---
title: ProteinGym_v1
description: ProteinGym is a benchmark suite for evaluating protein fitness prediction and design models. It includes both substitution and indel mutations, a wide variety of experimentally assayed proteins, and clinically annotated mutations that are relevant to human disease. In total, ProteinGym includes nearly 3 million different
tags:
- benchmark
- biology
- deep-learning
- dms
- protein
- protein-fitness
source_url: https://huggingface.co/datasets/OATML-Markslab/ProteinGym_v1
---

# ProteinGym_v1

> **Mirrored metadata.** This card is reproduced on Atlas for discovery. The artifact itself is not hosted here — follow the source link for the files, and refer to the upstream licence for terms of use.

ProteinGym is a benchmark suite for evaluating protein fitness prediction and design models. It includes both substitution and indel mutations, a wide variety of experimentally assayed proteins, and clinically annotated mutations that are relevant to human disease. In total, ProteinGym includes nearly 3 million different

Upstream identifier: `OATML-Markslab/ProteinGym_v1`.

**Source:** https://huggingface.co/datasets/OATML-Markslab/ProteinGym_v1

_This dataset is part of the Atlas demo catalogue. See the repository history for provenance._