Researchers at the University of Southern California (USC) have revealed an incredibly powerful AI-powered method for producing new candidates for the Covid-19 vaccine in minutes or even seconds.
The new process, developed at the USC Viterbi School of Engineering, could mark a major turning point in the information war against the coronavirus and its many increasingly virulent mutations that are overwhelming the already challenging worldwide launch of vaccines.
The USC team took advantage of artificial intelligence (AI) to accelerate the analysis of the vaccine, which can be adapted quickly and easily to analyze the viral mutations themselves.
Using a machine learning algorithm, the model is supposed to complete vaccine design cycles in a matter of minutes, or even seconds, in a feat that before the pandemic took months, if not years, showing how far humanity has advanced in the past 12 months or so.
“This AI structure, applied to the specifics of this virus, can deliver vaccine candidates in seconds and take them to clinical trials quickly to obtain preventive medical therapies without compromising safety,” said Paul Bogdan, associate professor of electrical and computer engineering at USC Viterbi, adding that this would allow medical researchers to “stay ahead of the coronavirus in its mutation worldwide”.
Also at rt.com
Antiviral derived from ‘deadly carrot’ could be a magic bullet against Covid-19, flu and future pandemics
The method optimizes the possible treatments for the specific strain of SARS-CoV-2, the virus that causes Covid-19, extremely quickly, eliminating about 95% of the possible compounds that could be used in vaccines.
Using only one strain of SARS-CoV-2, the system predicted 26 potential vaccines that it then reduced to just 11, all of which attack the peak virus proteins it uses to break down and enter human cells and begin to self- replicating.
The AI-powered system can create new vaccines in less than a minute and validate its quality in less than an hour, in a truly surprising and promising advance, once independently verified and thoroughly tested, of course.
The timing could not be better, as the medical community is increasingly concerned that new variants and mutations of the virus are resistant to the current generation of vaccines that are currently being launched worldwide.
In addition, the current prototype system used only two of the 700,000 possible proteins to develop its vaccine designs, opening the door to a potentially unbeatable and constantly adapting arsenal of vaccine candidates.
The machine learning algorithm extracts its intelligence from a giant bioinformatics database called Immune Epitope Database (IEDB). An epitope is the part of an antigen – something that triggers an immune response – where an antibody – the immune system’s response to an antigen – can bind.
The database contains 600,000 known epitopes from about 3,600 different species, including the SARS-CoV-2 genome and spike protein sequence.
Do you think your friends would be interested? Share this story!