Supervised clustering of genes

Background  

We focus on microarray data where experiments monitor gene expression in different tissues and where each experiment is equipped with an additional response variable such as a cancer type. Although the number of measured genes is in the thousands, it is assumed that only a few marker components of gene subsets determine the type of a tissue. Here we present a new method for finding such groups of genes by directly incorporating the response variables into the grouping process, yielding a supervised clustering algorithm for genes.     

Methods for assessing reproducibility of clustering patterns observed in analyses of microarray data

MOTIVATION: Recent technological advances such as cDNA microarray technology have made it possible to simultaneously interrogate thousands of genes in a biological specimen. A cDNA microarray experiment produces a gene expression 'profile'. Often interest lies in discovering novel subgroupings, or 'clusters', of specimens based on their profiles, for example identification of new tumor taxonomies. Cluster analysis techniques such as hierarchical clustering and self-organizing maps have frequently been used for investigating structure in microarray data. However, clustering algorithms always detect clusters, even on random data, and it is easy to misinterpret the results without some objective measure of the reproducibility of the clusters. RESULTS: We present statistical methods for testing for overall clustering of gene expression profiles, and we define easily interpretable measures of cluster-specific reproducibility that facilitate understanding of the clustering structure. We apply these methods to elucidate structure in cDNA microarray gene expression profiles obtained on melanoma tumors and on prostate specimens.     

Determination of stromal signatures in breast carcinoma

Many soft tissue tumors recapitulate features of normal connective tissue. We hypothesize that different types of fibroblastic tumors are representative of different populations of fibroblastic cells or different activation states of these cells. We examined two tumors with fibroblastic features, solitary fibrous tumor (SFT) and desmoid-type fibromatosis (DTF), by DNA microarray analysis and found that they have very different expression profiles, including significant differences in their patterns of expression of extracellular matrix genes and growth factors. Using immunohistochemistry and in situ hybridization on a tissue microarray, we found that genes specific for these two tumors have mutually specific expression in the stroma of nonneoplastic tissues. We defined a set of 786 gene spots whose pattern of expression distinguishes SFT from DTF. In an analysis of DNA microarray gene expression data from 295 previously published breast carcinomas, we found that expression of this gene set defined two groups of breast carcinomas with significant differences in overall survival. One of the groups had a favorable outcome and was defined by the expression of DTF genes. The other group of tumors had a poor prognosis and showed variable expression of genes enriched for SFT type. Our findings suggest that the host stromal response varies significantly among carcinomas and that gene expression patterns characteristic of soft tissue tumors can be used to discover new markers for normal connective tissue cells.     

Accurate and robust gene selection for disease classification using a simple statistic

Discrimination of disease patients based on gene expression data is a crucial problem in clinical area. An important issue to solve this problem is to find a discriminative subset of genes from thousands of genes on a microarray or DNA chip. Aiming at finding informative genes for disease classification on microarray, we present a gene selection method based on the forward variable (gene) selection method (FSM) and show, using typical public microarray datasets, that our method can extract a small set of genes being crucial for discriminating different classes with a very high accuracy almost closed to perfect classification.     

A Robust Statistical Method for Detecting Differentially Expressed Genes

DNA microarray technology allows researchers to monitor the expressions of thousands of genes under different conditions, and to measure the levels of thousands of different DNA molecules at a given point in the life of an organism, tissue or cell. A wide variety of different diseases that are characterised by unregulated gene expression, DNA replication, cell division and cell death, can be detected early using microarrays. One of the major objectives of microarray experiments is to identify differentially expressed genes under various conditions. The detection of differential gene expression under two different conditions is very important in biological studies, and allows us to identify experimental variables that affect different biological processes. Most of the tests available in the literature are based on the assumption of normal distribution. However, the assumption of normality may not be true in real-life data, particularly with respect to microarray data.A test is proposed for the identification of differentially expressed genes in replicated microarray experiments conducted under two different conditions. The proposed test does not assume the distribution of the parent population; thus, the proposed test is strictly nonparametric in nature. We calculate the p-value and the asymptotic power function of the proposed test statistic. The proposed test statistic is compared with some of its competitors under normal, gamma and exponential population setup using the Monte Carlo simulation technique. The application of the proposed test statistic is presented using microarray data. The proposed test is robust and highly efficient when populations are non-normal.     

