Deep‐GB: A novel deep learning model for globular protein prediction using CNN‐BiLSTM architecture and enhanced PSSM with trisection strategy

Abstract Globular proteins (GPs) play vital roles in a wide range of biological processes, encompassing enzymatic catalysis and immune responses. Enzymes, among these globular proteins, facilitate biochemical reactions, while others, such as haemoglobin, contribute to essential physiological functio...

Full description

Saved in:
Bibliographic Details
Main Authors: Sonia Zouari, Farman Ali, Atef Masmoudi, Sarah Abu Ghazalah, Wajdi Alghamdi, Faris A. Kateb, Nouf Ibrahim
Format: Article
Language:English
Published: Wiley 2024-12-01
Series:IET Systems Biology
Subjects:
Online Access:https://doi.org/10.1049/syb2.12108
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850243582853644288
author Sonia Zouari
Farman Ali
Atef Masmoudi
Sarah Abu Ghazalah
Wajdi Alghamdi
Faris A. Kateb
Nouf Ibrahim
author_facet Sonia Zouari
Farman Ali
Atef Masmoudi
Sarah Abu Ghazalah
Wajdi Alghamdi
Faris A. Kateb
Nouf Ibrahim
author_sort Sonia Zouari
collection DOAJ
description Abstract Globular proteins (GPs) play vital roles in a wide range of biological processes, encompassing enzymatic catalysis and immune responses. Enzymes, among these globular proteins, facilitate biochemical reactions, while others, such as haemoglobin, contribute to essential physiological functions such as oxygen transport. Given the importance of these considerations, accurately identifying Globular proteins is essential. To address the need for precise GP identification, this research introduces an innovative approach that employs a hybrid‐based deep learning model called Deep‐GP. We generated two datasets based on primary sequences and developed a novel feature descriptor called, Consensus Sequence‐based Trisection‐Position Specific Scoring Matrix (CST‐PSSM). The model training phase involved the application of deep learning techniques, including the bidirectional long short‐term memory network (BiLSTM), gated recurrent unit (GRU), and convolutional neural network (CNN). The BiLSTM and CNN were hybridised for ensemble learning. The CST‐PSSM‐based ensemble model achieved the most accurate predictive outcomes, outperforming other competitive predictors across both training and testing datasets. This demonstrates the potential of harnessing deep learning for precise GB prediction as a robust tool to expedite research, streamline drug discovery, and unveil novel therapeutic targets.
format Article
id doaj-art-1051302e881d4e01917c8104d711ddba
institution OA Journals
issn 1751-8849
1751-8857
language English
publishDate 2024-12-01
publisher Wiley
record_format Article
series IET Systems Biology
spelling doaj-art-1051302e881d4e01917c8104d711ddba2025-08-20T01:59:57ZengWileyIET Systems Biology1751-88491751-88572024-12-0118620821710.1049/syb2.12108Deep‐GB: A novel deep learning model for globular protein prediction using CNN‐BiLSTM architecture and enhanced PSSM with trisection strategySonia Zouari0Farman Ali1Atef Masmoudi2Sarah Abu Ghazalah3Wajdi Alghamdi4Faris A. Kateb5Nouf Ibrahim6National Engineering School of Sfax University of Sfax Sfax TunisiaDepartment of Computer Science Bahria University Islamabad Campus Islamabad PakistanDepartment of Computer Science College of Computer Science King Khalid University Abha Saudi ArabiaDepartment of Informatics and Computer System College of Computer Science King Khalid University Abha Saudi ArabiaDepartment of Information Technology Faculty of Computing and Information Technology King Abdulaziz University Jeddah Saudi ArabiaDepartment of Information Technology Faculty of Computing and Information Technology King Abdulaziz University Jeddah Saudi ArabiaFamily Medicine Clinic Makkah Armed Force Medical Center Makkah Saudi ArabiaAbstract Globular proteins (GPs) play vital roles in a wide range of biological processes, encompassing enzymatic catalysis and immune responses. Enzymes, among these globular proteins, facilitate biochemical reactions, while others, such as haemoglobin, contribute to essential physiological functions such as oxygen transport. Given the importance of these considerations, accurately identifying Globular proteins is essential. To address the need for precise GP identification, this research introduces an innovative approach that employs a hybrid‐based deep learning model called Deep‐GP. We generated two datasets based on primary sequences and developed a novel feature descriptor called, Consensus Sequence‐based Trisection‐Position Specific Scoring Matrix (CST‐PSSM). The model training phase involved the application of deep learning techniques, including the bidirectional long short‐term memory network (BiLSTM), gated recurrent unit (GRU), and convolutional neural network (CNN). The BiLSTM and CNN were hybridised for ensemble learning. The CST‐PSSM‐based ensemble model achieved the most accurate predictive outcomes, outperforming other competitive predictors across both training and testing datasets. This demonstrates the potential of harnessing deep learning for precise GB prediction as a robust tool to expedite research, streamline drug discovery, and unveil novel therapeutic targets.https://doi.org/10.1049/syb2.12108bioinformaticsbiological techniques
spellingShingle Sonia Zouari
Farman Ali
Atef Masmoudi
Sarah Abu Ghazalah
Wajdi Alghamdi
Faris A. Kateb
Nouf Ibrahim
Deep‐GB: A novel deep learning model for globular protein prediction using CNN‐BiLSTM architecture and enhanced PSSM with trisection strategy
IET Systems Biology
bioinformatics
biological techniques
title Deep‐GB: A novel deep learning model for globular protein prediction using CNN‐BiLSTM architecture and enhanced PSSM with trisection strategy
title_full Deep‐GB: A novel deep learning model for globular protein prediction using CNN‐BiLSTM architecture and enhanced PSSM with trisection strategy
title_fullStr Deep‐GB: A novel deep learning model for globular protein prediction using CNN‐BiLSTM architecture and enhanced PSSM with trisection strategy
title_full_unstemmed Deep‐GB: A novel deep learning model for globular protein prediction using CNN‐BiLSTM architecture and enhanced PSSM with trisection strategy
title_short Deep‐GB: A novel deep learning model for globular protein prediction using CNN‐BiLSTM architecture and enhanced PSSM with trisection strategy
title_sort deep gb a novel deep learning model for globular protein prediction using cnn bilstm architecture and enhanced pssm with trisection strategy
topic bioinformatics
biological techniques
url https://doi.org/10.1049/syb2.12108
work_keys_str_mv AT soniazouari deepgbanoveldeeplearningmodelforglobularproteinpredictionusingcnnbilstmarchitectureandenhancedpssmwithtrisectionstrategy
AT farmanali deepgbanoveldeeplearningmodelforglobularproteinpredictionusingcnnbilstmarchitectureandenhancedpssmwithtrisectionstrategy
AT atefmasmoudi deepgbanoveldeeplearningmodelforglobularproteinpredictionusingcnnbilstmarchitectureandenhancedpssmwithtrisectionstrategy
AT sarahabughazalah deepgbanoveldeeplearningmodelforglobularproteinpredictionusingcnnbilstmarchitectureandenhancedpssmwithtrisectionstrategy
AT wajdialghamdi deepgbanoveldeeplearningmodelforglobularproteinpredictionusingcnnbilstmarchitectureandenhancedpssmwithtrisectionstrategy
AT farisakateb deepgbanoveldeeplearningmodelforglobularproteinpredictionusingcnnbilstmarchitectureandenhancedpssmwithtrisectionstrategy
AT noufibrahim deepgbanoveldeeplearningmodelforglobularproteinpredictionusingcnnbilstmarchitectureandenhancedpssmwithtrisectionstrategy