EUVIMEDEUVIMED entdecken
Crossref

Integrating Pre-Trained protein language model and multiple window scanning deep learning networks for accurate identification of secondary active transporters in membrane proteins

Muhammad Shahid Malik, Yu-Yen Ou

Methods · 2023-12 · 220 · 11-20

DOI: 10.1016/j.ymeth.2023.10.008 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Methods, 2023-12. Verfasst von Muhammad Shahid Malik und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Engineering, Yuan Ze University, Chung-Li 32003, Taiwan; Department of Computer Sciences, Karakoram International …. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 31 Literaturangaben. Gefördert von: National Science and Technology Council, Ministry of Science and Technology, Taiwan.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Secondary active transporters play pivotal roles in regulating ion and molecule transport across cell membranes, with implications in diseases like cancer. However, studying transporters via biochemical experiments poses challenges. We propose an effective computational approach to identify secondary active transporters from membrane protein sequences using pre-trained language models and deep learning neural networks. Our dataset comprised 290 secondary active transporters and 5,420 other membrane proteins from UniProt. Three types of features were extracted - one-hot encodings, position-specific scoring matrix profiles, and contextual embeddings from the ProtTrans language model. A multi-window convolutional neural network architecture scanned the ProtTrans embeddings using varying window sizes to capture multi-scale sequence patterns. The proposed model combining ProtTrans embeddings and multi-window convolutional neural networks achieved 86% sensitivity, 99% specificity and 98% overall accuracy in identifying secondary active transporters, outperforming conventional machine learning approaches. This work demonstrates the promise of integrating pre-trained language models like ProtTrans with multi-scale deep neural networks to effectively interpret transporter sequences for functional analysis. Our approach enables more accurate computational identification of secondary active transporters, advancing membrane protein research.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningMembrane ProteinsNeural Networks, ComputerMachine LearningAmino Acid Sequence

Stichwörter der Autor:innen

Deep learningMultiple window scanningPre-trained language modelSecondary active transporters

Substanzen

Membrane Proteins

Autor:innen und Institutionen

  • Department of Computer Science and Engineering, Yuan Ze University, Chung-Li 32003, Taiwan; Department of Computer Sciences, Karakoram International University, Gilgit-Baltistan, Pakistan.
  • Department of Computer Science and Engineering, Yuan Ze University, Chung-Li 32003, Taiwan; Graduate Program in Biomedical Informatics, Yuan Ze University, Chung-Li 32003, Taiwan. Electronic address: yien@saturn.yzu.edu…

Förderung

  • National Science and Technology Council
  • Ministry of Science and Technology, Taiwan

Zitieren

APA

Shahid Malik, M., & Ou, Y. Y. (2023). Integrating Pre-Trained protein language model and multiple window scanning deep learning networks for accurate identification of secondary active transporters in membrane proteins. Methods, 220, 11-20. https://doi.org/10.1016/j.ymeth.2023.10.008

Vancouver

Shahid Malik M, Ou YY. Integrating Pre-Trained protein language model and multiple window scanning deep learning networks for accurate identification of secondary active transporters in membrane proteins. Methods. 2023;220:11-20. doi:10.1016/j.ymeth.2023.10.008

BibTeX
@article{ShahidMalik2023,
  author = {Shahid Malik, Muhammad and Ou, Yu-Yen},
  title = {Integrating Pre-Trained protein language model and multiple window scanning deep learning networks for accurate identification of secondary active transporters in membrane proteins},
  journal = {Methods},
  year = {2023},
  volume = {220},
  pages = {11--20},
  doi = {10.1016/j.ymeth.2023.10.008}
}
Kostenlos starten →