On the statistical assessment of classifiers using DNA microarray data

Abstract

Background: In this paper we present a method for the statistical assessment of cancer predictors which make use of gene expression profiles. The methodology is applied to a new data set of microarray gene expression data collected in Casa Sollievo della Sofferenza Hospital, Foggia -Italy. The data set is made up of normal (22) and tumor (25) specimens extracted from 25 patients affected by colon cancer. We propose to give answers to some questions which are relevant for the automatic diagnosis of cancer such as: Is the size of the available data set sufficient to build accurate classifiers? What is the statistical significance of the associated error rates? In what ways can accuracy be considered dependant on the adopted classification scheme? How many genes are correlated with the pathology and how many are sufficient for an accurate colon cancer classification? The method we propose answers these questions whilst avoiding the potential pitfalls hidden in the analysis and interpretation of microarray data.

Model selection for support vector machines: Advantages and disadvantages of the Machine Learning Theory

“…In addition to these two sets, we also make use of a gene expression dataset for myeloma diagnosis taken from [28], and a DNA microarray dataset collected in Casa Sollievo della SofJerenza Hospital, Foggia -Italy, relative to patients affected by colon cancer [29]. Table III Tables IV and V show the total number of misclassifi cations, obtained using both the random and the stratified data sampling.…”

Biomarker Applications in the Pharmaceutical Industry

“…With the advent of 'omic' technologies allowing the simultaneous measurements of tens to thousands of endpoints, multivariate analysis has led to the concept of the 'signature', wherein a specific algorithmic evaluation of a defined, multiple endpoint becomes the biomarker [46]. While the use of signatures was initially controversial [47], and research into their optimal derivation continues [48][49][50][51][52][53], signatures based on mRNA expression levels have been shown to be consistent across methodologies [54] and have a functional basis to their collection [55,56]. Several mRNA-based signature assays for prognostic applications in oncology are currently commercially available, with two (MammaPrint and Oncotype Dx) having convincing data supporting their clinical benefit in predicting recurrence and aggressiveness of breast cancers [57].…”

Semi-supervised model applied to the prediction of the response to preoperative chemotherapy for breast cancer

“…The importance of developing such predictors relies on the fact that only 30% of patients have a positive response to the treatment and, in absence of efficient predictors of the response, most of the patients are allocated to the standard treatment. A lot of statistical and machine learning models have been developed to address the problem (Cooper 2001;Glas et al 2006;Ancona et al 2006;Michiels et al 2005), but no genomic predictor is yet accurate enough to be used in clinical routine. Among the main issues in the development of such models are: (a) selecting relevant genes to enter the predictors among thousands of genes whose expression levels are measured by DNA microarrays (the vast majority of them being not involved in the response to the chemotherapy treatments), (b) the small number of cases compared to the numbers of features (genes expressions), (c) the representativeness of the data.…”