Plaque assay of WH6501 slope 0m by Chisholm Lab. Creative Commons.
ViQi to Test AI on Plaque Assays
National Science Foundation grant to accelerate coronavirus research
ViQi, Inc. has been awarded a special COVID-19 grant to use artificial intelligence to accelerate vaccine development. We will use the grant to design and run a series of experiments using machine learning to detect infection in individual cells prior to the formation of plaques. If successful, the research will prove an AI can detect changes in virus-infected cells days or weeks before human observation could reliably notice the change. Since plaque assays are a vital part of virology research, this new approach would speed the search for vaccines and antivirals.
"AIs are able to identify many kinds of subtle morphological changes. Our approach will detect these changes in virus-infected cells imaged with conventional microscopy techniques, without requiring specific labels or probes. Plaques, caused by cell death, are observable by human researchers currently in 2-14 days," ViQi's Chief Science Officer Dr. Ilya Goldberg says.
"Plaque assays are some of the most time-consuming and laborious parts of the drug discovery process, but they are crucial for measuring the effects of antivirals or neutralizing antibodies on a live virus's ability to infect cells. If this is successful, it will speed up the search for vaccines and mean biologists can use high-content analysis techniques and automate antiviral compound screening," Dr. Goldberg says.
The SBIR Phase I grant was part of a special funding round in September, 2020, developed by the National Science Foundation as a response to the COVID-19 pandemic. These initial experiments will use human Beta-CoV, a close relative of SARS-CoV-2, and may have enormous potential impact for current and future pandemics, as well as research into other viruses. ViQi anticipates the AI will recognize infected cells within hours, expediting the two-week wait period for traditional assays.
ViQi CEO Kathy Yeung said the experiments would be designed and run by a multidisciplinary team with deep experience in life sciences and scalable infrastructure, and leverage ViQi's web-based platform that already supports high-content analysis workflows.
"Our success would be a watershed moment for virology. The faster we know how compounds impact the virus, the faster a vaccine can be found to stop the spread of coronaviruses and other diseases like the seasonal flu," says Ms. Yeung. “With more COVID-19 outbreaks and other seasonal viruses forecast, identifying antiviral agents quickly will be critical to our collective future.”
Read coverage of our grant win in the Santa Barbara News-Press.