Predicting protein-peptide binding sites with a deep convolutional neural network.

Journal: Journal of theoretical biology
Published Date:

Abstract

MOTIVATION: Interactions between proteins and peptides influence biological functions. Predicting such bio-molecular interactions can lead to faster disease prevention and help in drug discovery. Experimental methods for determining protein-peptide binding sites are costly and time-consuming. Therefore, computational methods have become prevalent. However, existing models show extremely low detection rates of actual peptide binding sites in proteins. To address this problem, we employed a two-stage technique - first, we extracted the relevant features from protein sequences and transformed them into images applying a novel method and then, we applied a convolutional neural network to identify the peptide binding sites in proteins.

Authors

  • Wafaa Wardah
    School of Computing, Information and Mathematical Sciences, The University of the South Pacific, Suva, Fiji.
  • Abdollah Dehzangi
    1] Signal Processing Laboratory, School of Engineering, Griffith University, Brisbane, Australia [2] Institute for Integrated and Intelligent Systems, Griffith University, Brisbane, Australia.
  • Ghazaleh Taherzadeh
    School of Information and Communication Technology, Griffith University, Parklands Drive, Southport, Queensland, 4215, Australia.
  • Mahmood A Rashid
    Institute for Sustainable Industries and Liveable Cities, Victoria University Melbourne, Victoria, Australia; Institute for Integrated and Intelligent Systems, Griffith University, Queensland, Australia. Electronic address: mahmood.rashid@griffith.edu.au.
  • M G M Khan
    School of Computing, Information and Mathematical Sciences, The University of the South Pacific, Suva, Fiji.
  • Tatsuhiko Tsunoda
    Center for Integrative Medical Sciences, RIKEN Yokohama, Yokohama, 230-0045, Japan. tatsuhiko.tsunoda@riken.jp.
  • Alok Sharma
    Center for Integrative Medical Sciences, RIKEN Yokohama, Yokohama, 230-0045, Japan.