Research published in mBio in October 2023 shows that artificial intelligence (AI) could be used to effectively identify vaccine candidates for gonorrhoea. Using a platform called Efficacy Discriminative Education Network (EDEN), the team of researchers from the USA and Denmark screened 26 gonococcal proteins discovered by EDEN. They combined two to three antigens, adjuvanted with GLA-SE, to form 11 groups for vaccination of mice.  


The study reports that Neisseria gonorrhoeae, the “causative agent” of the sexually transmitted infection gonorrhoea, has become resistant to “almost every antibiotic in clinical use”. Alongside the resistance is a concerning increase in cases of gonorrhoea, with a 118% increase in cases reported to the CDC between 2009 and 2021.  

“There is an urgent need to develop safe and effective vaccines against gonorrhoea.”  

Developed to support efforts against the “growing problem of antibiotic resistance”, EDEN is an innovative platform that uses AI to identify antigens that will “trigger a robust, protective immune response”. Antigens are assessed on their ability to elicit this response, with promising candidates progressing before vaccine formulation.  

Evaxion Biotech explains that “the core” of this technology is a “proprietary machine-learning ensemble of AI models” that is used to “interpret immunological-relevant information about bacterial antigens that incur protection in vaccine setting”. EDEN has been “trained” on a “curated data set”. Andreas Holm Mattsson, founder of Evaxion, explained to News Medical that EDEN uses a “feature like face recognition” to “understand the difference among proteins”.  

Promising candidates 

The study identifies two “promising gonococcal vaccine candidates”. Although 8 out of 11 groups showed efficacy against the target strain, MS11, by “at least one of two measures – time to clearance or area under curve”, only a combination of NGO1549 and NGO0265 showed efficacy against H041. The authors report that, coupled with the “broad bacterial activity of sera” obtained from the group, NGO1549 and NGO0265 were selected as “lead candidates”.  

EDEN was also used to generate “scores” to predict how well antigen combinations would reduce pathogenic bacterial populations of Neisseria gonorrhoeae. Dr Sanjay Ram of the University of Massachusetts Chan Medical School believes that “this correlation has not been shown before”.  

The next steps would be to move the candidates beyond preclinical research to test in humans, but the team is also considering applying EDEN to other pathogenic microbes. How do you think EDEN might revolutionise vaccine development?  

For more technology insights don’t forget to subscribe to our weekly newsletter here.