A de novo molecular generation method using latent vector based generative adversarial network
Artikel i vetenskaplig tidskrift, 2019
Deep learning methods applied to drug discovery have been used to generate novel structures. In this study, we propose a new deep learning architecture, LatentGAN, which combines an autoencoder and a generative adversarial neural network for de novo molecular design. We applied the method in two scenarios: One to generate random drug-like compounds and another to generate target-biased compounds. Our results show that the method works well in both cases. Sampled compounds from the trained model can largely occupy the same chemical space as the training set and also generate a substantial fraction of novel compounds. Moreover, the drug-likeness score of compounds sampled from LatentGAN is also similar to that of the training set. Lastly, generated compounds differ from those obtained with a Recurrent Neural Network-based generative model approach, indicating that both methods can be used complementarily.[Figure not available: See fulltext.]
Generative adversarial networks
Deep learning
Molecular design
Autoencoder networks
Författare
Oleksii Shevtsov
Chalmers, Mikroteknologi och nanovetenskap (MC2), Tillämpad kvantfysik
AstraZeneca AB
Simon Johansson
Chalmers, Data- och informationsteknik, Data Science
AstraZeneca AB
Panagiotis Christos Kotsias
AstraZeneca AB
Josep Arús-Pous
AstraZeneca AB
Universität Bern
Esben Jannik Bjerrum
AstraZeneca AB
Ola Engkvist
AstraZeneca AB
Hongming Chen
AstraZeneca AB
Chinese Academy of Sciences
Journal of Cheminformatics
1758-2946 (ISSN)
Vol. 11 74Ämneskategorier
Farmaceutisk vetenskap
Bioinformatik (beräkningsbiologi)
Sannolikhetsteori och statistik
DOI
10.1186/s13321-019-0397-9