Lightweight feature ensemble: CADD input features with GPN-MSA LLR and Borzoi l2-of-l2
Ridge logistic regression on the full set of CADD input features together with a much reduced set of features from other models, the GPN-MSA log-likelihood ratio and the Borzoi l2-of-l2 score.
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 Lightweight feature ensemble: CADD input features with GPN-MSA LLR and Borzoi l2-of-l2. Fields the record does not carry are marked not recorded.
Evaluations and results
8 evaluations · 8 results. Different protocols are not a single leaderboard.
Protocol: TraitGym Mendelian traits per trait, AUPRC, best of zero-shot and linear probing
Sorted by AUPRC (best of zero-shot and linear probing; single trait; chromosome aggregation unreported) (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.
All 8 result rows with coverage, uncertainty and sources
Filter evaluations
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Method: Lightweight feature ensemble: CADD input features with GPN-MSA LLR and Borzoi l2-of-l2 | Protocol: TraitGym Mendelian traits per trait, AUPRC, best of zero-shot and linear probing Dataset subset: TraitGym Mendelian traits: Beta-thalassemia | 0.955 AUPRC (best of zero-shot and linear probing; single trait; chromosome aggregation unreported) unitless · higher Uncertainty: Not reported by the source: The table prints no standard error; the bootstrap errors of Appendix B.4 are reported only in the figures. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceEnsemble on TraitGym Mendelian traits, trait Beta-thalassemia traitgym-20261116-protocol-mendelian-per-trait-best-of-zero-shot-and-linear-probing Aggregation: Not reported Benegas, Eraslan and Song 2025, TraitGym benchmark preprint (bioRxiv v2) · Table S11, row "Beta-thalassemia", column "Ensemble" (page 28) |
| Method: Lightweight feature ensemble: CADD input features with GPN-MSA LLR and Borzoi l2-of-l2 | Protocol: TraitGym Mendelian traits per trait, AUPRC, best of zero-shot and linear probing Dataset subset: TraitGym Mendelian traits: Cartilage-hair hypoplasia | 0.918 AUPRC (best of zero-shot and linear probing; single trait; chromosome aggregation unreported) unitless · higher Uncertainty: Not reported by the source: The table prints no standard error; the bootstrap errors of Appendix B.4 are reported only in the figures. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceEnsemble on TraitGym Mendelian traits, trait Cartilage-hair hypoplasia traitgym-20261116-protocol-mendelian-per-trait-best-of-zero-shot-and-linear-probing Aggregation: Not reported Benegas, Eraslan and Song 2025, TraitGym benchmark preprint (bioRxiv v2) · Table S11, row "Cartilage-hair hypoplasia", column "Ensemble" (page 28) |
| Method: Lightweight feature ensemble: CADD input features with GPN-MSA LLR and Borzoi l2-of-l2 | Protocol: TraitGym Mendelian traits per trait, AUPRC, best of zero-shot and linear probing Dataset subset: TraitGym Mendelian traits: Dwarfism (MOPD1) | 1 AUPRC (best of zero-shot and linear probing; single trait; chromosome aggregation unreported) unitless · higher Uncertainty: Not reported by the source: The table prints no standard error; the bootstrap errors of Appendix B.4 are reported only in the figures. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceEnsemble on TraitGym Mendelian traits, trait Dwarfism (MOPD1) traitgym-20261116-protocol-mendelian-per-trait-best-of-zero-shot-and-linear-probing Aggregation: Not reported Benegas, Eraslan and Song 2025, TraitGym benchmark preprint (bioRxiv v2) · Table S11, row "Dwarfism (MOPD1)", column "Ensemble" (page 28) |
| Method: Lightweight feature ensemble: CADD input features with GPN-MSA LLR and Borzoi l2-of-l2 | Protocol: TraitGym Mendelian traits per trait, AUPRC, best of zero-shot and linear probing Dataset subset: TraitGym Mendelian traits: Hemophilia B | 0.991 AUPRC (best of zero-shot and linear probing; single trait; chromosome aggregation unreported) unitless · higher Uncertainty: Not reported by the source: The table prints no standard error; the bootstrap errors of Appendix B.4 are reported only in the figures. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceEnsemble on TraitGym Mendelian traits, trait Hemophilia B traitgym-20261116-protocol-mendelian-per-trait-best-of-zero-shot-and-linear-probing Aggregation: Not reported Benegas, Eraslan and Song 2025, TraitGym benchmark preprint (bioRxiv v2) · Table S11, row "Hemophilia B", column "Ensemble" (page 28) |
| Method: Lightweight feature ensemble: CADD input features with GPN-MSA LLR and Borzoi l2-of-l2 | Protocol: TraitGym Mendelian traits per trait, AUPRC, best of zero-shot and linear probing Dataset subset: TraitGym Mendelian traits: Hypercholesterolemia-1 | 0.938 AUPRC (best of zero-shot and linear probing; single trait; chromosome aggregation unreported) unitless · higher Uncertainty: Not reported by the source: The table prints no standard error; the bootstrap errors of Appendix B.4 are reported only in the figures. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceEnsemble on TraitGym Mendelian traits, trait Hypercholesterolemia-1 traitgym-20261116-protocol-mendelian-per-trait-best-of-zero-shot-and-linear-probing Aggregation: Not reported Benegas, Eraslan and Song 2025, TraitGym benchmark preprint (bioRxiv v2) · Table S11, row "Hypercholesterolemia-1", column "Ensemble" (page 28) |
