Datasets

ProteinGym is a benchmark suite for evaluating protein fitness prediction and design models.

Dataset artifact mirrored from the HuggingFace Hub.

Complete UniRef90 dataset from UniProt, converted from XML to sharded Parquet.

Official repository for the ProteinGym benchmarks

A collection of tasks to probe the effectiveness of protein sequence representations in modeling aspects of protein design

Tasks Assessing Protein Embeddings (TAPE), a set of five biologically relevant semi-supervised learning tasks spread across different domains of protein…

PEER Benchmark, appear at NeurIPS 2022 Dataset and Benchmark Track (https://arxiv.org/abs/2206.02096)

Plausibility checks for generated molecule poses.

The Protein Data Bank is the single worldwide archive of structural data of biological macromolecules.

The UniProt Knowledgebase (UniProtKB) is a comprehensive resource for protein sequence and functional information with extensive cross-references to more than…