FragOPT: An ML-Driven Computational Workflow for Rational Fragments Optimization Toward Lead Compounds
Journal of Chemical Information and Modeling · 27.10.2025 · 65 (20) · 10844-10854
DOI: 10.1021/acs.jcim.5c01225 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 13.10.2025. Verfasst von Xiaoyan Wu und 7 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory for Bio-Based Materials and Energy of Ministry of Education, College of Materials and Energy, South China Agricultural University, Gua…. Hauptthemen laut MEDLINE: Drug Discovery, Machine Learning. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 53 Literaturangaben. Gefördert von: South China Agricultural University, Construction Plan of Guangdong Province High-Level Universities.
Abstract (Originalsprache)
Advances in machine learning (ML) offer significant potential to accelerate drug discovery. Although mathematical modeling and ML have become crucial in predicting drug-target interactions and properties, the complexity of chemical space and the "black box" nature of ML leave untapped potential in computational drug discovery. In this study, we propose a comprehensive workflow, termed FragOPT, for optimizing molecules for specific targets. FragOPT identifies advantageous and disadvantageous fragments of molecules to be optimized by using a classification model for bioactive molecules and a model interpretability method (SHAP). These fragments are then sampled within the 3D pocket of the target protein, and disadvantageous fragments are redesigned by using a deep learning model. Finally, the advantageous fragments of the original molecule are recombined with the redesigned fragments to generate new molecules with enhanced binding affinity. This method was validated on two distinct protein targets associated with solid tumors and the SARS-CoV-2 virus, respectively. Compared to the other two fragment-based drug discovery methods, the majority of molecules generated by FragOPT exhibited superior synthesizability and enhanced binding affinity. Moreover, MMPBSA and FEP calculations indicated that the novel molecules with the best docking scores possess lower binding free energies than the original ligands. Overall, the results indicate that guiding the molecular generation workflow with QSAR models and the interpretability method can significantly optimize the initial drug discovery process, providing a more precise and efficient pathway for developing new therapeutics. The FragOPT is available at https://github.com/WxyChem/FragOPT.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Key Laboratory for Bio-Based Materials and Energy of Ministry of Education, College of Materials and Energy, South China Agricultural University, Guangzhou 510630, China.
ORCID-Profile: Xiaoyan Wu, Bingfeng Wang, Yulong Jin
Förderung
- South China Agricultural University
- Construction Plan of Guangdong Province High-Level Universities
Zitieren
APA
Wu, X., Meng, L., Zheng, J., Huang, J., Huang, Y., Wang, B., Liu, B., & Jin, Y. (2025). FragOPT: An ML-Driven Computational Workflow for Rational Fragments Optimization Toward Lead Compounds. Journal of Chemical Information and Modeling, 65(20), 10844-10854. https://doi.org/10.1021/acs.jcim.5c01225
Vancouver
Wu X, Meng L, Zheng J, Huang J, Huang Y, Wang B, et al. FragOPT: An ML-Driven Computational Workflow for Rational Fragments Optimization Toward Lead Compounds. Journal of Chemical Information and Modeling. 2025;65(20):10844-10854. doi:10.1021/acs.jcim.5c01225
BibTeX
@article{Wu2025,
author = {Wu, Xiaoyan and Meng, Luming and Zheng, Jianqiang and Huang, Junwen and Huang, Yongbin and Wang, Bingfeng and Liu, Boping and Jin, Yulong},
title = {FragOPT: An ML-Driven Computational Workflow for Rational Fragments Optimization Toward Lead Compounds},
journal = {Journal of Chemical Information and Modeling},
year = {2025},
volume = {65},
number = {20},
pages = {10844--10854},
doi = {10.1021/acs.jcim.5c01225}
}
EUVIMED