FlowPacker: Protein side-chain packing with torsional flow matching

Jin Sub Lee; Philip M Kim

doi:10.1093/bioinformatics/btaf010

FlowPacker: Protein side-chain packing with torsional flow matching

Bioinformatics. 2025 Jan 9:btaf010. doi: 10.1093/bioinformatics/btaf010. Online ahead of print.

Authors

Jin Sub Lee¹, Philip M Kim^{1

2}

Affiliations

¹ Department of Molecular Genetics, University of Toronto, Ontario, M5S 3K3, Canada.
² Department of Computer Science, University of Toronto, Ontario, M5S 2E4, Canada.

PMID: 39786861
DOI: 10.1093/bioinformatics/btaf010

Abstract

Motivation: Accurate prediction of protein side-chain conformations is necessary to understand protein folding, protein-protein interactions and facilitate de novo protein design.

Results: Here we apply torsional flow matching and equivariant graph attention to develop FlowPacker, a fast and performant model to predict protein side-chain conformations conditioned on the protein sequence and backbone. We show that FlowPacker outperforms previous state-of-the-art baselines across most metrics with improved runtime. We further show that FlowPacker can be used to inpaint missing side-chain coordinates and also for multimeric targets, and exhibits strong performance on a test set of antibody-antigen complexes.

Availability: Code is available at https://gitlab.com/mjslee0921/flowpacker.

Supplementary information: Supplementary data are available at Bioinformatics online.

Keywords: deep learning; flow matching; protein structure prediction; side-chain packing.