Multivariate boosting for integrative analysis of high-dimensional cancer genomic data

Lie Xiong, Pei Fen Kuan, Jianan Tian, Sunduz Keles, Sijian Wang

Research output: Contribution to journalArticlepeer-review

2 Scopus citations

Abstract

In this paper, we propose a novel multivariate component-wise boosting method for fitting multivariate response regression models under the high-dimension, low sample size setting. Our method is motivated by modeling the association among different biological molecules based on multiple types of high-dimensional genomic data. Particularly, we are interested in two applications: studying the influence of DNA copy number alterations on RNA transcript levels and investigating the association between DNA methylation and gene expression. For this purpose, we model the dependence of the RNA expression levels on DNA copy number alterations and the dependence of gene expression on DNA methylation through multivariate regression models and utilize boosting-type method to handle the high dimensionality as well as model the possible nonlinear associations. The performance of the proposed method is demonstrated through simulation studies. Finally, our multivariate boosting method is applied to two breast cancer studies.

Original languageEnglish (US)
Pages (from-to)123-131
Number of pages9
JournalCancer Informatics
Volume13
Issue numberSuppl. 7
DOIs
StatePublished - 2014
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Oncology
  • Cancer Research

Keywords

  • Boosting
  • Breast cancer
  • Integrative genomic analysis
  • Multivariate regression

Fingerprint

Dive into the research topics of 'Multivariate boosting for integrative analysis of high-dimensional cancer genomic data'. Together they form a unique fingerprint.

Cite this