Enhanced identification of membrane transport proteins: a hybrid approach combining ProtBERT-BFD and convolutional neural networks
Journal of Integrative Bioinformatics · 2023
DOI: 10.1515/jib-2022-0055 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Integrative Bioinformatics, 2023. Verfasst von Hamed Ghazikhani und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Software Engineering, Concordia University, Montreal, Canada. Hauptthemen laut MEDLINE: Membrane Transport Proteins, Membrane Proteins. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Transmembrane transport proteins (transporters) play a crucial role in the fundamental cellular processes of all organisms by facilitating the transport of hydrophilic substrates across hydrophobic membranes. Despite the availability of numerous membrane protein sequences, their structures and functions remain largely elusive. Recently, natural language processing (NLP) techniques have shown promise in the analysis of protein sequences. Bidirectional Encoder Representations from Transformers (BERT) is an NLP technique adapted for proteins to learn contextual embeddings of individual amino acids within a protein sequence. Our previous strategy, TooT-BERT-T, differentiated transporters from non-transporters by employing a logistic regression classifier with fine-tuned representations from ProtBERT-BFD. In this study, we expand upon this approach by utilizing representations from ProtBERT, ProtBERT-BFD, and MembraneBERT in combination with classical classifiers. Additionally, we introduce TooT-BERT-CNN-T, a novel method that fine-tunes ProtBERT-BFD and discriminates transporters using a Convolutional Neural Network (CNN). Our experimental results reveal that CNN surpasses traditional classifiers in discriminating transporters from non-transporters, achieving an MCC of 0.89 and an accuracy of 95.1 % on the independent test set. This represents an improvement of 0.03 and 1.11 percentage points compared to TooT-BERT-T, respectively.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Computer Science and Software Engineering, Concordia University, Montreal, Canada.
ORCID-Profile: Hamed Ghazikhani, Gregory Butler
Zitieren
APA
Ghazikhani, H., & Butler, G. (2023). Enhanced identification of membrane transport proteins: a hybrid approach combining ProtBERT-BFD and convolutional neural networks. Journal of Integrative Bioinformatics. https://doi.org/10.1515/jib-2022-0055
Vancouver
Ghazikhani H, Butler G. Enhanced identification of membrane transport proteins: a hybrid approach combining ProtBERT-BFD and convolutional neural networks. Journal of Integrative Bioinformatics. 2023. doi:10.1515/jib-2022-0055
BibTeX
@article{Ghazikhani2023,
author = {Ghazikhani, Hamed and Butler, Gregory},
title = {Enhanced identification of membrane transport proteins: a hybrid approach combining ProtBERT-BFD and convolutional neural networks},
journal = {Journal of Integrative Bioinformatics},
year = {2023},
doi = {10.1515/jib-2022-0055}
}
EUVIMED