A comprehensive survey explores Drug-Drug interaction prediction using Machine-Learning techniques

Abstract

Drug-Drug Interactions is a critical health and safety concern that receives a lot of attention from both academia and business. Polypharmacy is often employed as a strategy to manage complex diseases such as cancer, diabetes, and age-related ailments. However, combining medications with other drugs can lead to unintended adverse reactions. Interactions between drugs may increase the chance of unanticipated negative effects and even unknown toxicity, putting patients at risk. Detecting and identifying Interactions not only helps clinicians avoid chronic but will also encourage the co-prescription of safe drugs for more effective therapies. It is expensive and time-consuming to identify drug-drug interactions and Adverse Reactions among several medication pairings, both in vivo and in vitro. Recent advancements in computer science, specifically in the field of Artificial Intelligence, have yielded techniques that enable researchers to identify drug-drug interactions. We present comprehensive approaches that enable in-depth analysis of potential interactions by taking into account various factors, including molecular structure, clinical data, network relationships, and existing literature. This paper offers an all-encompassing survey of research studies that utilize Machine Learning and Deep Learning algorithms for the prediction of Drug-Drug interactions.