Abstract
Gene expression data sets hold the promise to provide cancer diagnosis on the molecular level. However, using all the gene profiles for diagnosis may be suboptimal. Detection of the molecular signatures not only reduces the number of genes needed for discrimination purposes, but may elucidate the roles they play in the biological processes. Therefore, a central part of diagnosis is to detect a small set of tumor biomarkers which can be used for accurate multiclass cancer classification. This task calls for effective multiclass classifiers with built-in biomarker selection mechanism. We propose the sparse optimal scoring (SOS) method for multiclass cancer characterization. SOS is a simple prototype classifier based on linear discriminant analysis, in which predictive biomarkers can be automatically determined together with accurate classification. Thus, SOS differentiates itself from many other commonly used classifiers, where gene preselection must be applied before classification. We obtain satisfactory performance while applying SOS to several public data sets.
References
Dec 1, 1994·Human Genetics·F SchwartzG Bruns
Oct 16, 1999·Science·T R GolubE S Lander
Feb 17, 2000·Nature·A A AlizadehL M Staudt
Dec 14, 2001·Proceedings of the National Academy of Sciences of the United States of America·S RamaswamyT R Golub
Jan 25, 2002·Nature·Scott L PomeroyTodd R Golub
May 16, 2002·Proceedings of the National Academy of Sciences of the United States of America·Robert TibshiraniGilbert Chu
Sep 10, 2002·Bioinformatics·Danh V Nguyen, David M Rocke
Jun 13, 2003·Bioinformatics·Yoonkyung Lee, Cheol-Koo Lee
Feb 19, 2004·Biometrics·Debashis Ghosh
Apr 9, 2004·BMC Bioinformatics·Kamesh MunagalaPatrick O Brown
Oct 7, 2004·Bioinformatics·Marcel Dettling
Apr 9, 2005·Bioinformatics·Jane Jijun LiuXuefeng Bruce Ling
Jul 28, 2005·Journal of Biomedicine & Biotechnology·Debashis Ghosh, Arul M Chinnaiyan
Feb 3, 2006·Bioinformatics·Ja-Yong KooJae Won Lee
Aug 3, 2006·Bioinformatics·Chad A DavisRalf Zimmer
Citations
Feb 11, 2012·Journal of the Royal Statistical Society. Series B, Statistical Methodology·Daniela M Witten, Robert Tibshirani
Sep 30, 2010·The Journal of Comparative Neurology·Jason B NikasWalter C Low
Jan 10, 2013·NeuroImage·Logan GrosenickJonathan E Taylor
Aug 15, 2017·Journal of Animal Science·B R BrunsvigD W Brake
Nov 3, 2015·Journal of Animal Science·C LeeK A Beauchemin
Aug 15, 2017·Journal of Animal Science·C LeeK A Beauchemin
May 29, 2015·Journal of Animal Science·C LeeK A Beauchemin
May 29, 2015·Journal of Animal Science·C LeeK A Beauchemin
Jan 14, 2021·Journal of Neural Engineering·Linda Katherine Wood FordBrendan Ames
Jul 19, 2019·Neural Networks : the Official Journal of the International Neural Network Society·Duy Nhat Phan, Hoai An Le Thi