Adaptive quality-based clustering of gene expression profiles

MOTIVATION: Microarray experiments generate a considerable amount of data, which analyzed properly help us gain a huge amount of biologically relevant information about the global cellular behaviour. Clustering (grouping genes with similar expression profiles) is one of the first steps in data analysis of high-throughput expression measurements. A number of clustering algorithms have proved useful to make sense of such data. These classical algorithms, though useful, suffer from several drawbacks (e.g. they require the predefinition of arbitrary parameters like the number of clusters; they force every gene into a cluster despite a low correlation with other cluster members). In the following we describe a novel adaptive quality-based clustering algorithm that tackles some of these drawbacks. RESULTS: We propose a heuristic iterative two-step algorithm: First, we find in the high-dimensional representation of the data a sphere where the "density" of expression profiles is locally maximal (based on a preliminary estimate of the radius of the cluster-quality-based approach). In a second step, we derive an optimal radius of the cluster (adaptive approach) so that only the significantly coexpressed genes are included in the cluster. This estimation is achieved by fitting a model to the data using an EM-algorithm. By inferring the radius from the data itself, the biologist is freed from finding an optimal value for this radius by trial-and-error. The computational complexity of this method is approximately linear in the number of gene expression profiles in the data set. Finally, our method is successfully validated using existing data sets. AVAILABILITY: http://www.esat.kuleuven.ac.be/~thijs/Work/Clustering.html     

基于SVM和平均影响值的人肿瘤信息基因提取

基于基因表达谱的肿瘤分类信息基因选取是发现肿瘤特异表达基因、探索肿瘤基因表达模式的重要手段。借助由基因表达谱获得的分类信息进行肿瘤诊断是当今生物信息学领域中的一个重要研究方向,有望成为临床医学上一种快速而有效的肿瘤分子诊断方法。鉴于肿瘤基因表达谱样本数据维数高、样本量小以及噪音大等特点,提出一种结合支持向量机应用平均影响值来寻找肿瘤信息基因的算法,其优点是能够搜索到基因数量尽可能少而分类能力尽可能强的多个信息基因子集。采用二分类肿瘤数据集验证算法的可行性和有效性,对于结肠癌样本集,只需3个基因就能获得100%的留一法交叉验证识别准确率。为避免样本集的不同划分对分类性能的影响,进一步采用全折交叉验证方法来评估各信息基因子集的分类性能,优选出更可靠的信息基因子集。与基它肿瘤分类方法相比,实验结果在信息基因数量以及分类性能方面具有明显的优势。     

Extracting dynamics from static cancer expression data

Static expression experiments analyze samples from many individuals. These samples are often snapshots of the progression of a certain disease such as cancer. This raises an intriguing question: Can we determine a temporal order for these samples? Such an ordering can lead to better understanding of the dynamics of the disease and to the identification of genes associated with its progression. In this paper we formally prove, for the first time, that under a model for the dynamics of the expression levels of a single gene, it is indeed possible to recover the correct ordering of the static expression datasets by solving an instance of the traveling salesman problem (TSP). In addition, we devise an algorithm that combines a TSP heuristic and probabilistic modeling for inferring the underlying temporal order of the microarray experiments. This algorithm constructs probabilistic continuous curves to represent expression profiles leading to accurate temporal reconstruction for human data. Applying our method to cancer expression data we show that the ordering derived agrees well with survival duration. A classifier that utilizes this ordering improves upon other classifiers suggested for this task. The set of genes displaying consistent behavior for the determined ordering are enriched for genes associated with cancer progression.     

