% This file was created with JabRef 2.3.1.
% Encoding: Cp1252

@ARTICLE{Ambroise2002,
  author = {Christophe Ambroise and Geoffrey J McLachlan},
  title = {Selection bias in gene extraction on the basis of microarray gene-expression
	data.},
  journal = {Proc Natl Acad Sci U S A},
  year = {2002},
  volume = {99},
  pages = {6562--6566},
  number = {10},
  month = {May},
  abstract = {In the context of cancer diagnosis and treatment, we consider the
	problem of constructing an accurate prediction rule on the basis
	of a relatively small number of tumor tissue samples of known type
	containing the expression data on very many (possibly thousands)
	genes. Recently, results have been presented in the literature suggesting
	that it is possible to construct a prediction rule from only a few
	genes such that it has a negligible prediction error rate. However,
	in these results the test error or the leave-one-out cross-validated
	error is calculated without allowance for the selection bias. There
	is no allowance because the rule is either tested on tissue samples
	that were used in the first instance to select the genes being used
	in the rule or because the cross-validation of the rule is not external
	to the selection process; that is, gene selection is not performed
	in training the rule at each stage of the cross-validation process.
	We describe how in practice the selection bias can be assessed and
	corrected for by either performing a cross-validation or applying
	the bootstrap external to the selection process. We recommend using
	10-fold rather than leave-one-out cross-validation, and concerning
	the bootstrap, we suggest using the so-called .632+ bootstrap error
	estimate designed to handle overfitted prediction rules. Using two
	published data sets, we demonstrate that when correction is made
	for the selection bias, the cross-validated error is no longer zero
	for a subset of only a few genes.},
  doi = {10.1073/pnas.102102699},
  institution = {Laboratoire Heudiasyc, Unité Mixte de Recherche/Centre National de
	la Recherche Scientifique 6599, 60200 Compiègne, France.},
  keywords = {Discriminant Analysis; Gene Expression; Linear Models; Oligonucleotide
	Array Sequence Analysis; Selection Bias},
  owner = {wtalloen},
  pii = {102102699},
  pmid = {11983868},
  timestamp = {2008.05.21},
  url = {http://dx.doi.org/10.1073/pnas.102102699}
}

@ARTICLE{Diaz-Uriarte2006,
  author = {Ramón Díaz-Uriarte and Sara Alvarez de Andrés},
  title = {Gene selection and classification of microarray data using random
	forest.},
  journal = {BMC Bioinformatics},
  year = {2006},
  volume = {7},
  pages = {3},
  abstract = {BACKGROUND: Selection of relevant genes for sample classification
	is a common task in most gene expression studies, where researchers
	try to identify the smallest possible set of genes that can still
	achieve good predictive performance (for instance, for future use
	with diagnostic purposes in clinical practice). Many gene selection
	approaches use univariate (gene-by-gene) rankings of gene relevance
	and arbitrary thresholds to select the number of genes, can only
	be applied to two-class problems, and use gene selection ranking
	criteria unrelated to the classification algorithm. In contrast,
	random forest is a classification algorithm well suited for microarray
	data: it shows excellent performance even when most predictive variables
	are noise, can be used when the number of variables is much larger
	than the number of observations and in problems involving more than
	two classes, and returns measures of variable importance. Thus, it
	is important to understand the performance of random forest with
	microarray data and its possible use for gene selection. RESULTS:
	We investigate the use of random forest for classification of microarray
	data (including multi-class problems) and propose a new method of
	gene selection in classification problems based on random forest.
	Using simulated and nine microarray data sets we show that random
	forest has comparable performance to other classification methods,
	including DLDA, KNN, and SVM, and that the new gene selection procedure
	yields very small sets of genes (often smaller than alternative methods)
	while preserving predictive accuracy. CONCLUSION: Because of its
	performance and features, random forest and gene selection using
	random forest should probably become part of the "standard tool-box"
	of methods for class prediction and gene selection with microarray
	data.},
  doi = {10.1186/1471-2105-7-3},
  institution = {Bioinformatics Unit, Biotechnology Programme, Spanish National Cancer
	Centre (CNIO), Melchor Fernandez Almagro 3, Madrid, 28029, Spain.
	rdiaz@ligarto.org},
  keywords = {Algorithms; Cluster Analysis; Computer Simulation; Gene Expression
	Profiling; Models, Genetic; Models, Statistical; Oligonucleotide
	Array Sequence Analysis; Pattern Recognition, Automated},
  owner = {wtalloen},
  pii = {1471-2105-7-3},
  pmid = {16398926},
  timestamp = {2008.05.21},
  url = {http://dx.doi.org/10.1186/1471-2105-7-3}
}

