A visual analytics framework for cluster analysis of DNA microarray data

Cluster analysis of DNA microarray data is an important but difficult task in knowledge discovery processes. Many clustering methods are applied to analysis of data for gene expression, but none of them is able to deal with an absolute way with the challenges that this technology raises. Due to this, many applications have been developed for visually representing clustering algorithm results on DNA microarray data, usually providing dendrogram and heat map visualizations. Most of these applications focus only on the above visualizations, and do not offer further visualization components to the validate the clustering methods or to validate one another. This paper proposes using a visual analytics framework in cluster analysis of gene expression data. Additionally, it presents a new method for finding cluster boundaries based on properties of metric spaces. Our approach presents a set of visualization components able to interact with each other; namely, parallel coordinates, cluster boundary genes, 3D cluster surfaces and DNA microarray visualizations as heat maps. Experimental results have shown that our framework can be very useful in the process of more fully understanding DNA microarray data. The software has been implemented in Java, and the framework is publicly available at http://www.analiticavisual.com/jcastellanos/3DVisualCluster/3D-VisualCluster.     

利用U矩阵对SOM网络的处理

自组织神经网络的最大优点是能够保持原始数据的拓扑结构。但是当数据量很大的时候,自组织神经网络的神经元的数据也随之增大。因此为了更好地对数据进行分析,需要将自组织神经网络中相似的神经元进行分组,也就是聚类。在对SOM网络进行再次分析之前,为了减少“噪音”数据和孤立点对聚类结构的影响,用U矩阵的变型方法对自组织神经网络分析的结果进行预处理。     

Interactive Gene Clustering—A Case Study of Breast Cancer Microarray Data

We present a new approach to clustering and visualization of the DNA microarray gene expression data. We utilize the self-organizing map (SOM) framework for handling (dis)similarities between genes in terms of their expression characteristics. We rely on appropriately defined distances between ranked genes-attributes, also capable of handling missing values. As a case study, we consider breast cancer data and the gene ESR1, whose expression alterations, appearing for many of the tumor subtypes, have been already observed to be correlated with some other significant genes. Preliminary results positively verify applicability of our approach, although further development is definitely needed. They suggest that it may be very effective when used by the domain experts. The algorithmic toolkit is enriched with GUI enabling the users to interactively support the SOM optimization process. Its effectiveness is achieved by drag&drop techniques allowing for the cluster modification according to the expert knowledge or intuition.     

Cluster analysis for gene expression data: a survey

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.     

An insight-based methodology for evaluating bioinformatics visualizations

High-throughput experiments, such as gene expression microarrays in the life sciences, result in very large data sets. In response, a wide variety of visualization tools have been created to facilitate data analysis. A primary purpose of these tools is to provide biologically relevant insight into the data. Typically, visualizations are evaluated in controlled studies that measure user performance on predetermined tasks or using heuristics and expert reviews. To evaluate and rank bioinformatics visualizations based on real-world data analysis scenarios, we developed a more relevant evaluation method that focuses on data insight. This paper presents several characteristics of insight that enabled us to recognize and quantify it in open-ended user tests. Using these characteristics, we evaluated five microarray visualization tools on the amount and types of insight they provide and the time it takes to acquire it. The results of the study guide biologists in selecting a visualization tool based on the type of their microarray data, visualization designers on the key role of user interaction techniques, and evaluators on a new approach for evaluating the effectiveness of visualizations for providing insight. Though we used the method to analyze bioinformatics visualizations, it can be applied to other domains.     

A probabilistic relaxation labeling framework for reducing the noise effect in geometric biclustering of gene expression data

Biclustering is an important method in DNA microarray analysis which can be applied when only a subset of genes is co-expressed in a subset of conditions. Unlike standard clustering analyses, biclustering methodology can perform simultaneous classification on two dimensions of genes and conditions in a microarray data matrix. However, the performance of biclustering algorithms is affected by the inherent noise in data, types of biclusters and computational complexity. In this paper, we present a geometric biclustering method based on the Hough transform and the relaxation labeling technique. Unlike many existing biclustering algorithms, we first consider the biclustering patterns through geometric interpretation. Such a perspective makes it possible to unify the formulation of different types of biclusters as hyperplanes in spatial space and facilitates the use of a generic plane finding algorithm for bicluster detection. In our algorithm, the Hough transform is employed for hyperplane detection in sub-spaces to reduce the computational complexity. Then sub-biclusters are combined into larger ones under the probabilistic relaxation labeling framework. Our simulation studies demonstrate the robustness of the algorithm against noise and outliers. In addition, our method is able to extract biologically meaningful biclusters from real microarray gene expression data.     

