Molecular Activity prediction using deep learning Graph Neural Network

Abstract

Basic structural features and physicochemical properties of chemical molecules determine their behavior during chemical, physical, biological and environmental processes and hence need to be investigated for determining and modelling the actions of the molecule. Computational approaches such as machine learning methods are alternatives to predict physiochemical properties of molecules based on their structures. However, limited accuracy and error rates of these predictions restrict their use. In order to enhance the effectiveness of the similarity methods and QSAR measurement, the aim of this research is to develop a novel method of biological activity prediction, based on deep learning Graph neural network (GNN)