Clustering and GNN prediction with DrugMatrix

In this paper, we propose a novel metric to characterize drug molecules based on their interaction with genes, to tackle dimensionality challenges with the DrugMatrix toxicogenomics dataset. We developed a graph neural network (GNN) that is able to accurately predict this metric and produce informative graph-level vector representations that represent relative similarity between drug molecules, by capturing both structural and functional information of drug molecules. The GNN’s resulting embedding vector representations achieve better performance than both traditional fingerprint representations and the functional property data, in clustering tasks. With its demonstrated efficacy, there is potential for further advancements in the field of toxicogenomics and future applications of GNNs in high-dimensional data analysis.