STTR Phase I: New Paradigm for Combination Drug Optimization and Discovery

The broader impact of this Small Business Innovation Research (STTR) Phase I project is in addressing directly the challenge of optimizing the use and discovery of drug combinations. Effective combination drug therapies optimize the therapeutic effects of these drugs and minimize harmful and/or uncomfortable side effects. Many diseases, including cancer, Alzheimer’s, heart disease, and life-threatening infections, are treated by drugs used in combination. Amazingly, the use of these drug combination is guided by analytical methods that are over 100 years old. Researchers have developed the first components of a new analytical toolkit for combination drug discovery and development across a range of disease indications. This STTR Phase 1 research project will enable the commercialization of this toolkit by discovering how to harness the power of artificial intelligence (AI) to sift through a range of existing (and future) laboratory and clinical data to find the drug combinations that work best. The combination drug toolkit may create significant value for its customers by (1) improving target selection, (2) reducing the number of drug development programs that fail, (3) increasing the efficiency of clinical trials data analysis, and (4) extending the patent life of important drugs with new viable combinations. The proposed project seeks to leverage improvements in quantitative understanding of drug – drug synergy to overcome challenges associated with the optimization and discovery of combination drug therapies. The Multidimensional Synergies of Combination (MuSyC) algorithm is valued as an improvement in understanding drug – drug synergy by rigorously defining synergy of efficacy and synergy of potency and extracting these different synergies from experimental data sets. The proposed research seeks to innovate the means of data production and integration across diverse data sources and merge this with additional relevant databases and clinical data to create an effective analytical toolkit for optimizing all stages of combination drug research and development. The research plan consists of an experimental track and a computational track. The experimental track will use the MuSyC algorithm to inform experimental design and high-throughput data collection for three use cases of considerable clinical relevance. In parallel, the Artificial Intelligence/Machine Learning approaches will be used to integrate diverse data sets with the MuSyC algorithm to predict synergies of combinations. The data track and the AI-track will then be merged to provide proof-of-concept for an AI-enabled MuSyC toolkit for optimizing combination drug use and discovery. 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.