Multi-epitope vaccines are constructed by multiple virus protein fragments rich in overlapping epitopes.
Investigators from the University of Southern California have created an artificial intelligence (AI) tool that is able to counter emergent mutations of the coronavirus disease 2019 (COVID-19), while also quickening the development of vaccines, potentially aiding in putting the ongoing pandemic to an end. Data from the study was published in the journal Scientific Reports.
The team behind the study gathered data from the Immune Epitope Database (IEDB), the Virus Pathogen Resource and the National Center for Biotechnical Information. They then developed an AI tool that is able to speed up the analysis of vaccines and home in on the best preventative medical therapy. The tool lends itself easily to adapt to analyzing viral mutations, accomplishing vaccine design cycles in a matter of minutes instead of the typical months or years.
Employing the new tool, they were able to eliminate 95% of compounds that have the potential to treat COVID-19, focusing on 26 of the best possible therapies. Of those 26, the investigators identified 11 to create a vaccine that is able to attack the viral spike proteins to disrupt them and neutralize the replication process.
"This AI framework, applied to the specifics of this virus, can provide vaccine candidates within seconds and move them to clinical trials quickly to achieve preventive medical therapies without compromising safety," Paul Bogdan, associate professor of electrical and computer engineering at USC Viterbi and corresponding author of the study said. "Moreover, this can be adapted to help us stay ahead of the coronavirus as it mutates around the world."
The investigators believe that they will be able to create new multi-epitope vaccines for novel variants in less than 1 minute, while also validating within an hour their quality. This process is usually lengthy, lasting up to a year, time that can’t be wasted when there is an epidemic spreading through the world.
"The proposed vaccine design framework can tackle the three most frequently observed mutations and be extended to deal with other potentially unknown mutations," Bogdan said.