Elly Yates-Roberts |
Microsoft has partnered with Seattle-based Adaptive Biotechnologies to combine the latest advances in artificial intelligence (AI) and machine learning with recent breakthroughs in biotechnology to build a technology capable of decoding the human immune system.
In a recent blog post, Peter Lee, corporate vice president at Microsoft AI and Research, discussed the partnership and how AI can be used to map out the human immune system and treat diseases in their early stages.
“Together, we have a goal that is simple to state but also incredibly ambitious: create a universal blood test that reads a person’s immune system to detect a wide variety of diseases including infections, cancers and autoimmune disorders in their earliest stage, when they can be most effectively diagnosed and treated,” said Lee.
“We now have the technology to be able to do what we’ve been talking about for the past decade – develop a universal T-cell receptor antigen map that presents an opportunity to help patients at an unprecedented scale,” said Chad Robins, president, CEO and co-founder of Adaptive Biotechnologies. “Some conditions like cancer or autoimmune disorders can be difficult to diagnose, but this universal map of the immune system will enable earlier and more accurate diagnosis of disease, potentially helping physicians to connect the dots to understand the relationship between disease states and eventually lead to a better understanding of overall human health.”
Mapping T-cell receptors (TCR) to antigens requires deep AI technology and machine learning capabilities coupled with emerging biotechnology research and techniques in computational biology applied to genomics and immunosequencing. The result would provide an insight into the workings of the immune system as sequencing it can reveal what diseases the body is currently fighting or has in the past.
“We’re incredibly excited to collaborate on this project with our partners at Adaptive, who have developed unique immunosequencing capabilities and immune system knowledge, along with very large data sets of TCR sequences,” said Lee. “Classifying and mapping this data represents a large-scale machine learning project for which we’ll lean heavily on Microsoft’s cloud computing capabilities and our elite research teams.”