SBIR Phase I: An omics-based computational platform for the personalization of gut microbiome therapeutics

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase I project is substantial, considering the fact that gut microbiome is now known to be one of the primary role-players in a range of diseases from asthma to inflammatory bowel disease. These diseases affect more than 120 million people and cost more than $580 B in the US. Standard treatments for many of these diseases have variable efficacy and serious side effects, calling for novel therapeutic approaches. While microbiome therapies (MBTs) have proven useful as a new class of therapeutics, their efficacy is largely affected by highly variable gut microbiota composition between individuals. Since there is no reliable approach to personalize MBTs prior to administration, MBTs are developed as a one-size-fits-all treatment. As a result, a major need exists for the development of cost-effective techniques for personalization of MBTs. By enabling new treatment scenarios and mitigating the risks associated with MBT treatments, our technology will help reduce the cost of treatment and the overall economic burden of these diseases worldwide. This Small Business Innovation Research Phase I project addresses an essential need at the intersection of microbiome research and precision medicine by developing the first technology to efficiently and reliably personalize MBTs prior to their administration. A growing body of research is unearthing the close associations between a range of diseases and the gut microbiome. As a result, MBTs are emerging as a new paradigm in medicine to fight various diseases by modulating the gut microbiota. A primary challenge, however, is the highly variable compositional and functional landscape of the gut microbiome across individuals. Despite extensive research on gut microbiome medicine over that past several years, a reliable and robust technology has proven elusive due to many impediments. The biggest challenge in personalization of MBTs is the lack of a mechanistic or statistical link between individual-specific omics data and MBT-gut interactions. Using machine learning techniques and advanced optimization approaches, we will develop a computational platform as a virtual, cost-effective tool to personalize MBTs. 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.