Deep Learning and Antibiotic Resistance

Abstract

Antibiotic resistance (AR) is a naturally occurring phenomenon with the capacity to render useless all known antibiotics in the fight against bacterial infections. Although bacterial resistance appeared before any human life form, this process has accelerated in the past years. Important causes of AR in modern times could be the over-prescription of antibiotics, the presence of faulty infection-prevention strategies, pollution in overcrowded areas, or the use of antibiotics in agriculture and farming, together with a decreased interest from the pharmaceutical industry in researching and testing new antibiotics. The last cause is primarily due to the high costs of developing antibiotics. The aim of the present review is to highlight the techniques that are being developed for the identification of new antibiotics to assist this lengthy process, using artificial intelligence (AI). AI can shorten the preclinical phase by rapidly generating many substances based on algorithms created by machine learning (ML) through techniques such as neural networks (NN) or deep learning (DL). Recently, a text mining system that incorporates DL algorithms was used to help and speed up the data curation process. Moreover, new and old methods are being used to identify new antibiotics, such as the combination of quantitative structure-activity relationship (QSAR) methods with ML or Raman spectroscopy and MALDI-TOF MS combined with NN, offering faster and easier interpretation of results. Thus, AI techniques are important additional tools for researchers and clinicians in the race for new methods of overcoming bacterial resistance.

Harnessing of Artificial Intelligence for the Diagnosis and Prevention of Hospital-Acquired Infections: A Systematic Review

“…Fu et al have also reported the possibility of rapid identification of antibiotic sensitivity and MDR patterns among urinary tract pathogens using SERS spectra and CNN [ 93 ]. A number of reviews have focused on the application of AI for tackling antibiotic resistance [ 94 , 95 , 96 ]. Interestingly, a more recent study by Jeon et al has also explored the use of MALDI-TOF spectral data combined with ML for the identification of MRSA using the MALDI-TOF MS technique.…”

The Silent Threat: Antimicrobial-Resistant Pathogens in Food-Producing Animals and Their Impact on Public Health

“…Campylobacter jejuni ( C. jejuni ) is a type of bacteria that is spiral-shaped and classified as Gram-negative and microaerophilic. This bacterial species is commonly found in the intestinal tracts of animals, particularly poultry and pigs [ 47 , 48 ], and can be transmitted to humans through the consumption of contaminated food or water [ 49 ]. Recently, it has been recognized as the primary culprit for bacterial foodborne illnesses in the U.S. [ 38 ].…”

Personal Care Products as a Contributing Factor to Antimicrobial Resistance: Current State and Novel Approach to Investigation

“…However, new technologies play a significant part in monitoring antibiotic resistance. There may be several options to explore antibiotic resistance thanks to artificial intelligence (AI) [ 95 ]. AI may be used, for instance, to analyze vast volumes of data that are produced by studies on antibiotic resistance, spot trends, and make predictions about the spread of antibiotic resistance.…”