rewirebio.iobenchmarks
Configuration

GPN-Star ablation 'only use one target species (human)' (Supplementary Table 3)

GPN-Star trained with the human genome as its only target species instead of 20 target species sampled across clades.

7 evaluations · 7 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.

Model Capabilities & Hardware Requirements

Deployment facts recorded for GPN-Star ablation 'only use one target species (human)' (Supplementary Table 3). Fields the record does not carry are marked not recorded.

ParametersNot recorded
Minimum VRAMNot recorded
Inference LatencyNot recorded
Context WindowNot recorded
AccessNot recorded
LicenseNot recorded

Evaluated Checkpoint: Ablation model trained by the authors for Supplementary Table 3; not a released checkpoint

Evaluations and results

7 evaluations · 7 results. Different protocols are not a single leaderboard.

Sorted by AUPRC (mean over three random initializations; zero-shot) (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 configurationProtocol and datasetAUPRC (mean over three random initializations; zero-shot)Spearman (mean over three random initializations; zero-shot)
GPN-Star ablation 'only use one target species (human)' (Supplementary Table 3)EvaluationClinVar pathogenic vs benign missense, AUPRC (GPN-Star Supplementary Table 3), ClinVar pathogenic vs benign missense variants (GPN-Star paper)0.883 (best in column)Not reported
GPN-Star ablation 'only use one target species (human)' (Supplementary Table 3)EvaluationOMIM pathogenic vs gnomAD common regulatory variants, AUPRC (GPN-Star Supplementary Table 3), TraitGym Mendelian traits, matched 9 controls0.699Not reported
GPN-Star ablation 'only use one target species (human)' (Supplementary Table 3)EvaluationHGMD pathogenic vs gnomAD common regulatory variants, AUPRC (GPN-Star Supplementary Table 3), HGMD pathogenic vs gnomAD common regulatory variants, nine matched controls (GPN-Star paper)0.561Not reported
GPN-Star ablation 'only use one target species (human)' (Supplementary Table 3)EvaluationCOSMIC frequent vs gnomAD common missense, AUPRC (GPN-Star Supplementary Table 3), COSMIC frequent vs gnomAD common missense variants (GPN-MSA paper)0.353Not reported
GPN-Star ablation 'only use one target species (human)' (Supplementary Table 3)EvaluationUK Biobank fine-mapped coding variants, AUPRC (GPN-Star Supplementary Table 3), UK Biobank fine-mapped coding variants, MAF-matched controls (GPN-Star paper)0.233Not reported
GPN-Star ablation 'only use one target species (human)' (Supplementary Table 3)EvaluationUK Biobank fine-mapped non-coding variants, AUPRC (GPN-Star Supplementary Table 3), TraitGym Complex traits, matched 9 controls0.218Not reported
GPN-Star ablation 'only use one target species (human)' (Supplementary Table 3)EvaluationProteinGym human deep mutational scanning, mean Spearman (GPN-Star Supplementary Table 3), ProteinGym v0.1 human deep mutational scanning assays in genomic coordinates (GPN-Star paper)Not reported0.35
All 7 result rows with coverage, uncertainty and sources
Filter evaluations

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configurationProtocol and datasetFindingEvidence and details
Configuration: GPN-Star ablation 'only use one target species (human)' (Supplementary Table 3)Protocol: ClinVar pathogenic vs benign missense, AUPRC (GPN-Star Supplementary Table 3)
Dataset: ClinVar pathogenic vs benign missense variants (GPN-Star paper)
0.883 AUPRC (mean over three random initializations; zero-shot)
unitless · higher

Uncertainty: Not reported by the source: The table prints a mean and a maximum over three initializations, not a spread

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

only use one target species (human) on ClinVar (GPN-Star Supplementary Table 3)

gpn-star-20261116-protocol-ablation-clinvar-auprc

Aggregation: Not reported

Ye et al. 2026 GPN-Star, Nature Supplementary Information · Supplementary Table 3, row 'only use one target species (human)', column 'ClinVar' (PDF page 23)
Configuration: GPN-Star ablation 'only use one target species (human)' (Supplementary Table 3)Protocol: COSMIC frequent vs gnomAD common missense, AUPRC (GPN-Star Supplementary Table 3)
Dataset: COSMIC frequent vs gnomAD common missense variants (GPN-MSA paper)
0.353 AUPRC (mean over three random initializations; zero-shot)
unitless · higher

Uncertainty: Not reported by the source: The table prints a mean and a maximum over three initializations, not a spread

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

only use one target species (human) on COSMIC (GPN-Star Supplementary Table 3)

gpn-star-20261116-protocol-ablation-cosmic-auprc

Aggregation: Not reported

Ye et al. 2026 GPN-Star, Nature Supplementary Information · Supplementary Table 3, row 'only use one target species (human)', column 'COSMIC' (PDF page 23)
Configuration: GPN-Star ablation 'only use one target species (human)' (Supplementary Table 3)Protocol: UK Biobank fine-mapped coding variants, AUPRC (GPN-Star Supplementary Table 3)
Dataset: UK Biobank fine-mapped coding variants, MAF-matched controls (GPN-Star paper)
0.233 AUPRC (mean over three random initializations; zero-shot)
unitless · higher

