RESEARCH ARTICLE


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
1 Department of Microbiology, Constantine 1 University, Constantine, Algeria
2 Department of Applied Biology, Constantine 1 University, Constantine, Algeria
3 Department of Informatique, Université Constantine 2, Constantine, Algeria


Article Metrics

CrossRef Citations:
0
Total Statistics:

Full-Text HTML Views: 936
Abstract HTML Views: 681
PDF Downloads: 357
ePub Downloads: 179
Total Views/Downloads: 2153
Unique Statistics:

Full-Text HTML Views: 597
Abstract HTML Views: 241
PDF Downloads: 261
ePub Downloads: 141
Total Views/Downloads: 1240



Creative Commons License
© 2023 Boulahrouf et al.

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.

* Address correspondence to this author at the Microbiology, Constantine 1 University, Constantine, Algeria; E-mail: khaled.boulahrouf@umc.edu.dz


Abstract

Introduction:

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.

Methods:

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.

Results:

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.

Conclusion:

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.

Keywords: Bioinformatics, Enzyme function prediction, EC number, Deep learning, Sequence analysis, Convolutional neural network, Enzyme classification.