.; Previously reported performances are marked in blue in the published table; the colour is not in the XML artifact, so prior and new cells are not distinguished here.; Many rows are '1% eval': models were evaluated with 1% of the training set (Table 2 footnote).
source locator: Table 2 column 'cons30'

Related records

part of: GUANinE v1.1
uses data: GUANinE cons30 test set
assessment: 5-mer kNN on GUANinE cons30
assessment: 5-mer LinSVR on GUANinE cons30
assessment: AIDO.DNA_300m on GUANinE cons30
assessment: Borzoi on GUANinE cons30
assessment: Caduceus-PS on GUANinE cons30
assessment: ChromBPNet-ATAC-F0 on GUANinE cons30
assessment: ChromBPNet-ATAC-F3 on GUANinE cons30
assessment: DeepSEA on GUANinE cons30
assessment: DNABERT-2 on GUANinE cons30
assessment: ENCFF180XQC on GUANinE cons30
assessment: Enformer on GUANinE cons30
assessment: Enformer (Pre-output) on GUANinE cons30
assessment: Enigma-Distilled on GUANinE cons30
assessment: ESA-dna2vec on GUANinE cons30
assessment: Evo2_1B_base on GUANinE cons30
assessment: Evo2_7B on GUANinE cons30
assessment: Evo2_7B_base on GUANinE cons30
assessment: GC-content on GUANinE cons30
assessment: GENA-LM-bert-base-t2t on GUANinE cons30
assessment: GENA-LM-bert-base-t2t-enf on GUANinE cons30
assessment: GENA-LM-bert-large-t2t on GUANinE cons30
assessment: GENA-LM-bigbird-base-t2t on GUANinE cons30
assessment: hgT5-8195 on GUANinE cons30
assessment: Mistral-DNA-422m-hg38 on GUANinE cons30
assessment: NTv2-100m on GUANinE cons30
assessment: NTv2-500m on GUANinE cons30
assessment: NTv3-100m-post on GUANinE cons30
assessment: NTv3-100m-pre on GUANinE cons30
assessment: NTv3-650m-post on GUANinE cons30
assessment: PhyloGPN on GUANinE cons30
assessment: Sei on GUANinE cons30
assessment: ⋆ T5 on GUANinE cons30

Suggest a correction