2011
Lack of sufficiently strong informative features limits the potential of gene expression analysis as predictive tool for many clinical classification problems
Hess KR, Wei C, Qi Y, Iwamoto T, Symmans WF, Pusztai L. Lack of sufficiently strong informative features limits the potential of gene expression analysis as predictive tool for many clinical classification problems. BMC Bioinformatics 2011, 12: 463. PMID: 22132775, PMCID: PMC3245512, DOI: 10.1186/1471-2105-12-463.Peer-Reviewed Original ResearchConceptsPrediction problemCurrent statistical methodsClinical prediction problemsReal data setsMonte Carlo cross validationStatistical methodsData setsAccurate modelPerturbedInformative featuresPrediction modelCancer data setsPredictor performanceGene expression dataProblemBreast cancer data setsClassification problemSuch featuresMean expression valuesSet
2009
Building Networks with Microarray Data
Broom BM, Rinsurongkawong W, Pusztai L, Do KA. Building Networks with Microarray Data. Methods In Molecular Biology 2009, 620: 315-343. PMID: 20652510, DOI: 10.1007/978-1-60761-580-4_10.Peer-Reviewed Original ResearchConceptsDetailed differential equation modelsDifferential equation modelAvailable breast cancer dataMathematical detailsNetwork modelBayesian network modelCo-expression network analysisMicroarray dataGene expression data setsFalse interactionsBayesian networkGene interaction networksData setsNumber of samplesPlausible networksRobust networkBreast cancer dataExpression data setsMicroarray data setsGene clusterGene shavingGene interactionsInteraction networksPreliminary clusteringSubsequent biological experiments