Google goes cancer: improving outcome prediction for cancer patients by network-based ranking of marker genes

Predicting the clinical outcome of cancer patients based on the expression of marker genes in their tumors has received increasing interest in the past decade. Accurate predictors of outcome and response to therapy could be used to personalize and thereby improve therapy. However, state of the art methods used so far often found marker genes with limited prediction accuracy, limited reproducibility, and unclear biological relevance. To address this problem, we developed a novel computational approach to identify genes prognostic for outcome that couples gene expression measurements from primary tumor samples with a network of known relationships between the genes. Our approach ranks genes according to their prognostic relevance using both expression and network information in a manner similar to Google's PageRank. We applied this method to gene expression profiles which we obtained from 30 patients with pancreatic cancer, and identified seven candidate marker genes prognostic for outcome. Compared to genes found with state of the art methods, such as Pearson correlation of gene expression with survival time, we improve the prediction accuracy by up to 7%. Accuracies were assessed using support vector machine classifiers and Monte Carlo cross-validation. We then validated the prognostic value of our seven candidate markers using immunohistochemistry on an independent set of 412 pancreatic cancer samples. Notably, signatures derived from our candidate markers were independently predictive of outcome and superior to established clinical prognostic factors such as grade, tumor size, and nodal status. As the amount of genomic data of individual tumors grows rapidly, our algorithm meets the need for powerful computational approaches that are key to exploit these data for personalized cancer therapies in clinical practice.     

Minreg: inferring an active regulator set

Regulatory relations between genes are an important component of molecular pathways. Here, we devise a novel global method that uses a set of gene expression profiles to find a small set of relevant active regulators, identify the genes that they regulate, and automatically annotate them. We show that our algorithm is capable of handling a large number of genes in a short time and is robust to a wide range of parameters. We apply our method to a combined dataset of S. cerevisiae expression profiles, and validate the resulting model of regulation by cross-validation and extensive biological analysis of the selected regulators and their derived annotations.     

Unsupervised feature selection via two-way ordering in gene expression analysis

MOTIVATION: Selection of genes most relevant and informative for certain phenotypes is an important aspect in gene expression analysis. Most current methods select genes based on known phenotype information. However, certain set of genes may correspond to new phenotypes which are yet unknown, and it is important to develop novel effective selection methods for their discovery without using any prior phenotype information. RESULTS: We propose and study a new method to select relevant genes based on their similarity information only. The method relies on a mechanism for discarding irrelevant genes. A two-way ordering of gene expression data can force irrelevant genes towards the middle in the ordering and thus can be discarded. Mechanisms based on variance and principal component analysis are also studied. When applied to expression profiles of colon cancer and leukemia, the unsupervised method outperforms the baseline algorithm that simply uses all genes, and it also selects relevant genes close to those selected using supervised methods. SUPPLEMENT: More results and software are online: http://www.nersc.gov/~cding/2way.     

Gene selection and clustering for time-course and dose-response microarray experiments using order-restricted inference

We propose an algorithm for selecting and clustering genes according to their time-course or dose-response profiles using gene expression data. The proposed algorithm is based on the order-restricted inference methodology developed in statistics. We describe the methodology for time-course experiments although it is applicable to any ordered set of treatments. Candidate temporal profiles are defined in terms of inequalities among mean expression levels at the time points. The proposed algorithm selects genes when they meet a bootstrap-based criterion for statistical significance and assigns each selected gene to the best fitting candidate profile. We illustrate the methodology using data from a cDNA microarray experiment in which a breast cancer cell line was stimulated with estrogen for different time intervals. In this example, our method was able to identify several biologically interesting genes that previous analyses failed to reveal.     

The mode-of-action by network identification (MNI) algorithm: a network biology approach for molecular target identification

This protocol details the use of the mode-of-action by network identification (MNI) algorithm to identify the gene targets of a drug treatment based on gene-expression data. Investigators might also use the MNI algorithm to identify the gene mediators of a disease or the physiological state of cells and tissues. The MNI algorithm uses a training data set of hundreds of expression profiles to construct a statistical model of gene-regulatory networks in a cell or tissue. The model describes combinatorial influences of genes on one another. The algorithm then uses the model to filter the expression profile of a particular experimental treatment and thereby distinguish the molecular targets or mediators of the treatment response from hundreds of additional genes that also exhibit expression changes. It takes approximately 1 h per run, although run time is significantly affected by the size of the genome and data set.     

