EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Beyond the leaderboard: leveraging predictive modeling for protein–ligand insights and discovery

Dan Kalifa iD, Kira Radinsky, Eric Horvitz iD

Bioinformatics · 2025

DOI: 10.1093/bioinformatics/btaf425 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2025. Verfasst von Dan Kalifa und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Technion-Israel Institute of Technology, Haifa 3200003, Israel. Hauptthemen laut MEDLINE: Proteins, Computational Biology. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Ligands are biomolecules that bind to specific sites on target proteins, often inducing conformational changes important in the protein’s function. Knowledge about ligand interactions with proteins are fundamental to understanding biological mechanisms and advancing drug discovery. Traditional protein language models focus on amino acid sequences and 3D structures, overlooking the structural and functional changes induced by protein-ligand interactions. We investigate the value of integrating ligand–protein binding data in several predictive challenges and leverage findings to frame research directions and questions. Results We show how the integration of protein-ligand interaction data in protein representation learning can increase predictive power. We evaluate the methodology across diverse biological tasks, demonstrating consistent improvements over state-of-the-art models. We further demonstrate how the study of the specific boosts in predictive capabilities coming with the introduction of the ligand modality can serve to focus attention and provide insights on biological mechanisms. By leveraging large pretrained protein language models and enriching them with interaction-specific features through a tailored learning process, we capture functional and structural nuances of proteins in their biochemical context. Availability and implementation The full code and data are freely available at https://github.com/kalifadan/ProtLigand (DOI: https://doi.org/10.5281/zenodo.15808053).

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ProteinsComputational BiologyLigandsProtein BindingDrug DiscoveryModels, MolecularProtein Conformation

Substanzen

LigandsProteins

Autor:innen und Institutionen

  • Department of Computer Science, Technion-Israel Institute of Technology, Haifa 3200003, Israel.
  • Office of the Chief Scientific Officer, Microsoft, Redmond, WA 14820, United States.
  • Department of Biomedical Informatics and Medical Education, University of Washington, Seattle, WA 98195, United States.

ORCID-Profile: Dan Kalifa, Eric Horvitz

Zitieren

APA

Kalifa, D., Radinsky, K., & Horvitz, E. (2025). Beyond the leaderboard: leveraging predictive modeling for protein–ligand insights and discovery. Bioinformatics. https://doi.org/10.1093/bioinformatics/btaf425

Vancouver

Kalifa D, Radinsky K, Horvitz E. Beyond the leaderboard: leveraging predictive modeling for protein–ligand insights and discovery. Bioinformatics. 2025. doi:10.1093/bioinformatics/btaf425

BibTeX
@article{Kalifa2025,
  author = {Kalifa, Dan and Radinsky, Kira and Horvitz, Eric},
  title = {Beyond the leaderboard: leveraging predictive modeling for protein–ligand insights and discovery},
  journal = {Bioinformatics},
  year = {2025},
  doi = {10.1093/bioinformatics/btaf425}
}
Kostenlos starten →