Bob Thurman

Research Scientist
Noble Lab
University of Washington Division of Medical Genetics

Research Profile

Currently I'm working on analysis to integrate a variety of genomic datasets as part of the ENCODE project. A lot of that work uses wavelets as a tool to normalize disparate datasets to a common set of scales so that they can be properly correlated, and to uncover higher-order features in the data. See the related links under Presentations below.

I'm also interested in the very difficult problem of motif discovery, both using existing tools and developing new algorithms based on machine learning techniques.

A somewhat dormant project is the application of support vector machines to identify promoter regions of the genome, using the so-called "promoter kernel".

Links to work pages:

Contact Information

    1705 NE Pacific St
    Health Sciences J-205
    Box 357720
    Seattle WA 98195-7720
    rthurman@u.washington.edu
    206-543-8916

Presentations

"The Multicategory Support Vector Machine (MSVM)," March 2, 2005, Lab group meeting. Slides from the presentation.
References:
- Yoonkyung Lee, Yi Lin, and Grace Wahba (2004), "Multicategory Support Vector Machines: Theory and Application to the Classification of Microarray Data and Satellite Radiance Data," Journal of the American Statistical Association, Theory and Methods, 99 (465), 67-81.
- Yi Lin (2002), "Support Vector Machines and the Bayes Rule in Classification," Data Mining and Knowledge Discovery, 6, 279-275.
"Feature extraction and quantification for mass spectrometry in biomedical applications using the mean spectrum" May 11, 2005 Lab group meeting. Slides from the presentation.
References:
- Jeffrey S. Morris, Kevin R. Coombes, John Koomen, Keith Baggerly and Ryuji Kobayashi (2005), "Feature extraction and quantification for mass spectrometry in biomedical applications using the mean spectrum," Bioinformatics, 21 (9), 1764-1775.
- Kevin R. Coombes, John Koomen, Keith Baggerly, Jeffrey S. Morris, and Ryuji Kobayashi (2005), "Understanding the characteristics of mass spectrometry data through the use of simulation," Cancer Informatics, 1 (1), 41-52.
- Kevin R. Coombes, Spiridon Tsavachidis, Jeffrey S. Morris, Keith Baggerly, Mien-Chie Hung, and Henry M. Kuerer (2005), "Improved peak detection and quantification of mass spectrometry data acquired from surface-enhanced laser desorption and ionization by denoising spectra with the undecimated discrete wavelet transform," Proteomics, to appear.
"Discovery of higher-order functional features in large genomes,"

UW Department of Genome Sciences Research Reports, February 28, 2006. Slides from the presentation.
UW Computer Science Department computational biology seminar, May 1, 2006. Slides from the presentation.
Cold Spring Harbor Laboratory, Biology of Genomes meeting, May 10 - 14, 2006. Poster (pdf)., Poster (ps).
ENCODE meeting, Bethesday, MD, July 5 - 7, 2006. Poster (pdf).

Biographical Information

My background is in mathematics and computing. I received my Ph.D. in Mathematics from the University of Michigan. My research area was complex analysis, and my advisor was Peter Duren. I have always maintained an interest in computation and programming. I had a postdoctoral fellowship at the Geometry Center, University of Minnesota. I taught for two years in the Department of Mathematical Sciences at the University of Texas at El Paso, and for one year in the Mathematics Department at Pacific Lutheran University. Prior to coming to the Noble Lab, I worked for four years as a research scientist at Insightful Corporation, makers of S-PLUS.

Other Stuff

Genome Sciences Retreat, 2006, Sleeping Lady Resort, Leavenworth, WA

At the retreat in Sleeping Lady Resort, Leavenworth, WA, several of us went on a really spectacular hike to Lake Minotaur, about 30 miles away from the resort in the Henry M. Jackson Wilderness of the Wenatchee National Forest. Here are some pictures.