VizStruct: exploratory visualization for gene expression profiling

MOTIVATION: DNA arrays provide a broad snapshot of the state of the cell by measuring the expression levels of thousands of genes simultaneously. Visualization techniques can enable the exploration and detection of patterns and relationships in a complex data set by presenting the data in a graphical format in which the key characteristics become more apparent. The dimensionality and size of array data sets however present significant challenges to visualization. The purpose of this study is to present an interactive approach for visualizing variations in gene expression profiles and to assess its usefulness for classifying samples. RESULTS: The first Fourier harmonic projection was used to map multi-dimensional gene expression data to two dimensions in an implementation called VizStruct. The visualization method was tested using the differentially expressed genes identified in eight separate gene expression data sets. The samples were classified using the oblique decision tree (OC1) algorithm to provide a procedure for visualization-driven classification. The classifiers were evaluated by the holdout and the cross-validation techniques. The proposed method was found to achieve high accuracy. AVAILABILITY: Detailed mathematical derivation of all mapping properties as well as figures in color can be found as supplementary on the web page http://www.cse.buffalo.edu/DBGROUP/bioinformatics/supplementary/vizstruct. All programs were written in Java and Matlab and software code is available by request from the first author.     

Analysis of temporal gene expression profiles: clustering by simulated annealing and determining the optimal number of clusters

MOTIVATION: Cluster analysis of genome-wide expression data from DNA microarray hybridization studies has proved to be a useful tool for identifying biologically relevant groupings of genes and samples. In the present paper, we focus on several important issues related to clustering algorithms that have not yet been fully studied. RESULTS: We describe a simple and robust algorithm for the clustering of temporal gene expression profiles that is based on the simulated annealing procedure. In general, this algorithm guarantees to eventually find the globally optimal distribution of genes over clusters. We introduce an iterative scheme that serves to evaluate quantitatively the optimal number of clusters for each specific data set. The scheme is based on standard approaches used in regular statistical tests. The basic idea is to organize the search of the optimal number of clusters simultaneously with the optimization of the distribution of genes over clusters. The efficiency of the proposed algorithm has been evaluated by means of a reverse engineering experiment, that is, a situation in which the correct distribution of genes over clusters is known a priori. The employment of this statistically rigorous test has shown that our algorithm places greater than 90% genes into correct clusters. Finally, the algorithm has been tested on real gene expression data (expression changes during yeast cell cycle) for which the fundamental patterns of gene expression and the assignment of genes to clusters are well understood from numerous previous studies.     

A Bayesian regression approach to the inference of regulatory networks from gene expression data

MOTIVATION: There is currently much interest in reverse-engineering regulatory relationships between genes from microarray expression data. We propose a new algorithmic method for inferring such interactions between genes using data from gene knockout experiments. The algorithm we use is the Sparse Bayesian regression algorithm of Tipping and Faul. This method is highly suited to this problem as it does not require the data to be discretized, overcomes the need for an explicit topology search and, most importantly, requires no heuristic thresholding of the discovered connections. RESULTS: Using simulated expression data, we are able to show that this algorithm outperforms a recently published correlation-based approach. Crucially, it does this without the need to set any ad hoc threshold on possible connections.     

