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

GÖRMEZ Y., Sabzekar M., AYDIN Z.

PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS, vol.89, no.10, pp.1277-1288, 2021 (SCI-Expanded) identifier identifier identifier

  • Publication Type: Article / Article
  • Volume: 89 Issue: 10
  • Publication Date: 2021
  • Doi Number: 10.1002/prot.26149
  • Journal Name: PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, BIOSIS, Biotechnology Research Abstracts, CAB Abstracts, Chemical Abstracts Core, EMBASE, Food Science & Technology Abstracts, INSPEC, MEDLINE, Veterinary Science Database
  • Page Numbers: pp.1277-1288
  • Keywords: Bayesian optimization, convolutional neural network, deep learning, graph convolutional network, protein secondary structure prediction
  • Abdullah Gül University Affiliated: Yes

Abstract

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.