Generate Novel Molecules With Target Properties Using Conditional Generative Models

TL;DR

This paper introduces a novel neural network model that generates small molecules with specific target properties, improving upon previous methods in drug discovery tasks.

Contribution

A new conditional generative model with an encoder-predictor-decoder architecture for property-controlled molecule generation.

Findings

Outperforms previous methods on molecular weight, LogP, and drug-likeness metrics.

Uses a combined loss function and property prediction metrics.

Effective in generating molecules with desired properties.

Abstract

Drug discovery using deep learning has attracted a lot of attention of late as it has obvious advantages like higher efficiency, less manual guessing and faster process time. In this paper, we present a novel neural network for generating small molecules similar to the ones in the training set. Our network consists of an encoder made up of bi-GRU layers for converting the input samples to a latent space, predictor for enhancing the capability of encoder made up of 1D-CNN layers and a decoder comprised of uni-GRU layers for reconstructing the samples from the latent space representation. Condition vector in latent space is used for generating molecules with the desired properties. We present the loss functions used for training our network, experimental details and property prediction metrics. Our network outperforms previous methods using Molecular weight, LogP and Quantitative Estimation of Drug-likeness as the evaluation metrics.