Incorporating higher-order representative features improves prediction in network-based cancer prognosis analysis.

TitleIncorporating higher-order representative features improves prediction in network-based cancer prognosis analysis.
Publication TypeJournal Article
Year of Publication2011
AuthorsMa, Shuangge, Michael R. Kosorok, Jian Huang, and Ying Dai
JournalBMC Med Genomics
Volume4
Pagination5
Date Published2011 Jan 12
ISSN1755-8794
KeywordsAlgorithms, DNA, Complementary, Female, Gene Expression Profiling, Humans, Models, Statistical, Neoplasms, Neural Networks, Computer, Oligonucleotide Array Sequence Analysis, Predictive Value of Tests, Principal Component Analysis, Prognosis
Abstract

BACKGROUND: In cancer prognosis studies with gene expression measurements, an important goal is to construct gene signatures with predictive power. In this study, we describe the coordination among genes using the weighted coexpression network, where nodes represent genes and nodes are connected if the corresponding genes have similar expression patterns across samples. There are subsets of nodes, called modules, that are tightly connected to each other. In several published studies, it has been suggested that the first principal components of individual modules, also referred to as "eigengenes", may sufficiently represent the corresponding modules.RESULTS: In this article, we refer to principal components and their functions as representative features". We investigate higher-order representative features, which include the principal components other than the first ones and second order terms (quadratics and interactions). Two gradient thresholding methods are adopted for regularized estimation and feature selection. Analysis of six prognosis studies on lymphoma and breast cancer shows that incorporating higher-order representative features improves prediction performance over using eigengenes only. Simulation study further shows that prediction performance can be less satisfactory if the representative feature set is not properly chosen.CONCLUSIONS: This study introduces multiple ways of defining the representative features and effective thresholding regularized estimation approaches. It provides convincing evidence that the higher-order representative features may have important implications for the prediction of cancer prognosis.

DOI10.1186/1755-8794-4-5
Alternate JournalBMC Med Genomics
Original PublicationIncorporating higher-order representative features improves prediction in network-based cancer prognosis analysis.
PubMed ID21226928
PubMed Central IDPMC3037289
Grant ListP30 ES010126 / ES / NIEHS NIH HHS / United States
P01 CA142538-01 / CA / NCI NIH HHS / United States
LM009754 / LM / NLM NIH HHS / United States
P01 CA142538-02 / CA / NCI NIH HHS / United States
CA120988 / CA / NCI NIH HHS / United States
P01 CA142538 / CA / NCI NIH HHS / United States
CA142774 / CA / NCI NIH HHS / United States
CA142538 / CA / NCI NIH HHS / United States
Project: