Identifying new uses for approved or investigational drugs using graph machine learning.

What is it about?

Graph representation learning has recently emerged as a promising approach to solve pharmacological tasks by modeling biological networks. Among the different tasks, drug repurposing, the task of identifying new uses for approved or investigational drugs, has attracted a lot of attention recently. In this work, the authors propose a node embedding algorithm for the problem of drug repurposing. The proposed algorithm learns node representations that capture the influence of nodes in the biological network by learning a mass term for each node along with its embedding. They apply the proposed algorithm to a multiscale interactome network and embed its nodes (i. e., proteins, drugs, diseases and biological functions) into a low-dimensional space. The experiments show that the proposed approach outperforms the baselines and offers an improvement of 53.33% in average precision over typical walk-based embedding approaches.

Featured Image

Photo by J K on Unsplash

Photo by J K on Unsplash

Why is it important?

The identification of new disease treatments from established drugs plays an important role in drug discovery as the development of new drugs is extremely time-consuming and costly. Drug repurposing is a very effective technique that can provide highly efficient solutions in drug discovery with limited amount of resources. The authors leverage biological networks that can capture the interactions between drugs, diseases and proteins and provide an interpretable way to model these effects. With their proposed algorithm, they can identify new uses of already existing drugs.