IGPRED: Combination of convolutional neural and graph convolutional networks for protein secondary structure prediction

作     者：Gormez, Yasin Sabzekar, Mostafa Aydin, Zafer 

作者机构：Sivas Cumhuriyet Univ Fac Econ & Adm Sci Management Informat Syst Sivas Turkey Birjand Univ Technol Dept Comp Engn Birjand Iran Abdullah Gul Univ Comp Engn Dept Engn Fac Kayseri Turkey 

出 版 物：《PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS》 (蛋白质：结构、性能和生物信息学)

年 卷 期：2021年第89卷第10期

页      面：1277-1288页

核心收录：

学科分类：0710[理学-生物学] 071010[理学-生物化学与分子生物学] 07[理学] 

基　　金：National Center for High Performance Computing of Turkey (UHeM) 

主　　题：Bayesian optimization convolutional neural network deep learning graph convolutional network protein secondary structure prediction 

摘      要：There is a close relationship between the tertiary structure and the function of a protein. One of the important steps to determine the tertiary structure is protein secondary structure prediction (PSSP). For this reason, predicting secondary structure with higher accuracy will give valuable information about the tertiary structure. Recently, deep learning techniques have obtained promising improvements in several machine learning applications including PSSP. In this article, a novel deep learning model, based on convolutional neural network and graph convolutional network is proposed. PSIBLAST PSSM, HHMAKE PSSM, physico-chemical properties of amino acids are combined with structural profiles to generate a rich feature set. Furthermore, the hyper-parameters of the proposed network are optimized using Bayesian optimization. The proposed model IGPRED obtained 89.19%, 86.34%, 87.87%, 85.76%, and 86.54% Q3 accuracies for CullPDB, EVAset, CASP10, CASP11, and CASP12 datasets, respectively.