USP Electronic Research Repository

Predicting protein-peptide binding sites with a Deep Convolutional Neural Network

Wardah, Wafaa and Dehzangi, Abdollah and Taherzadeh, G. and Rashid, Mahmood and Khan, Mohammad G.M. and Tsunoda, Tatsuhiko and Sharma, Alokanand (2020) Predicting protein-peptide binding sites with a Deep Convolutional Neural Network. Journal of Theoretical Biology, 110278 . TBC. ISSN 0022-5193

Full text not available from this repository.

Abstract

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

Item Type: Journal Article
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
T Technology > TA Engineering (General). Civil engineering (General)
Divisions: Office of the DVC (ARC)
Depositing User: Fulori Nainoca
Date Deposited: 20 Apr 2020 16:08
Last Modified: 20 Apr 2020 16:08
URI: http://repository.usp.ac.fj/id/eprint/12096
UNSPECIFIED

Actions (login required)

View Item