Using machine learning, Immunai plans to map immune system

Using machine learning, Immunai plans to map immune system

New York-based startup Immunai launched out of stealth Thursday, announcing its plan to map the immune system and improve diagnosis and treatment of disease. 

According to the company’s founders, Immunai has already used single-cell technologies and machine learning algorithms to map out millions of immune cells.


Therapies that use components of the immune system have gained increasing popularity as cancer treatments in recent years. However, the complexity of the human body means that immune response to cell therapies can be unpredictable – and immunotherapy development can be costly.

Immunai hopes to address that through its platform, which it claims pharmaceutical companies can use to get a broader look at the immune system and more accurately track immunotherapy efficacy.

“When looking at a specific disease or patient cohort, one gets a limited and siloed view of the immune system,” said Immunai CEO Noam Solomon in a statement.

“By using machine learning and applying it to our proprietary diverse database of single-sequencing data paired with rich clinical data, our platform identifies common patterns that are not visible when looking at the narrower disease-specific view,” Solomon continued.

According to press statements, Immunai uses single-cell technologies to extract data from blood samples, then uses machine learning algorithms to map data to cell types and create immune profiles. 

“The database of immune profiles support biomarker discovery and insight generation to help answer important questions about the immune system by identifying subtle changes in cell type and state-specific expression and helping distinguish that from normal expression,” explained company representatives in a press release.


Researchers have repeatedly turned to artificial intelligence to improve the efficacy of immunotherapy treatment. 

GE Healthcare partnered with Vanderbilt University Medical Center last year to use AI to retroactively analyze data from anonymized patient records and determine better courses for care.

“Immunotherapy offers tremendous promise but given the current unpredictability of some patients’ reactions to treatments, it is also associated with increased morbidity and cost,” said Dr. Jeff Balser, president and CEO of Vanderbilt University Medical Center, at the time. 

“This partnership provides the opportunity to leverage strengths of both of our organizations to further personalize cancer care by creating new tools that allow clinicians to more accurately predict how patients will respond to a specific therapy,” Balser said.

Earlier this year, a team at the National University of Singapore unveiled a so-called cancer “scorecard,” or Tumor Matrisome Index (TMI), developed using big data and predictive analysis of more than 30,000 patient-derived biopsies. 

A patient’s TMI scores can help determine their response to immunotherapies, researchers said. 


“Our mission is to map the immune system with neural networks and transfer learning techniques informed by deep immunology knowledge,” said Immunai CTO Luis Voloch.

“This helps the speed in which drugs are developed and brought to market by elucidating their mechanisms of action and resistance,” Voloch continued. 

Kat Jercich is senior editor of Healthcare IT News.
Twitter: @kjercich
Healthcare IT News is a HIMSS Media publication.

Source: Read Full Article