scholarly journals Graph Theoretic Techniques for Clustering and Biclustering gene expression data.

2012 ◽  
pp. 173-181
Author(s):  
Prangyaparamita Mohapatra ◽  
Tripti Swarnkar
Keyword(s):  
Gene Expression ◽  
Data Mining ◽  
Gene Expression Data ◽  
Biological Networks ◽  
Clustering Algorithms ◽  
Expression Data ◽  
Microarray Technology ◽  
Clustering Methods ◽  
Experimental Conditions ◽  
Data Set

DNA microarray technology has made it possible to simultaneously monitor the expression levels of thousands of genes during biological processes and across collections of related samples. However, the large number of genes and the complexity of biological networks greatly increase 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. 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. A large number of clustering approaches have been proposed for the analysis of gene expression data obtained from microarray experiments. However, the results of the application of standard clustering methods to genes are limited. These limited results are imposed by the existence of a number of experimental conditions where the activity of genes is uncorrelated. A similar limitation exists when clustering of conditions is performed. For this reason, a number of algorithms that perform simultaneous clustering on the row and column dimensions of the gene expression matrix have been proposed to date. This simultaneous clustering, usually designated by biclustering, seeks to find submatrices that are subgroups of genes and subgroups of columns, where the genes exhibit highly correlated activities for every condition. This type of algorithms has also been proposed and used in other fields, such as information retrieval and data mining. In this paper, we first briefly introduce the concepts of microarray technology and discuss the basic elements of clustering on gene expression data. Then, we present specific challenges pertinent to each clustering category and introduce several representative approaches.

scholarly journals Subpopulation identification for single-cell RNA-sequencing data using functional data analysis

2019 ◽  
Author(s):  
Kyungmin Ahn ◽  
Hironobu Fujiwara
Keyword(s):  
Gene Expression ◽  
Data Analysis ◽  
Single Cell ◽  
Gene Expression Data ◽  
Functional Data Analysis ◽  
Functional Data ◽  
Clustering Algorithms ◽  
Expression Data ◽  
Clustering Methods ◽  
Single Cell Rna Sequencing

AbstractBackgroundIn single-cell RNA-sequencing (scRNA-seq) data analysis, a number of statistical tools in multivariate data analysis (MDA) have been developed to help analyze the gene expression data. This MDA approach is typically focused on examining discrete genomic units of genes that ignores the dependency between the data components. In this paper, we propose a functional data analysis (FDA) approach on scRNA-seq data whereby we consider each cell as a single function. To avoid a large number of dropouts (zero or zero-closed values) and reduce the high dimensionality of the data, we first perform a principal component analysis (PCA) and assign PCs to be the amplitude of the function. Then we use the index of PCs directly from PCA for the phase components. This approach allows us to apply FDA clustering methods to scRNA-seq data analysis.ResultsTo demonstrate the robustness of our method, we apply several existing FDA clustering algorithms to the gene expression data to improve the accuracy of the classification of the cell types against the conventional clustering methods in MDA. As a result, the FDA clustering algorithms achieve superior accuracy on simulated data as well as real data such as human and mouse scRNA-seq data.ConclusionsThis new statistical technique enhances the classification performance and ultimately improves the understanding of stochastic biological processes. This new framework provides an essentially different scRNA-seq data analytical approach, which can complement conventional MDA methods. It can be truly effective when current MDA methods cannot detect or uncover the hidden functional nature of the gene expression dynamics.

scholarly journals Clustering of gene expression profiles: creating initialization-independent clusterings by eliminating unstable genes

2010 ◽  
Vol 7 (3) ◽  
Author(s):  
Wim De Mulder ◽  
Martin Kuiper ◽  
René Boel
Keyword(s):  
Gene Expression ◽  
Gene Expression Data ◽  
Expression Profiles ◽  
Clustering Algorithms ◽  
Gene Expression Profiles ◽  
Biological Data ◽  
Biological Knowledge ◽  
Expression Data ◽  
Data Set ◽  
Cluster Membership

