Gonorrhea, a sexually transmitted bacterial infection, afflicts over 80 million individuals globally annually. It has developed resistance to nearly all recognized antibiotics, rendering it exceptionally challenging to manage.
Image Credit: New Africa/Shutterstock.com
When left untreated, this infection can give rise to severe, and potentially fatal, complications, while also elevating an individual’s susceptibility to contracting HIV.
Recent research shows that artificial intelligence (AI) may support the recognition of a vaccine’s key ingredients. Identification of two promising antigens as candidates for a gonorrhea vaccine by an international partnership between academic and commercial scientists is published in mBio. The protective proteins are recognized using an AI model called Efficacy Discriminative Educated Network (EDEN) by scientists.
EDEN also helps in detecting the combinations of antigens to decrease the pathogenic bacterial populations of Neisseria gonorrhoeae, the microbe that causes gonorrhea.
To the best of our knowledge, this correlation has not been shown before.
Sanjay Ram, M.D., Infectious Disease Researcher, Chan Medical School, University of Massachusetts
Ram, Sunita Gulati, DSc, and their colleagues analyzed the antigens recognized by EDEN in lab and animal models.
In 2008, Andreas Holm Mattsson initiated his work in Denmark by mining published literature to compile an extensive dataset of protective surface proteins derived from various pathogenic bacteria. During that very year, Mattsson established Evaxion, an artificial intelligence (AI) immunology startup, with the aim of creating an AI-driven system capable of pinpointing vaccine targets within infectious microorganisms.
Mattsson and his colleagues implemented this new AI model to the proteomes of 10 clinically relevant strains of Neisseria gonorrhoeae to forecast a set of bacterial proteins that, in a vaccine, could support the body’s immune system to diagnose and oppose the bacteria.
EDEN uses a feature like face recognition to understand the difference among proteins.
Andreas Holm Mattsson, Author, EVAXION Biotech
After gathering the list, it was sent to Ram and Gulati in Massachusetts. “We tested and validated all of their candidates in mouse models,” says Ram. The team initially tested combinations of two or three antigens in mice. The investigation recognized two proteins involved in cell division as promising candidates, earlier known to be exposed on the surface of the cell.
Lab experiments show that the blood samples from mice vaccinated with these 2 proteins killed bacteria from multiple strains of gonorrhea in vitro. These results lined up with EDEN’s predictions. In further research, immunized mice were infected with N. gonorrhoeae, and the injection reduced the bacterial burden.
“That really was a surprise,” says Ram. “Nobody would have predicted that these 2 proteins that were believed not to be surface exposed would work in vaccines, and other researchers reacted with skepticism.”
Taking into account the effectiveness of the individual tests, the Evaxion team proceeded to merge the proteins into a single chimeric protein. This composite protein triggered an immune response that demonstrated comparable efficacy in both laboratory and animal models.
Ram observed that the investigation also unveiled a crucial mechanism for clearing N. gonorrhoeae infection by the vaccine candidate. Whether such bacterial clearance mechanisms are present in humans remains a topic for future study.
The researchers are currently utilizing EDEN to search for potential vaccine candidate proteins in other pathogenic microorganisms, including various bacteria for which EDEN has predicted high efficacy in mouse models.
Furthermore, they are exploring ways to advance beyond the potential of preclinical research and assess the protective properties of these proteins within the human body. They have recently formed a partnership with a South African biotechnology company to develop an experimental mRNA vaccine based on these antigens.
Journal Reference
Gulati, S., et al. (2023). Preclinical efficacy of a cell division protein candidate gonococcal vaccine identified by artificial intelligence. mBio. doi.org/10.1128/mbio.02500-23
Source: https://asm.org/