A novel means of using gene clusters in a two-step empirical Bayes method for predicting classes of samples

MOTIVATION: The classification of samples using gene expression profiles is an important application in areas such as cancer research and environmental health studies. However, the classification is usually based on a small number of samples, and each sample is a long vector of thousands of gene expression levels. An important issue in parametric modeling for so many gene expression levels is the control of the number of nuisance parameters in the model. Large models often lead to intensive or even intractable computation, while small models may be inadequate for complex data.Methodology: We propose a two-step empirical Bayes classification method as a solution to this issue. At the first step, we use the model-based cluster algorithm with a non-traditional purpose of assigning gene expression levels to form abundance groups. At the second step, by assuming the same variance for all the genes in the same group, we substantially reduce the number of nuisance parameters in our statistical model. RESULTS: The proposed model is more parsimonious, which leads to efficient computation under an empirical Bayes estimation procedure. We consider two real examples and simulate data using our method. Desired low classification error rates are obtained even when a large number of genes are pre-selected for class prediction.     

Application of MUTIC to the exploration of gene expression data in prostate cancer

We show here an example of the application of a novel method, MUTIC (model utilization-based clustering), used for identifying complex interactions between genes or gene categories based on gene expression data. The method deals with binary categorical data which consist of a set of gene expression profiles divided into two biologically meaningful categories. It does not require data from multiple time points. Gene expression profiles are represented by feature vectors whose component features are either gene expression values, or averaged expression values corresponding to gene ontology or protein information resource categories. A supervised learning algorithm (genetic programming) is used to learn an ensemble of classification models distinguishing the two categories based on the feature vectors corresponding to their members. Each feature is associated with a "model utilization vector", which has an entry for each high-quality classification model found, indicating whether or not the feature was used in that model. These utilization vectors are then clustered using a variant of hierarchical clustering called Omniclust. The result is a set of model utilization-based clusters, in which features are gathered together if they are often considered together by classification models - which may be because they are co-expressed, or may be for subtler reasons involving multi-gene interactions. The MUTIC method is illustrated here by applying it to a dataset regarding gene expression in prostate cancer and control samples. Compared to traditional expression-based clustering, MUTIC yields clusters that have higher mathematical quality (in the sense of homogeneity and separation) and that also yield novel insights into the underlying biological processes.     

Mining co-regulated gene profiles for the detection of functional associations in gene expression data

MOTIVATION: Association pattern discovery (APD) methods have been successfully applied to gene expression data. They find groups of co-regulated genes in which the genes are either up- or down-regulated throughout the identified conditions. These methods, however, fail to identify similarly expressed genes whose expressions change between up- and down-regulation from one condition to another. In order to discover these hidden patterns, we propose the concept of mining co-regulated gene profiles. Co-regulated gene profiles contain two gene sets such that genes within the same set behave identically (up or down) while genes from different sets display contrary behavior. To reduce and group the large number of similar resulting patterns, we propose a new similarity measure that can be applied together with hierarchical clustering methods. RESULTS: We tested our proposed method on two well-known yeast microarray data sets. Our implementation mined the data effectively and discovered patterns of co-regulated genes that are hidden to traditional APD methods. The high content of biologically relevant information in these patterns is demonstrated by the significant enrichment of co-regulated genes with similar functions. Our experimental results show that the Mining Attribute Profile (MAP) method is an efficient tool for the analysis of gene expression data and competitive with bi-clustering techniques.     

Importance of correlation between gene expression levels: application to the type I interferon signature in rheumatoid arthritis

Background

The analysis of gene expression data shows that many genes display similarity in their expression profiles suggesting some co-regulation. Here, we investigated the co-expression patterns in gene expression data and proposed a correlation-based research method to stratify individuals.

Methodology/Principal Findings

Using blood from rheumatoid arthritis (RA) patients, we investigated the gene expression profiles from whole blood using Affymetrix microarray technology. Co-expressed genes were analyzed by a biclustering method, followed by gene ontology analysis of the relevant biclusters. Taking the type I interferon (IFN) pathway as an example, a classification algorithm was developed from the 102 RA patients and extended to 10 systemic lupus erythematosus (SLE) patients and 100 healthy volunteers to further characterize individuals. We developed a correlation-based algorithm referred to as Classification Algorithm Based on a Biological Signature (CABS), an alternative to other approaches focused specifically on the expression levels. This algorithm applied to the expression of 35 IFN-related genes showed that the IFN signature presented a heterogeneous expression between RA, SLE and healthy controls which could reflect the level of global IFN signature activation. Moreover, the monitoring of the IFN-related genes during the anti-TNF treatment identified changes in type I IFN gene activity induced in RA patients.

