SBIR Phase I: A discovery and prediction platform for microbial data

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) project is to develop a software platform to automate the integration and analysis of large sets of biological data. This project will help lift the barrier that exists in data analysis and experimental planning by providing the latest computational advances in machine learning and bioinformatics. The goal is to create a cohesive data universe for microbial organisms, where each new dataset can be easily integrated, compared, and ultimately leveraged to increase collective knowledge. Such homogenized sets of structured biological data are ideal training sets for predictive models that can accelerate discovery times by transforming the traditional "shot-in-the dark" way of experimentation to guided, well-connected hypotheses, generated from the complete set of data at hand. This SBIR Phase I project proposes to build a software tool for automated hypothesis generation based on biological datasets. First, it will support the design of a novel multi-omics engine that will allow the creation of a cohesive compendium of the omics and interaction universe for microbial organisms. Second, it will lead to the development of predictive modeling tools that will interrogate and transform this data compendium into a semantic web of actionable predictions. Third, it will support the evaluation of novel active learning methodologies for omics data. This project will lead to a software architecture that can put all of these tools under one platform to empower commercial clients as well as the academic community. Once completed, the product will offer an automated, end-to-end environment and decision support engine fueled by the collective knowledge. In that sense, it will be a personalized experience on an ecosystem of pre- and post-processing services for biological data. 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.