Application of Generative Autoencoder in De Novo Molecular Design

• Published in: Molecular informatics Vol. 37; no. 1-2
• Main Authors: Blaschke, Thomas, Olivecrona, Marcus, Engkvist, Ola, Bajorath, Jürgen, Chen, Hongming
• Format: Journal Article
• Language: English
• Published: Germany Wiley Subscription Services, Inc 01.01.2018; John Wiley and Sons Inc
• Subjects: Autoencoder; Chemical fingerprinting; chemoinformatics; Computational chemistry; Computer applications; de novo molecular design; Deep Learning; Dopamine; Drug Design; Energy management; inverse QSAR; Machine learning; Pharmacology; Physiochemistry; Quantitative Structure-Activity Relationship; chemoinformatics; deep learning; inverse QSAR; Autoencoder; de novo molecular design
• ISSN: 1868-1743; 1868-1751; 1868-1751
• DOI: 10.1002/minf.201700123

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.