# Drug-drug interaction prediction based on co-medication patterns and graph matching

## TL;DR

This paper introduces novel kernel methods utilizing graph matching and co-medication patterns within support vector machines to accurately predict adverse drug reactions from complex drug combinations.

## Contribution

It presents new kernels based on graph matching and co-medication data for predicting drug interactions of arbitrary orders, advancing the accuracy of adverse drug reaction prediction.

## Key findings

- Achieved an AUC of 0.912 on real-world data
- Utilized co-medication patterns to measure drug similarities
- Developed kernels effective for complex drug combination prediction

## Abstract

Background: The problem of predicting whether a drug combination of arbitrary orders is likely to induce adverse drug reactions is considered in this manuscript. Methods: Novel kernels over drug combinations of arbitrary orders are developed within support vector machines for the prediction. Graph matching methods are used in the novel kernels to measure the similarities among drug combinations, in which drug co-medication patterns are leveraged to measure single drug similarities. Results: The experimental results on a real-world dataset demonstrated that the new kernels achieve an area under the curve (AUC) value 0.912 for the prediction problem. Conclusions: The new methods with drug co-medication based single drug similarities can accurately predict whether a drug combination is likely to induce adverse drug reactions of interest. Keywords: drug-drug interaction prediction; drug combination similarity; co-medication; graph matching