Maximal Subspace Coregulated Gene Clustering

Clustering is a popular technique for analyzing microarray data sets, with n genes and m experimental conditions. As explored by biologists, there is a real need to identify coregulated gene clusters, which include both positive and negative regulated gene clusters. The existing pattern-based and tendency-based clustering approaches cannot directly be applied to find such coregulated gene clusters, because they are designed for finding positive regulated gene clusters. In this paper, in order to cluster coregulated genes, we propose a coding scheme that allows us to cluster two genes into the same cluster if they have the same code, where two genes that have the same code can be either positive or negative regulated. Based on the coding scheme, we propose a new algorithm for finding maximal subspace coregulated gene clusters with new pruning techniques. A maximal subspace coregulated gene cluster clusters a set of genes on a condition sequence such that the cluster is not included in any other subspace coregulated gene clusters. We conduct extensive experimental studies. Our approach can effectively and efficiently find maximal subspace coregulated gene clusters. In addition, our approach outperforms the existing approaches for finding positive regulated gene clusters.     

Ensemble Rough Hypercuboid Approach for Classifying Cancers

Cancer classification is the critical basis for patient-tailored therapy. Conventional histological analysis tends to be unreliable because different tumors may have similar appearance. The advances in microarray technology make individualized therapy possible. Various machine learning methods can be employed to classify cancer tissue samples based on microarray data. However, few methods can be elegantly adopted for generating accurate and reliable as well as biologically interpretable rules. In this paper, we introduce an approach for classifying cancers based on the principle of minimal rough fringe. For training rough hypercuboid classifiers from gene expression data sets, the method dynamically evaluates all available genes and sifts the genes with the smallest implicit regions as the dimensions of implicit hypercuboids. An unseen object is predicted to be a certain class if it falls within the corresponding class hypercuboid. Based upon the method, ensemble rough hypercuboid classifiers are subsequently constructed. Experimental results on some open cancer gene expression data sets show that the proposed method is capable of generating accurate and interpretable rules compared with some other machine learning methods. Hence, it is a feasible way of classifying cancer tissues in biomedical applications.     

基于边缘分布模型的基因选择方法

一个微阵列数据集包含了成千上万的基因、相对少量的样本,而在这成千上万的基因中,只有一少部分基因对肿瘤分类是有贡献的,因此,对于肿瘤分类来说,最重要的一个问题就是识别选择出对肿瘤分类最有贡献的基因。为了能有效地进行微阵列基因选择,提出用一个边缘分布模型(marginal distribution model,MDM)来描述微阵列数据。该模型不仅能区分基因是否在两样本中差异表达,而且能区分出基因在哪一类样本中表达,从而选择出的基因更具有生物学意义。模拟数据及真实微阵列数据集上的实验结果表明,该方法能有效地进行微阵列基因选择。     

ViSOM - a novel method for multivariate data projection andstructure visualization

When used for visualization of high-dimensional data, the self-organizing map (SOM) requires a coloring scheme, such as the U-matrix, to mark the distances between neurons. Even so, the structures of the data clusters may not be apparent and their shapes are often distorted. In this paper, a visualization-induced SOM (ViSOM) is proposed to overcome these shortcomings. The algorithm constrains and regularizes the inter-neuron distance with a parameter that controls the resolution of the map. The mapping preserves the inter-point distances of the input data on the map as well as the topology. It produces a graded mesh in the data space such that the distances between mapped data points on the map resemble those in the original space, like in the Sammon mapping. However, unlike the Sammon mapping, the ViSOM can accommodate both training data and new arrivals and is much simpler in computational complexity. Several experimental results and comparisons with other methods are presented.     

A novel hybrid feature selection method for microarray data analysis

Recently, many methods have been proposed for microarray data analysis. One of the challenges for microarray applications is to select a proper number of the most relevant genes for data analysis. In this paper, we propose a novel hybrid method for feature selection in microarray data analysis. This method first uses a genetic algorithm with dynamic parameter setting (GADP) to generate a number of subsets of genes and to rank the genes according to their occurrence frequencies in the gene subsets. Then, this method uses the χ²-test for homogeneity to select a proper number of the top-ranked genes for data analysis. We use the support vector machine (SVM) to verify the efficiency of the selected genes. Six different microarray datasets are used to compare the performance of the GADP method with the existing methods. The experimental results show that the GADP method is better than the existing methods in terms of the number of selected genes and the prediction accuracy.     

