Conference proceeding
Integrating multi-platform genomic data using hierarchical Bayesian relevance vector machines
Proceedings 2012 IEEE International Workshop on Genomic Signal Processing and Statistics (GENSIPS), pp.18-21
12/2012
DOI: 10.1109/GENSIPS.2012.6507716
PMCID: PMC3726335
Abstract
We present a statistical framework, hierarchical relevance vector machine (H-RVM), for improved prediction of scalar outcomes using interacting high-dimensional input covariates from different sources. We illustrate our methodology for integrating genomic data from multiple platforms to predict observed clinical phenotypes. H-RVM is a hierarchical Bayesian generalization of the relevance vector machine and its learning algorithm is a special case of the computationally efficient variational method of hierarchic kernel learning frame-work. We apply H-RVM to data from the Cancer Genome Atlas based Glioblastoma study to predict imaging-based tumor volume by integrating gene and miRNA expression data and show that H-RVM performs much better in prediction as compared to competing methods.
Details
- Title: Subtitle
- Integrating multi-platform genomic data using hierarchical Bayesian relevance vector machines
- Creators
- S Srivastava - Purdue University West LafayetteWenyi Wang - Departments of Bioinformatics and Computational BiologyP. O Zinn - The University of Texas MD Anderson Cancer CenterR. R Colen - Diagnostic RadiologyV Baladandayuthapani - The University of Texas MD Anderson Cancer Center
- Resource Type
- Conference proceeding
- Publication Details
- Proceedings 2012 IEEE International Workshop on Genomic Signal Processing and Statistics (GENSIPS), pp.18-21
- Publisher
- IEEE
- DOI
- 10.1109/GENSIPS.2012.6507716
- PMCID
- PMC3726335
- ISSN
- 2150-3001
- eISSN
- 2150-301X
- Language
- English
- Date published
- 12/2012
- Academic Unit
- Statistics and Actuarial Science
- Record Identifier
- 9984257735802771
Metrics
15 Record Views