This article has been updated to reflect the correct amount of funding awarded under the Convergence 1.0 grants.
CHICAGO (GenomeWeb) – Stand Up to Cancer is committing $11 million to fund research on immune system responses to cancer treatments, in part by applying Microsoft machine learning and artificial intelligence. Several of the projects being funded lean heavily on genome interpretation and other omics-related technologies.
SU2C announced these three-year Convergence 2.0 multidisciplinary research awards today at the organization's Scientific Summit in Santa Monica, California. The charity had awarded $12.5 million in the Convergence 1.0 first round of grants in 2016.
"Through the collaboration with Microsoft, and using well characterized, de-identified patient data, we will look at how individuals vary in their immune responses to an array of therapies. And we will create standardized measurement protocols that may speed the development of cancer therapies and ultimately save lives," Arnold Levine, chair of the SU2C Convergence Initiative and professor emeritus of the Institute for Advanced Study in Princeton, New Jersey, said in a statement.
Notable among the seven grant recipients is a team from the Yale School of Medicine and the University of Pennsylvania Perelman School of Medicine, which will study single-cell multi-omics data sets to assess the efficacy of CAR-T immunotherapies. This group, also funded by the Society for Immunotherapy of Cancer, will apply machine learning and other computational models to help identify molecular characteristics of CAR-T in hopes of discovering new cancer biomarkers.
Another group, from the Dana-Farber Cancer Institute and the Broad Institute, will use tools such as CRISPR to explore potential tumor sensitivity and resistance to natural killer cells. These researchers then will apply analytics techniques to validate the biomarkers they find.
Researchers from MIT, Penn, Memorial Sloan Kettering Cancer Center, Dana-Farber, and the Broad will use their awards to develop technology for integrating multi-omic data machine learning, and natural language processing to mine free text in medical records and test results in hopes of identifying patients who might benefit from existing immunotherapies, SU2C added.