Predicting protein-peptide binding sites with a deep convolutional neural network. (7th July 2020)

• Record Type: Journal Article
• Authors: Wardah, Wafaa; Dehzangi, Abdollah; Taherzadeh, Ghazaleh; Rashid, Mahmood A.; Khan, M.G.M.; Tsunoda, Tatsuhiko; Sharma, Alok
• Is Part Of: Journal of theoretical biology. Volume 496(2020)
• Publication Date: 2020-07-07
• Subjects: Protein-peptide binding -- Artificial intelligence -- Deep learning -- Convolutional neural network -- Protein sequence; Biology -- Periodicals; Biological Science Disciplines -- Periodicals; Biology -- Periodicals; Biologie -- Périodiques; Theoretische biologie; Biology; Periodicals; 571.05
• DOI: 10.1016/j.jtbi.2020.110278
• Languages: English
• ISSNs: 0022-5193

Abstract

Graphical abstract: 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. Results: We found that our approach achieves 67% sensitivity or recall (true positive rate) surpassing existing methods by over 35%.