The novel COVID-19 test uses a mass spectrometer paired with a powerful machine-learning platform to detect SARS-CoV-2 in nasal swabs. The mass spectrometer can analyze samples in minutes, with the entire process taking a total of about 20 minutes.
A partnership between UC Davis and alumnus Maurice J. Gallagher, Jr., chairman and CEO of Allegiant Travel Company, has led to a new rapid COVID-19 test.
A recent study published Nature Scientific Reports shows the novel method to be 98.3% accurate for positive COVID-19 tests and 96% for negative tests.
“This test was made from the ground up,” said Nam Tran, lead author for the study and a professor of pathology in the UC Davis School of Medicine. “Nothing like this test ever existed. We were starting with a clean slate.”
Last year, when the pandemic brought the airline and hospitality industries almost to a standstill, Gallagher began conceptualizing approaches that would allow people to gather again safely.
Gallagher approached H. Rao Unnava, professor and dean of the UC Davis Graduate School of Management, who connected him with Tran at the School of Medicine.
Gallagher and UC Davis entered into a Sponsored Research Agreement, with support from Shimadzu Scientific Instruments, to develop an automated COVID-19 test on a mass spectrometer.
This is the first test for COVID-19 that pairs mass spectrometry with robotics and a robust automated machine learning platform to rapidly deliver test results.
“Mr. Gallagher, through his generosity as an alum, has shown how business and universities can work together in solving problems of critical importance to the world,” said Unnava. “I am glad that this groundbreaking work will continue to build on the reputation of UC Davis as a place where you always ‘Expect Greater.'”
Project builds on the prior success of MILO platform
The collaboration is part of a new center in the School of Medicine, the UC Davis Center for Diagnostic Innovation.
“This game-changing, rapid new COVID-19 test speaks to the deep expertise of our faculty and scientists to find novel solutions to pressing global health challenges,” said Allison Brashear, dean of the UC Davis School of Medicine. “It’s this kind of innovation and collaboration that has been the hallmark of our response to the pandemic.”
The machine, a mass spectrometer MALDI-TOF, or matrix-assisted laser desorption/ionization time-of-flight, uses a laser to create small particles — ions — from large molecules in the testing sample. These ionized particles create signals that can be used to identify many compounds, including those associated with microorganisms and pathogens.
For the study, 226 nasal swabs from UC Davis’ biorepository of COVID-19 tests were ionized in the Shimadzu 8020. The swabs were from leftover samples and volunteers who consented to the study. Some of the participants had COVID-19 symptoms, and some were asymptomatic.
The hundreds of peaks and signals produced by the ionized test swabs were analyzed by the automated machine learning platform MILO (Machine Intelligence Learning Optimizer). Machine learning is a subset of artificial intelligence, or AI. Tran, Rashidi and Samer Albahra are the co-developers of MILO. The platform has previously been used to predict severe infections and acute kidney disease.
For the COVID-19 test, MILO finds distinguishing patterns among the many mass spectrometry peaks and signals and deciphers which patterns correspond to the presence or absence of the SARS-CoV-2 virus in the samples.
MILO accomplished the analysis in a fraction of the time that a non-automated machine-learning approach would have taken. “This meant drastically expediting the study without compromising any performance measures,” said Rashidi.
Gallagher has launched a new startup, SpectraPass, to develop the rapid, automated system into a means to facilitate opening businesses and the economy.
Experts at UC Davis Health are helping guide the SpectraPass team through the scientific, machine learning and clinical steps needed to move the COVID-19 testing technology closer to emergency use authorization by the Food and Drug Administration (FDA).
Novel application of automated machine learning with MALDI-TOF-MS for rapid high-throughput screening of COVID-19: a proof of concept. Scientific Reports, 15 April 2021.