Researchers at the University of Southern California's (USC) Viterbi School of Engineering have used Artificial Intelligence to design and analyse developing vaccines against the COVID-19 virus's emerging variants. The new findings have been published in Nature Research's "Scientific Reports".
"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," said Paul Bogdan, Associate Professor of Electrical and Computer Engineering at USC Viterbi, as quoted by USC News. "Moreover, this can be adapted to help us stay ahead of the coronavirus as it mutates around the world."
The raw data for the research comes from a giant bioinformatics database called the Immune Epitope Database (IEDB) in which scientists around the world have been compiling data about the coronavirus and other diseases. The USC team used AI to eliminate therapies and narrow-in on 26 potential vaccine designs from which 11 emerged as the best candidates to create a "multi-epitope" vaccine for the virus. By creating a vaccine that can target multiple proteins on the viral surface, scientists hope to stop the virus from replicating within the body.
By creating vaccines "in-silico" or via computerised processes, it was also much faster to assess the vaccine's quality than growing the actual pathogen, deactivating it and then injecting it as a regular vaccine, the researchers said.
In addition to this, the new technology could provide hope for multiple vaccines against emerging mutant strains of SARS-CoV-2, Bogdan added.
"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.