Molecular Design in Synthetically Accessible Chemical Space via Deep Reinforcement Learning.

Molecular Design in Synthetically Accessible Chemical Space via Deep Reinforcement Learning.
复制标题

DOI:
10.1021/acsomega.0c04153
复制
发表时间:
2020-12-29
期刊:
影响因子:
4.1
通讯作者:
Noutahi E
Noutahi E
中科院分区:
化学3区
文献类型:
--
作者:
Horwood J;Noutahi E

文献摘要

参考文献

被引文献

相似文献

生成性药物设计的基本目标是提出满足预定义活性、选择性和药代动力学标准的优化分子。尽管最近的进展,我们认为,现有的生成方法是有限的,在优化过程中有利地改变分子特性的分布的能力。相反,我们提出了一种新的分子设计强化学习框架,其中代理学习通过合成可访问的药物样分子空间直接优化。通过将马尔可夫决策过程中的过渡定义为化学反应,这成为可能,并允许我们利用合成路线作为归纳偏差。我们验证了我们的方法,证明它优于现有的国家的最先进的方法,在优化相关的目标,而多目标优化任务的结果表明,现实的制药设计问题的可扩展性增加。
The fundamental goal of generative drug design is to propose optimized molecules that meet predefined activity, selectivity, and pharmacokinetic criteria. Despite recent progress, we argue that existing generative methods are limited in their ability to favorably shift the distributions of molecular properties during optimization. We instead propose a novel Reinforcement Learning framework for molecular design in which an agent learns to directly optimize through a space of synthetically accessible drug-like molecules. This becomes possible by defining transitions in our Markov decision process as chemical reactions and allows us to leverage synthetic routes as an inductive bias. We validate our method by demonstrating that it outperforms existing state-of-the-art approaches in the optimization of pharmacologically relevant objectives, while results on multi-objective optimization tasks suggest increased scalability to realistic pharmaceutical design problems.
DOI: 10.1038/nchem.1243
发表时间: 2012-01-24
期刊: Nature chemistry
影响因子: 21.8
作者:
通讯作者: --
DOI: 10.1093/nar/gky1033
发表时间: 2019-01-08
影响因子: 14.9
作者:
Kim S;Chen J;Cheng T;Gindulyte A;He J;He S;Li Q;Shoemaker BA;Thiessen PA;Yu B;Zaslavsky L;Zhang J;Bolton EE
通讯作者: Bolton EE
DOI: 10.1021/jm00101a012
发表时间: 1992-11-13
影响因子: 7.3
作者:
GILLIGAN, PJ;CAIN, GA;TAM, SW
通讯作者: TAM, SW
DOI: 10.1186/1758-2946-1-8
发表时间: 2009-06-10
影响因子: 8.6
作者:
Ertl P;Schuffenhauer A
通讯作者: Schuffenhauer A
DOI: 10.1111/j.1755-5949.2008.00047.x
发表时间: 2008
影响因子: 5.5
作者:
Martelle JL;Nader MA
通讯作者: Nader MA