Artificial intelligence to combat antibiotic resistance in bacteria with significant human impact
A team of researchers from the Universitat Politècnica de València (UPV) and the Fundación para la Investigación Biomédica del Hospital Universitario Ramón y Cajal (FIBio-HRC), has developed, with the collaboration of the technology company Biotech Vana S. L, ARES (Antibiotic Resistance Evolution Simulator), an artificial intelligence tool to predict the evolution of the dynamics of transmission of antibiotic resistance in bacteria with a significant impact on humans, in order to be able to act in those cases in which the predicted scenario involves serious risks.
Based on membrane computing, the tool analyzes the behavior of the living eukaryotic cell and processes the information in a biomolecular key through DNA, RNA and proteins. From this, and through different algorithmic combinations, it is possible to know whether a given antibiotic will lose its effectiveness in one or another scenario.
Anticipation from accurate predictions
In this regard, it should be noted that membrane computing makes it possible to model, at many different levels, aspects of antibiotic resistance. For example, the behavior of a bacterium that has acquired resistance genes can be modeled.
As José María Sempere, member of the Research Group on Automata, Formal Languages and their Applications (ALFA)-VRAIN Institute, explains, “the idea is that a bacterium that has acquired or developed resistance to antibiotics can lodge in a healthy person (without bacteria with resistance) and this person, in turn, can transmit these resistant bacteria to other people in the form of an epidemic. The scenarios can be very complex and ARES has the ability to simulate them. It allows us to anticipate what would happen under a range of conditions.
At the individual level, ARES allows us to model, for a patient, both the frequency and the doses required of an antibiotic with certain characteristics. “We can also see, based on the rate of transmission of resistance genes, how bacterial colonies are growing in what would be a person’s microbiota,” says Sempere. “In reality, what the tool does is to give an accurate prediction of what could happen at the micro and macro levels and, from there, if an unfavorable scenario is glimpsed, it can be corrected,” he adds.
The latest work of the FIBio-HRC and Biotech Vana S.L. team has revealed how plasmid parameters affect the transmission dynamics of resistance genes. Their results have recently been published in the journal Antimicrobial Agents and Chemotherapy of the American Society for Microbiology.
33,000 deaths per year in Europe
Antibiotic resistance is currently one of the greatest threats to global health. Not surprisingly, according to a study by the European Centre for Disease Prevention and Control (ECDC), more than 33,000 people die each year in Europe alone from infections caused by bacteria that have developed resistance to antibiotics.
Likewise, the World Health Organization (WHO) indicates that the number of infections that are becoming more difficult to treat due to the loss of antibiotic efficacy is increasing. This is the case, for example, of pneumonia, tuberculosis, gonorrhea and salmonellosis. Already in 2018, the WHO warned that, if urgent action is not taken, the world is heading for a post-antibiotic era in which many common infections and minor injuries will once again become life-threatening.
In this context, the development of ARES, which is already being used at the Department of Microbiology of the Ramón y Cajal University Hospital in Madrid and at the Network Research Center for Epidemiology and Public Health (CIBERESP), takes on even greater importance.
Click here for more information (spanish)