USC researchers have developed a new way to combat emergency mutations of the coronavirus and accelerate vaccine development to stop the pathogen that is responsible for killing thousands of people and damaging the economy.
Using artificial intelligence (AI), the research team at the USC Viterbi School of Engineering developed a method to accelerate the analysis of vaccines and zero in on the best possible immune medical treatment.
The method is easy to adapt to analyze the mutations of the virus, ensuring that the best vaccines are identified promptly – solutions that will greatly benefit people over the growth of the virus. growth. Their machine learning model can complete vaccine design cycles that took months or years in a matter of seconds and minutes, the study says.
“This AI framework, implemented in the details of this virus, can provide vaccine candidates within seconds and move them to clinical trials quickly to achieve immune-mediated medical treatments without affecting safety, “said Paul Bogdan, associate professor of electrical and computer engineering at USC Viterbi and corresponding author of the study. “Furthermore, this can be modified to help us stay ahead of the coronavirus as it moves around the world.”
The findings appear today in Nature Research Scientific Reports
When applied to SARS-CoV-2 – the virus that causes COVID-19 – the computer model quickly eliminated 95% of the fertilizers that could have been treated by the pathogen and the identify best options, the study says.
The AI-assisted method predicted 26 vaccines that may work against the coronavirus. From those, the scientists identified the top 11 for building a multi-epitope vaccine, which can attack the spike proteins that the coronavirus uses to bind and pass through a host cell. Vaccines target the area – or epitope – of the contagion to block the spike protein, neutralizing the virus’ ability to reproduce.
In addition, the engineers can build a new multi-epitope vaccine for a new virus in less than a minute and verify its quality within an hour. In contrast, routine processes for controlling the virus require the growth of the pathogen in the laboratory, shutting it down and injecting the virus that caused infection. The process takes time and takes more than a year; at the same time, the disease spreads.
The USC approach could help counteract COVID-19 mutations
The method is especially useful at this stage of the pandemic as the coronavirus begins to circulate in numbers around the world. Some scientists are concerned that the mutations could reduce the effectiveness of vaccines with Pfizer and Moderna, which are now releasing them. Recent variations of the virus that have emerged in the United Kingdom, South Africa and Brazil appear to be spreading more easily, which scientists say will quickly lead to many more cases, deaths and hospitalizations. .
But Bogdan said if SARS-CoV-2 becomes unregulated with routine vaccines, or if new vaccines are needed to deal with other emerging viruses, the AI-backed USC method can be used to protect design another quickly.
For example, the study explains that USC scientists used only one B-cell epitope and one T-cell epitope, but by applying a larger data set and more possible combinations a more effective vaccine design tool complete and faster development. The study estimates that the method can accurately predict with over 700,000 different proteins in the data.
“The proposed vaccine design framework can address the three most commonly seen mutations and be extended to address other mutations that may be unknown,” Bogdan said.
The raw data for the research comes from a large bioinformatics database called the Immune Epitope Database (IEDB) in which scientists around the world have been compiling data about the coronavirus , among other diseases. IEDB contains more than 600,000 known epitopes from some 3,600 different species, along with the Pathogen Virus, a complementary source of information on pathogenic viruses. The genome and spike protein sequence of SARS-CoV-2 is derived from the National Center for Biotechnological Information.
COVID-19 has resulted in 87 million cases and more than 1.88 million deaths worldwide, including more than 400,000 deaths in the United States. It has damaged the social, financial and political content of many countries.
The study’s authors are Bogdan, Zikun Yang and Shahin Nazarian of USC Viterbi’s Department of Electrical and Computer Engineering Ming Hsieh.
Support for the study comes from the National Science Foundation (NSF) under the Career Award (CPS / CNS-1453860) and NSF grants (CCF-1837131, MCB-1936775 and CNS-1932620); a grant from the U.S. Army Bureau of Investigation (W911NF-17-1-0076); Defense Advanced Research Projects Agency (DARPA) Young Faculty award and Director Award (N66001-17-1-4044), and Northrop Grumman grant.
###
Disclaimer: AAAS and EurekAlert! they are not responsible for the accuracy of press releases posted to EurekAlert! by sending institutions or for using any information through the EurekAlert system.