SummaryClustering is an important approach in the analysis of biological data, and often a first step to identify interesting patterns of coexpression in gene expression data. Because of the high complexity and diversity of gene expression data, many genes cannot be easily assigned to a cluster, but even if the dissimilarity of these genes with all other gene groups is large, they will finally be forced to become member of a cluster. In this paper we show how to detect such elements, called unstable elements. We have developed an approach for iterative clustering algorithms in which unstable elements are deleted, making the iterative algorithm less dependent on initial centers. Although the approach is unsupervised, it is less likely that the clusters into which the reduced data set is subdivided contain false positives. This clustering yields a more differentiated approach for biological data, since the cluster analysis is divided into two parts: the pruned data set is divided into highly consistent clusters in an unsupervised way and the removed, unstable elements for which no meaningful cluster exists in unsupervised terms can be given a cluster with the use of biological knowledge and information about the likelihood of cluster membership. We illustrate our framework on both an artificial and real biological data set.

scholarly journals One-Step Robust Low-Rank Subspace Segmentation for Tumor Sample Clustering

2021 ◽  
Vol 2021 ◽  
pp. 1-16
Author(s):  
Jian Liu ◽  
Yuhu Cheng ◽  
Xuesong Wang ◽  
Shuguang Ge
Keyword(s):  
Gene Expression ◽  
Gene Expression Data ◽  
Low Rank ◽  
Expression Data ◽  
Clustering Methods ◽  
Data Set ◽  
Tumor Sample ◽  
Cancer Subtypes ◽  
Subspace Segmentation ◽  
One Step

Clustering of tumor samples can help identify cancer types and discover new cancer subtypes, which is essential for effective cancer treatment. Although many traditional clustering methods have been proposed for tumor sample clustering, advanced algorithms with better performance are still needed. Low-rank subspace clustering is a popular algorithm in recent years. In this paper, we propose a novel one-step robust low-rank subspace segmentation method (ORLRS) for clustering the tumor sample. For a gene expression data set, we seek its lowest rank representation matrix and the noise matrix. By imposing the discrete constraint on the low-rank matrix, without performing spectral clustering, ORLRS learns the cluster indicators of subspaces directly, i.e., performing the clustering task in one step. To improve the robustness of the method, capped norm is adopted to remove the extreme data outliers in the noise matrix. Furthermore, we conduct an efficient solution to solve the problem of ORLRS. Experiments on several tumor gene expression data demonstrate the effectiveness of ORLRS.

scholarly journals Current State-of-the-Art of Clustering Methods for Gene Expression Data with RNA-Seq

2020 ◽  
Author(s):  
Ismail Jamail ◽  
Ahmed Moussa
Keyword(s):  
Gene Expression ◽  
Cluster Analysis ◽  
Data Analysis ◽  
Gene Expression Data ◽  
Expression Profile ◽  
Clustering Algorithms ◽  
Expression Data ◽  
Rna Seq ◽  
Clustering Methods ◽  
Clustering And Classification

Latest developments in high-throughput cDNA sequencing (RNA-seq) have revolutionized gene expression profiling. This analysis aims to compare the expression levels of multiple genes between two or more samples, under specific circumstances or in a specific cell to give a global picture of cellular function. Thanks to these advances, gene expression data are being generated in large throughput. One of the primary data analysis tasks for gene expression studies involves data-mining techniques such as clustering and classification. Clustering, which is an unsupervised learning technique, has been widely used as a computational tool to facilitate our understanding of gene functions and regulations involved in a biological process. Cluster analysis aims to group the large number of genes present in a sample of gene expression profile data, such that similar or related genes are in same clusters, and different or unrelated genes are in distinct ones. Classification on the other hand can be used for grouping samples based on their expression profile. There are many clustering and classification algorithms that can be applied in gene expression experiments, the most widely used are hierarchical clustering, k-means clustering and model-based clustering that depend on a model to sort out the number of clusters. Depending on the data structure, a fitting clustering method must be used. In this chapter, we present a state of art of clustering algorithms and statistical approaches for grouping similar gene expression profiles that can be applied to RNA-seq data analysis and software tools dedicated to these methods. In addition, we discuss challenges in cluster analysis, and compare the performance of height commonly used clustering methods on four different public datasets from recount2.

