Abstract
BackgroundProtein structure prediction has always been an important issue in bioinformatics. Prediction of the two-dimensional structure of proteins based on the hydrophobic polarity model is a typical non-deterministic polynomial hard problem. Currently reported hydrophobic polarity model optimization methods, greedy method, brute-force method, and genetic algorithm usually cannot converge robustly to the lowest energy conformations. Reinforcement learning with the advantages of continuous Markov optimal decision-making and maximizing global cumulative return is especially suitable for solving global optimization problems of biological sequences.ResultsIn this study, we proposed a novel hydrophobic polarity model optimization method derived from reinforcement learning which structured the full state space, and designed an energy-based reward function and a rigid overlap detection rule. To validate the performance, sixteen sequences were selected from the classical data set. The results indicated that reinforcement learning with full states successfully converged to the lowest energy conformations against all sequences, while the reinforcement learning with partial states folded 50% sequences to the lowest energy conformations. Reinforcement learning with full states hits the lowest energy on an average 5 times, which is 40 and 100% higher than the three and zero hit by the greedy algorithm and reinforcement learning with partial states respectively in the last 100 episodes.ConclusionsOur results indicate that reinforcement learning with full states is a powerful method for predicting two-dimensional hydrophobic-polarity protein structure. It has obvious competitive advantages compared with greedy algorithm and reinforcement learning with partial states.
Highlights
Protein structure prediction has always been an important issue in bioinformatics
The most typical one is the two-dimensional hydrophobic-polarity (2D-hydrophobic polarity (HP)) grid model proposed by Dill et al [23]
According to the differences in the hydrophilicity and hydrophobicity of each type of amino acid, they are divided into two categories: one is a hydrophobic amino acid, and the other is a hydrophilic amino acid, so any protein chain can be expressed as a finite-length string of H and P [24, 25]
Summary
Protein structure prediction has always been an important issue in bioinformatics. Prediction of the two-dimensional structure of proteins based on the hydrophobic polarity model is a typical non-deterministic polynomial hard problem. Reported hydrophobic polarity model optimization methods, greedy method, brute-force method, and genetic algorithm usually cannot converge robustly to the lowest energy conformations. The biological function of proteins is determined by their spatial folding structure. The HP model is a widely studied simplified protein folding model with high confidence in the prediction of the protein helical structure. In this model, each amino acid is treated either hydrophobic (H) or hydrophilic (P) and represented as a point on a two-dimensional lattice structure. The rationale behind the HP model is that the hydrophobicity of
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have