Protocol

Prediction of Protein Secondary Structure

Volume 1484 of the series Methods in Molecular Biology pp 55-63

Date:

SPIDER2: A Package to Predict Secondary Structure, Accessible Surface Area, and Main-Chain Torsional Angles by Deep Neural Networks

  • Yuedong YangAffiliated withInstitute for Glycomics and School of Information and Communication Technology, Griffith University
  • , Rhys HeffernanAffiliated withSignal Processing Laboratory, School of Engineering, Griffith University
  • , Kuldip PaliwalAffiliated withSignal Processing Laboratory, School of Engineering, Griffith University
  • , James LyonsAffiliated withSignal Processing Laboratory, School of Engineering, Griffith University
  • , Abdollah DehzangiAffiliated withDepartment of Psychiatry, Medical Research Center, University of Iowa
  • , Alok SharmaAffiliated withInstitute for Integrated and Intelligent Systems, Griffith UniversitySchool of Engineering and Physics, University of the South Pacific
  • , Jihua WangAffiliated withShandong Provincial Key Laboratory of Functional Macromolecular Biophysics, Dezhou University
  • , Abdul SattarAffiliated withInstitute for Integrated and Intelligent Systems, Griffith UniversityNational ICT Australia (NICTA)
  • , Yaoqi ZhouAffiliated withInstitute for Glycomics and School of Information and Communication Technology, Griffith University Email author 

* Final gross prices may vary according to local VAT.

Get Access

Abstract

Predicting one-dimensional structure properties has played an important role to improve prediction of protein three-dimensional structures and functions. The most commonly predicted properties are secondary structure and accessible surface area (ASA) representing local and nonlocal structural characteristics, respectively. Secondary structure prediction is further complemented by prediction of continuous main-chain torsional angles. Here we describe a newly developed method SPIDER2 that utilizes three iterations of deep learning neural networks to improve the prediction accuracy of several structural properties simultaneously. For an independent test set of 1199 proteins SPIDER2 achieves 82 % accuracy for secondary structure prediction, 0.76 for the correlation coefficient between predicted and actual solvent accessible surface area, 19° and 30° for mean absolute errors of backbone φ and ψ angles, respectively, and 8° and 32° for mean absolute errors of Cα-based θ and τ angles, respectively. The method provides state-of-the-art, all-in-one accurate prediction of local structure and solvent accessible surface area. The method is implemented, as a webserver along with a standalone package that are available in our website: http://​sparks-lab.​org.

Key words

Secondary structure prediction Solvent accessible surface area Backbone torsion angles Deep neural networks C alpha-based angles