Now, an AI platform to speed up vaccine development

One of the most time-consuming part in making a vaccine is to identify the right target. Or the right protein in a pathogen which can stimulate the immune system to start making the right antibodies. A joint team of Indian and US scientists have announced the successful development of an artificial intelligence-powered platform, which can speed up the identification of this target from a few years to a matter of days.
Researchers from Amity University (Noida) and Baylor College of Medicine (BCM-Houston, USA) have developed an AI platform to find clinically important vaccine targets and epitopes that speed up the vaccine designing process for deadly infectious diseases such as COVID-19 and Chagas disease.
The results of this study have been published in UK-based journal called Scientific Reports and PubMed, titled ‘Identification of vaccine targets in pathogens and design of a vaccine using computational approaches” with Dr Kamal Rawal, scientist, associate professor and project director, Amity Institute of Biotechnology, Amity University, as the lead author. The platform, called Vaxi-AI, has been tested on 40 different pathogens, including SARS-CoV-2 (COVID-19), Mycobacterium tuberculosis (TB), Vibro cholerae (cholera) and Plasmodium falciparum (malaria).
The research was supported by the Kleberg Foundation, USA, and Baylor College of Medicine, with a total grant of USD 1.9 million. Most of the research work was done in India over four years.
“We are talking to biotech companies to include this AI platform in their next generation of vaccine development programmes,” Rawal told THE WEEK. “This AI-driven identification process will speed up vaccine development by two to three years, the cost of making them will come down and they will yield better, next-generation vaccines which can significantly reduce side effects and breakthrough infections.” He also said that AI will encourage rational vaccine designing methods.
To validate the AI system, the team shortlisted over 335 experimentally verified antigens belonging to 40 different pathogens and found their system was correctly predicting most of them with reasonable accuracy. These examples also include targets from FDA approved/marketed vaccines. The next line of action is to inject mice with these computer suggested vaccines to demonstrate that the designed vaccines are non-toxic and sufficiently immunogenic (produce enough antibodies) before entering into clinical trials.
To help other biologists working in the area of immunology and vaccines, Rawal has created a cloud-based server which can be used by the researchers across the world to analyse their proteins and genes as potential vaccine targets. In the wake of emergence of delta variant of COVID-19, the team is also engaging with various pharmaceutical and biotechnology companies for customised deployment for commercial scale application to develop new vaccines against emerging infectious diseases.

Leave a Reply

Your email address will not be published.