The improvement of breast cancer prognosis accuracy from integrated gene expression and clinical data

Predicting the accurate prognosis of breast cancer from high throughput microarray data is often a challenging task. Although many statistical methods and machine learning techniques were applied to diagnose the prognosis outcome of breast cancer, they are suffered from the low prediction accuracy (usually lower than 70%). In this paper, we propose a better method (genetic algorithm-support vector machine, we called GASVM) to significant improve the prediction accuracy of breast cancer from gene expression profiles. To further improve the classification performance, we also apply GASVM model using combined clinical and microarray data. In this paper, we evaluate the performance of the GASVM model based on data provided by 97 breast cancer patients. Four kinds of gene selection methods are used: all genes (All), 70 correlation-selected genes (C70), 15 medical literature-selected genes (R15), and 50 T-test-selected genes (T50). With optimized parameter values identified from GASVM model, the average predictive accuracy of our model approaches 95% for T50 and 90% for C70 or R15 in all four kernel functions using integrated clinical and microarray data. Our model produces results more accurately than the average 70% predictive accuracy of other machine learning methods. The results indicate that the GASVM model has the potential to better assist physicians in the prognosis of breast cancer through the use of both clinical and microarray data.     

A novel approach to feature extraction from classification models based on information gene pairs

Various microarray experiments are now done in many laboratories, resulting in the rapid accumulation of microarray data in public repositories. One of the major challenges of analyzing microarray data is how to extract and select efficient features from it for accurate cancer classification. Here we introduce a new feature extraction and selection method based on information gene pairs that have significant change in different tissue samples. Experimental results on five public microarray data sets demonstrate that the feature subset selected by the proposed method performs well and achieves higher classification accuracy on several classifiers. We perform extensive experimental comparison of the features selected by the proposed method and features selected by other methods using different evaluation methods and classifiers. The results confirm that the proposed method performs as well as other methods on acute lymphoblastic-acute myeloid leukemia, adenocarcinoma and breast cancer data sets using a fewer information genes and leads to significant improvement of classification accuracy on colon and diffuse large B cell lymphoma cancer data sets.     

An interactive approach to mining gene expression data

Effective identification of coexpressed genes and coherent patterns in gene expression data is an important task in bioinformatics research and biomedical applications. Several clustering methods have recently been proposed to identify coexpressed genes that share similar coherent patterns. However, there is no objective standard for groups of coexpressed genes. The interpretation of co-expression heavily depends on domain knowledge. Furthermore, groups of coexpressed genes in gene expression data are often highly connected through a large number of "intermediate" genes. There may be no clear boundaries to separate clusters. Clustering gene expression data also faces the challenges of satisfying biological domain requirements and addressing the high connectivity of the data sets. In this paper, we propose an interactive framework for exploring coherent patterns in gene expression data. A novel coherent pattern index is proposed to give users highly confident indications of the existence of coherent patterns. To derive a coherent pattern index and facilitate clustering, we devise an attraction tree structure that summarizes the coherence information among genes in the data set. We present efficient and scalable algorithms for constructing attraction trees and coherent pattern indices from gene expression data sets. Our experimental results show that our approach is effective in mining gene expression data and is scalable for mining large data sets.     

Gene selection for designing optimal fuzzy rule base classifier by estimating missing value

DNA microarray technology, a high throughput technology evaluates the expression of thousands of genes simultaneously under different experimental conditions. Analysis of the gene expression data reveals that not all but few important genes are responsible for the diseases. However, the DNA microarray data set usually contain multiple missing value and therefore, selection of important genes using the incomplete data set may be erroneous, resulting misclassification in disease prediction. In the paper we propose an integrated framework, which first imputes the missing value and then in order to achieve maximum accuracy in classifying the patients a classifier has been designed to select the genes using the complete microarray data set.Here functionally similar genes are employed to estimate the missing value unlike the existing gene expression value based distance similarity measure. However, the functionally similar genes may differ in their protein production capacity and so the degree of similarity between the genes varies from gene to gene. The problem has been dealt by proposing a novel method to impute the missing value using the concept of fuzzy similarity. After imputing the missing value, the continuous gene expression matrix is discretized using fuzzy sets to distinguish the activation levels of different genes. The proposed fuzzy importance factor (FIf) of each gene represents its activation level or protein production capacity both in the disease and normal class. The importance of each gene is evaluated while optimizing the number of rules in the fuzzy classifier depending on the FIf. The methodology we propose has been demonstrated using nine different cancer data sets and compared with the state of the art methods. Analysis of experimental results reveals that the proposed framework able to classify the diseased and normal patients with improved accuracy.     

