|
University of Houston • University of Houston-Clear Lake • ISSO Annual Report Y2005 • 102
A Recursive Application of a Support Vector Machine for Protein Spot Detection in 2-Dimensional Gel Electrophoresis
The analysis of large collections of proteins has historically utilized two-dimensional polyacrylamide gel electrophoresis. Proteomic technology, however, needs less labor-intensive protein spot detection methodology. UHCL resarchers are studying techniques for recurseively applying a Support Vector Machine (SVM) in identifying protein. An SVM can be programmed to optimize differences between classes, which correspond to the presence or absence of a protein.
Publications
Boetticher, G., H. Al-Mubaid, and K. Frasier-Scott. "Automated Hybridization of
Machine Learners for Recursive Spot Identification, Optimization, and Gel Matching of
2-Dimensional Gel Electrophoresis," J. Comp. Sci. (2005). (Accepted.)
Dasika, M. "A User Driven Protein Spot Detection Web Service On 2-Dimensional Gel
Electrophoresis," Master's thesis, U. of Houston-Clear Lake, Houston, TX. Chair: Dr.
Boetticher, 2005.
Funding and Proposals
"Mucosal Biomarkers of Viral Induced CAP," SEPSIS and CAP: Partnerships for
Diagnostics Development, National Institute of Allergy and Infectious Diseases, National
Institutes of Health, involving the University of Texas Medical Branch (UTMB), 5 years,
$251,362. (Not funded.)
"Using Machine Learners To Predict Infant RSV Infections," National Heart Lung
Blood Institute, Clinical Proteomics Programs, RFA-HL-04-019, National Institutes of
Health, involving the University of Texas Medical Branch (UTMB), 4 years, $199,282. (Not
funded.)
Institute for Space Systems Operations - Y2005 Annual Report
Copyright © 2006
|
