Application of generative autoencoder in de novo molecular design
This addresses the problem of de novo molecular design for computational chemists, but it is incremental as it applies existing autoencoder methods to a known bottleneck in the field.
The study tackled generating novel molecular structures with desired properties by using generative autoencoders to map molecules into a continuous latent space, enabling the generation of analog structures and identifying new compounds with predicted activity against dopamine receptor type 2, including compounds similar to known actives not in the training set.
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 training set were identified.