Coronavirus analysis

AI-generated design blueprints for SARS-CoV-2 vaccines published

NEC Corporation announced analysis results from efforts using AI prediction platforms to design blueprints for SARS-CoV-2 vaccines that can drive potent T-cell responses in the majority of the global population.

This initiative by the scientific teams within the NEC Group to help combat outbreaks of COVID-19 and support international vaccine development efforts is led by NEC OncoImmunity (NOI) in collaboration with NEC Laboratories Europe (NLE). These AI prediction platforms are based on the AI technology used by NEC and NOI in the development of personalized neoantigen cancer vaccines. During the analysis, which is published at bioRxiv, the team analyzed thousands of sequences from the SARS-CoV-2 virus (responsible for causing COVID-19) and identified epitopes (potential vaccine targets) for the 100 most frequent HLA alleles (diverse immunological makeup) in the global population.

Photo

Image source: Centers for Disease Control and Prevention (CDC) / Alissa Eckert, MS; Dan Higgins, MAMS

The prediction algorithms scanned for epitopes across the entire repertoire of proteins in SARS-CoV-2, not only the spike surface protein that gives this family of coronavirus its name. The team then used this data to identify "hotspots" in the viral proteome that contained overlapping and co-located epitopes from multiple HLA-alleles. The optimal constellation of "hotspots" was then selected by their algorithms to generate the optimal immune response with the broadest coverage of the human population, whilst prioritizing hotspots that occurred in conserved regions of the viral proteome. These conserved regions are less likely to mutate in future strains. In addition, hotspots containing viral epitopes that had significant similarity with human proteins, especially those expressed in critical organs, were removed from the vaccine design blueprints to avoid adverse effects.

The analysis demonstrates the significant capabilities of the NEC Group to leverage their AI platforms to design blueprints for a vaccine that is safe and efficacious in a global population and could address the current and future divergent strains of the SARS-CoV-2 virus. NEC is now publishing this research to support scientific advancements in the field and is ready to start partnering efforts to pursue the development of an effective vaccine targeting the global population.

This is an important step towards the development of an effective vaccine for the global population

Saverio Niccolini

"We are pleased that NEC's AI technology can contribute to the resolution of serious problems facing the world today. As a company that seeks to enhance the well-being of society, NEC will continue to capitalize on research and development that maximizes the strengths of our AI technology to help prevent the spread of COVID-19. In collaboration with companies and institutions around the world, we aim to enable people to live their daily lives with as much safety and security as possible," said Motoo Nishihara, Executive Vice President and Chief Technology Officer at NEC.

"It has been exhilarating hard work between our CEO, Dr. Richard Stratford, the entire team at NEC OncoImmunity and our colleagues in the NEC Group to adapt our NEC Immune Profiler technology from its current cancer focus and quickly make it applicable to infectious diseases to help deal with the COVID-19 threat. It is encouraging that our AI and bioinformatics platform can design vaccine blueprints that have the potential to induce a broad immune response, that may not only be protective for the global population, but also stimulate a long-lived memory immune responses against SARS-CoV-2 and its future mutated versions," said Dr. Trevor Clancy, Chief Scientific Officer at NEC OncoImmunity and the lead corresponding author in the paper.

"We have been repurposing our algorithms originally designed for predicting immune responses in individual cancer patients to scale to large population targets for infectious diseases. The in-silico validation of our algorithms takes into account the genetic background of humans across all continents. Now demonstrating that our predictions can contribute to the worldwide efforts to stop COVID-19 is of utmost importance. We have already started discussions with partner organizations for wet-lab validation activities. This is an important step towards the development of an effective vaccine for the global population," said Dr. Saverio Niccolini, General Manager of the Data Science and System Platform Division at NEC Laboratories Europe GmbH. 


Source: NEC Corporation

23.04.2020

More on the subject:
Read all latest stories

Related articles

Photo

Joint Research

AI helps diagnosing Covid-19

Fujitsu and Tokyo Shinagawa Hospital today announced the launch of a joint R&D project for AI technology to support diagnostic imaging via chest CT (Computed Tomography), which represents a…

Photo

Reducing coronavirus test burden

AI speeds up COVID-19 screening in emergency rooms

Researchers from Eindhoven University of Technology (TU/e) and the Catharina Hospital in Eindhoven have developed a new algorithm for the rapid screening for COVID-19. The software is intended for…

Photo

Improved accuracy and efficiency

AI could improve CT screening for COVID-19

Researchers at the University of Notre Dame are developing a new technique using artificial intelligence (AI) that would improve CT screening to more quickly identify patients with the coronavirus.…