With the rise of antibiotics in the 1930s, phage therapy (i.e. the use of viruses called bacteriophages in the fight against bacterial infections) was abandoned. Today, the rise of antibiotic resistance makes the treatment of bacterial infections more and more difficult and phage therapy is once again arousing the interest of doctors and researchers despite its complexity of implementation due to the very great diversity and specificity bacteriophages. This is how scientists from the Pasteur Institute, Inserm, AP-HP and Paris Cité University have developed a new tool capable of choosing, in a simple and effective way, the best cocktail of bacteriophages possible for a given patient. To do this, they developed and trained an artificial intelligence-based model capable of tailor-made bacteriophages based solely on the genome of the targeted bacteria. The results of this work were published on October 31, 2024 in the journal Nature Microbiologyand pave the way for personalized phage therapies to combat antibiotic-resistant bacterial infections.
Certain bacteria, such as Escherichia coliare becoming more and more resistant to classic antibiotics and are becoming what we call “superbugs”. To circumvent this resistance, which represents a major public health problem, research teams are exploring the route of phage therapy. The principle: use viruses, called phages or bacteriophages, which only infect bacteria to specifically eliminate those that are pathogenic for humans. “ Phage therapy was invented by the Pasteurian researcher Félix d’Hérelle in the 1920s then was abandoned with the rise of antibiotics in the late 1930s, which were much simpler and more economical to manufacture and use. Today, only a few countries in Eastern Europe, such as Georgia, still use phage therapy, while in Western countries, phages “large spectre” are used occasionally on a compassionate basis to treat chronic infections that are multi-resistant to antibiotics(1), when no authorized medication is effective, recalls Baptiste Gaborieau, co-first author of the article, resuscitation doctor at Louis Mourier Hospital (AP-HP) and researcher in the IAME laboratory (Paris Cité-Inserm University). For around twenty years, thanks to its promotion by the WHO(2)and more recently the establishment of clinical trials, particularly in Europe, phage therapy is once again attracting interest. »
One of the challenges is knowing which bacteriophage will be effective in fighting a given infection, knowing that each phage can only infect certain strains(3) bacterial. In soil or water where phages are naturally present, they circulate until they find the right target. This is how scientists from the Pasteur Institute, Inserm, AP-HP and Paris-Cité University decided to study bacteria-phage interactions more closely in order to find out if It was possible to predict the effectiveness of a bacteriophage on a given bacterial strain. The first step therefore consisted of the creation of a quality database with on one side 403 strains of bacteria Escherichia coli and on the other 96 bacteriophages. A job that required more than two years of effort. “ We brought the phages into contact with the bacteria in culture and observed which bacteria were killed. We studied 350,000 interactions and succeeded in identifying, at the bacterial genome level, the characteristics likely to predict the effectiveness of phages.summarizes Aude Bernheim, main author of the study and head of the Molecular Diversity of Microbes laboratory at the Pasteur Institute. “ Contrary to what was initially thought, it is the receptors on the surface of bacteria and not their defense mechanisms which primarily determine the capacity of bacteriophages to be able to infect bacteria or not, and which predict their effectiveness. », continues Florian Tesson, co-first author of the article and doctoral student in the Molecular diversity of microbes laboratories at the Pasteur Institute and IAME at the University of Paris Cité-Inserm.
Thanks to this precise and complete analysis of the interaction mechanisms between bacteria and phages, the team’s bioinformaticians were able to design an optimized and efficient artificial intelligence program. The latter is based on the analysis of the genome of bacteria, and more particularly on the analysis of the regions involved in the coding of the membrane receptors of the bacteria, the entry point for phages. “ We are not here in front of a “ black box “and this is what makes our AI-based model strong. We know exactly how it works, which helps us improve its performance », underlines Hugo Vaysset, co-first author of the article and doctoral student in the Molecular Diversity of Microbes laboratory at the Pasteur Institute. After more than two years of design and training, the AI was able to correctly predict the effectiveness of bacteriophages against bacteria E. coli from the database in 85% of cases, simply by analyzing the DNA of the bacteria. “ This is a result that exceeds our expectations », admits Aude Bernheim. To go further, the researchers tested their model on a new collection of bacterial strains fromE. coli responsible for pneumonia and selected, for each of them, a tailor-made “cocktail” of three bacteriophages. In 90% of cases, the bacteriophages tailor-made by the AI succeeded in their mission and destroyed the bacteria present. This method, easily usable in hospital biology laboratories, opens the way in the years to come for a personalized and rapid selection of bacteriophage treatments in the event of a diagnosis of bacterial infection with Escherichia coli very resistant to antibiotics. “ We still need to test how the phages behave in different environments, but the proof of concept is done. We hope to be able to extend it to other pathogenic bacteria, because our AI has been designed to easily adapt to other scenarios, and offer personalized phage therapy treatments in the future. », concludes Aude Bernheim
About AP-HP: The leading hospital and university center (CHU) in Europe, the AP-HP and its 38 hospitals are organized into six hospital-university groups (AP-HP. Center – Université Paris Cité; AP-HP. Sorbonne Université; AP-HP . North – Paris Cité University; Paris-Saclay University; Seine-Saint-Denis) and revolve around five universities in the Ile-de-France region. Closely linked to major research organizations, the AP-HP has eight world-class university hospital institutes (ICM, ICAN, IMAGINE, FOReSIGHT, PROMETHEUS, lnovAND, reConnect, THEMA) and the largest health data warehouse ( EDS) French. A major player in applied research and innovation in health, AP-HP holds a portfolio of 810 active patents, its clinical researchers sign more than 11,000 each year scientific publications and nearly 4,400 research projects are currently under development, all promoters combined. In 2020, AP-HP obtained the Carnot Institute label, which rewards the quality of partnership research: Carnot@AP-HP offers industrial players solutions in applied and clinical research in the field of health. The AP-HP also created the AP-HP Foundation in 2015, which acts directly with caregivers in order to support the organization of care, hospital staff and research within the AP–HP. http://www.aphp.fr