Uncertainty: Not reported by the source: The table prints a mean and a maximum over three initializations, not a spread

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

only use one target species (human) on Finemapped coding (GPN-Star Supplementary Table 3)

gpn-star-20261116-protocol-ablation-finemapped-coding-auprc

Aggregation: Not reported

Ye et al. 2026 GPN-Star, Nature Supplementary Information · Supplementary Table 3, row 'only use one target species (human)', column 'Finemapped coding' (PDF page 23)
Configuration: GPN-Star ablation 'only use one target species (human)' (Supplementary Table 3)Protocol: UK Biobank fine-mapped non-coding variants, AUPRC (GPN-Star Supplementary Table 3)
Dataset: TraitGym Complex traits, matched 9 controls
0.218 AUPRC (mean over three random initializations; zero-shot)
unitless · higher

Uncertainty: Not reported by the source: The table prints a mean and a maximum over three initializations, not a spread

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

only use one target species (human) on Finemapped non-coding (GPN-Star Supplementary Table 3)

gpn-star-20261116-protocol-ablation-finemapped-noncoding-auprc

Aggregation: Not reported

Ye et al. 2026 GPN-Star, Nature Supplementary Information · Supplementary Table 3, row 'only use one target species (human)', column 'Finemapped non-coding' (PDF page 23)
Configuration: GPN-Star ablation 'only use one target species (human)' (Supplementary Table 3)Protocol: HGMD pathogenic vs gnomAD common regulatory variants, AUPRC (GPN-Star Supplementary Table 3)
Dataset: HGMD pathogenic vs gnomAD common regulatory variants, nine matched controls (GPN-Star paper)
0.561 AUPRC (mean over three random initializations; zero-shot)
unitless · higher

Uncertainty: Not reported by the source: The table prints a mean and a maximum over three initializations, not a spread

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

only use one target species (human) on HGMD (GPN-Star Supplementary Table 3)

gpn-star-20261116-protocol-ablation-hgmd-auprc

Aggregation: Not reported

Ye et al. 2026 GPN-Star, Nature Supplementary Information · Supplementary Table 3, row 'only use one target species (human)', column 'HGMD' (PDF page 23)
Configuration: GPN-Star ablation 'only use one target species (human)' (Supplementary Table 3)Protocol: OMIM pathogenic vs gnomAD common regulatory variants, AUPRC (GPN-Star Supplementary Table 3)
Dataset: TraitGym Mendelian traits, matched 9 controls
0.699 AUPRC (mean over three random initializations; zero-shot)
unitless · higher

Uncertainty: Not reported by the source: The table prints a mean and a maximum over three initializations, not a spread

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

only use one target species (human) on OMIM (GPN-Star Supplementary Table 3)

gpn-star-20261116-protocol-ablation-omim-auprc

Aggregation: Not reported

Ye et al. 2026 GPN-Star, Nature Supplementary Information · Supplementary Table 3, row 'only use one target species (human)', column 'OMIM' (PDF page 23)
Configuration: GPN-Star ablation 'only use one target species (human)' (Supplementary Table 3)Protocol: ProteinGym human deep mutational scanning, mean Spearman (GPN-Star Supplementary Table 3)
Dataset: ProteinGym v0.1 human deep mutational scanning assays in genomic coordinates (GPN-Star paper)
0.35 Spearman (mean over three random initializations; zero-shot)
unitless · higher

Uncertainty: Not reported by the source: The table prints a mean and a maximum over three initializations, not a spread

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

only use one target species (human) on ProteinGym (GPN-Star Supplementary Table 3)

gpn-star-20261116-protocol-ablation-proteingym-spearman

Aggregation: Not reported

Ye et al. 2026 GPN-Star, Nature Supplementary Information · Supplementary Table 3, row 'only use one target species (human)', column 'ProteinGym' (PDF page 23)

Source checking is not independent reproduction. Release 2026-11-21-c8bea25e5abb.

Use this configuration

How it works, versions and access

Additional methodological details, versions and access terms have not yet been extracted into a structured profile for this configuration. Consult the linked sources and evaluation records below.

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 2026-11-21-c8bea25e5abb
Property and statementOriginal source and locationReview and provenance

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

Sources and history

Release 2026-11-21-c8bea25e5abb · Record review: source checked

1 source record and release historyDownload this release (gzip)
Technical metadata and record identifiers

Technical metadata for this record is tracked under stable ID gpn-star-20261116-config-ablation-one-target-species-human.

Source locator: Supplementary Information, Supplementary Table 3, row 'only use one target species (human)' (PDF page 23)

Related records

How to cite

GPN-Star ablation 'only use one target species (human)' (Supplementary Table 3). Rewire biological model benchmark database, release 2026-11-21-c8bea25e5abb. https://benchmarks.rewirebio.io/database/configuration/gpn-star-20261116-config-ablation-one-target-species-human/

Release 2026-11-21-c8bea25e5abb. Rankings and values change between releases, so keep the release id in the citation. Cite the original publication as well for any value you reuse: each result links its source.

The compilation and annotations made by Rewire in this release are offered under CC BY 4.0; values and text taken from cited sources stay under the terms of those sources and are not covered by this licence. Data licence

Suggest a correction