|
Activity Number:
|
283
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, July 31, 2007 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #309497 |
|
Title:
|
Integrated Clustering of Heterogeneous Genomic Data
|
|
Author(s):
|
Jyotsna Kasturi*+
|
|
Companies:
|
Johnson & Johnson PRD
|
|
Address:
|
1000 Route 202 South PO Box 300, Raritan, NJ, 08869,
|
|
Keywords:
|
clustering ; heterogeneous data ; information fusion ; gene expression ; motif frequency
|
|
Abstract:
|
The availability of high throughput technologies facilitates the inference of gene regulatory mechanisms on a global scale via genome-wide studies. Data from a single microarray study alone, though information-rich, lacks the specificity to identify these complex mechanisms of action, and often need to be combined with data from multiple microarray studies as well as other genomic sources such as DNA binding motifs and gene ontologies. Analytical methods that perform integrated analysis on such data are much needed. An unsupervised clustering algorithm to perform information fusion from heterogeneous genomic data to identify clusters of genes using the combined data is introduced. A weighting scheme allows the influence of each data type on the final clustering to be specified a priori. Results on real data show that this approach identifies co-regulated genes effectively.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2007 program |