| Method: Lightweight feature ensemble: CADD input features with GPN-MSA LLR and Borzoi l2-of-l2 | Protocol: TraitGym Mendelian traits per trait, AUPRC, best of zero-shot and linear probing Dataset subset: TraitGym Mendelian traits: Hyperferritinemia | 0.985 AUPRC (best of zero-shot and linear probing; single trait; chromosome aggregation unreported) unitless · higher Uncertainty: Not reported by the source: The table prints no standard error; the bootstrap errors of Appendix B.4 are reported only in the figures. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceEnsemble on TraitGym Mendelian traits, trait Hyperferritinemia traitgym-20261116-protocol-mendelian-per-trait-best-of-zero-shot-and-linear-probing Aggregation: Not reported Benegas, Eraslan and Song 2025, TraitGym benchmark preprint (bioRxiv v2) · Table S11, row "Hyperferritinemia", column "Ensemble" (page 28) |
| Method: Lightweight feature ensemble: CADD input features with GPN-MSA LLR and Borzoi l2-of-l2 | Protocol: TraitGym Mendelian traits per trait, AUPRC, best of zero-shot and linear probing Dataset subset: TraitGym Mendelian traits: Preaxial polydactyly II | 0.967 AUPRC (best of zero-shot and linear probing; single trait; chromosome aggregation unreported) unitless · higher Uncertainty: Not reported by the source: The table prints no standard error; the bootstrap errors of Appendix B.4 are reported only in the figures. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceEnsemble on TraitGym Mendelian traits, trait Preaxial polydactyly II traitgym-20261116-protocol-mendelian-per-trait-best-of-zero-shot-and-linear-probing Aggregation: Not reported Benegas, Eraslan and Song 2025, TraitGym benchmark preprint (bioRxiv v2) · Table S11, row "Preaxial polydactyly II", column "Ensemble" (page 28) |
| Method: Lightweight feature ensemble: CADD input features with GPN-MSA LLR and Borzoi l2-of-l2 | Protocol: TraitGym Mendelian traits per trait, AUPRC, best of zero-shot and linear probing Dataset subset: TraitGym Mendelian traits: Pulmonary fibrosis | 1 AUPRC (best of zero-shot and linear probing; single trait; chromosome aggregation unreported) unitless · higher Uncertainty: Not reported by the source: The table prints no standard error; the bootstrap errors of Appendix B.4 are reported only in the figures. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceEnsemble on TraitGym Mendelian traits, trait Pulmonary fibrosis traitgym-20261116-protocol-mendelian-per-trait-best-of-zero-shot-and-linear-probing Aggregation: Not reported Benegas, Eraslan and Song 2025, TraitGym benchmark preprint (bioRxiv v2) · Table S11, row "Pulmonary fibrosis", column "Ensemble" (page 28) |
Source checking is not independent reproduction. Release 2026-11-21-adc15377fab2.
Use this method
How it works, versions and access
Additional methodological details, versions and access terms have not yet been extracted into a structured profile for this method. 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
| Property and statement | Original source and location | Review and provenance |
|---|
No evidence rows match these filters. Choose another scope or clear the search.
Sources and history
Release 2026-11-21-adc15377fab2 · Record review: source checked
1 source record and release history
- Benegas, Eraslan and Song 2025, TraitGym benchmark preprint (bioRxiv v2) · Original source · bioRxiv version 2, posted 2025-03-04 (37 pages, main text and Supplementary Material)
Technical metadata and record identifiers
Technical metadata for this record is tracked under stable ID traitgym-20261116-method-lightweight-ensemble.
Source locator: Section 6 'Model ensembling' and Figure 8 (page 10); Table S11 caption (page 28)
Related records
- system: Ensemble on TraitGym Mendelian traits, trait Beta-thalassemia
- system: Ensemble on TraitGym Mendelian traits, trait Cartilage-hair hypoplasia
- system: Ensemble on TraitGym Mendelian traits, trait Dwarfism (MOPD1)
- system: Ensemble on TraitGym Mendelian traits, trait Hemophilia B
- system: Ensemble on TraitGym Mendelian traits, trait Hypercholesterolemia-1
- system: Ensemble on TraitGym Mendelian traits, trait Hyperferritinemia
- system: Ensemble on TraitGym Mendelian traits, trait Preaxial polydactyly II
- system: Ensemble on TraitGym Mendelian traits, trait Pulmonary fibrosis
How to cite
Lightweight feature ensemble: CADD input features with GPN-MSA LLR and Borzoi l2-of-l2. Rewire biological model benchmark database, release 2026-11-21-adc15377fab2. https://benchmarks.rewirebio.io/database/method/traitgym-20261116-method-lightweight-ensemble/
Release 2026-11-21-adc15377fab2. 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