University of Southern California researchers have developed an AI framework to counter emergent mutations of the coronavirus and accelerate vaccine development.
Public health emergency
SARS-CoV-2, first detected in 2019 in Wuhan, has spread globally causing millions of deaths and devastating the global economy. There is currently no single specific antiviral therapy for SARS-CoV-2. Methods to control the virus are early diagnosis, reporting, isolation, supportive treatments and timely publishing of information. In addition, during the last few months, several vaccines have begun to be rolled out across the globe.
The traditional process of vaccine design is based on growing pathogens. This however is very time-consuming and therefore, does very little to avoid the current spread of disease. More recently, researchers have been working on constructing multi-epitope vaccines by in silico methods based on immunoinformatics. This removes the need to grow pathogens which can accelerate the vaccine design process. Multi-epitope vaccines can be powerful for fighting viral infections, providing excellent vaccine candidates for clinical trials.
Vaccine
In this study, published in Scientific Reports, researchers proposed an in silico deep-learning approach for prediction and design of a multi-epitope vaccine (DeepVacPred). This computational framework specifically combines in silico immunoinformatics and deep neural network strategies.
The team found that this AI-assisted method was able to predict 26 potential vaccines that would work against the virus. From those, the scientists identified the best 11 from which to construct a multi-epitope vaccine for SARS-CoV-2.
Most importantly, this method allows engineers to construct a new multi-epitope vaccine for a new virus in less than a minute and validate its quality within an hour. This method is particularly useful currently as the coronavirus continues to mutate across populations. In fact, the designed multi-epitope vaccine can tackle the current RNA mutations of the coronavirus.
Paul Bogdan, corresponding author of the study, noted that if the virus becomes uncontrollable by current vaccines or if new vaccines are needed to deal with other emerging viruses, then this AI-assisted method can be used to design other preventive mechanisms rapidly.
Image credit: By crowf – www.freepik.com
