PUGSVM: A caBIG analytical tool for multiclass gene selection and predictive classification

Guoqiang Yu, Huai Li, Sook Ha, Ie Ming Shih, Robert Clarke, Eric P. Hoffman, Subha Madhavan, Jianhua Xuan, Yue Wang

Research output: Contribution to journalArticlepeer-review

Abstract

Summary: Phenotypic Up-regulated Gene Support Vector Machine (PUGSVM) is a cancer Biomedical Informatics Grid (caBIG) analytical tool for multiclass gene selection and classification. PUGSVM addresses the problem of imbalanced class separability, small sample size and high gene space dimensionality, where multiclass gene markers are defined by the union of oneversus-everyone phenotypic upregulated genes, and used by a well-matched one-versus-rest support vector machine. PUGSVM provides a simple yet more accurate strategy to identify statistically reproducible mechanistic marker genes for characterization of heterogeneous diseases.

Original languageEnglish (US)
Article numberbtq721
Pages (from-to)736-738
Number of pages3
JournalBioinformatics
Volume27
Issue number5
DOIs
StatePublished - Mar 2011

ASJC Scopus subject areas

  • Statistics and Probability
  • Biochemistry
  • Molecular Biology
  • Computer Science Applications
  • Computational Theory and Mathematics
  • Computational Mathematics

Fingerprint Dive into the research topics of 'PUGSVM: A caBIG<sup>™</sup> analytical tool for multiclass gene selection and predictive classification'. Together they form a unique fingerprint.

Cite this