How Adaptive Biotechnologies and Microsoft are working to 'decode' our immune response to COVID-19

Adaptive Biotechnologies and tech giant Microsoft first teamed up in 2018, they were using cloud computing to “decode” the immune system.

Using immuno-sequencing, proprietary computational modeling and machine learning, the companies began working on an atlas mapping out the interactions between the immune system and multiple diseases. This makes it possible to "read" what an immune system has fought or is currently fighting, such as certain cancers, the companies said.

The goal of the partnership was to use the biotech company’s immune sequencing capabilities combined with Microsoft's cloud computing to create a universal blood test that reads a person’s immune system to diagnose and treat diseases. 

But now, in the midst of the COVID-19 pandemic, the scope of that work has expanded in recent months. When the coronavirus began to surge in the U.S back in March, Seattle-based Adaptive pivoted to focus on how the immune system responds to COVID-19.

"We need every tool to diagnose, combat, contain and cure COVID-19," Lance Baldo, M.D., chief medical officer at Adaptive Biotechnologies told Fierce Healthcare.

Decoding COVID-19 immune response, or why some patients become critically ill while others are asymptomatic, will help advance solutions to diagnose, treat and prevent the disease, according to Adaptive.

RELATED: Microsoft announces Cloud for Healthcare, first industry-specific cloud service

Although most efforts to look at the immune response are focused on the B cell or the virus itself, Adaptive Biotechnologies' work is different because it focuses on the T cell.

T cells are the adaptive immune system’s first responders to detect any virus. These cells also recruit B cells to produce antibodies after about a week or two to potentially provide immunity against future infection, according to the company.

To date, testing for COVID-19 has either been in the form of a viral test to detect the presence of the virus or a serology test to detect the presence of antibodies to signal prior infection.

"We cannot go after just one approach. There is an important third pillar which is the cellular basis of immunity," Baldo said.

Adaptive Biotechnologies’ sequencing of T-cells sets up an "extremely large but manageable machine learning problem," according to Peter Lee, corporate vice president, Microsoft Research and Incubation.

The company's work makes it possible, for the first time, to catalog and share how the adaptive immune system responds to viruses, including the novel virus that causes COVID-19, he said.

As part of this ongoing work, Adaptive launched last week a new research and data analysis tool for vaccine developers to measure and track COVID-19 specific T-cell response in clinical trials.

T-cell response is necessary for a complete picture of immunity, according to Harlan Robins, Adaptive Biotechnologies chief scientific officer and co-founder.

The research and analysis service, called immunoSEQ T-MAP COVID, gives researchers the ability to look at the cellular immune response of their vaccine candidates or vaccines in clinical development at high throughput and with high precision and do it reproducibly, Baldo said.

RELATED: Microsoft joins Adaptive’s pursuit of blood-based diagnostics

The tool is powered by T-cell immune response data from over 1,000 COVID-19 patients from ImmuneCODE, the largest public database mapping T-cell receptors to COVID-19.

Adaptive also is pursuing an Emergency Use Authorization (EUA) from the Food and Drug Administration for a new diagnostic test for COVID-19, one that is T-cell based.

"We originally thought the first application would be in Lyme disease, but it’s very likely our first clinical application will be an EUA for a T-cell-based diagnostic for COVID-19," Baldo said. "It's an amazing opportunity to put the platform through its paces."

Spun out from Fred Hutchinson Cancer Research Center a decade ago, Adaptive focuses on developing personalized diagnostics and therapeutics using it's "immune medicine" platform.

Microsoft invested $45 million in the company two years ago as part of its partnership, placing a big bet on the use of its cloud technology in life sciences and Adaptive's capabilities to improve disease detection.

Adaptive went public in June 2019, closing up more than 100% at $40.30 a share on its first trading day, making it at the time in the top five IPO debuts that year, according to CNBC.

As part of their research partnership, Microsoft and Adaptive recently launched the ImmuneCODE database that provides a detailed population-level view into the adaptive immune response to the virus. The database is freely available to researchers.

RELATED: Apple, Google and Amazon are sprinting to battle COVID-19. Here are lessons that can be learned

It represents the largest, most detailed views of the immune response to COVID-19 in real time based on de-identified data generated from thousands of COVID-19 blood samples from patients around the globe, the companies said.

The ImmuneCODE project is a collaboration between Adaptive, LabCorp, Ilumina, which is sequencing the immune cell receptors, and Microsoft Azure’s hyperscale cloud and machine learning capabilities to help continuously update the accuracy of the immune response online in real time.

Using machine learning and cloud computing, Adaptive is able to advance the understanding of immunity which could "fundamentally change our ability to recover from this pandemic and the way in which all viruses are studied in the future," Robins said.

"What we pulled off in four months, it would have taken 10 years had we started a decade ago. We are doing something at least an order magnitude faster than we’ve done before," Baldo said.