AmoebaContact and GDFold: a new pipeline for rapid prediction of protein structures

TL;DR

This paper introduces AmoebaContact and GDFold, a novel pipeline that rapidly predicts protein structures by combining an optimized contact predictor with a differentiable folding algorithm, achieving quality comparable to current top methods.

Contribution

The paper presents a new pipeline integrating an automatically optimized contact predictor with a differentiable folding method for fast protein structure prediction.

Findings

Achieves rapid protein structure prediction with quality comparable to state-of-the-art methods.

Uses a novel neural network architecture optimized through automatic search.

Incorporates all predicted residue pairs in a differentiable loss for improved folding.

Abstract

Native contacts between residues could be predicted from the amino acid sequence of proteins, and the predicted contact information could assist the de novo protein structure prediction. Here, we present a novel pipeline of a residue contact predictor AmoebaContact and a contact-assisted folder GDFold for rapid protein structure prediction. Unlike mainstream contact predictors that utilize human-designed neural networks, AmoebaContact adopts a set of network architectures that are found as optimal for contact prediction through automatic searching and predicts the residue contacts at a series of cutoffs. Different from conventional contact-assisted folders that only use top-scored contact pairs, GDFold considers all residue pairs from the prediction results of AmoebaContact in a differentiable loss function and optimizes the atom coordinates using the gradient descent algorithm. Combination of AmoebaContact and GDFold allows quick reconstruction of the protein structure, with comparable model quality to the state-of-the-art protein structure prediction methods.