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.
@article{arxiv.2412.20329,
title = {Protein Structure Prediction in the 3D HP Model Using Deep Reinforcement Learning},
author = {Giovanny Espitia and Yui Tik Pang and James C. Gumbart},
journal= {arXiv preprint arXiv:2412.20329},
year = {2024}
}