Bayesian Statistics Seminar
North Carolina State University
presents
Dr. Scott Schmidler
Duke University
"Bayesian Methods in Structural Bioinformatics and Biophysics"
ABSTRACT
Most statisticians today are familiar with the various challenges associated with analysis of high-throughput genomic data. However, many interesting problems arising in other areas of biomolecular science are less well known. I will present some of our recent work in the areas of structural biochemistry and biophysics. Addressing core problems in these areas lead us to innovations in several areas of statistics, including Bayesian shape analysis, Bayesian computation and estimation in random field models, convergence rates of MCMC algorithms, and high-dimensional Bayesian variable selection. Applications include problems in protein structure analysis, macromolecular simulation, antibody-antigen binding in vaccine design, and analysis of single-molecule AFM force spectroscopy curves.
Tuesday, November, 13, 2007
4:00 - 5:00 pm
208 Patterson Hall