Molecular de-novo design through deep reinforcement learning

@inproceedings{Olivecrona2017MolecularDD,
  title={Molecular de-novo design through deep reinforcement learning},
  author={Marcus Olivecrona and Thomas Blaschke and Ola Engkvist and Hongming Chen},
  booktitle={J. Cheminformatics},
  year={2017}
}
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… CONTINUE READING
Related Discussions
This paper has been referenced on Twitter 75 times. VIEW TWEETS

Citations

Publications citing this paper.
Showing 1-10 of 35 extracted citations

Artificial intelligence in drug design

Science China Life Sciences • 2018

Conditional molecular design with deep generative models

Journal of chemical information and modeling • 2018

References

Publications referenced by this paper.
Showing 1-10 of 44 references

ChEMBL: a large-scale bioactivity database for drug discovery

Nucleic Acids Research • 2012
View 9 Excerpts
Highly Influenced

Étude comparative de la distribution florale dans une portion des Alpes et des Jura

P. Jaccard
Bulletin del la Société Vaudoise des Sciences Naturelles 37, 547–579 • 1901
View 7 Excerpts
Highly Influenced

Extended-Connectivity Fingerprints

Journal of Chemical Information and Modeling • 2010
View 4 Excerpts
Highly Influenced

Reinforcement Learning: An Introduction

IEEE Transactions on Neural Networks • 1998
View 6 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…