Conclusions

In conclusion, we have proposed an original method to analyze genes sharing an expression pattern and a biological function showing that the activation levels of a biological signature could be characterized by its overall state of correlation.     

Mining gene expression profiles: an integrated implementation of kernel principal component analysis and singular value decomposition

The detection of genes that show similar profiles under different experimental conditions is often an initial step in inferring the biological significance of such genes. Visualization tools are used to identify genes with similar profiles in microarray studies. Given the large number of genes recorded in microarray experiments, gene expression data are generally displayed on a low dimensional plot, based on linear methods. However, microarray data show nonlinearity, due to high-order terms of interaction between genes, so alternative approaches, such as kernel methods, may be more appropriate. We introduce a technique that combines kernel principal component analysis (KPCA) and Biplot to visualize gene expression profiles. Our approach relies on the singular value decomposition of the input matrix and incorporates an additional step that involves KPCA. The main properties of our method are the extraction of nonlinear features and the preservation of the input variables (genes) in the output display. We apply this algorithm to colon tumor, leukemia and lymphoma datasets. Our approach reveals the underlying structure of the gene expression profiles and provides a more intuitive understanding of the gene and sample association.     

Kernel hierarchical gene clustering from microarray expression data

MOTIVATION: Unsupervised analysis of microarray gene expression data attempts to find biologically significant patterns within a given collection of expression measurements. For example, hierarchical clustering can be applied to expression profiles of genes across multiple experiments, identifying groups of genes that share similar expression profiles. Previous work using the support vector machine supervised learning algorithm with microarray data suggests that higher-order features, such as pairwise and tertiary correlations across multiple experiments, may provide significant benefit in learning to recognize classes of co-expressed genes. RESULTS: We describe a generalization of the hierarchical clustering algorithm that efficiently incorporates these higher-order features by using a kernel function to map the data into a high-dimensional feature space. We then evaluate the utility of the kernel hierarchical clustering algorithm using both internal and external validation. The experiments demonstrate that the kernel representation itself is insufficient to provide improved clustering performance. We conclude that mapping gene expression data into a high-dimensional feature space is only a good idea when combined with a learning algorithm, such as the support vector machine that does not suffer from the curse of dimensionality. AVAILABILITY: Supplementary data at www.cs.columbia.edu/compbio/hiclust. Software source code available by request.     

Tissue differences revealed by gene expression profiles of various cell lines

Mechanisms through which tissues are formed and maintained remain unknown but are fundamental aspects in biology. Tissue-specific gene expression is a valuable tool to study such mechanisms. But in many biomedical studies, cell lines, rather than human body tissues, are used to investigate biological mechanisms Whether or not cell lines maintain their tissue-specific characteristics after they are isolated and cultured outside the human body remains to be explored. In this study, we applied a novel computational method to identify core genes that contribute to the differentiation of cell lines from various tissues. Several advanced computational techniques, such as Monte Carlo feature selection method, incremental feature selection method, and support vector machine (SVM) algorithm, were incorporated in the proposed method, which extensively analyzed the gene expression profiles of cell lines from different tissues. As a result, we extracted a group of functional genes that can indicate the differences of cell lines in different tissues and built an optimal SVM classifier for identifying cell lines in different tissues. In addition, a set of rules for classifying cell lines were also reported, which can give a clearer picture of cell lines in different issues although its performance was not better than the optimal SVM classifier. Finally, we compared such genes with the tissue-specific genes identified by the Genotype-tissue Expression project. Results showed that most expression patterns between tissues remained in the derived cell lines despite some uniqueness that some genes show tissue specificity.