Deciphering Membrane Proteins Through Deep Learning Models by Revealing Their Locale Within the Cell

Membrane proteins constitute essential biomolecules attached to or integrated into cellular and organelle membranes, playing diverse roles in cellular processes. Their precise localization is crucial for understanding their functions. Existing protein subcellular localization predictors are predomin...

Full description

Saved in:
Bibliographic Details
Main Authors: Mehwish Faiz, Saad Jawaid Khan, Fahad Azim, Nazia Ejaz, Fahad Shamim
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Bioengineering
Subjects:
Online Access:https://www.mdpi.com/2306-5354/11/11/1150
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850267246668021760
author Mehwish Faiz
Saad Jawaid Khan
Fahad Azim
Nazia Ejaz
Fahad Shamim
author_facet Mehwish Faiz
Saad Jawaid Khan
Fahad Azim
Nazia Ejaz
Fahad Shamim
author_sort Mehwish Faiz
collection DOAJ
description Membrane proteins constitute essential biomolecules attached to or integrated into cellular and organelle membranes, playing diverse roles in cellular processes. Their precise localization is crucial for understanding their functions. Existing protein subcellular localization predictors are predominantly trained on globular proteins; their performance diminishes for membrane proteins, explicitly via deep learning models. To address this challenge, the proposed study segregates membrane proteins into three distinct locations, including the plasma membrane, internal membrane, and membrane of the organelle, using deep learning algorithms including recurrent neural networks (RNN) and Long Short-Term Memory (LSTM). A redundancy-curtailed dataset of 3000 proteins from the MemLoci approach is selected for the investigation, along with incorporating pseudo amino acid composition (PseAAC). PseAAC is an exemplary technique for extracting protein information hidden in the amino acid sequences. After extensive testing, the results show that the accuracy for LSTM and RNN is 83.4% and 80.5%, respectively. The results show that the LSTM model outperforms the RNN and is most commonly employed in proteomics.
format Article
id doaj-art-8cd7997bdbe54bc0a197af3ca9220a89
institution OA Journals
issn 2306-5354
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Bioengineering
spelling doaj-art-8cd7997bdbe54bc0a197af3ca9220a892025-08-20T01:53:52ZengMDPI AGBioengineering2306-53542024-11-011111115010.3390/bioengineering11111150Deciphering Membrane Proteins Through Deep Learning Models by Revealing Their Locale Within the CellMehwish Faiz0Saad Jawaid Khan1Fahad Azim2Nazia Ejaz3Fahad Shamim4Department of Electrical Engineering, Faculty of Engineering, Science, Technology and Management, Ziauddin University, Karachi 74200, PakistanDepartment of Biomedical Engineering, Faculty of Engineering, Science, Technology and Management, Ziauddin University, Karachi 74200, PakistanDepartment of Electrical Engineering, Faculty of Engineering, Science, Technology and Management, Ziauddin University, Karachi 74200, PakistanDepartment of Biomedical Engineering, Balochistan University of Engineering and Technology, Khuzdar 89100, PakistanInstitute of Biomedical Engineering & Technology (IBET), Liaquat University of Medical and Health Sciences, Jamshoro 76060, PakistanMembrane proteins constitute essential biomolecules attached to or integrated into cellular and organelle membranes, playing diverse roles in cellular processes. Their precise localization is crucial for understanding their functions. Existing protein subcellular localization predictors are predominantly trained on globular proteins; their performance diminishes for membrane proteins, explicitly via deep learning models. To address this challenge, the proposed study segregates membrane proteins into three distinct locations, including the plasma membrane, internal membrane, and membrane of the organelle, using deep learning algorithms including recurrent neural networks (RNN) and Long Short-Term Memory (LSTM). A redundancy-curtailed dataset of 3000 proteins from the MemLoci approach is selected for the investigation, along with incorporating pseudo amino acid composition (PseAAC). PseAAC is an exemplary technique for extracting protein information hidden in the amino acid sequences. After extensive testing, the results show that the accuracy for LSTM and RNN is 83.4% and 80.5%, respectively. The results show that the LSTM model outperforms the RNN and is most commonly employed in proteomics.https://www.mdpi.com/2306-5354/11/11/1150membrane proteinsubcellular localizationcellpseudo amino acid compositiondeep learning modelsproteomics
spellingShingle Mehwish Faiz
Saad Jawaid Khan
Fahad Azim
Nazia Ejaz
Fahad Shamim
Deciphering Membrane Proteins Through Deep Learning Models by Revealing Their Locale Within the Cell
Bioengineering
membrane protein
subcellular localization
cell
pseudo amino acid composition
deep learning models
proteomics
title Deciphering Membrane Proteins Through Deep Learning Models by Revealing Their Locale Within the Cell
title_full Deciphering Membrane Proteins Through Deep Learning Models by Revealing Their Locale Within the Cell
title_fullStr Deciphering Membrane Proteins Through Deep Learning Models by Revealing Their Locale Within the Cell
title_full_unstemmed Deciphering Membrane Proteins Through Deep Learning Models by Revealing Their Locale Within the Cell
title_short Deciphering Membrane Proteins Through Deep Learning Models by Revealing Their Locale Within the Cell
title_sort deciphering membrane proteins through deep learning models by revealing their locale within the cell
topic membrane protein
subcellular localization
cell
pseudo amino acid composition
deep learning models
proteomics
url https://www.mdpi.com/2306-5354/11/11/1150
work_keys_str_mv AT mehwishfaiz decipheringmembraneproteinsthroughdeeplearningmodelsbyrevealingtheirlocalewithinthecell
AT saadjawaidkhan decipheringmembraneproteinsthroughdeeplearningmodelsbyrevealingtheirlocalewithinthecell
AT fahadazim decipheringmembraneproteinsthroughdeeplearningmodelsbyrevealingtheirlocalewithinthecell
AT naziaejaz decipheringmembraneproteinsthroughdeeplearningmodelsbyrevealingtheirlocalewithinthecell
AT fahadshamim decipheringmembraneproteinsthroughdeeplearningmodelsbyrevealingtheirlocalewithinthecell