@ARTICLE{Mansmann2006,
  author = {U. Mansmann and M. Ruschhaupt and W. Huber},
  title = {Reproducible statistical analysis in microarray profiling studies.},
  journal = {Methods Inf Med},
  year = {2006},
  volume = {45},
  pages = {139--145},
  number = {2},
  abstract = {OBJECTIVES: Microarrays are a recent biotechnology that offers the
	hope of improved cancer classification. A number of publications
	presented clinically promising results by combining this new kind
	of biological data with specifically designed algorithmic approaches.
	But, reproducing published results in this domain is harder than
	it may seem. METHODS: This paper presents examples, discusses the
	problems hidden in the published analyses and demonstrates a strategy
	to improve the situation which is based on the vignette technology
	available from the R and Bioconductor projects. RESULTS: The tool
	of a compendium is discussed to achieve reproducible calculations
	and to offer an extensible computational framework. A compendium
	is a document that bundles primary data, processing methods (computational
	code), derived data, and statistical output with textual documentation
	and conclusions. It is interactive in the sense that it allows for
	the modification of the processing options, plugging in new data,
	or inserting further algorithms and visualizations. CONCLUSIONS:
	Due to the complexity of the algorithms, the size of the data sets,
	and the limitations of the medium printed paper it is usually not
	possible to report all the minutiae of the data processing and statistical
	computations. The technique of a compendium allows a complete critical
	assessment of a complex analysis.},
  doi = {10.1267/METH06020139},
  institution = {IBE, Medical School, LMU München, Marchioninistr. 15, 81377 München,
	Germany. mansmann@ibe.med.uni-muenchen.de},
  keywords = {Gene Expression Profiling; Humans; Oligonucleotide Array Sequence
	Analysis; Reproducibility of Results},
  owner = {wtalloen},
  pii = {06020139},
  pmid = {16538278},
  timestamp = {2008.05.21},
  url = {http://dx.doi.org/10.1267/METH06020139}
}

@ARTICLE{Michiels2005,
  author = {Stefan Michiels and Serge Koscielny and Catherine Hill},
  title = {Prediction of cancer outcome with microarrays: a multiple random
	validation strategy.},
  journal = {Lancet},
  year = {2005},
  volume = {365},
  pages = {488--492},
  number = {9458},
  abstract = {BACKGROUND: General studies of microarray gene-expression profiling
	have been undertaken to predict cancer outcome. Knowledge of this
	gene-expression profile or molecular signature should improve treatment
	of patients by allowing treatment to be tailored to the severity
	of the disease. We reanalysed data from the seven largest published
	studies that have attempted to predict prognosis of cancer patients
	on the basis of DNA microarray analysis. METHODS: The standard strategy
	is to identify a molecular signature (ie, the subset of genes most
	differentially expressed in patients with different outcomes) in
	a training set of patients and to estimate the proportion of misclassifications
	with this signature on an independent validation set of patients.
	We expanded this strategy (based on unique training and validation
	sets) by using multiple random sets, to study the stability of the
	molecular signature and the proportion of misclassifications. FINDINGS:
	The list of genes identified as predictors of prognosis was highly
	unstable; molecular signatures strongly depended on the selection
	of patients in the training sets. For all but one study, the proportion
	misclassified decreased as the number of patients in the training
	set increased. Because of inadequate validation, our chosen studies
	published overoptimistic results compared with those from our own
	analyses. Five of the seven studies did not classify patients better
	than chance. INTERPRETATION: The prognostic value of published microarray
	results in cancer studies should be considered with caution. We advocate
	the use of validation by repeated random sampling.},
  doi = {10.1016/S0140-6736(05)17866-0},
  institution = {Biostatistics and Epidemiology Unit, Institut Gustave Roussy, Villejuif,
	France.},
  keywords = {Gene Expression Profiling; Humans; Neoplasms; Oligonucleotide Array
	Sequence Analysis; Prognosis; Sample Size},
  owner = {wtalloen},
  pii = {S0140-6736(05)17866-0},
  pmid = {15705458},
  timestamp = {2008.05.21},
  url = {http://dx.doi.org/10.1016/S0140-6736(05)17866-0}
}

@ARTICLE{Ransohoff2004,
  author = {David F Ransohoff},
  title = {Rules of evidence for cancer molecular-marker discovery and validation.},
  journal = {Nat Rev Cancer},
  year = {2004},
  volume = {4},
  pages = {309--314},
  number = {4},
  month = {Apr},
  doi = {10.1038/nrc1322},
  institution = {Department of Medicine, University of North Carolina at Chapel Hill,
	27599-7080, USA. ransohof@med.unc.edu},
  keywords = {Humans; Neoplasms; Prognosis; Reproducibility of Results; Tumor Markers,
	Biological},
  owner = {wtalloen},
  pii = {nrc1322},
  pmid = {15057290},
  timestamp = {2008.05.21},
  url = {http://dx.doi.org/10.1038/nrc1322}
}

@ARTICLE{Ruschhaupt2004,
  author = {Markus Ruschhaupt and Wolfgang Huber and Annemarie Poustka and Ulrich
	Mansmann},
  title = {A compendium to ensure computational reproducibility in high-dimensional
	classification tasks.},
  journal = {Stat Appl Genet Mol Biol},
  year = {2004},
  volume = {3},
  pages = {Article37},
  abstract = {We demonstrate a concept and implementation of a compendium for the
	classification of high-dimensional data from microarray gene expression
	profiles. A compendium is an interactive document that bundles primary
	data, statistical processing methods, figures, and derived data together
	with the textual documentation and conclusions. Interactivity allows
	the reader to modify and extend these components. We address the
	following questions: how much does the discriminatory power of a
	classifier depend on the choice of the algorithm that was used to
	identify it; what alternative classifiers could be used just as well;
	how robust is the result. The answers to these questions are essential
	prerequisites for validation and biological interpretation of the
	classifiers. We show how to use this approach by looking at these
	questions for a specific breast cancer microarray data set that first
	has been studied by Huang et al. (2003).},
  doi = {10.2202/1544-6115.1078},
  institution = {Division of Molecular Genome Analysis, German Cancer Research Centre.
	m.ruschhaupt@dkfz-heidelberg.de},
  owner = {wtalloen},
  pmid = {16646817},
  timestamp = {2008.05.21},
  url = {http://dx.doi.org/10.2202/1544-6115.1078}
}

@comment{jabref-meta: selector_publisher:}

@comment{jabref-meta: selector_author:}

@comment{jabref-meta: selector_journal:}

@comment{jabref-meta: selector_keywords:}