SBIR Phase I: AI-Enabled Discovery of Multi-Omics Biomarkers Applicable to Broad Cancer Populations

The broader/commercial impact of this Small Business Innovation Research (SBIR) Phase I project is to deliver a novel software product for oncologists to browse biomarkers potentially applicable to large patient populations. The proposed software discovers novel biomarkers predictive of therapeutic responses for improved personalized cancer treatment and patient survival. This software will also facilitate the development of gene assays by biotech companies with reduced research and development costs which can lead to lower healthcare costs. Many drugs failed in clinical trials because patient responders were not well characterized. The proposed technology can identify biomarker-based patient sub-populations responding to a drug in clinical trials so that it can have a successful market entry. This Small Business Innovation Research (SBIR) Phase I project aims to develop a cloud-based software platform to identify multi-omics biomarkers critical for guiding non-small cell lung cancer treatment decisions that can be applied to broad patient populations. The proposed technology is based on the prediction logic Boolean implication networks which can better integrate disparate data, model the cyclic molecular interactions and genome-scale gene regulatory networks efficiently, and model multinary data with robust statistical tests. The project will deliver a software solution featuring a cloud-based data portal that provides access to validated biomarkers for prediction of tumor recurrence/metastasis and drug response to 21 National Comprehensive Cancer Network (NCCN) recommended treatments leveraging national cancer registries. A user-friendly web-based graphical interface will enable oncologists to select optimal treatments and assess biomarker applicability across broad populations. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.