A team of engineers at the University of Southern California has created a new AI framework that should help speed-up the analysis of COVID vaccine candidates as well as find the best preventative medical therapies.
With the new mutations, it is even more important to make sure that the vaccines are efficient and working. Hence, scientists believe that AI could become one of the most powerful tools in the fight to eradicate COVID-19.
It was found out that the AI was able to eliminate 95% of the compounds that could treat the pathogen and pinpointed the best options in SARS-CoV-2. Thus, the machine-learning model could accomplish vaccine design cycles in a matter of seconds and minutes instead of months and years.
The AI framework will find vaccine candidates within seconds and get them to clinical trials quickly to achieve preventive medical therapies without compromising safety. Besides, the model should also help scientists to adapt and remain ahead of the mutations.
Hence, it was reported that the AI framework was able to predict 26 potential vaccines that would work against the coronavirus and, among them, 11 from which to construct a multi-epitope vaccine, that can attack the spike proteins that the virus uses to penetrate a host cell.
The research revealed that this method can provide accurate predictions with over 700,000 different proteins in the dataset. Besides, this framework should also help tackle the most frequent mutations as well as deal with other potentially unknown mutations.