Pitfalls of supervised feature selection

被引：144

作者：

Smialowski, Pawel ^{[1
,2
]}

Frishman, Dmitrij ^{[1
,2
]}

Kramer, Stefan ^{[3
]}

机构：

[1] Tech Univ Munich, Wissensch Zentrum Weihenstephan, Dept Genome Oriented Bioinformat, D-85350 Freising Weihenstephan, Germany

[2] Inst Bioinformat, Helmholtz Zentrum Munich, Natl Res Ctr Environm & Hlth, D-85764 Neuherberg, Germany

[3] Tech Univ Munich, Inst Informat I12, D-85748 Garching, Germany

来源：

BIOINFORMATICS | 2010年 / 26卷 / 03期

关键词：

GENE-EXPRESSION DATA; PREDICTION; BIAS;

D O I：

10.1093/bioinformatics/btp621

中图分类号：

Q5 [生物化学];

学科分类号：

070307 [化学生物学];

摘要：

引用

页码：440 / 443

页数：4

共 18 条

[1]

AHA DW, 1991, MACH LEARN, V6, P37, DOI 10.1007/BF00153759

[2]

Selection bias in gene extraction on the basis of microarray gene-expression data [J].

Ambroise, C ;

McLachlan, GJ .

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2002, 99 (10) :6562-6566

[3]

[Anonymous], 2002, Principal components analysis

[4]

Machine learning methods for predictive proteomics [J].

Barla, Annalisa ;

Jurman, Giuseppe ;

Riccadonna, Samantha ;

Merler, Stefano ;

Chierici, Marco ;

Furlanello, Cesare .

BRIEFINGS IN BIOINFORMATICS, 2008, 9 (02) :119-128

[5]

EFRON B, 2005, 22 INT C MACH LEARN, P81

[6]

Data mining in bioinformatics using Weka [J].

Frank, E ;

Hall, M ;

Trigg, L ;

Holmes, G ;

Witten, IH .

BIOINFORMATICS, 2004, 20 (15) :2479-2481

[7]

Computational Methods for Protein Secondary Structure Prediction Using Multiple Sequence Alignments [J].

Heringa, Jaap .

CURRENT PROTEIN & PEPTIDE SCIENCE, 2000, 1 (03) :273-301

[8]

Wrappers for feature subset selection [J].

Kohavi, R ;

John, GH .

ARTIFICIAL INTELLIGENCE, 1997, 97 (1-2) :273-324

[9]

Progress from CASP6 to CASP7 [J].

Kryshtafovych, Andriy ;

Fidelis, Krzysztof ;

Moult, John .

PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS, 2007, 69 :194-207

[10]

SVM approach for predicting LogP [J].

Liao, Quan ;

Yao, Jianhua ;

Yuan, Shengang .

MOLECULAR DIVERSITY, 2006, 10 (03) :301-309

← 1 2 →