← Datasets & benchmarks

ProteinGym

Benchmarks for protein fitness and mutation effect prediction.

Visit website ↗

CategoryDatasets & benchmarks
GitHubOATML-Markslab/ProteinGym
First public2023-12-08 (source)
Paperhttps://www.biorxiv.org/content/10.1101/2023.12.07.570727
LicenseMIT
PricingOpen source
Tags#benchmark
Last checked2026-10-16

Specs

Size250+ DMS assays, millions of mutated sequences + clinical sets
ModalityProtein fitness / mutation effects
AccessOpen (MIT code; downloadable benchmarks)
GitHub stars478
InterfaceDocker

Specs come from each project's README, paper or official page · ProteinGym README · ProteinGym paper. “—” means we couldn't verify it.

Compare with…

Pick 1–3 other Datasets & benchmarks tools to compare side by side with ProteinGym.

Select 1–3 tools

Related

CZ CELLxGENE

Curated single-cell data portal and Census API with 100M+ cells.

Datasets & benchmarksOpen source#atlas#single-cell

Data portal of the Human Cell Atlas consortium.

Datasets & benchmarksOpen source#atlas

Tahoe-100M

100M-cell single-cell drug perturbation atlas.

Datasets & benchmarksOpen source#perturbation#dataset