arXiv Open Access 2024

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

Giovanny Espitia Yui Tik Pang James C. Gumbart

Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

cs.LG cs.AI q-bio.BM

Penulis (3)

Giovanny Espitia

Yui Tik Pang

James C. Gumbart

Format Sitasi

APA MLA BibTeX

Espitia, G., Pang, Y.T., Gumbart, J.C. (2024). Protein Structure Prediction in the 3D HP Model Using Deep Reinforcement Learning. https://arxiv.org/abs/2412.20329

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2024
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