TigerLily: Finding drug interactions in silico with the Graph
This work addresses the real-world problem of predicting drug interactions for medical and pharmaceutical applications, but it appears incremental as it applies existing graph methods to a specific domain.
The researchers tackled the problem of predicting adverse drug interactions by developing TigerLily, a system that uses graph mining techniques on a biological graph of drugs and proteins, resulting in a gradient boosting predictor for drug interaction prediction.
Tigerlily is a TigerGraph based system designed to solve the drug interaction prediction task. In this machine learning task, we want to predict whether two drugs have an adverse interaction. Our framework allows us to solve this highly relevant real-world problem using graph mining techniques in these steps: (a) Using PyTigergraph we create a heterogeneous biological graph of drugs and proteins. (b) We calculate the personalized PageRank scores of drug nodes in the TigerGraph Cloud. (c) We embed the nodes using sparse non-negative matrix factorization of the personalized PageRank matrix. (d) Using the node embeddings we train a gradient boosting based drug interaction predictor.