rewirebio.iobenchmarks
Protocol

TraitGym Complex traits per trait, AUPRC, best of zero-shot and linear probing

AUPRC on the causal and matched control variants of one complex traits trait, reporting for each system the better of its zero-shot and its linear probing score, with the full feature ensemble standing for the ensemble.

72 evaluations · 72 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.

72 recorded evaluations, 72 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

72 evaluations · 72 results. Different protocols are not a single leaderboard.

Protocol: TraitGym Complex 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.

Tested configurationProtocol and datasetAUPRC (best of zero-shot and linear probing; single trait; chromosome aggregation unreported)
CADD+GPN-MSA+Borzoi logistic regression ensembleEvaluationTraitGym Complex traits: Balding Type 40.625 (best in column)
BorzoiEvaluationTraitGym Complex traits: Albumin0.615
CADD+GPN-MSA+Borzoi logistic regression ensembleEvaluationTraitGym Complex traits: Albumin0.602
BorzoiEvaluationTraitGym Complex traits: Blood clot in the leg0.574
CADD+GPN-MSA+Borzoi logistic regression ensembleEvaluationTraitGym Complex traits: Blood clot in the leg0.565
BorzoiEvaluationTraitGym Complex traits: Monocyte count0.561
CADD+GPN-MSA+Borzoi logistic regression ensembleEvaluationTraitGym Complex traits: Albumin/Globulin ratio0.559
CADD+GPN-MSA+Borzoi logistic regression ensembleEvaluationTraitGym Complex traits: High density lipoprotein cholesterol0.554
GPN-MSAEvaluationTraitGym Complex traits: Blood clot in the leg0.551
GPN-MSAEvaluationTraitGym Complex traits: Albumin0.544
GPN-MSAEvaluationTraitGym Complex traits: Balding Type 40.536
CADD+GPN-MSA+Borzoi logistic regression ensembleEvaluationTraitGym Complex traits: Monocyte count0.535
CADD+GPN-MSA+Borzoi logistic regression ensembleEvaluationTraitGym Complex traits: Gamma-glutamyl transferase0.527
BorzoiEvaluationTraitGym Complex traits: High density lipoprotein cholesterol0.521
CADD+GPN-MSA+Borzoi logistic regression ensembleEvaluationTraitGym Complex traits: Hemoglobin A1c0.517
CADDEvaluationTraitGym Complex traits: Albumin/Globulin ratio0.516
BorzoiEvaluationTraitGym Complex traits: Gamma-glutamyl transferase0.515
GPN-MSAEvaluationTraitGym Complex traits: Body mass index0.514
CADDEvaluationTraitGym Complex traits: FEV1/FVC ratio0.505
CADD+GPN-MSA+Borzoi logistic regression ensembleEvaluationTraitGym Complex traits: Body mass index0.499
CADDEvaluationTraitGym Complex traits: Blood clot in the leg0.498
GPN-MSAEvaluationTraitGym Complex traits: FEV1/FVC ratio0.494
BorzoiEvaluationTraitGym Complex traits: Alkaline phosphatase0.492
CADD+GPN-MSA+Borzoi logistic regression ensembleEvaluationTraitGym Complex traits: Pulse pressure0.489
CADD+GPN-MSA+Borzoi logistic regression ensembleEvaluationTraitGym Complex traits: FEV1/FVC ratio0.487
CADDEvaluationTraitGym Complex traits: Albumin0.48
CADD+GPN-MSA+Borzoi logistic regression ensembleEvaluationTraitGym Complex traits: Platelet count0.478
BorzoiEvaluationTraitGym Complex traits: Hemoglobin A1c0.475
CADD+GPN-MSA+Borzoi logistic regression ensembleEvaluationTraitGym Complex traits: Estimated glomerular filtration rate (cystain C)0.47
BorzoiEvaluationTraitGym Complex traits: Calcium0.468
CADDEvaluationTraitGym Complex traits: Gamma-glutamyl transferase0.46
BorzoiEvaluationTraitGym Complex traits: Balding Type 40.459
BorzoiEvaluationTraitGym Complex traits: Estimated glomerular filtration rate (cystain C)0.457
BorzoiEvaluationTraitGym Complex traits: Pulse pressure0.457
GPN-MSAEvaluationTraitGym Complex traits: Estimated glomerular filtration rate (cystain C)0.456
BorzoiEvaluationTraitGym Complex traits: Albumin/Globulin ratio0.455
CADD+GPN-MSA+Borzoi logistic regression ensembleEvaluationTraitGym Complex traits: Mean corpuscular volume0.454
CADD+GPN-MSA+Borzoi logistic regression ensembleEvaluationTraitGym Complex traits: Alkaline phosphatase0.446
CADDEvaluationTraitGym Complex traits: Body mass index0.436
GPN-MSAEvaluationTraitGym Complex traits: Pulse pressure0.435
BorzoiEvaluationTraitGym Complex traits: Mean corpuscular volume0.434
GPN-MSAEvaluationTraitGym Complex traits: Calcium0.433
GPN-MSAEvaluationTraitGym Complex traits: Estimated heel bone mineral density0.432
GPN-MSAEvaluationTraitGym Complex traits: Albumin/Globulin ratio0.431
BorzoiEvaluationTraitGym Complex traits: FEV1/FVC ratio0.43
CADDEvaluationTraitGym Complex traits: Hemoglobin A1c0.426
BorzoiEvaluationTraitGym Complex traits: Platelet count0.426
CADDEvaluationTraitGym Complex traits: Calcium0.425
CADDEvaluationTraitGym Complex traits: High density lipoprotein cholesterol0.425
CADDEvaluationTraitGym Complex traits: Estimated heel bone mineral density0.422
CADDEvaluationTraitGym Complex traits: Estimated glomerular filtration rate (cystain C)0.421
CADDEvaluationTraitGym Complex traits: Pulse pressure0.42
CADDEvaluationTraitGym Complex traits: Balding Type 40.414
CADD+GPN-MSA+Borzoi logistic regression ensembleEvaluationTraitGym Complex traits: Calcium0.408
CADDEvaluationTraitGym Complex traits: Adult height0.407
CADD+GPN-MSA+Borzoi logistic regression ensembleEvaluationTraitGym Complex traits: Estimated heel bone mineral density0.406
GPN-MSAEvaluationTraitGym Complex traits: Monocyte count0.404
CADDEvaluationTraitGym Complex traits: Platelet count0.397
CADDEvaluationTraitGym Complex traits: Mean corpuscular volume0.391
GPN-MSAEvaluationTraitGym Complex traits: Adult height0.383
GPN-MSAEvaluationTraitGym Complex traits: Gamma-glutamyl transferase0.382
GPN-MSAEvaluationTraitGym Complex traits: Hemoglobin A1c0.375
CADDEvaluationTraitGym Complex traits: Monocyte count0.375
GPN-MSAEvaluationTraitGym Complex traits: High density lipoprotein cholesterol0.362
CADDEvaluationTraitGym Complex traits: Alkaline phosphatase0.352
BorzoiEvaluationTraitGym Complex traits: Body mass index0.344
CADD+GPN-MSA+Borzoi logistic regression ensembleEvaluationTraitGym Complex traits: Adult height0.339
GPN-MSAEvaluationTraitGym Complex traits: Mean corpuscular volume0.319
GPN-MSAEvaluationTraitGym Complex traits: Platelet count0.309
BorzoiEvaluationTraitGym Complex traits: Estimated heel bone mineral density0.308
BorzoiEvaluationTraitGym Complex traits: Adult height0.292
GPN-MSAEvaluationTraitGym Complex traits: Alkaline phosphatase0.292
All 72 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
Model: BorzoiProtocol: TraitGym Complex traits per trait, AUPRC, best of zero-shot and linear probing
Dataset subset: TraitGym Complex traits: Adult height
0.292 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 checked
Methods, coverage and source

