Invariant point message passing for protein side chain packing

Abstract

Protein side chain packing (PSCP) is a fundamental problem in the field of protein engineering, as high confidence and low energy conformations of amino acid side chains are crucial for understanding (and designing) protein folding, protein-protein interactions, and protein-ligand interactions. Traditional PSCP methods (such as the Rosetta Packer) often rely on a library of discrete side chain conformations, or rotamers, and a forcefield to guide the structure to low energy conformations. Recently, deep learning (DL) based methods (such as DLPacker, AttnPacker, and DiffPack) have demonstrated state-of-the-art predictions and speed in the PSCP task. Building off the success of graph and message passing neural networks for protein modeling, we present the Protein Invariant Point Packer (PIPPack) which effectively processes local structural and sequence information to produce realistic, idealized side chain coordinates using 𝜒-angle distribution predictions and geometry-aware invariant point message passing (IPMP). To demonstrate its broad applicability to protein-related tasks, IPMP was additionally incorporated in a fixed backbone protein design method, which enabled the generation of more native-like sequences than common message passing schemes. On a test set of ∼1,400 high-quality protein chains, PIPPack performs competitively with other state-of-the-art PSCP methods in rotamer recovery and per-residue RMSDs but is significantly faster.

FlowPacker: Protein side-chain packing with torsional flow matching

“…However, these methods are often ineffective due to inefficient search algorithms and the reliance of often inaccurate scoring functions that converge to suboptimal local minima. Recent deep learning-based methods have shown significant improvements in runtime and efficacy to physicsbased modeling in side-chain packing [8,9,10,11], the most notable of which is DiffPack [10], a torsional diffusion model that autoregressively generates the four χ torsion angles that constitute the only degrees of freedom for side-chain conformations. DiffPack presents a number of innovations, such as autoregressive generation and confidence sampling, to attain state-of-the-art performance in protein side-chain packing.…”