Scholarlink

<p>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 (pIC<sub>50</sub>) 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 <a href="https://github.com/AppliedAI-Lab/FRAIL">https://github.com/AppliedAI-Lab/FRAIL</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

FRAIL: fragment-based reinforcement learning for molecular design and benchmarking on fatty acid amide hydrolase 1 (FAAH-1)

  • 期刊论文

  • 发表日期：

    2026年1月9日

查看全文
  • Manh-Tu Luong,
  • Khanh Huyen Thi Pham,
  • Nhat-Hai Nguyen,
  • Van-Tuan Le,
  • Phu Tran Vinh Pham,
  • Tan Khanh Nguyen,
  • Thi-Thu Nguyen

摘要

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.