An end-to-end deep learning method for protein side-chain packing and inverse folding

Protein side-chain packing (PSCP), the task of determining amino acid side-chain conformations given only backbone atom positions, has important applications to protein structure prediction, refinement, and design. Many methods have been proposed to tackle this problem, but their speed or accuracy is still unsatisfactory. To address this, we present AttnPacker, a deep learning (DL) method for directly predicting protein side-chain coordinates. Unlike existing methods, AttnPacker directly incorporates backbone 3D geometry to simultaneously compute all side -chain coordinates without delegating to a discrete rotamer library or performing expensive conformational search and sampling steps. This enables a significant increase in computational efficiency, decreasing inference time by over 100x compared to the DL-based method DLPacker and physics-based RosettaPacker. Tested on the CASP13 and CASP14 native and nonnative protein backbones, AttnPacker computes physically realistic side-chain conformations, reducing steric clashes and improving both rmsd and dihedral accuracy compared to state-of-the-art methods SCWRL4, FASPR, RosettaPacker, and DLPacker. Different from traditional PSCP approaches, AttnPacker can also codesign sequences and side chains, producing designs with subnative Rosetta energy and high in silico consistency.SignificanceAll amino acids are bound to unique chemical groups (side chains), which interact to facilitate protein folding. Thus, accurate modeling of protein side-chain conformations is essential for accurate protein structure prediction and design. Although many methods have been proposed to address this problem, their performance often suffers from simplified modeling assumptions or long inference times. This work provides a fast and precise machine learning approach that jointly models side-chain interactions and directly predicts physically realistic packings, having few atom clashes and ideal bond lengths and angles. Compared to existing methods, our approach exhibits improved accuracy and efficiency for both native and nonnative backbone structures.

Automated summary

Protein side-chain packing is important for predicting, refining, and designing protein structures. Existing methods for this task are not satisfactory in terms of speed and accuracy. AttnPacker is a deep learning method that directly predicts protein side-chain coordinates, incorporating backbone 3D geometry to improve computational efficiency. It produces physically realistic side-chain conformations, reducing steric clashes and improving accuracy compared to state-of-the-art methods.