Share
 

By Peter Lee, Corporate Vice President, Microsoft AI and Research

 

The human immune system is an amazing diagnostic system, continually adapting to detect any signs of illness in the body. Essentially, the state of the immune system tells a story about just about everything that affects a person's health. It may sound like science fiction, but what if we could “read” that story? Our scientific understanding of human health would be fundamentally advanced. And, most importantly, it would provide a foundation for a new generation of accurate medical diagnoses and treatment options.
 
Surprisingly, this is not just science fiction, but it could be science fact. And so we are excited to announce a new partnership with Seattle-based Adaptive Biotechnologies, combining the latest advances in Artificial Intelligence (AI) and machine learning with recent advances in biotechnology to build practical technology for mapping and decoding the system. human immune. Together, we have a goal that is simple to define, but also incredibly ambitious: to create a universal blood test that reads a person's immune system to detect a wide variety of diseases, including infections, cancers and early-stage autoimmune disorders. when they can be most effectively diagnosed and treated.
 
We deeply believe in the potential of this partnership with Adaptive and have made a substantial financial investment in the company. We also initiated a major research and development collaboration that involves Adaptive scientists working closely with our leading researchers to use Adaptive's innovative sequencing technology and large-scale Microsoft cloud computing and machine learning capabilities to make deep reading of the immune system a reality.
 
Adaptive CEO and co-founder Chad Robins said in a press release today that this announcement comes at a turning point in health and biotechnology, as we now have the technology to be able to map the immune system. The potential to help clinicians and researchers connect the dots and understand the relationship between disease states could eventually lead to a better understanding of human health in general.
 
Imagine a world with an “immune system X-ray”. This would open new doors to predictive medicine, as a person's immune history is believed to shape their response to new pathogens and treatments in ways that are currently not possible to explore. The impact on human health of such a universal blood test that reads a person's exposure and response to disease would be, in a word, transformational.
  
The immune system's response to the presence of disease is expressed in the genetics of special cells, called T cells and B cells, which form the distributed command and control for the adaptive immune system. Each T cell has a corresponding surface protein called a T cell receptor (TCR), which has a genetic code that targets a specific disease signal or antigen.
 
Mapping TCRs to antigens is a huge challenge, requiring very deep AI technology and machine learning capabilities, along with emerging research and computational biology techniques applied to genomics and immunosequencing. A challenge of this nature hasn't been solved before, but with the team we've formed with Adaptive, we believe we have the experience, technical capability and tenacity to solve it.
 
The result would provide a real breakthrough – a detailed look at what the immune system is doing. Simply put, sequencing the immune system can reveal the diseases the body is struggling with or has struggled with. A blood sample therefore contains the key information needed to read what the immune system is currently detecting.
 
The basis of this approach is to develop a universal T cell receptor/antigen map – a model of the sequence of T cell receptors and the codes of the antigens they have struggled with. This universal map of the immune system will allow for an early and accurate diagnosis of disease and will eventually lead to a better understanding of human health in general. Microsoft and Adaptive hope this universal map will be the key to the research and development of simple blood-based diagnostics that are widely accessible to people around the world.
 
We are incredibly excited to collaborate on this project with our partners at Adaptive, who have developed unique immunosequencing capabilities and knowledge of the immune system, coupled with very large datasets of TCR sequences. Classifying and mapping this data represents a large-scale machine learning project for which we will rely heavily on Microsoft's cloud computing capabilities and our elite research teams.
 
We are aware of this partnership and the resulting work represents a great challenge. But we believe in the impact technology can have on healthcare, specifically how AI, the cloud and collaboration with our partners can transform what's possible.
 
This project is a milestone in our Healthcare NExT initiative, aiming to empower innovators and unite leading capabilities in the life sciences and computing to dramatically accelerate the diagnosis and treatment of autoimmune, cancer and infectious diseases. At Microsoft, we believe that AI and the cloud have the power to transform healthcare – improving outcomes, providing better access and reducing costs. The Microsoft Healthcare NExT initiative was launched last year to maximize the power of artificial intelligence and cloud computing to accelerate healthcare innovation, advance science through technology and transform the life-saving potential of upcoming discoveries.
 

 

quick access

en_USEN