Journal article Open Access

Application of Generative Autoencoder in de Novo Molecular Design

Blaschke, Thomas; Olivecrona, Marcus; Engkvist, Ola; Bajorath, Jürgen; Chen, Hongming

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 mole- cule 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.

Files (2.9 MB)
Name Size
2.9 MB Download
Views 46
Downloads 38
Data volume 111.8 MB
Unique views 46
Unique downloads 37


Cite as