Supervised chemical graph mining improves drug-induced liver injury prediction

Drug-induced liver injury (DILI) is the main cause of drug failure in clinical trials. The characterization of toxic compounds in terms of chemical structure is impor-tant because compounds can be metabolized to toxic substances in the liver. Traditional machine learning approaches have had limited success in predicting DILI, and emerging deep graph neural network (GNN) models are yet powerful enough to predict DILI. In this study, we developed a completely different approach, supervised subgraph mining (SSM), a strategy to mine explicit sub -graph features by iteratively updating individual graph transitions to maximize DILI fidelity. Our method outperformed previous methods including state-of-the-art GNN tools in classifying DILI on two different datasets: DILIst and TDC-benchmark. We also combined the subgraph features by using SMARTS-based frequent structural pattern matching and associated them with drugs' ATC code.

Automated summary

Drug-induced liver injury (DILI) is a major cause of drug failure in clinical trials. Traditional machine learning approaches and emerging deep graph neural network (GNN) models have limited success in predicting DILI. In this study, a new approach called supervised subgraph mining (SSM) was developed, which outperformed previous methods in classifying DILI on two different datasets. Subgraph features were also associated with drugs' ATC code using structural pattern matching.