Improving VAE based molecular representations for compound property prediction.

ABSTRACT: Collecting labeled data for many important tasks in chemoinformatics is time consuming and requires expensive experiments. In recent years, machine learning has been used to learn rich representations of molecules using large scale unlabeled molecular datasets and transfer the knowledge to solve the more challenging tasks with limited datasets. Variational autoencoders are one of the tools that have been proposed to perform the transfer for both chemical property prediction and molecular generation tasks. In this work we propose a simple method to improve chemical property prediction performance of machine learning models by incorporating additional information on correlated molecular descriptors in the representations learned by variational autoencoders. We verify the method on three prop

SUBMITTER: Tevosyan A 

PROVIDER: S-EPMC9569108 | biostudies-literature | 2022 Oct

REPOSITORIES: biostudies-literature