FRAIL: fragment-based reinforcement learning for molecular design and benchmarking on fatty acid amide hydrolase 1 (FAAH-1)
Molecular Diversity · 2026
DOI: 10.1007/s11030-025-11448-4 ↗Kurz gefasst
Fachartikel in der Zeitschrift Molecular Diversity, 2026. Verfasst von Manh-Tu Luong und 6 weiteren Autor:innen. Beteiligte Einrichtung: Institute for AI Innovation and Societal Impact (AI4LIFE), Hanoi University of Science and Technology, Hanoi, Vietnam. Hauptthemen laut MEDLINE: Amidohydrolases, Drug Design, Enzyme Inhibitors. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 31 Literaturangaben.
Abstract (Originalsprache)
We propose FRAIL (Fragment-based Reinforcement Learning for Inhibitors), a generative AI framework that integrates fragment-based molecular design, multi- objective reinforcement learning, and molecular modeling to accelerate inhibitor discovery. Several deep generative models were fine-tuned on FAAH-1 (Fatty Acid Amide Hydrolase 1)-specific dataset and systematically benchmarked, with the best-performing model incorporated into FRAIL. The framework employs a customized reward function that jointly optimizes physicochemical properties and predicted bioactivity (pIC50) to guide molecular generation toward FAAH- favorable chemotypes. FRAIL generated structurally novel, fragment-grown compounds exhibiting high predicted binding affinity, desirable drug-likeness, and synthetic accessibility. These findings demonstrate FRAIL's capability to enhance rational drug design and provide a reproducible pipeline for the discovery of experimentally viable FAAH inhibitors. Our pipeline source code is released in https://github.com/AppliedAI-Lab/FRAIL .
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Institute for AI Innovation and Societal Impact (AI4LIFE), Hanoi University of Science and Technology, Hanoi, Vietnam.
- College of Pharmacy and Integrated Research Institute for Drug Development, Dongguk University-Seoul, Goyang-si, Gyeonggi-do, 10326, Republic of Korea.
- VN-UK Institute for Research and Executive Education, The University of Danang, Danang, Vietnam.
- Scientific Management Department, Dong A University, Danang, Vietnam. khanhnt2501@gmail.com.
- Institute for Biocomputation and Physics of Complex Systems, University of Zaragoza, Saragossa, Spain. khanhnt2501@gmail.com.
- Institute for AI Innovation and Societal Impact (AI4LIFE), Hanoi University of Science and Technology, Hanoi, Vietnam. thithu.nguyen6@hust.edu.vn.
Zitieren
APA
Luong, M. T., Pham, K. H. T., Nguyen, N. H., Le, V. T., Pham, P. T. V., Nguyen, T. K., & Nguyen, T. T. (2026). FRAIL: fragment-based reinforcement learning for molecular design and benchmarking on fatty acid amide hydrolase 1 (FAAH-1). Molecular Diversity. https://doi.org/10.1007/s11030-025-11448-4
Vancouver
Luong MT, Pham KHT, Nguyen NH, Le VT, Pham PTV, Nguyen TK, et al. FRAIL: fragment-based reinforcement learning for molecular design and benchmarking on fatty acid amide hydrolase 1 (FAAH-1). Molecular Diversity. 2026. doi:10.1007/s11030-025-11448-4
BibTeX
@article{Luong2026,
author = {Luong, Manh-Tu and Pham, Khanh Huyen Thi and Nguyen, Nhat-Hai and Le, Van-Tuan and Pham, Phu Tran Vinh and Nguyen, Tan Khanh and Nguyen, Thi-Thu},
title = {FRAIL: fragment-based reinforcement learning for molecular design and benchmarking on fatty acid amide hydrolase 1 (FAAH-1)},
journal = {Molecular Diversity},
year = {2026},
doi = {10.1007/s11030-025-11448-4}
}
EUVIMED