Immunai raises $60 million to analyze the immune system with AI

Immunai, a startup developing an AI platform to analyze the human immune system, today announced that it raised $60 million. The company says it will use the funds to broaden its functional genomics capabilities and help its partners prioritize, discover, and develop new therapies and drug combinations.

Emerging treatments like gene cell therapies and cancer immunotherapies promise to revolutionize the field of medicine. But the immune system’s complexity — trillions of cells partitioned into hundreds of types and states that interplay with various systems and proteins — threatens to stymie research. In 1999, a patient in a trial died after an immune system attack likely resulting from preexisting antibodies against a virus used as part of gene therapy — a death that experts believe led to years lost in gene therapy development. Immunai aims to prevent such mistakes with immune profile-generating AI.

Immunai was founded in 2018 by Noam Solomon, an ex-Harvard and -MIT postdoctoral researcher, and Luis Voloch, an MIT graduate and former machine learning engineer at Palantir. The two teamed up with members of the Parker Institute, which works with researchers to accelerate the development of immune therapies, to pursue a platform that sheds light on cell populations post- and pre-treatments.

“When I met my cofounder Luis, I was a math postdoc at MIT and Luis was working to apply machine learning to biology. Together, we wanted to bring ‘transfer learning’ AI methods to what we believe would solve the biggest problem in society today — disease,” Solomon told VentureBeat via email. “All disease can be traced back to the immune system. But what Luis and I realized is that pharmaceutical companies don’t have access to any comprehensive, granular insight into how the immune system works, how it responds to the drugs or therapies they’re developing, and what patients are most likely to benefit.”

Immunai’s tech records over a terabyte of data from a blood sample, profiling cells at what the company characterizes as “unprecedented” depth. Samples are compared with a database using AI that maps data to hundreds of cell types and states, creating immune profiles.

It’s an approach similar to that of scientists affiliated with the Human Vaccines Project, who are working to identify biomarkers — i.e., indicators of particular disease states — that predict immune responses to vaccines and cell therapies. Microsoft and startup Adaptive Biotechnologies are also collaborating to develop algorithms that create a “translation map” for cell receptors to antigens, or pathogen molecules that trigger an immune response, and map those antigens back to diseases.

Clinical studies have traditionally focused on testing thousands or even tens of thousands of subjects and collecting a limited amount of data on each. But massive corpora and AI enable millions of data points to be collected about a single individual.

“The immune system is implicated in nearly every illness, making our technology critical for identifying, diagnosing, and treating disease, from cancer to autoimmune disorders,” Solomon said in a statement. “Our expansion into functional genomics will help our partners tackle their most pressing questions in therapy development, and will ultimately improve the lives of many patients.”

Immunai’s immune profiles could support the discovery of biomarkers by spotting changes in cell type and expression. For example, the Immunai team characterized a CAR-Natural Killer T (NKT) infusion cell therapy product developed at the Baylor College of Medicine for use in neuroblastoma patients. Baylor researchers and Immunai identified a gene potentially involved in CAR-NKT-mediated killing of tumor cells and are working to validate it. Elsewhere, Immunai says it’s engaging with commercial partners to develop cell therapy candidates in solid tumors.

Voloch says that Immunai is working with 5 of the world’s largest pharma companies in addition to institutions including Stanford, Harvard, Memorial Sloan Kettering, and the University of Pennsylvania. “We’ve developed a novel platform to reprogram immunity by mining AMICA, our proprietary harmonized single-cell immunology database, with cutting-edge transfer and multi-task learning algorithms,” he added. “Our vertically integrated functional genomics and AI capabilities allow us to  prioritize and validate targets more accurately.”

Seventy-employee Immunai is headquartered in New York City, with offices in San Francisco and Tel Aviv. The series A round announced today was led by the Schusterman Foundation, the Duquesne Family, Catalio Capital Management, and Dexcel Pharma. Existing investors Viola Ventures and TLV Partners also participated, bringing Immunai’s total raised to date to $80 million.