Learning Molecular Representations for Medicinal Chemistry Miniperspective
Learning Molecular Representations for Medicinal Chemistry Miniperspective
复制标题
DOI：
10.1021/acs.jmedchem.0c00385
复制
发表时间：
2020-08-27
影响因子：
7.3
通讯作者：
Keiser, Michael J.
中科院分区：
文献类型：
--
作者：
Chuang, Kangway, V;Gunsalus, Laura M.;Keiser, Michael J.
小分子性质和生物活性的准确建模和预测依赖于分子表示的关键选择。几十年来，信息学驱动的研究依赖于专家设计的分子描述符来建立药物发现的定量结构-活性和结构-性质关系。现在，深度学习的进展使得直接从数据中高效而紧凑地学习分子表示成为可能。在这篇综述中，我们讨论了分子深度学习的积极研究如何解决当前描述符和指纹的局限性，同时在化学信息学和虚拟筛选方面创造新的机会。我们简要概述了表示在化学信息学中的作用，深度学习中的关键概念，并认为学习表示提供了一种改进小分子生物活性和性质的预测建模的方法。
The accurate modeling and prediction of small molecule properties and bioactivities depend on the critical choice of molecular representation. Decades of informatics-driven research have relied on expert-designed molecular descriptors to establish quantitative structure-activity and structure-property relationships for drug discovery. Now, advances in deep learning make it possible to efficiently and compactly learn molecular representations directly from data. In this review, we discuss how active research in molecular deep learning can address limitations of current descriptors and fingerprints while creating new opportunities in cheminformatics and virtual screening. We provide a concise overview of the role of representations in cheminformatics, key concepts in deep learning, and argue that learning representations provides a way forward to improve the predictive modeling of small molecule bioactivities and properties.