Protein secondary structure prediction by using deep learning method

Abstract

The prediction of protein structures directly from amino acid sequences is one of the biggest challenges in computational biology. It can be divided into several independent sub-problems in which protein secondary structure (SS) prediction is fundamental. Many computational methods have been proposed for SS prediction problem. Few of them can model well both the sequence-structure mapping relationship between input protein features and SS, and the interaction relationship among residues which are both important for SS prediction. In this paper, we proposed a deep recurrent encoder-decoder networks called Secondary Structure Recurrent Encoder-Decoder Networks (SSREDNs) to solve this SS prediction problem. Deep architecture and recurrent structures are employed in the SSREDNs to model both the complex nonlinear mapping relationship between input protein features and SS, and the mutual interaction among continuous residues of the protein chain. A series of techniques are also used in this paper to refine the model’s performance. The proposed model is applied to the open dataset CullPDB and CB513. Experimental results demonstrate that our method can improve both Q3 and Q8 accuracy compared with some public available methods. For Q8 prediction problem, it achieves 68.20% and 73.1% accuracy on CB513 and CullPDB dataset in fewer epochs better than ∗Hua Mao Email addresses: mellowxu@gmail.com (Yangxu Wang), huamao@scu.edu.cn (Hua Mao), zhangyi@scu.edu.cn (Zhang Yi) This work was supported by the National Science Foundation of China (Grant No. 61432012 and 61402306). Preprint submitted to Journal of Knowledge-Based Systems November 17, 2016

DOI: 10.1016/j.knosys.2016.11.015

8 Figures and Tables

Cite this paper

@article{Wang2017ProteinSS, title={Protein secondary structure prediction by using deep learning method}, author={Yangxu Wang and Hua Mao and Zhang Yi}, journal={Knowl.-Based Syst.}, year={2017}, volume={118}, pages={115-123} }