Oral
in
Workshop: Machine Learning in Structural Biology
FlowPacker: protein side-chain packing with torsional flow matching
Jin Sub Lee · Philip Kim
[
Abstract
]
presentation:
Machine Learning in Structural Biology
Sun 15 Dec 8:30 a.m. PST — 5 p.m. PST
Sun 15 Dec 2:20 p.m. PST
— 2:35 p.m. PST
Sun 15 Dec 8:30 a.m. PST — 5 p.m. PST
Abstract:
Accurate prediction of protein side-chain conformations is necessary to understand protein folding, protein-protein interactions and facilitate de novo protein design. 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.
Chat is not available.