Improving the Hit Rates of Virtual Screening by Active Learning from Bioactivity Feedback
Journal of Chemical Theory and Computation · 13.05.2025 · 21 (9) · 4640-4651
DOI: 10.1021/acs.jctc.4c01618 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Chemical Theory and Computation, online erschienen am 16.04.2025. Verfasst von Xun Deng und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Science and Technology, University of Science and Technology of China, Hefei 230026, China. Hauptthemen laut MEDLINE: Drug Discovery, Problem-Based Learning. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 59 Literaturangaben. Gefördert von: Alibaba.
Abstract (Originalsprache)
Virtual screening has been widely used to identify potential hit candidates that can bind to the target protein in drug discovery. Contemporary screening methods typically rely on oversimplified scoring functions, frequently yielding one-digit hit rates (or even zero) among top-ranked candidates. The substantial cost of laboratory validation further constrains the exploration of candidate molecules. We find that test-time prediction refinement is almost blank in this area, which means bioactivity feedback in the wet-lab experiments is neglected. Here, we introduce an Active Learning from Bioactivity Feedback (ALBF) framework to enhance the weak hit rate of current virtual screening methods. ALBF spends the budget of wet-lab experiments iteratively and leverages the target-specific bioactivity insights from current wet-lab tests to refine the score results (i.e., rankings). Our framework consists of two components: a novel query strategy that considers the evaluation quality and its overall influence on other top-scored molecules; and an efficient score optimization strategy that propagates the bioactivity feedback to structurally similar molecules. We evaluated ALBF on diverse subsets of the well-known DUD-E and LIT-PCBA benchmarks. Our active learning protocol averagely enhances top-100 hit rates by 60% and 30% on DUD-E and LIT-PCBA with 50 to 200 bioactivity queries on the selected molecules that are deployed in ten rounds. The consistently superior performance demonstrates ALBF's potential to enhance both the accuracy and cost-effectiveness of active learning-based laboratory testing.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Information Science and Technology, University of Science and Technology of China, Hefei 230026, China.
- Alibaba Cloud Computing, Beijing 100012, China.
- School of Cyber Science and Technology, University of Science and Technology of China, Hefei 230026, China.
- School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing 210023, China.
ORCID-Profile: Xun Deng, Jiansheng Wu
Förderung
- Alibaba
Zitieren
APA
Deng, X., Liu, J., Liu, Z., Wu, J., Feng, F., Ye, J., & Wang, Z. (2025). Improving the Hit Rates of Virtual Screening by Active Learning from Bioactivity Feedback. Journal of Chemical Theory and Computation, 21(9), 4640-4651. https://doi.org/10.1021/acs.jctc.4c01618
Vancouver
Deng X, Liu J, Liu Z, Wu J, Feng F, Ye J, et al. Improving the Hit Rates of Virtual Screening by Active Learning from Bioactivity Feedback. Journal of Chemical Theory and Computation. 2025;21(9):4640-4651. doi:10.1021/acs.jctc.4c01618
BibTeX
@article{Deng2025,
author = {Deng, Xun and Liu, Junlong and Liu, Zhike and Wu, Jiansheng and Feng, Fuli and Ye, Jieping and Wang, Zheng},
title = {Improving the Hit Rates of Virtual Screening by Active Learning from Bioactivity Feedback},
journal = {Journal of Chemical Theory and Computation},
year = {2025},
volume = {21},
number = {9},
pages = {4640--4651},
doi = {10.1021/acs.jctc.4c01618}
}
EUVIMED