Bruce Church, Ph.D.

Vice President, Analytics, Gene Network Sciences, Inc.

High Performance Computing for Industrial Scale Advanced Analytics

GNS Healthcare has deployed a key portion of its REFS(TM) machine learning and causal modeling platform on the Blue Gene/L at RPI. Running on the BG/L at CCNI gives GNS access to significant computing resources that are used in production to reverse engineer network models in problem domains across healthcare. The problems we solve range from discovering novel biology reflecting the mechanism of efficacy of drugs to modeling the processes by which hospitals and insurers deliver healthcare. I will describe both the role the BG/L plays in our computational processes and some of the challenges in using advanced HPC in a production environment.

Biography

Bruce Church leads the design and implementation of the GNS Healthcare's proprietary REFS™ network inference and forward simulation engine.

An expert in computational biophysics and supercomputing, Dr. Church spent the previous decade developing global optimization methods for computational protein folding, the results of which have been published in several peer-reviewed journals. Dr. Church has been awarded and served as the principal investigator on several major grants, including a $2.5 million award from the Department of Energy. Dr. Church received a B.S. in Applied and Engineering Physics and a Ph.D. in Applied Physics from Cornell University in Ithaca, New York.

Workshop Program
updated: 2011-10-19