A Unified View of Relational Deep Learning for Drug Pair Scoring

TL;DR

This paper offers a comprehensive theoretical framework for relational deep learning models applied to drug pair scoring, unifying various approaches and discussing their applications, datasets, and future research directions.

Contribution

It provides a unified theoretical perspective on relational deep learning models for drug pair scoring, comparing architectures and highlighting future research avenues.

Findings

Comparison of existing model architectures

Discussion of datasets and evaluation protocols

Identification of high-impact applications

Abstract

In recent years, numerous machine learning models which attempt to solve polypharmacy side effect identification, drug-drug interaction prediction and combination therapy design tasks have been proposed. Here, we present a unified theoretical view of relational machine learning models which can address these tasks. We provide fundamental definitions, compare existing model architectures and discuss performance metrics, datasets and evaluation protocols. In addition, we emphasize possible high impact applications and important future research directions in this domain.