Machine learning has emerged as a promising tool in the fight against AMR, making significant contributions to understanding, preventing and reducing antimicrobial resistance, in addition to aiding in rapid and more accurate antibiotic discovery. This review focuses on machine learning techniques and their recent applications to antibiotic discovery and resistance prediction.

Abstract

Antimicrobial resistance (AMR) poses a serious threat to human health worldwide. It is now more difficult than ever to bring a potent antibiotic to the market given the rapid rise of antimicrobial resistance, which is outpacing the speed of antibiotic drug discovery. Therefore, new approaches must be developed to accelerate the speed of the drug discovery process and meet the demand for new antibiotics while reducing the cost of their development. Machine learning holds immense promise to become a useful tool, especially as the past two decades have seen exponential growth in computing power and big data biological analytics. Recent advances in machine learning algorithms for drug discovery have provided important clues to potential antibiotic classes. In addition to discovering new scaffolds, machine learning protocols will have a significant impact on the prediction of AMR patterns and drug metabolism. In this review, we outline the power of machine learning in antibiotic drug discovery, metabolic fate, and AMR prediction to support researchers involved and interested in this field.