Paper Info
Title
Integrative Biomarker Discovery for Breast Cancer Metastasis from Gene Expression and Protein Interaction Data Using Error-tolerant Pattern Mining
Abstract
Biomarker discovery for complex diseases is a chal- lenging problem. Most of the existing approaches identify individual genes as disease markers, thereby missing the interactions among genes. Moreover, often only single bi- ological data source is used to discover biomarkers. These factors account for the discovery of inconsistent biomark- ers. In this paper, we propose a novel error-tolerant pattern mining approach for integrated analysis of gene expression and protein interaction data. This integrated approach in- corporates constraints from protein interaction network and efficiently discovers patterns (groups of genes) in a bottom- up fashion from the gene-expression data. We call these patterns active sub-network biomarkers. To illustrate the efficacy of our proposed approach, we used four breast can- cer gene expression data sets and a human protein interac- tion network and showed that active sub-network biomark- ers are more biologically plausible and genes discovered are more reproducible across studies. Finally, through path- way analysis, we also showed a substantial enrichment for known cancer genes and hence were able to generate rel- evant hypotheses for understanding the molecular mecha- nisms of breast cancer metastasis.
Year
Venue
Keywords
2010
BICoB
bottom up,breast cancer,gene expression,general relativity
Field
DocType
Citations 
Metastasis,Biological data,Gene,Breast cancer,Biology,Gene expression,Interaction network,Biomarker (medicine),Bioinformatics,Biomarker discovery,Genetics
Conference
3
PageRank 
References 
Authors
0.45
15
6
Name
Order
Citations
PageRank
Rohit Gupta1382.58
Smita Agrawal2142.16
Navneet Rao329413.51
Ze Tian4704.91
Rui Kuang548431.16
Vipin Kumar6205.66