Molecular de-novo design through deep reinforcement learning

Molecular de-novo design through deep reinforcement learning

Abstract This work introduces a method to tune a sequence-based generative model for molecular de novo design that through augmented episodic likelihood can learn to generate structures with certain specified desirable properties. We demonstrate how this model can execute a range of tasks such as ge...

Full description

Bibliographic Details
Main Authors: Marcus Olivecrona, Thomas Blaschke, Ola Engkvist, Hongming Chen
Format: Article
Language:English
Published: BMC 2017-09-01
Series:Journal of Cheminformatics
Subjects:
De novo design
Recurrent neural networks
Reinforcement learning
Online Access:http://link.springer.com/article/10.1186/s13321-017-0235-x

Internet

http://link.springer.com/article/10.1186/s13321-017-0235-x

Similar Items