EUVIMEDEUVIMED entdecken
Crossref

Improved Prediction of Drug–Protein Interactions through Physics-Based Few-Shot Learning

Keqiong Zhang, Zhiran Fan, Qilong Wu iD, Jianfeng Liu, Sheng-You Huang iD

Journal of Chemical Information and Modeling · 2025

DOI: 10.1021/acs.jcim.5c00427 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, 2025. Verfasst von Keqiong Zhang und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Physics, Huazhong University of Science and Technology, Wuhan, Hubei 430074, P. R. China. Hauptthemen laut MEDLINE: Machine Learning, Drug Discovery, Proteins. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 91 Literaturangaben. Gefördert von: Huazhong University of Science and Technology, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate prediction of drug-protein interactions is crucial for drug discovery. Due to the bottleneck of traditional scoring functions, many machine learning scoring functions (MLSFs) have been proposed for structure-based drug screening. However, existing MLSFs face two challenges: small data limitations and poor interpretability. To address these challenges, we have proposed a physics-based small data machine learning framework for interpretable and generalizable prediction of drug-protein interactions on the target with scarce positive data through a strategy of three training phases with three (score, weight, and ranking) loss functions, named DrugBaiter. DrugBaiter has been extensively evaluated on the 102 targets of DUD-E and 81 targets of DEKOIS 2.0 for drug screening, and compared with 14 other MLSFs. It is shown that our DrugBaiter model can significantly improve the drug screening performance even if few actives are known for a target. In addition, DrugBaiter is interpretable in describing the interactions at the atomic level. The power of DrugBaiter is also confirmed by a drug screening application on the SARS-Cov-2 main protease target. It is anticipated that DrugBaiter will serve as a general machine learning scoring model for screening novel drugs on new targets with scarce known actives. DrugBaiter is freely available at http://huanglab.phys.hust.edu.cn/DrugBaiter.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningDrug DiscoveryProteinsSARS-CoV-2HumansProtein BindingCOVID-19Pharmaceutical Preparations

Substanzen

ProteinsPharmaceutical Preparations

Autor:innen und Institutionen

  • School of Physics, Huazhong University of Science and Technology, Wuhan, Hubei 430074, P. R. China.
  • Key Laboratory of Molecular Biophysics of MOE, Huazhong University of Science and Technology, Wuhan, Hubei 430074, P. R. China.
  • College of Life Science and Technology, Huazhong University of Science and Technology, Wuhan, Hubei 430074, P. R. China.

ORCID-Profile: Qilong Wu, Sheng-You Huang

Förderung

  • Huazhong University of Science and Technology
  • National Natural Science Foundation of China

Zitieren

APA

Zhang, K., Fan, Z., Wu, Q., Liu, J., & Huang, S. Y. (2025). Improved Prediction of Drug–Protein Interactions through Physics-Based Few-Shot Learning. Journal of Chemical Information and Modeling. https://doi.org/10.1021/acs.jcim.5c00427

Vancouver

Zhang K, Fan Z, Wu Q, Liu J, Huang SY. Improved Prediction of Drug–Protein Interactions through Physics-Based Few-Shot Learning. Journal of Chemical Information and Modeling. 2025. doi:10.1021/acs.jcim.5c00427

BibTeX
@article{Zhang2025,
  author = {Zhang, Keqiong and Fan, Zhiran and Wu, Qilong and Liu, Jianfeng and Huang, Sheng-You},
  title = {Improved Prediction of Drug–Protein Interactions through Physics-Based Few-Shot Learning},
  journal = {Journal of Chemical Information and Modeling},
  year = {2025},
  doi = {10.1021/acs.jcim.5c00427}
}
Kostenlos starten →