A hypergraph-based learning algorithm for classifying arraycgh data with spatial prior

Ze Tian, TaeHyun Hwang, Rui Kuang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Array-based comparative genomic hybridization (arrayCGH) has been used to detect DNA copy number variations at genome scale for molecular diagnosis and prognosis of cancer. A special property of arrayCGH data is that, among the spot-intensity variables in the arrayCGH data, there are spatial relations introduced by the layout of the probes along the chromosomes. Standard classification algorithms are not capable of capturing the spatial relations for accurate cancer classification or biomarker identification from the arrayCGH data. We introduce a hypergraph based learning algorithm to classify arrayCGH data with spatial priors modeled as correlations among variables for cancer classification and biomarker identification. In the experiments, we show that, by incorporating the spatial relations among the spots as prior, our algorithm is more accurate than other baseline algorithms on a bladder cancer arrayCGH data. Furthermore, some discriminative regions identified by our algorithm contain genomic elements that are cancer-relavent.

Original languageEnglish (US)
Title of host publication2009 IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS 2009
DOIs
StatePublished - 2009
Event2009 IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS 2009 - Minneapolis, MN, United States
Duration: May 17 2009May 21 2009

Publication series

Name2009 IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS 2009

Other

Other2009 IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS 2009
Country/TerritoryUnited States
CityMinneapolis, MN
Period5/17/095/21/09

ASJC Scopus subject areas

  • Molecular Biology
  • Computational Theory and Mathematics
  • Computer Vision and Pattern Recognition
  • Biomedical Engineering

Fingerprint

Dive into the research topics of 'A hypergraph-based learning algorithm for classifying arraycgh data with spatial prior'. Together they form a unique fingerprint.

Cite this