EZYDeep: A Deep Learning Tool for Enzyme Function Prediction based on Sequence Information
Khaled Boulahrouf1, *, Salah Eddine Aliouane2, Hamza Chehili2, Mohamed Skander Daas2, Adel Belbekri3, Mohamed Abdelhafid Hamidechi2
Identifiers and Pagination:Year: 2023
E-location ID: e187503622306270
Publisher ID: e187503622306270
Article History:Received Date: 20/02/2023
Revision Received Date: 19/05/2023
Acceptance Date: 07/06/2023
Electronic publication date: 14/07/2023
Collection year: 2023
open-access license: This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International Public License (CC-BY 4.0), a copy of which is available at: https://creativecommons.org/licenses/by/4.0/legalcode. This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Enzymes play a crucial role in numerous chemical processes that are essential for life. Accurate prediction and classification of enzymes are crucial for bioindustrial and biomedical applications.
In this study, we present EZYDeep, a deep learning tool based on convolutional neural networks, for classifying enzymes based on their sequence information. The tool was evaluated against two existing methods, HECNet and DEEPre, on the HECNet July 2019 dataset, and showed exceptional performance with accuracy rates over 95% at all four levels of prediction.
Additionally, our tool was compared to state-of-the-art enzyme function prediction tools and demonstrated superior performance at all levels of prediction. We also developed a user-friendly web application for the tool, making it easily accessible to researchers and practitioners.
Our work demonstrates the potential of using machine learning techniques for accurate and efficient enzyme classification, highlighting the significance of sequence information in predicting enzyme function.