Borzoi on TraitGym Complex traits, trait Adult height

traitgym-20261116-protocol-complex-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 "Adult height", column "Borzoi" (page 28)
Method: CADDProtocol: TraitGym Complex traits per trait, AUPRC, best of zero-shot and linear probing
Dataset subset: TraitGym Complex traits: Adult height
0.407 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 checked
Methods, coverage and source

CADD on TraitGym Complex traits, trait Adult height

traitgym-20261116-protocol-complex-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 "Adult height", column "CADD" (page 28)
Method: CADD+GPN-MSA+Borzoi logistic regression ensembleProtocol: TraitGym Complex traits per trait, AUPRC, best of zero-shot and linear probing
Dataset subset: TraitGym Complex traits: Adult height
0.339 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 checked
Methods, coverage and source

Ensemble on TraitGym Complex traits, trait Adult height

traitgym-20261116-protocol-complex-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 "Adult height", column "Ensemble" (page 28)
Model: GPN-MSAProtocol: TraitGym Complex traits per trait, AUPRC, best of zero-shot and linear probing
Dataset subset: TraitGym Complex traits: Adult height
0.383 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 checked
Methods, coverage and source

GPN-MSA on TraitGym Complex traits, trait Adult height

traitgym-20261116-protocol-complex-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 "Adult height", column "GPN-MSA" (page 28)
Model: BorzoiProtocol: TraitGym Complex traits per trait, AUPRC, best of zero-shot and linear probing
Dataset subset: TraitGym Complex traits: Albumin
0.615 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 checked
Methods, coverage and source

