TigerLily: Finding drug interactions in silico with the Graph

TL;DR

TigerLily is a graph-based system that predicts drug interactions by constructing a biological graph, computing personalized PageRank scores, embedding nodes, and training a gradient boosting classifier.

Contribution

It introduces a novel in silico approach combining graph mining, personalized PageRank, and node embeddings for drug interaction prediction.

Findings

Effective prediction of drug interactions demonstrated.

Utilizes graph mining techniques for biological data.

Employs gradient boosting for classification.

Abstract

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.