Generative schemes for drug design with shape captioning

We present three related schemes to generate novel molecules based on seed molecule; all the methods use as input the voxelized representation of the seed molecule to generate the SMILES representation of the novel molecule. At heart of these methods are two networks (a) a variational auto encoder that uses a Riemannian metric to encode the latent space of (hence named RHVAE) and can use pharmacophoric requirements as additional input for decoder and (b) attentive captioning network (a type of recurring neural network) that can efficiently focus, capture and use the ‘content’ of input to generate the SMILES output of novel molecules. We analyze the performance of the three proposed methods. We demonstrate the generation of meaningful new molecules, by generating shapes through an auto encoder network which can then be passed to our attentive captioning network, while requiring smaller datasets for training and retaining similar performance to existing state-of-art methods.

Graphical abstract

SYNOPSIS Study demonstrates the generation of meaningful ligands using machine learning; specifically, an autoencoder that uses Remannian geometry represenation for its latent space whose output grid can be passed to a attentive captioning network. We demonstrate suggested schemes require smaller data sets for training while retaining similar performance as to state-of-art methods.. The VAE model employed