High-dimensional pharmacogenetic prediction of a continuous trait using machine learning techniques with application to warfarin dose prediction in African Americans


Creative Commons License

Cosgun E., Limdi N. A., Duarte C. W.

BIOINFORMATICS, vol.27, no.10, pp.1384-1389, 2011 (SCI-Expanded) identifier identifier identifier

  • Publication Type: Article / Article
  • Volume: 27 Issue: 10
  • Publication Date: 2011
  • Doi Number: 10.1093/bioinformatics/btr159
  • Journal Name: BIOINFORMATICS
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.1384-1389
  • Hacettepe University Affiliated: No

Abstract

Motivation: With complex traits and diseases having potential genetic contributions of thousands of genetic factors, and with current genotyping arrays consisting of millions of single nucleotide polymorphisms (SNPs), powerful high-dimensional statistical techniques are needed to comprehensively model the genetic variance. Machine learning techniques have many advantages including lack of parametric assumptions, and high power and flexibility.