Borzoi on TraitGym Complex traits, trait Albumin

traitgym-20261116-protocol-complex-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 "Albumin", column "Borzoi" (page 28)
Method: CADDProtocol: TraitGym Complex traits per trait, AUPRC, best of zero-shot and linear probing
Dataset subset: TraitGym Complex traits: Albumin
0.48 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 checked
Methods, coverage and source

CADD on TraitGym Complex traits, trait Albumin

traitgym-20261116-protocol-complex-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 "Albumin", column "CADD" (page 28)
Method: CADD+GPN-MSA+Borzoi logistic regression ensembleProtocol: TraitGym Complex traits per trait, AUPRC, best of zero-shot and linear probing
Dataset subset: TraitGym Complex traits: Albumin
0.602 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 checked
Methods, coverage and source

Ensemble on TraitGym Complex traits, trait Albumin

traitgym-20261116-protocol-complex-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 "Albumin", column "Ensemble" (page 28)
Model: BorzoiProtocol: TraitGym Complex traits per trait, AUPRC, best of zero-shot and linear probing
Dataset subset: TraitGym Complex traits: Albumin/Globulin ratio
0.455 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 checked
Methods, coverage and source

Borzoi on TraitGym Complex traits, trait Albumin/Globulin ratio

traitgym-20261116-protocol-complex-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 "Albumin/Globulin ratio", column "Borzoi" (page 28)
Method: CADDProtocol: TraitGym Complex traits per trait, AUPRC, best of zero-shot and linear probing
Dataset subset: TraitGym Complex traits: Albumin/Globulin ratio
0.516 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 checked
Methods, coverage and source

CADD on TraitGym Complex traits, trait Albumin/Globulin ratio

traitgym-20261116-protocol-complex-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 "Albumin/Globulin ratio", column "CADD" (page 28)
Method: CADD+GPN-MSA+Borzoi logistic regression ensembleProtocol: TraitGym Complex traits per trait, AUPRC, best of zero-shot and linear probing
Dataset subset: TraitGym Complex traits: Albumin/Globulin ratio
0.559 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 checked
Methods, coverage and source

Ensemble on TraitGym Complex traits, trait Albumin/Globulin ratio

traitgym-20261116-protocol-complex-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 "Albumin/Globulin ratio", column "Ensemble" (page 28)
Model: GPN-MSAProtocol: TraitGym Complex traits per trait, AUPRC, best of zero-shot and linear probing
Dataset subset: TraitGym Complex traits: Albumin/Globulin ratio
0.431 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 checked
Methods, coverage and source

GPN-MSA on TraitGym Complex traits, trait Albumin/Globulin ratio

traitgym-20261116-protocol-complex-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 "Albumin/Globulin ratio", column "GPN-MSA" (page 28)
Model: GPN-MSAProtocol: TraitGym Complex traits per trait, AUPRC, best of zero-shot and linear probing
Dataset subset: TraitGym Complex traits: Albumin
0.544 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 checked
Methods, coverage and source

GPN-MSA on TraitGym Complex traits, trait Albumin

traitgym-20261116-protocol-complex-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 "Albumin", column "GPN-MSA" (page 28)
Model: BorzoiProtocol: TraitGym Complex traits per trait, AUPRC, best of zero-shot and linear probing
Dataset subset: TraitGym Complex traits: Alkaline phosphatase
0.492 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 checked
Methods, coverage and source

Borzoi on TraitGym Complex traits, trait Alkaline phosphatase

traitgym-20261116-protocol-complex-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 "Alkaline phosphatase", column "Borzoi" (page 28)
Method: CADDProtocol: TraitGym Complex traits per trait, AUPRC, best of zero-shot and linear probing
Dataset subset: TraitGym Complex traits: Alkaline phosphatase
0.352 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 checked
Methods, coverage and source

CADD on TraitGym Complex traits, trait Alkaline phosphatase

traitgym-20261116-protocol-complex-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 "Alkaline phosphatase", column "CADD" (page 28)
Method: CADD+GPN-MSA+Borzoi logistic regression ensembleProtocol: TraitGym Complex traits per trait, AUPRC, best of zero-shot and linear probing
Dataset subset: TraitGym Complex traits: Alkaline phosphatase
0.446 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 checked
Methods, coverage and source

Ensemble on TraitGym Complex traits, trait Alkaline phosphatase

traitgym-20261116-protocol-complex-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 "Alkaline phosphatase", column "Ensemble" (page 28)
Model: GPN-MSAProtocol: TraitGym Complex traits per trait, AUPRC, best of zero-shot and linear probing
Dataset subset: TraitGym Complex traits: Alkaline phosphatase
0.292 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 checked
Methods, coverage and source