High-confidence discovery of genetic network regulators in expression quantitative trait loci data

Expression QTL (eQTL) studies involve the collection of microarray gene expression data and genetic marker data from segregating individuals in a population to search for genetic determinants of differential gene expression. Previous studies have found large numbers of trans-regulated genes (regulated by unlinked genetic loci) that link to a single locus or eQTL "hotspot," and it would be desirable to find the mechanism of coregulation for these gene groups. However, many difficulties exist with current network reconstruction algorithms such as low power and high computational cost. A common observation for biological networks is that they have a scale-free or power-law architecture. In such an architecture, highly influential nodes exist that have many connections to other nodes. If we assume that this type of architecture applies to genetic networks, then we can simplify the problem of genetic network reconstruction by focusing on discovery of the key regulatory genes at the top of the network. We introduce the concept of "shielding" in which a specific gene expression variable (the shielder) renders a set of other gene expression variables (the shielded genes) independent of the eQTL. We iteratively build networks from the eQTL to the shielder down using tests of conditional independence. We have proposed a novel test for controlling the shielder false-positive rate at a predetermined level by requiring a threshold number of shielded genes per shielder. Using simulation, we have demonstrated that we can control the shielder false-positive rate as well as obtain high shielder and edge specificity. In addition, we have shown our method to be robust to violation of the latent variable assumption, an important feature in the practical application of our method. We have applied our method to a yeast expression QTL data set in which microarray and marker data were collected from the progeny of a backcross of two species of Saccharomyces cerevisiae (Brem et al. 2002). Seven genetic networks have been discovered, and bioinformatic analysis of the discovered regulators and corresponding regulated genes has generated plausible hypotheses for mechanisms of regulation that can be tested in future experiments.     

Identifying Genes Relevant to Specific Biological Conditions in Time Course Microarray Experiments

Microarrays have been useful in understanding various biological processes by allowing the simultaneous study of the expression of thousands of genes. However, the analysis of microarray data is a challenging task. One of the key problems in microarray analysis is the classification of unknown expression profiles. Specifically, the often large number of non-informative genes on the microarray adversely affects the performance and efficiency of classification algorithms. Furthermore, the skewed ratio of sample to variable poses a risk of overfitting. Thus, in this context, feature selection methods become crucial to select relevant genes and, hence, improve classification accuracy. In this study, we investigated feature selection methods based on gene expression profiles and protein interactions. We found that in our setup, the addition of protein interaction information did not contribute to any significant improvement of the classification results. Furthermore, we developed a novel feature selection method that relies exclusively on observed gene expression changes in microarray experiments, which we call “relative Signal-to-Noise ratio” (rSNR). More precisely, the rSNR ranks genes based on their specificity to an experimental condition, by comparing intrinsic variation, i.e. variation in gene expression within an experimental condition, with extrinsic variation, i.e. variation in gene expression across experimental conditions. Genes with low variation within an experimental condition of interest and high variation across experimental conditions are ranked higher, and help in improving classification accuracy. We compared different feature selection methods on two time-series microarray datasets and one static microarray dataset. We found that the rSNR performed generally better than the other methods.     

Unbiased pattern detection in microarray data series

MOTIVATION: Following the advent of microarray technology in recent years, the challenge for biologists is to identify genes of interest from the thousands of genetic expression levels measured in each microarray experiment. In many cases the aim is to identify pattern in the data series generated by successive microarray measurements. RESULTS: Here we introduce a new method of detecting pattern in microarray data series which is independent of the nature of this pattern. Our approach provides a measure of the algorithmic compressibility of each data series. A series which is significantly compressible is much more likely to result from simple underlying mechanisms than series which are incompressible. Accordingly, the gene associated with a compressible series is more likely to be biologically significant. We test our method on microarray time series of yeast cell cycle and show that it blindly selects genes exhibiting the expected cyclic behaviour as well as detecting other forms of pattern. Our results successfully predict two independent non-microarray experimental studies.     

