Standing on the Shoulders of Giants: How Massive Knowledge-Bases are Transforming Data Analytics in Biology

Speaker: Saurabh Sinh, University of Illinois at Urbana-Champaign

Abstract: The NIH BD2K Center of Excellence at UIUC and Mayo Clinic is developing advanced analytics and cyberinfrastructure to empower biological scientists seeking to understand their genomic data sets in the context of prior biological knowledge. Our analytical approaches include combining machine learning and statistical techniques with graph mining and data mining tools in novel ways. Cyberinfrastructure challenges arise from our vision of offering the users access to a scalable, easy-to-use, cloud-based platform for performing compute-intensive analytics, obviating heavy investments in hardware, software and human resources. We also strive to achieve interoperability of this analysis system with the several emerging cloud-based data repositories that are changing the face of genomics. All of our research and development is carried out in the context of impactful driver projects that include individualized medicine for cancer and genetic bases of social behavior. This talk will present an overview of the Center’s progress towards democratizing genomics analysis.