Fuzzy clustering with biological knowledge for gene selection

This paper presents an application of Fuzzy Clustering of Large Applications based on Randomized Search (FCLARANS) for attribute clustering and dimensionality reduction in gene expression data. Domain knowledge based on gene ontology and differential gene expressions are employed in the process. The use of domain knowledge helps in the automated selection of biologically meaningful partitions. Gene ontology (GO) study helps in detecting biologically enriched and statistically significant clusters. Fold-change is measured to select the differentially expressed genes as the representatives of these clusters. Tools like Eisen plot and cluster profiles of these clusters help establish their coherence. Important representative features (or genes) are extracted from each enriched gene partition to form the reduced gene space. While the reduced gene set forms a biologically meaningful attribute space, it simultaneously leads to a decrease in computational burden. External validation of the reduced subspace, using various well-known classifiers, establishes the effectiveness of the proposed methodology on four sets of publicly available microarray gene expression data.     

基于相容关系的基因选择方法

有效的基因选择是对基因表达数据进行分析的重要内容。粗糙集作为一种软计算方法能够保持在数据集分类能力不变的基础上,对属性进行约简。由于基因表达数据的连续性,为了避免运用粗糙集方法所必需的离散化过程带来的信息丢失,将相容粗糙集应用于基因的特征选取,提出了基于相容关系的基因选择方法。首先,通过i检验对基因表达数据进行排列,选择评分靠前的若干基因;然后,通过相容粗糙集对这些基因进一步约简。在两个标准的基因表达数据上进行了实验,结果表明该方法是可行性和有效性的。     

MIGSOM: Multilevel Interior Growing Self-Organizing Maps for High Dimensional Data Clustering

Understanding the inherent structure of high-dimensional datasets is a very challenging task. This can be tackled from visualization, summarizing or simply clustering points of view. The Self-Organizing Map (SOM) is a powerful and unsupervised neural network to resolve these kinds of problems. By preserving the data topology mapped onto a grid, SOM can facilitate visualization of data structure. However, classical SOM still suffers from the limits of its predefined structure. Growing variants of SOM can overcome this problem, since they have tried to define a network structure with no need an advance a fixed number of output units by dynamic growing architecture. In this paper we propose a new dynamic SOMs called MIGSOM: Multilevel Interior Growing SOMs for high-dimensional data clustering. MIGSOM present a different architecture than dynamic variants presented in the literature. Using an unsupervised training process MIGSOM has the capability of growing map size from the boundaries as well as the interior of the network in order to represent more faithfully the structure present in a data collection. As a result, MIGSOM can have three-dimensional (3-D) structure with different levels of oriented maps developed according to data direction. We demonstrate the potential of the MIGSOM with real-world datasets of high-dimensional properties in terms of topology preserving visualization, vectors summarizing by efficient quantization and data clustering. In addition, MIGSOM achieves better performance compared to growing grid and the classical SOM.     

Class prediction and gene selection for DNA microarrays using regularized sliced inverse regression

The monitoring of the expression profiles of thousands of genes have proved to be particularly promising for biological classification. DNA microarray data have been recently used for the development of classification rules, particularly for cancer diagnosis. However, microarray data present major challenges due to the complex, multiclass nature and the overwhelming number of variables characterizing gene expression profiles. A regularized form of sliced inverse regression (REGSIR) approach is proposed. It allows the simultaneous development of classification rules and the selection of those genes that are most important in terms of classification accuracy. The method is illustrated on some publicly available microarray data sets. Furthermore, an extensive comparison with other classification methods is reported. The REGSIR performance is comparable with the best classification methods available, and when appropriate feature selection is made the performance can be considerably improved.     

A feature selection method using improved regularized linear discriminant analysis

Investigation of genes, using data analysis and computer-based methods, has gained widespread attention in solving human cancer classification problem. DNA microarray gene expression datasets are readily utilized for this purpose. In this paper, we propose a feature selection method using improved regularized linear discriminant analysis technique to select important genes, crucial for human cancer classification problem. The experiment is conducted on several DNA microarray gene expression datasets and promising results are obtained when compared with several other existing feature selection methods.