Molecular de-novo design through deep reinforcement learning

被引:781
作者
Olivecrona, Marcus [1 ]
Blaschke, Thomas [1 ]
Engkvist, Ola [1 ]
Chen, Hongming [1 ]
机构
[1] AstraZeneca R&D Gothenburg, Hit Discovery Discovery Sci Innovat Med & Early D, S-43183 Molndal, Sweden
关键词
De novo design; Recurrent neural networks; Reinforcement learning; GENERATION; SIMILARITY; PREDICTION;
D O I
10.1186/s13321-017-0235-x
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
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 generating analogues to a query structure and generating compounds predicted to be active against a biological target. As a proof of principle, the model is first trained to generate molecules that do not contain sulphur. As a second example, the model is trained to generate analogues to the drug Celecoxib, a technique that could be used for scaffold hopping or library expansion starting from a single molecule. Finally, when tuning the model towards generating compounds predicted to be active against the dopamine receptor type 2, the model generates structures of which more than 95% are predicted to be active, including experimentally confirmed actives that have not been included in either the generative model nor the activity prediction model.
引用
收藏
页数:14
相关论文
共 44 条
[1]  
[Anonymous], 2017, Objective-reinforced generative adversarial networks (ORGAN) for sequence generation models
[2]  
[Anonymous], 2014, P NIPS WORKSHOP DEEP
[3]  
[Anonymous], 2016, RDKIT OPEN SOURCE CH
[4]  
[Anonymous], 1997, Neural Computation
[5]  
[Anonymous], 2016, DEEP LEARNING
[6]  
[Anonymous], CORR
[7]  
[Anonymous], 2002, TECHNICAL REPORT
[8]  
[Anonymous], 2016, CORR
[9]  
[Anonymous], 2014, CORR
[10]  
[Anonymous], 2013, CORR