ProteinShake: Building datasets and benchmarks for deep learning on protein structures

Part of Advances in Neural Information Processing Systems 36 (NeurIPS 2023) Datasets and Benchmarks Track

Bibtex Paper Supplemental

Authors

Tim Kucera, Carlos Oliver, Dexiong Chen, Karsten Borgwardt

Abstract

We present ProteinShake, a Python software package that simplifies datasetcreation and model evaluation for deep learning on protein structures. Users cancreate custom datasets or load an extensive set of pre-processed datasets fromthe Protein Data Bank (PDB) and AlphaFoldDB. Each dataset is associated withprediction tasks and evaluation functions covering a broad array of biologicalchallenges. A benchmark on these tasks shows that pre-training almost alwaysimproves performance, the optimal data modality (graphs, voxel grids, or pointclouds) is task-dependent, and models struggle to generalize to new structures.ProteinShake makes protein structure data easily accessible and comparisonamong models straightforward, providing challenging benchmark settings withreal-world implications.ProteinShake is available at: https://proteinshake.ai