A Regression-Based Differential Expression Detection Algorithm for Microarray Studies with Ultra-Low Sample Size

Global gene expression analysis using microarrays and, more recently, RNA-seq, has allowed investigators to understand biological processes at a system level. However, the identification of differentially expressed genes in experiments with small sample size, high dimensionality, and high variance remains challenging, limiting the usability of these tens of thousands of publicly available, and possibly many more unpublished, gene expression datasets. We propose a novel variable selection algorithm for ultra-low-n microarray studies using generalized linear model-based variable selection with a penalized binomial regression algorithm called penalized Euclidean distance (PED). Our method uses PED to build a classifier on the experimental data to rank genes by importance. In place of cross-validation, which is required by most similar methods but not reliable for experiments with small sample size, we use a simulation-based approach to additively build a list of differentially expressed genes from the rank-ordered list. Our simulation-based approach maintains a low false discovery rate while maximizing the number of differentially expressed genes identified, a feature critical for downstream pathway analysis. We apply our method to microarray data from an experiment perturbing the Notch signaling pathway in Xenopus laevis embryos. This dataset was chosen because it showed very little differential expression according to limma, a powerful and widely-used method for microarray analysis. Our method was able to detect a significant number of differentially expressed genes in this dataset and suggest future directions for investigation. Our method is easily adaptable for analysis of data from RNA-seq and other global expression experiments with low sample size and high dimensionality.     

Analysis of variance for gene expression microarray data.

Spotted cDNA microarrays are emerging as a powerful and cost-effective tool for large-scale analysis of gene expression. Microarrays can be used to measure the relative quantities of specific mRNAs in two or more tissue samples for thousands of genes simultaneously. While the power of this technology has been recognized, many open questions remain about appropriate analysis of microarray data. One question is how to make valid estimates of the relative expression for genes that are not biased by ancillary sources of variation. Recognizing that there is inherent "noise" in microarray data, how does one estimate the error variation associated with an estimated change in expression, i.e., how does one construct the error bars? We demonstrate that ANOVA methods can be used to normalize microarray data and provide estimates of changes in gene expression that are corrected for potential confounding effects. This approach establishes a framework for the general analysis and interpretation of microarray data.     

Gene expression profiling of human diseases by serial analysis of gene expression

Until recently, the approach to understanding the molecular basis of complex syndromes such as cancer, coronary artery disease, and diabetes was to study the behavior of individual genes. However, it is generally recognized that expression of a number of genes is coordinated both spatially and temporally and that this coordination changes during the development and progression of diseases. Newly developed functional genomic approaches, such as serial analysis of gene expression (SAGE) and DNA microarrays have enabled researchers to determine the expression pattern of thousands of genes simultaneously. One attractive feature of SAGE compared to microarrays is its ability to quantify gene expression without prior sequence information or information about genes that are thought to be expressed. SAGE has been successfully applied to the gene expression profiling of a number of human diseases. In this review, we will first discuss SAGE technique and contrast it to microarray. We will then highlight new biological insights that have emerged from its application to the study of human diseases.     

Selection of control genes for quantitative RT-PCR based on microarray data

Use of internal reference gene(s) is necessary for adequate quantification of target gene expression by RT-PCR. Herein, we elaborated a strategy of control gene selection based on microarray data and illustrated it by analyzing endomyocardial biopsies with acute cardiac rejection and infection. Using order statistics and binomial distribution we evaluated the probability of finding low-varying genes by chance. For analysis, the microarray data were divided into two sample subsets. Among the first 10% of genes with the lowest standard deviations, we found 14 genes common to both subsets. After normalization using two selected genes, high correlation was observed between expression of target genes evaluated by microarray and RT-PCR, and in independent dataset by RT-PCR (r = 0.9, p < 0.001). In conclusion, we showed a simple and reliable strategy of selection and validation of control genes for RT-PCR from microarray data that can be easily applied for different experimental designs and tissues.     

Tumor classification by partial least squares using microarray gene expression data

MOTIVATION: One important application of gene expression microarray data is classification of samples into categories, such as the type of tumor. The use of microarrays allows simultaneous monitoring of thousands of genes expressions per sample. This ability to measure gene expression en masse has resulted in data with the number of variables p(genes) far exceeding the number of samples N. Standard statistical methodologies in classification and prediction do not work well or even at all when N < p. Modification of existing statistical methodologies or development of new methodologies is needed for the analysis of microarray data. RESULTS: We propose a novel analysis procedure for classifying (predicting) human tumor samples based on microarray gene expressions. This procedure involves dimension reduction using Partial Least Squares (PLS) and classification using Logistic Discrimination (LD) and Quadratic Discriminant Analysis (QDA). We compare PLS to the well known dimension reduction method of Principal Components Analysis (PCA). Under many circumstances PLS proves superior; we illustrate a condition when PCA particularly fails to predict well relative to PLS. The proposed methods were applied to five different microarray data sets involving various human tumor samples: (1) normal versus ovarian tumor; (2) Acute Myeloid Leukemia (AML) versus Acute Lymphoblastic Leukemia (ALL); (3) Diffuse Large B-cell Lymphoma (DLBCLL) versus B-cell Chronic Lymphocytic Leukemia (BCLL); (4) normal versus colon tumor; and (5) Non-Small-Cell-Lung-Carcinoma (NSCLC) versus renal samples. Stability of classification results and methods were further assessed by re-randomization studies.     

