A novel three-class ROC method for eQTL analysis

Weichao Xu, Peikai Chen, Y. S. Hung, S. Y. Kung

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

3 Scopus citations

Abstract

The problem of identifying genetic factors underlying complex and quantitative traits such as height, weight and disease susceptibility in natural populations has become a major theme of research in recent years. Aiming at revealing the inter-dependency and causal relationship between the underlying genotypes and observed phenotypes, researchers from different areas have developed a variety of methods for expression quantitative trait loci (eQTL) mapping. Most of these methods rely on resampling-based algorithms that are computationally very expensive. To overcome the disadvantages of the current techniques, we propose a novel nonparametric method based on the volume under surface (VUS) within the framework of three-class receiver operating characteristic (ROC) analysis. With the fast algorithms developed, we can reduce the computation time of the genomewide analysis from several months down to several days.

Original languageEnglish (US)
Title of host publication2010 International Conference on Machine Learning and Cybernetics, ICMLC 2010
Pages3056-3061
Number of pages6
DOIs
StatePublished - 2010
Event2010 International Conference on Machine Learning and Cybernetics, ICMLC 2010 - Qingdao, China
Duration: Jul 11 2010Jul 14 2010

Publication series

Name2010 International Conference on Machine Learning and Cybernetics, ICMLC 2010
Volume6

Other

Other2010 International Conference on Machine Learning and Cybernetics, ICMLC 2010
Country/TerritoryChina
CityQingdao
Period7/11/107/14/10

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computational Theory and Mathematics
  • Human-Computer Interaction

Keywords

  • Expression quantitative trait loci (eQTL)
  • Nonparametric
  • Normal distribution
  • Receiver operating characteristic (ROC)
  • Volume under surface (VUS)

Fingerprint

Dive into the research topics of 'A novel three-class ROC method for eQTL analysis'. Together they form a unique fingerprint.

Cite this