[ad_1]
TThe Food and Drug Administration on Friday issued emergency authorization for a new test to detect Covid-19 infections – a test that stands out from the hundreds already authorized.
Unlike tests that detect fragments of SARS-CoV-2 or antibodies against it, the new test, called T-Detect COVID, looks for signals of past infections in the body’s adaptive immune system – in particular, T cells that help the body remember. what its viral enemies look like. Developed by Seattle-based Adaptive Biotechnologies, this is the first test of its kind.
Adaptive’s approach is to map antigens to their corresponding receptors on the surface of T cells. They and other researchers have previously shown that the distribution of T cells floating in an individual’s blood reflects disease. that they encountered, in many cases years later. The next step is to try and unlock this information to help diagnose these past infections.
publicity
This challenge is extremely data-intensive. “When you think about the level of a patient, we look at an average of 300,000 to 400,000 T cells,” said Lance Baldo, medical director of Adaptive. “When you look at a population level, we look at hundreds of millions, and then ultimately billions of T cells. So that ends up being a web-wide problem. “
Enter Microsoft. In 2018, Adaptive partnered with its tech giant neighbor to build the cloud infrastructure and machine learning models needed to manage these reams of data – in particular, to build a comprehensive map of T cells to which antigens .
publicity
“Microsoft wants and wanted to get into the healthcare industry,” Baldo said. “A necessary adaptive expertise in cloud computing, machine learning and AI. So it was a pretty ideal fit. Teams from the two companies worked together one day a week, in the Adaptive office in Seattle or at Microsoft in Redmond.
When the virus started picking up speed, they quickly rotated a large part of that team to work on Covid-19. In June, they were able to access blood samples from people infected with the coronavirus and sequence the T-cell receptor genomes. Then they were able to compare this dataset to their control group – the sequence database of T cell receptors they had been working on for years – and within two months, they had collected enough data to publish their first results.
The machine learning models needed to develop the T-Detect test, in the end, were relatively straightforward. “For me that’s actually a big plus,” said Jonathan Carlson, senior director of immunomics at Microsoft and responsible for the partnership with Adaptive. “It’s a viral infection that causes a raging T cell response, and it turns out you can find the exact same T cell receptors in a lot of people. And that allows you to use a fairly straightforward statistical approach. The test reported a sensitivity of 97.1% and a specificity of 100%.
The EUA published by the FDA reflects this early approach – but it’s not the end of the evolution of the test. “When we file an application with the FDA, we do something called ‘lock the classifier’,” said Baldo, the algorithm that determines whether T cell receptors in a blood sample say, “Yes. Covid ”or“ Non Covid ”.
These T cell responses, however, can vary depending on which version of the virus you are exposed to.
“We’ve already discussed this with the FDA,” Baldo said. “You have mutations and other variations coming.” So Adaptive and Microsoft continue to improve the classifier. “Models are improving frequently,” Carlson said. “Weekly, monthly.” The question that remains, then, is: “When is it better sufficient? This is where Adaptive really spends a lot of time thinking. “
At some point, when the test reaches a new threshold of sensitivity and specificity, they plan to file a second version of the test for FDA review.
This is just one of Adaptive’s three areas of focus in the coming months, Baldo said. “One of the pillars is improving the current algorithm and making sure that we continue to do a great test as the virus continues to mutate,” he said. The second is to direct the company’s expertise on T cells to other issues surrounding Covid-19, including the impacts of the long Covid and the effectiveness and sustainability of the immune response elicited by different vaccines.
The third is to continue working on other diagnoses, for conditions like celiac disease and multiple sclerosis. Prior to the pandemic, the company was focused on developing a proof-of-concept diagnosis for Lyme disease, which it announced in November 2019.
This distributed focus will force the company to continue to develop not only its biological capabilities, but also its machine learning approaches. While his approach to testing for Covid-19 is relatively straightforward, Carlson said, “I don’t think it will work for all diseases.”
[ad_2]
Source link