Heterogeneous Gene Data for Classifying Tumors

2011 ◽  
pp. 550-554
Author(s):  
Benny Yiu-ming Fung ◽  
Vincent To-yee Ng
Keyword(s):  
Gene Expression ◽  
Gene Expression Data ◽  
Single Gene ◽  
Data Sets ◽  
Expression Data ◽  
Classification Models ◽  
Experimental Conditions ◽  
Data Set ◽  
Single Data ◽  
Gene Data

When classifying tumors using gene expression data, mining tasks commonly make use of only a single data set. However, classification models based on patterns extracted from a single data set are often not indicative of an entire population and heterogeneous samples subsequently applied to these models may not fit, leading to performance degradation. In short, it is not possible to guarantee that mining results based on a single gene expression data set will be reliable or robust (Miller et al., 2002). This problem can be addressed using classification algorithms capable of handling multiple, heterogeneous gene expression data sets. Apart from improving mining performance, the use of such algorithms would make mining results less sensitive to the variations of different microarray platforms and to experimental conditions embedded in heterogeneous gene expression data sets.

scholarly journals A fuzzy logic approach to analyzing gene expression data

2000 ◽  
Vol 3 (1) ◽  
pp. 9-15 ◽  
Author(s):  
PETER J. WOOLF ◽  
YIXIN WANG
Keyword(s):  
Gene Expression ◽  
Fuzzy Logic ◽  
Gene Expression Data ◽  
Expression Data ◽  
Heuristic Rules ◽  
Yeast Gene ◽  
Data Set ◽  
Fuzzy Logic Approach ◽  
Logic Approach ◽  
Novel Algorithm

Woolf, Peter J., and Yixin Wang. A fuzzy logic approach to analyzing gene expression data. Physiol Genomics 3: 9–15, 2000.—We have developed a novel algorithm for analyzing gene expression data. This algorithm uses fuzzy logic to transform expression values into qualitative descriptors that can be evaluated by using a set of heuristic rules. In our tests we designed a model to find triplets of activators, repressors, and targets in a yeast gene expression data set. For the conditions tested, the predictions made by the algorithm agree well with experimental data in the literature. The algorithm can also assist in determining the function of uncharacterized proteins and is able to detect a substantially larger number of transcription factors than could be found at random. This technology extends current techniques such as clustering in that it allows the user to generate a connected network of genes using only expression data.

scholarly journals A Graph Feature Auto-Encoder for the prediction of unobserved node features on biological networks

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Ramin Hasibi ◽  
Tom Michoel
Keyword(s):  
Gene Expression ◽  
Neural Networks ◽  
Gene Expression Data ◽  
Biological Networks ◽  
Molecular Interaction ◽  
Interaction Networks ◽  
Omics Data ◽  
Expression Data ◽  
Molecular Interaction Networks ◽  
Graph Neural Networks

Abstract Background Molecular interaction networks summarize complex biological processes as graphs, whose structure is informative of biological function at multiple scales. Simultaneously, omics technologies measure the variation or activity of genes, proteins, or metabolites across individuals or experimental conditions. Integrating the complementary viewpoints of biological networks and omics data is an important task in bioinformatics, but existing methods treat networks as discrete structures, which are intrinsically difficult to integrate with continuous node features or activity measures. Graph neural networks map graph nodes into a low-dimensional vector space representation, and can be trained to preserve both the local graph structure and the similarity between node features. Results We studied the representation of transcriptional, protein–protein and genetic interaction networks in E. coli and mouse using graph neural networks. We found that such representations explain a large proportion of variation in gene expression data, and that using gene expression data as node features improves the reconstruction of the graph from the embedding. We further proposed a new end-to-end Graph Feature Auto-Encoder framework for the prediction of node features utilizing the structure of the gene networks, which is trained on the feature prediction task, and showed that it performs better at predicting unobserved node features than regular MultiLayer Perceptrons. When applied to the problem of imputing missing data in single-cell RNAseq data, the Graph Feature Auto-Encoder utilizing our new graph convolution layer called FeatGraphConv outperformed a state-of-the-art imputation method that does not use protein interaction information, showing the benefit of integrating biological networks and omics data with our proposed approach. Conclusion Our proposed Graph Feature Auto-Encoder framework is a powerful approach for integrating and exploiting the close relation between molecular interaction networks and functional genomics data.

Sign in / Sign up

Export Citation Format

Share Document