Predicting Antibiotic Resistance Using Genomic Data and Machine Learning Algorithms (Research Article)

Author(s): Shiji Thomas and O. Jamsheela

Abstract: A major public health concern of the twenty-first century is antibiotic resistance (AR). In addition to being time-consuming, traditional diagnostic techniques for identifying antimicrobial resistance (AMR) sometimes often fail to keep pace with emerging resistant pathogens. More recently, whole-genome sequencing (WGS) has enabled scientists to create extensive microbial genomic datasets. Together with machine learning (ML) methods, these data offer strong tools for quick and precise forecasting of resistance phenotypes. In this work, the current status of research on combining machine learning algorithms and genomic data to predict antibiotic resistance is reviewed. The application of ML algorithms to the problem of AMR has gained tremendous interest in the past few years due to the growth of experimental and clinical data, heavy investment in computational capacity, advances in algorithm performance, and growing urgency for innovative approaches to tackle the problem of drug resistance. Here, we review the current applications of machine learning in improving the diagnosis, treatment and prevention of bacterial AMR.

PAGES: 767-771  |  166 VIEWS  158 DOWNLOADS