Applying Deep Reinforcement Learning to the HP Model for Protein Structure Prediction

2022-11-27 · Kaiyuan Yang, Houjing Huang, Olafs Vandans, Adithya Murali, Fujia Tian, Roland H. C. Yap, Liang Dai

A central problem in computational biophysics is protein structure prediction, i.e., finding the optimal folding of a given amino acid sequence. This problem has been studied in a classical abstract model, the HP model, where the protein is modeled as a sequence of H (hydrophobic) and P (polar) amino acids on a lattice. The objective is to find conformations maximizing H-H contacts. It is known that even in this reduced setting, the problem is intractable (NP-hard). In this work, we apply deep reinforcement learning (DRL) to the two-dimensional HP model. We can obtain the conformations of best known energies for benchmark HP sequences with lengths from 20 to 50. Our DRL is based on a deep Q-network (DQN). We find that a DQN based on long short-term memory (LSTM) architecture greatly enhances the RL learning ability and significantly improves the search process. DRL can sample the state space efficiently, without the need of manual heuristics. Experimentally we show that it can find multiple distinct best-known solutions per trial. This study demonstrates the effectiveness of deep reinforcement learning in the HP model for protein folding.

📄 PDF Abstract BibTeX arXiv:2211.14939

Code (1)

compsoftmatterbiophysics-cityu-hk/applying-drl-to-hp-model-for-protein-structure-prediction 공식 구현 pytorch

Tasks

Deep Reinforcement LearningProtein FoldingProtein Structure Prediction reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Q-Learning Q-Learning is an off-policy temporal difference control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} +…

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

DQN A DQN, or Deep Q-Network, approximates a state-value function in a Q-Learning framework with a neural network. In the Atari…

Structure-Informed Protein Language Model

2024-02-07 · Zuobai Zhang, Jiarui Lu, Vijil Chenthamarakshan, Aurélie Lozano 외

Protein language models are a powerful tool for learning protein representations through pre-training on vast protein sequence datasets. However, traditional protein language models lack explicit structural supervision, …

Language Modeling Language Modelling model Prediction+2

PersGNN: Applying Topological Data Analysis and Geometric Deep Learning to Structure-Based Protein Function Prediction

2020-10-30 · Nicolas Swenson, Aditi S. Krishnapriyan, Aydin Buluc, Dmitriy Morozov 외

Understanding protein structure-function relationships is a key challenge in computational biology, with applications across the biotechnology and pharmaceutical industries. While it is known that protein structure direc…

Graph Representation Learning Protein Function Prediction Representation Learning Topological Data Analysis

Integrating protein sequence embeddings with structure via graph-based deep learning for the prediction of single-residue properties

2025-02-24 · Kevin Michalewicz, Mauricio Barahona, Barbara Bravi

Understanding the intertwined contributions of amino acid sequence and spatial structure is essential to explain protein behaviour. Here, we introduce INFUSSE (Integrated Network Framework Unifying Structure and Sequence…

Large Language Model

FoldingZero: Protein Folding from Scratch in Hydrophobic-Polar Model

2018-12-03 · Yanjun Li, Hengtong Kang, Ketian Ye, Shuyu Yin 외

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-Pola…

Deep Reinforcement Learning Protein Folding Protein Structure Prediction reinforcement-learning+2

DeepFoldit -- A Deep Reinforcement Learning Neural Network Folding Proteins

2020-10-28 · Dimitra N. Panou, Martin Reczko

Despite considerable progress, ab initio protein structure prediction remains suboptimal. A crowdsourcing approach is the online puzzle video game Foldit, that provided several useful results that matched or even outperf…

Deep Reinforcement Learning Protein Structure Prediction Q-Learning reinforcement-learning+2