An integrated cross-platform prognosis study on neuroblastoma patients

There have been several reports about the potential for predicting prognosis of neuroblastoma patients using microarray gene expression profiling of the tumors. However these studies have revealed an apparent diversity in the identity of the genes in their predictive signatures. To test the contribution of the platform to this discrepancy we applied the z-scoring method to minimize the impact of platform and combine gene expression profiles of neuroblastoma (NB) tumors from two different platforms, cDNA and Affymetrix. A total of 12442 genes were common to both cDNA and Affymetrix arrays in our data set. Two-way ANOVA analysis was applied to the combined data set for assessing the relative effect of prognosis and platform on gene expression. We found that 26.6% (3307) of the genes had significant impact on survival. There was no significant impact of microarray platform on expression after application of z-scoring standardization procedure. Artificial neural network (ANN) analysis of the combined data set in a leave-one-out prediction strategy correctly predicted the outcome for 90% of the samples. Hierarchical clustering analysis using the top-ranked 160 genes showed the great separation of two clusters, and the majority of matched samples from the different platforms were clustered next to each other. The ANN classifier trained with our combined cross-platform data for these 160 genes could predict the prognosis of 102 independent test samples with 71% accuracy. Furthermore it correctly predicted the outcome for 85/102 (83%) NB patients through the leave-one-out cross-validation approach. Our study showed that gene expression studies performed in different platforms could be integrated for prognosis analysis after removing variation resulting from different platforms.     

cDNA microarray technology and its applications

The cDNA microarray is the most powerful tool for studying gene expression in many different organisms. It has been successfully applied to the simultaneous expression of many thousands of genes and to large-scale gene discovery, as well as polymorphism screening and mapping of genomic DNA clones. It is a high throughput, highly parallel RNA expression assay technique that permits quantitative analysis of RNAs transcribed from both known and unknown genes. This technique provides diagnostic fingerprints by comparing gene expression patterns in normal and pathological cells, and because it can simultaneously track expression levels of many genes, it provides a source of operational context for inference and predication about complex cell control systems. This review describes this recently developed cDNA microarray technology and its application to gene discovery and expression, and to diagnostics for certain diseases.     

Gene selection and classification of microarray data using random forest

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.     

Coupled analysis of gene expression and chromosomal location

Microarray technology can be used to assess simultaneously global changes in expression of mRNA or genomic DNA copy number among thousands of genes in different biological states. In many cases, it is desirable to determine if altered patterns of gene expression correlate with chromosomal abnormalities or assess expression of genes that are contiguous in the genome. We describe a method, differential gene locus mapping (DIGMAP), which aligns the known chromosomal location of a gene to its expression value deduced by microarray analysis. The method partitions microarray data into subsets by chromosomal location for each gene interrogated by an array. Microarray data in an individual subset can then be clustered by physical location of genes at a subchromosomal level based upon ordered alignment in genome sequence. A graphical display is generated by representing each genomic locus with a colored cell that quantitatively reflects its differential expression value. The clustered patterns can be viewed and compared based on their expression signatures as defined by differential values between control and experimental samples. In this study, DIGMAP was tested using previously published studies of breast cancer analyzed by comparative genomic hybridization (CGH) and prostate cancer gene expression profiles assessed by cDNA microarray experiments. Analysis of the breast cancer CGH data demonstrated the ability of DIGMAP to deduce gene amplifications and deletions. Application of the DIGMAP method to the prostate data revealed several carcinoma-related loci, including one at 16q13 with marked differential expression encompassing 19 known genes including 9 encoding metallothionein proteins. We conclude that DIGMAP is a powerful computational tool enabling the coupled analysis of microarray data with genome location.