Graph residual based method for molecular property prediction

Abstract

Machine learning-driven methods for chemical property prediction have been of deep interest. However, much work remains to be done to improve the generalization ability, accuracy, and inference time of critical applications. Traditional machine learning models predict properties based on the features extracted from the molecules, which are often not readily available. In this work, a novel deep learning method, the Edge Conditioned Residual Graph Neural Network (ECRGNN), has been applied, allowing us to predict properties directly only the Graph-based structures of the molecules. SMILES (Simplified Molecular Input Line Entry System) representation of the molecules has been used in the present study as input data format, which has been further converted into a graph database, constituting the training data. This article highlights a detailed description of the novel GRU (Gated Recurrent Unit) - based methodology, ECRGNN, to map the inputs that have been used. Emphasis is placed on highlighting both the regressive property and the classification efficacy of the same. A detailed description of the Variational Autoencoder (VAE) and the end-to-end learning method used for multi-class multi-label property prediction has also been provided. The results have been compared with standard benchmark datasets and some newly developed datasets. All performance metrics that have been used have been clearly defined, and their reason for choice.