A new data analysis tool developed by Yale researchers has revealed specific immune cell types associated with an increased risk of death from COVID-19, they report Feb. 28 in the journal Nature Biotechnology.
Immune system cells such as T cells and antibody-producing B cells are known to provide broad protection against pathogens such as SARS-CoV-2, the virus that causes COVID-19. And large-scale data analyzes of millions of cells have given scientists broad insight into the immune system’s response to this particular virus. However, they also found that certain immune cell responses – including cell types that are typically protective – can sometimes trigger lethal inflammation and death in patients.
Other data analysis tools that allow examination down to the level of individual cells have given scientists clues about the culprits in severe COVID cases. But these focused viewpoints often lack the context of particular cell groupings that might lead to better or worse outcomes.
The Multiscale PHATE tool, a machine learning tool developed at Yale, allows researchers to go through all data resolutions, from millions of cells to a single cell, in minutes. The technology relies on an algorithm called PHATE, created in the lab of Smita Krishnaswamy, associate professor of genetics and computer science, which overcomes many of the shortcomings of existing data visualization tools.
“Machine learning algorithms typically focus on a single-resolution view of the data, ignoring information that may be found in other more focused views,” said Manik Kuchroo, a doctoral student at Yale School of Medicine who helped developing the technology and is co-lead author. paper. “For this reason, we created Multiscale PHATE which allows users to zoom in and focus on specific subsets of their data to perform more detailed analysis.”
Kuchroo, who works in Krishnaswamy’s lab, used the new tool to analyze 55 million blood cells taken from 163 patients admitted to Yale New Haven Hospital with severe cases of COVID-19. Overall, they found that high levels of T cells appeared to protect against poor outcomes, while high levels of two types of white blood cells called granulocytes and monocytes were associated with higher levels of mortality.
However, when the researchers got down to a more granular level, they found that TH17, a helper T cell, was also associated with higher mortality when grouped with the immune system cells IL-17 and IFNG.
By measuring the amounts of these cells in the blood, they could predict whether the patient lived or died with 83% accuracy, the researchers report.
“We were able to rank the risk factors for mortality to show which are the most dangerous,” Krishnaswamy said.
In theory, the new data analysis tool could be used to refine risk assessment across a host of diseases, she said.
Jessie Huang of Yale’s Department of Computer Science and Patrick Wong of the Department of Immunobiology are co-lead authors of the paper. Akiko Iwasaki, Waldemar Von Zedtwitz Professor of Immunobiology, is corresponding co-author.