Protein Structure Prediction in the 3D HP Model Using Deep Reinforcement Learning

TL;DR

This paper introduces two deep reinforcement learning architectures for predicting protein structures in the 3D HP model, improving training efficiency and accuracy for different protein lengths.

Contribution

It presents novel hybrid and LSTM-based deep learning models with reinforcement learning for protein structure prediction in the 3D HP lattice model.

Findings

Hybrid reservoir-based model reduces training episodes by 25%.

LSTM with attention matches best-known energy values.

Both models outperform existing methods in efficiency and accuracy.

Abstract

We address protein structure prediction in the 3D Hydrophobic-Polar lattice model through two novel deep learning architectures. For proteins under 36 residues, our hybrid reservoir-based model combines fixed random projections with trainable deep layers, achieving optimal conformations with 25% fewer training episodes. For longer sequences, we employ a long short-term memory network with multi-headed attention, matching best-known energy values. Both architectures leverage a stabilized Deep Q-Learning framework with experience replay and target networks, demonstrating consistent achievement of optimal conformations while significantly improving training efficiency compared to existing methods.