Integration of Machine Learning Algorithms in Drug Repurposing: Business and Market Implications

Elena Rossi
Department of Innovative Architectural Solutions, École Nationale Supérieure d' Architecture de Paris-Belleville, France

Abstract:

In the field of drug repurposing, artificial intelligence (AI) and machine learning (ML) approaches are becoming more and more important. In addition to understanding and carefully choosing the method itself, it is crucial to take into account the input data used to develop predictive models as the number of computational tools increases. In addition to addressing the present issues and offering viewpoints, this study attempts to delve into contemporary computational techniques that use AI and ML to drive and expedite chemical and drug target selection. Although there is no denying that AI and ML-based tools are revolutionizing conventional procedures, particularly in light of recent developments in graph-based techniques, they also pose new difficulties that need for professional assistance and the human eye. The significance of data quality and standardization is further emphasized by the increasing complexity of OMIC data. One method for finding new therapeutic uses for licensed medications in medical indications outside of their initial therapeutic usage is drug repurposing, also known as drug repositioning, drug rediscovery, drug repositioning, and drug reprofiling.