EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DeepAllo: allosteric site prediction using protein language model (pLM) with multitask learning

Moaaz Khokhar iD, Ozlem Keskin iD, Attila Gursoy iD

Bioinformatics · 02.06.2025 · 41 (6)

DOI: 10.1093/bioinformatics/btaf294 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 15.05.2025. Verfasst von Moaaz Khokhar und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Engineering, Koç University, 34450 Istanbul, Turkey. Hauptthemen laut MEDLINE: Allosteric Site, Proteins, Machine Learning, Software. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Scientific and Technological Research Council of Türkiye.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Allostery, the process by which binding at one site perturbs a distant site, is being rendered as a key focus in the field of drug development with its substantial impact on protein function. The identification of allosteric pockets (sites) is a challenging task and several techniques have been developed, including Machine Learning to predict allosteric pockets that utilize both static and pocket features. Results Our work, DeepAllo, is the first study that combines fine-tuned protein language model (pLM) with FPocket features and shows an increase in prediction performance of allosteric sites over previous studies. The pLM model was fine-tuned on AlloSteric Database (ASD) in Multitask Learning setting and was further used as a feature extractor to train XGBoost and AutoML models. The best model predicts allosteric pockets with 89.66% F1 score and 90.5% of allosteric pockets in the top 3 positions, outperforming previous results. A case study has been performed on proteins with known allosteric pockets, which shows the proof of our approach. Moreover, an effort was made to explain the pLM by visualizing its attention mechanism among allosteric and non-allosteric residues. Availability and implementation The source code is available on GitHub (https://github.com/MoaazK/deepallo) and archived on Zenodo (DOI: 10.5281/zenodo.15255379). The trained model is hosted on Hugging Face (DOI: 10.57967/hf/5198). The dataset used for training and evaluation is archived on Zenodo (DOI: 10.5281/zenodo.15255437).

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Allosteric SiteProteinsMachine LearningSoftwareComputational BiologyDatabases, ProteinModels, Molecular

Substanzen

Proteins

Autor:innen und Institutionen

  • Department of Computer Engineering, Koç University, 34450 Istanbul, Turkey.
  • KUIS AI Center, Koç University, 34450 Istanbul, Turkey.
  • Department of Chemical and Biological Engineering, Koç University, 34450 Istanbul, Turkey.

ORCID-Profile: Moaaz Khokhar, Ozlem Keskin, Attila Gursoy

Förderung

  • Scientific and Technological Research Council of Türkiye

Zitieren

APA

Khokhar, M., Keskin, O., & Gursoy, A. (2025). DeepAllo: allosteric site prediction using protein language model (pLM) with multitask learning. Bioinformatics, 41(6). https://doi.org/10.1093/bioinformatics/btaf294

Vancouver

Khokhar M, Keskin O, Gursoy A. DeepAllo: allosteric site prediction using protein language model (pLM) with multitask learning. Bioinformatics. 2025;41(6). doi:10.1093/bioinformatics/btaf294

BibTeX
@article{Khokhar2025,
  author = {Khokhar, Moaaz and Keskin, Ozlem and Gursoy, Attila},
  title = {DeepAllo: allosteric site prediction using protein language model (pLM) with multitask learning},
  journal = {Bioinformatics},
  year = {2025},
  volume = {41},
  number = {6},
  doi = {10.1093/bioinformatics/btaf294}
}
Kostenlos starten →