EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhanced identification of membrane transport proteins: a hybrid approach combining ProtBERT-BFD and convolutional neural networks

Hamed Ghazikhani iD, Gregory Butler iD

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).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

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)

Membrane Transport ProteinsMembrane ProteinsAmino Acid SequenceNeural Networks, Computer

Stichwörter der Autor:innen

ProtBERT-BFDneural networkprotein language modeltransformerstransmembrane transport proteins

Substanzen

Membrane Transport ProteinsMembrane Proteins

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}
}
Kostenlos starten →