Premium
Application of Generative Autoencoder in De Novo Molecular Design
Author(s) -
Blaschke Thomas,
Olivecrona Marcus,
Engkvist Ola,
Bajorath Jürgen,
Chen Hongming
Publication year - 2018
Publication title -
molecular informatics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.481
H-Index - 68
eISSN - 1868-1751
pISSN - 1868-1743
DOI - 10.1002/minf.201700123
Subject(s) - autoencoder , chemical space , generative grammar , similarity (geometry) , computer science , artificial intelligence , generator (circuit theory) , space (punctuation) , set (abstract data type) , generative model , deep learning , drug discovery , bioinformatics , biology , physics , power (physics) , quantum mechanics , image (mathematics) , programming language , operating system
A major challenge in computational chemistry is the generation of novel molecular structures with desirable pharmacological and physiochemical properties. In this work, we investigate the potential use of autoencoder, a deep learning methodology, for de novo molecular design. Various generative autoencoders were used to map molecule structures into a continuous latent space and vice versa and their performance as structure generator was assessed. Our results show that the latent space preserves chemical similarity principle and thus can be used for the generation of analogue structures. Furthermore, the latent space created by autoencoders were searched systematically to generate novel compounds with predicted activity against dopamine receptor type 2 and compounds similar to known active compounds not included in the trainings set were identified.