Motivation: DNA microarray experiments generating thousands of gene expression measurements, are being used to gather information from tissue and cell samples regarding gene expression differences that will be useful in diagnosing disease. We have developed a new method to analyse this kind of data using support vector machines (SVMs). This analysis consists of both classification of the tissue samples, and an exploration of the data for mis-labeled or questionable tissue results. Results: We demonstrate the method in detail on samples consisting of ovarian cancer tissues, normal ovarian tissues, and other normal tissues. The dataset consists of expression experiment results for 97 802 cDNAs for each tissue. As a result of computational analysis, a tissue sample is discovered and confirmed to be wrongly labeled. Upon correction of this mistake and the removal of an outlier, perfect classification of tissues is achieved, but not with high confidence. We identify and analyse a subset of genes from the ovarian dataset whose expression is highly differentiated between the types of tissues. To show robustness of the SVM method, two previously published datasets from other types of tissues or cells are analysed. The results are comparable to those previously obtained. We show that other machine learning methods also perform comparably to the SVM on many of those datasets. Availability: The SVM software is available at http:// www. cs.columbia.edu/#bgrundy/svm. Contact: booch@cse.ucsc.edu

There are many sources of systematic variation in cDNA microarray experiments which affect the measured gene expression levels (e.g. differences in labeling efficiency between the two fluorescent dyes). The term normalization refers to the process of removing such variation. A constant adjustment is often used to force the distribution of the intensity log ratios to have a median of zero for each slide. However, such global normalization approaches are not adequate in situations where dye biases can depend on spot overall intensity and/or spatial location within the array. This article proposes normalization methods that are based on robust local regression and account for intensity and spatial dependence in dye biases for different types of cDNA microarray experiments. The selection of appropriate controls for normalization is discussed and a novel set of controls (microarray sample pool, MSP) is introduced to aid in intensity-dependent normalization. Lastly, to allow for comparisons of expression levels across slides, a robust method based on maximum likelihood estimation is proposed to adjust for scale differences among slides.

Gene expression can be quantitatively analyzed by hybridizing fluor-tagged mRNA to targets on a cDNA microarray. Comparison of gene expression levels arising from cohybridized samples is achieved by taking ratios of average expression levels for individual genes. A novel method of image segmentation is provided to identify cDNA target sites and a hypothesis test and confidence interval is developed to quantify the significance of observed differences in expression ratios. In particular, the probability density of the ratio and the maximum-likelihood estimator for the distribution are derived, and an iterative procedure for signal calibration is developed. 1997 Society of Photo-Optical Instrumentation Engineers. [S1083-3668(97)00504-2] Keywords cDNA; microarray; gene expression; image segmentation; Mann--Whitney target detection; ratio density, ratio confidence interval.

DNA microarrays are a new and promising biotechnology whichallows the monitoring of expression levels in cells for thousands of genes simultaneously. The present paper describes statistical methods for the identification of differentially expressed genes in replicated cDNA microarray experiments. Although it is not the main focus of the paper, new methods for the important pre-processing steps of image analysis and normalization are proposed. Given suitably normalized data, the biological question of differential expression is restated as a problem in multiple hypothesis testing: the simultaneous test for each gene of the null hypothesis of no association between the expression levels and responses or covariates of interest. Di erentially expressed genes are identified based on adjusted p-values for a multiple testing procedure which strongly controls the family-wise Type I error rate and takes into account the dependence structure between the gene expression levels. No specific parametric form is assumed for the distribution of the test statistics and a permutation procedure is used to estimate adjusted p-values. Several data displays are suggested for the visual identification of differentially expressed genes and of important features of these genes. The above methods are applied to microarray data from a study of gene expression in the livers of mice with very low HDL cholesterol levels. The genes identified using data from multiple slides are compared to those identified by recently published single-slide methods.

Two-category support vector machines (SVM) have been very popular in the machine learning community for classi � cation problems. Solving multicategory problems by a series of binary classi � ers is quite common in the SVM paradigm; however, this approach may fail under various circumstances. We propose the multicategory support vector machine (MSVM), which extends the binary SVM to the multicategory case and has good theoretical properties. The proposed method provides a unifying framework when there are either equal or unequal misclassi � cation costs. As a tuning criterion for the MSVM, an approximate leave-one-out cross-validation function, called Generalized Approximate Cross Validation, is derived, analogous to the binary case. The effectiveness of the MSVM is demonstrated through the applications to cancer classi � cation using microarray data and cloud classi � cation with satellite radiance pro � les.

