FoldingZero: Protein Folding from Scratch in Hydrophobic-Polar Model

TL;DR

FoldingZero is a deep reinforcement learning framework that predicts 2D protein structures in the HP model from scratch, learning folding patterns without supervision and showing potential for real-world applications.

Contribution

It introduces a novel RL-based method combining a neural network and R-UCT for de novo protein folding in the HP model, without supervision or domain knowledge.

Findings

Achieves comparable results to existing methods

Learns latent folding knowledge to stabilize structures

Shows potential for real-world protein property prediction

Abstract

De novo protein structure prediction from amino acid sequence is one of the most challenging problems in computational biology. As one of the extensively explored mathematical models for protein folding, Hydrophobic-Polar (HP) model enables thorough investigation of protein structure formation and evolution. Although HP model discretizes the conformational space and simplifies the folding energy function, it has been proven to be an NP-complete problem. In this paper, we propose a novel protein folding framework FoldingZero, self-folding a de novo protein 2D HP structure from scratch based on deep reinforcement learning. FoldingZero features the coupled approach of a two-head (policy and value heads) deep convolutional neural network (HPNet) and a regularized Upper Confidence Bounds for Trees (R-UCT). It is trained solely by a reinforcement learning algorithm, which improves HPNet and R-UCT iteratively through iterative policy optimization. Without any supervision and domain knowledge, FoldingZero not only achieves comparable results, but also learns the latent folding knowledge to stabilize the structure. Without exponential computation, FoldingZero shows promising potential to be adopted for real-world protein properties prediction.