FOCUS on NOD2: Advancing IBD Drug Discovery with a User-Informed Machine Learning Framework

IF 4 3区医学 Q2 CHEMISTRY, MEDICINAL ACS Medicinal Chemistry Letters Pub Date : 2024-06-06 DOI:10.1021/acsmedchemlett.4c00148

Ruhi Choudhary, and , Radhakrishnan Mahadevan*,

引用次数: 0

Abstract

In this study, we introduce the Framework for Optimized Customizable User-Informed Synthesis (FOCUS), a generative machine learning model tailored for drug discovery. FOCUS integrates domain expertise and uses Proximal Policy Optimization (PPO) to guide Monte Carlo Tree Search (MCTS) to efficiently explore chemical space. It generates SMILES representations of potential drug candidates, optimizing for druggability and binding efficacy to NOD2, PEP, and MCT1 receptors. The model is highly interpretive, allowing for user-feedback and expert-driven adjustments based on detailed cycle reports. Employing tools like SHAP and LIME, FOCUS provides a transparent analysis of decision-making processes, emphasizing features such as docking scores and interaction fingerprints. Comparative studies with Muramyl Dipeptide (MDP) demonstrate improved interaction profiles. FOCUS merges advanced machine learning with expert insight, accelerating the drug discovery pipeline.

Abstract Image

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

聚焦 NOD2：利用用户知情的机器学习框架推进 IBD 药物研发

在本研究中，我们介绍了优化定制用户知情合成框架（FOCUS），这是一种专为药物发现量身定制的生成式机器学习模型。FOCUS 整合了领域专业知识，并使用近端策略优化（PPO）来指导蒙特卡洛树搜索（MCTS），从而高效地探索化学空间。它能生成潜在候选药物的 SMILES 表征，优化药物的可药性以及与 NOD2、PEP 和 MCT1 受体的结合效力。该模型具有很强的解释性，可根据详细的周期报告进行用户反馈和专家驱动的调整。利用 SHAP 和 LIME 等工具，FOCUS 对决策过程进行了透明的分析，强调了对接得分和相互作用指纹等特征。与氨甲酰二肽（MDP）的比较研究表明，相互作用曲线得到了改善。FOCUS 将先进的机器学习与专家的洞察力相结合，加快了药物发现的进程。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

ACS Medicinal Chemistry Letters CHEMISTRY, MEDICINAL-

CiteScore

7.30

自引率

2.40%

发文量

328

审稿时长

1 months

期刊介绍： ACS Medicinal Chemistry Letters is interested in receiving manuscripts that discuss various aspects of medicinal chemistry. The journal will publish studies that pertain to a broad range of subject matter, including compound design and optimization, biological evaluation, drug delivery, imaging agents, and pharmacology of both small and large bioactive molecules. Specific areas include but are not limited to: Identification, synthesis, and optimization of lead biologically active molecules and drugs (small molecules and biologics) Biological characterization of new molecular entities in the context of drug discovery Computational, cheminformatics, and structural studies for the identification or SAR analysis of bioactive molecules, ligands and their targets, etc. Novel and improved methodologies, including radiation biochemistry, with broad application to medicinal chemistry Discovery technologies for biologically active molecules from both synthetic and natural (plant and other) sources Pharmacokinetic/pharmacodynamic studies that address mechanisms underlying drug disposition and response Pharmacogenetic and pharmacogenomic studies used to enhance drug design and the translation of medicinal chemistry into the clinic Mechanistic drug metabolism and regulation of metabolic enzyme gene expression Chemistry patents relevant to the medicinal chemistry field.