Abstract—DNA microarray technology has now made it possible to simultaneously monitor the expression levels of thousands of genes during important biological processes and across collections of related samples. Elucidating the patterns hidden in gene expression data offers a tremendous opportunity for an enhanced understanding of functional genomics. However, the large number of genes and the complexity of biological networks greatly increases the challenges of comprehending and interpreting the resulting mass of data, which often consists of millions of measurements. A first step toward addressing this challenge is the use of clustering techniques, which is essential in the data mining process to reveal natural structures and identify interesting patterns in the underlying data. Cluster analysis seeks to partition a given data set into groups based on specified features so that the data points within a group are more similar to each other than the points in different groups. A very rich literature on cluster analysis has developed over the past three decades. Many conventional clustering algorithms have been adapted or directly applied to gene expression data, and also new algorithms have recently been proposed specifically aiming at gene expression data. These clustering algorithms have been proven useful for identifying biologically relevant groups of genes and samples. In this paper, we first briefly introduce the concepts of microarray technology and discuss the basic elements of clustering on gene expression data. In particular, we divide cluster analysis for gene expression data into three categories. Then, we present specific challenges pertinent to each clustering category and introduce several representative approaches. We also discuss the problem of cluster validation in three aspects and review various methods to assess the quality and reliability of clustering results. Finally, we conclude this paper and suggest the promising trends in this field. Index Terms—Microarray technology, gene expression data, clustering.

Motivation: Two practical realities constrain the analysis of microarray data, mass spectra from proteomics, and biomedical infrared or magnetic resonance spectra. One is the ‘curse of dimensionality’: the number of features characterizing these data is in the thousands or tens of thousands. The other is the ‘curse of dataset sparsity’: the number of samples is limited. The consequences of these two curses are far-reaching when such data are used to classify the presence or absence of disease. Results: Using very simple classifiers, we show for several publicly available microarray and proteomics datasets how these curses influence classification outcomes. In particular, even if the sample per feature ratio is increased to the recommended 5–10 by feature extraction/reduction methods, dataset sparsity can render any classification result statistically suspect. In addition, several ‘optimal’ feature sets are typically identifiable for sparse datasets, all producing perfect classification results, both for the training and independent validation sets. This non-uniqueness leads to interpretational difficulties and casts doubt on the biological relevance of any of these ‘optimal’ feature sets. We suggest an approach to assess the relative quality of apparently equally good classifiers.

Several microarray technologies that monitor the level of expression of a large number of genes have recently emerged. Given DNA-microarray data for a set of cells characterized by a given phenotype and for a set of control cells, an important problem is to identify "patterns" of gene expression that can be used to predict cell phenotype. The potential number of such patterns is exponential in the number of genes. In this paper, we propose a solution to this problem based on a supervised learning algorithm, which differs substantially from previous schemes. It couples a complex, non-linear similarity metric, which maximizes the probability of discovering discriminative gene expression patterns, and a pattern discovery algorithm called SPLASH. The latter discovers efficiently and deterministically all statistically significant gene expression patterns in the phenotype set. Statistical significance is evaluated based on the probability of a pattern to occur by chance in ...

DNA arrays of the entire set of Escherichia coli genes were used to measure the genomic expression patterns of cells growing in late logarithmic phase on minimal glucose medium and on Luria broth containing glucose. Ratios of the transcript levels for all 4,290 E. coli protein-encoding genes (cds) were obtained, and analysis of the expression ratio data indicated that the physiological state of the cells under the two growth conditions could be ascertained. The cells in the rich medium grew faster, and expression of the majority of the translation apparatus genes was significantly elevated under this growth condition, consistent with known patterns of growth rate-dependent regulation and increased rate of protein synthesis in rapidly growing cells. The cells grown on minimal medium showed significantly elevated expression of many genes involved in biosynthesis of building blocks, most notably the amino acid biosynthetic pathways. Nearly half of the known RpoS-dependent genes were expressed at significantly higher levels in minimal medium than in rich medium, and rpoS expression was similarly elevated. The role of RpoS regulation in these logarithmic phase cells was suggested by the functions of the RpoS dependent genes that were induced. The hallmark features of E. coli cells growing on glucose minimal medium appeared to be the formation and excretion of acetate, metabolism of the acetate, and protection of the cells from acid stress. A hypothesis invoking RpoS and UspA (universal stress protein, also significantly elevated in minimal glucose medium) as playing a role in coordinating these various aspects

This paper describes a novel approach to assess the codetermination of gene transcriptional states based upon statistical evaluation of reliably informative subsets of data derived from large-scale simultaneous gene expression measurements with cDNA microarrays. The method finds associations between the expression patterns of individual genes by determining whether knowledge of the transcriptional levels of a small gene set can be used to predict the associated transcriptional state of another gene. To test this approach for identification of the relevant contextual elements of cellular response, we have modeled our approach using data from known gene response pathways including ionizing radiation and downstream targets of inactivating gene mutations. This approach strongly suggests that evaluation of the transcriptional status of a given gene(s) can be combined with data from global expression analyses to predict the expression level of another gene. With data sets of the size currently available, this approach should be useful in finding sets of genes that participate in particular biological processes. As larger data sets and more computing power become available, the method can be extended to validating and ultimately identifying biologic (transcriptional) pathways based upon large-scale gene expression analysis. 2000 Academic Press