Response projected clustering for direct association with physiological and clinical response data

Sung-Gon Yi,Taesung Park,Jae K Lee

doi:10.1186/1471-2105-9-76

Sung-Gon Yi, Taesung Park + Show 1 more

Open Access

https://doi.org/10.1186/1471-2105-9-76

Copy DOI

Journal: BMC Bioinformatics	Publication Date: Jan 31, 2008
Citations: 27	License type: cc-by

Affiliation: Seoul National University

Abstract

BackgroundMicroarray gene expression data are often analyzed together with corresponding physiological response and clinical metadata of biological subjects, e.g. patients' residual tumor sizes after chemotherapy or glucose levels at various stages of diabetic patients. Current clustering analysis cannot directly incorporate such quantitative metadata into the clustering heatmap of gene expression. It will be quite useful if these clinical response data can be effectively summarized in the high-dimensional clustering display so that important groups of genes can be intuitively discovered with different degrees of relevance to target disease phenotypes.ResultsWe introduced a novel clustering analysis approach, response projected clustering (RPC), which uses a high-dimensional geometrical projection of response data to the gene expression space. The projected response vector, which becomes the origin in the projected space, is then clustered together with the projected gene vectors based on their different degrees of association with the response vector. A bootstrap-counting based RPC analysis is also performed to evaluate statistical tightness of identified gene clusters. Our RPC analysis was applied to the in vitro growth-inhibition and microarray profiling data on the NCI-60 cancer cell lines and the microarray gene expression study of macrophage differentiation in atherogenesis. These RPC applications enabled us to identify many known and novel gene factors and their potential pathway associations which are highly relevant to the drug's chemosensitivity activities and atherogenesis.ConclusionWe have shown that RPC can effectively discover gene networks with different degrees of association with clinical metadata. Performed on each gene's response projected vector based on its degree of association with the response data, RPC effectively summarizes individual genes' association with metadata as well as their own expression patterns. Thus, RPC greatly enhances the utility of clustering analysis on investigating high-dimensional microarray gene expression data with quantitative metadata.

Highlights

Microarray gene expression data are often analyzed together with corresponding physiological response and clinical metadata of biological subjects, e.g. patients' residual tumor sizes after chemotherapy or glucose levels at various stages of diabetic patients
We propose a novel clustering analysis approach, the so-called response projected clustering (RPC), which accounts for both the relationships among gene expression patterns themselves and their association with response data
We introduced a novel clustering analysis approach here – response projected clustering (RPC) that can simultaneously summarize associations both with important physiological response data and with gene expression patterns themselves

Summary

Introduction

Microarray gene expression data are often analyzed together with corresponding physiological response and clinical metadata of biological subjects, e.g. patients' residual tumor sizes after chemotherapy or glucose levels at various stages of diabetic patients. Current clustering analysis cannot directly incorporate such quantitative metadata into the clustering heatmap of gene expression It will be quite useful if these clinical response data can be effectively summarized in the high-dimensional clustering display so that important groups of genes can be intuitively discovered with different degrees of relevance to target disease phenotypes. Several supervised learning and statistical modeling approaches have been used to analyze the gene expression data along with other response variables such as treatment group variables [8], clinical response data such as survival times [9], and Bayesian regression modeling [10] These approaches are often based on the dichotomization of quantitative response data, resulting in significant loss of information. These methods are mainly used for the discovery of gene factors and prediction models between different response groups and cannot provide high-dimensional association information between genes and response variables

Methods

Results

Discussion

Conclusion