Immunai uses single-cell genomics and machine learning methods to map and reprogram the immune system, which enables the discovery and development of novel therapeutics for cancer, autoimmune disease, and other ailments.
Developing drugs without understanding the immune system is like throwing darts blindfolded: you may hit the right target, but it was by chance. You don’t understand how you did it, and you don’t know how to do it again. Alternatively, you may hit the wrong target and cause a lot of damage. Thus far, researchers have operated from a place of limited understanding of the immune system. Yet, investment continues to go toward programs that have low probabilities of success and often result in therapies that have unforeseen adverse side effects. With inefficient processes and high failure rates – approximately 90% of drug candidates fail to gain regulatory approval – the average cost to develop a new drug is greater than $1 billion. Researchers and clinicians need to better understand the immune system in order to accelerate their clinical trials and improve the quality of their therapies. Immunai’s dynamic insights allow its partners to look at the evolution of disease across different indications, from cancer to autoimmune disorders to cardiovascular diseases. The company aims for its platform to become a scalable benchmark for all pharma companies and to help hospitals, researchers, and clinicians find better ways to detect, diagnose, and treat various diseases by answering the most pressing questions in immuno-oncology, cell therapy, infectious disease, and autoimmunity.
Immunai is at the leading edge of advances in ML, single cell multi-omics, and big data computations, and no other companies are doing exactly what Immunai is doing. Immunai’s offering leads with better data, better analysis, and better insights for partners in drug R&D. Better Data: As AI is only as powerful as the quality of data upon which it is deployed, the size and breadth of Immunai’s cell-level knowledge base, AMICA, is a massive benefit to the company and its partners. This data is derived through a combination of approaches, such as multi-omic single cell biological assays, functional genomic screens, advanced data integration and bioinformatics infrastructure, and the integration of curated single cell data from both clinical trials and public literature. Better Analysis: By integrating machine learning into core architecture, Immunai is able to differentiate between cell subtypes and substates at hypergranular resolution, identify rare cell types and longitudinally track clonal expansion and phenotypic change, and enable harmonization analysis at scale. This provides an unprecedented breadth and depth of insight into the immune system. Better Insights: To encourage better immunological insight, Immunai characterizes immune mechanisms of response and resistance, measures immune response as a surrogate endpoint for clinical response, and measures heterogeneity in CAR T cell therapy products. In doing so, the company allows partners to design synergistic immunotherapy combinations, discover predictive markers of response or resistance, and identify rare cell subtypes or sub-states that correlate with outsized clinical effect.
Alongside Baylor College of Medicine, Immunai sought to advance treatment for solid tumor cancers, which are notoriously difficult to treat and make up 80 to 90 percent of all cancer cases. Leveraging Immunai’s technology, Baylor researchers identified a gene in CAR-NKT-mediated antitumor activity and is purposed with identifying cell therapy candidates in solid tumors. Immunai’s platform enabled the team to understand with unprecedented granularity how ex vivo numeric expansion and genetic modification affect individual NKT cells, and proved that NKT cells can cause certain solid tumors to shrink in patients. Baylor published these results in a peer-reviewed study in Nature Medicine. Similarly, Tel Aviv University leveraged Immunai's technology to support the genetic sequencing of immune cells. This study, published in PLOS Pathogens's peer-reviewed journal, led to the development of a COVID-19 antibody cocktail that acts as both a medication for patients and a preventive treatment for high-risk populations. The antibody cocktail could provide natural immunity for several months and can change the course and pace of the development of treatment for the disease.