GPN-MSA on TraitGym Complex traits, trait Alkaline phosphatase

traitgym-20261116-protocol-complex-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 "Alkaline phosphatase", column "GPN-MSA" (page 28)
Model: BorzoiProtocol: TraitGym Complex traits per trait, AUPRC, best of zero-shot and linear probing
Dataset subset: TraitGym Complex traits: Balding Type 4
0.459 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 checked
Methods, coverage and source

Borzoi on TraitGym Complex traits, trait Balding Type 4

traitgym-20261116-protocol-complex-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 "Balding Type 4", column "Borzoi" (page 28)
Method: CADDProtocol: TraitGym Complex traits per trait, AUPRC, best of zero-shot and linear probing
Dataset subset: TraitGym Complex traits: Balding Type 4
0.414 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 checked
Methods, coverage and source

CADD on TraitGym Complex traits, trait Balding Type 4

traitgym-20261116-protocol-complex-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 "Balding Type 4", column "CADD" (page 28)
Method: CADD+GPN-MSA+Borzoi logistic regression ensembleProtocol: TraitGym Complex traits per trait, AUPRC, best of zero-shot and linear probing
Dataset subset: TraitGym Complex traits: Balding Type 4
0.625 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 checked
Methods, coverage and source

Ensemble on TraitGym Complex traits, trait Balding Type 4

traitgym-20261116-protocol-complex-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 "Balding Type 4", column "Ensemble" (page 28)
Model: GPN-MSAProtocol: TraitGym Complex traits per trait, AUPRC, best of zero-shot and linear probing
Dataset subset: TraitGym Complex traits: Balding Type 4
0.536 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 checked
Methods, coverage and source

GPN-MSA on TraitGym Complex traits, trait Balding Type 4

traitgym-20261116-protocol-complex-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 "Balding Type 4", column "GPN-MSA" (page 28)
Model: BorzoiProtocol: TraitGym Complex traits per trait, AUPRC, best of zero-shot and linear probing
Dataset subset: TraitGym Complex traits: Blood clot in the leg
0.574 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 checked
Methods, coverage and source

Borzoi on TraitGym Complex traits, trait Blood clot in the leg

traitgym-20261116-protocol-complex-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 "Blood clot in the leg", column "Borzoi" (page 28)
Method: CADDProtocol: TraitGym Complex traits per trait, AUPRC, best of zero-shot and linear probing
Dataset subset: TraitGym Complex traits: Blood clot in the leg
0.498 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 checked
Methods, coverage and source

CADD on TraitGym Complex traits, trait Blood clot in the leg

traitgym-20261116-protocol-complex-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 "Blood clot in the leg", column "CADD" (page 28)
Method: CADD+GPN-MSA+Borzoi logistic regression ensembleProtocol: TraitGym Complex traits per trait, AUPRC, best of zero-shot and linear probing
Dataset subset: TraitGym Complex traits: Blood clot in the leg
0.565 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 checked
Methods, coverage and source

Ensemble on TraitGym Complex traits, trait Blood clot in the leg

traitgym-20261116-protocol-complex-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 "Blood clot in the leg", column "Ensemble" (page 28)
Model: GPN-MSAProtocol: TraitGym Complex traits per trait, AUPRC, best of zero-shot and linear probing
Dataset subset: TraitGym Complex traits: Blood clot in the leg
0.551 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 checked
Methods, coverage and source

GPN-MSA on TraitGym Complex traits, trait Blood clot in the leg

traitgym-20261116-protocol-complex-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 "Blood clot in the leg", column "GPN-MSA" (page 28)
Model: BorzoiProtocol: TraitGym Complex traits per trait, AUPRC, best of zero-shot and linear probing
Dataset subset: TraitGym Complex traits: Body mass index
0.344 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 checked
Methods, coverage and source

Borzoi on TraitGym Complex traits, trait Body mass index

traitgym-20261116-protocol-complex-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 "Body mass index", column "Borzoi" (page 28)

Source checking is not independent reproduction. Release 2026-11-21-adc15377fab2.

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
72

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

Null control

Proposed control: requires review

Protocol-valid seeded random ranking; no fitting on assay labels

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

Established label-free reference with explicitly permitted sequence/MSA inputs

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 2026-11-21-adc15377fab2. 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.

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-adc15377fab2
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-adc15377fab2 · 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 traitgym-20261116-protocol-complex-per-trait-best-of-zero-shot-and-linear-probing.

Source locator: Table S11, Complex traits block (page 28)

Related records

Suggest a correction