Gene expression modular analysis: an overview from the data mining perspective

Most of the traditional gene selection approaches are borrowed from other fields such as statistics and computer science, However, they do not prioritize biologically relevant genes since the ultimate goal is to determine features that optimize model performance metrics not to build a biologically meaningful model. Therefore, there is an imminent need for new computational tools that integrate the biological knowledge about the data in the process of gene selection and machine learning. Integrative gene selection enables incorporation of biological domain knowledge from external biological resources. In this study, we propose a new computational approach named CogNet that is an integrative gene selection tool that exploits biological knowledge for grouping the genes for the computational modeling tasks of ranking and classification. In CogNet, the pathfindR serves as the biological grouping tool to allow the main algorithm to rank active-subnetwork-oriented KEGG pathway enrichment analysis results to build a biologically relevant model. CogNet provides a list of significant KEGG pathways that can classify the data with a very high accuracy. The list also provides the genes belonging to these pathways that are differentially expressed that are used as features in the classification problem. The list facilitates deep analysis and better interpretability of the role of KEGG pathways in classification of the data thus better establishing the biological relevance of these differentially expressed genes. Even though the main aim of our study is not to improve the accuracy of any existing tool, the performance of the CogNet outperforms a similar approach called maTE while obtaining similar performance compared to other similar tools including SVM-RCE. CogNet was tested on 13 gene expression datasets concerning a variety of diseases.

The purpose of this paper is to introduce transductive inference with support vector machines (TSVM) as a powerful methodology for classification of gene expression data, using training and prediction data sets. The following classification problems will be considered: determination of cancer diagnosis categories and classification of genes from the budding yeast Saccharomyces cerevisiae in functional groups. In the case of training samples, experts have already classified the samples in their respective classes. So, given each prediction sample, the purpose is to determine its corresponding class. The main aspect of TSVM is that the classification task will be implemented in just one step, improving the generalization capability of the classifier. The TSVM will be compared with the traditional inductive method (SVM) in a series of experiments concerning the two classification problems, with promising results.

Contributors

Clustering is one of the most important techniques, which group genes of similar expression pattern into a small number of meaningful homogeneous groups or clusters. Gene expression data has certain special characteristics and is a challenging research problem. There are many applications for clustering gene expression data. Clustering can be applied for genes called gene clustering. Hard clustering allows a gene to get placed in exactly one cluster and converges in local optima. Soft clustering approach allows gene to get placed in all the clusters with some membership values. As the hard clustering approach converges in local optimum, an evolutionary computation technique like swarm clustering is required to find the global optimum solution. This chapter studies swarm clustering techniques such as Particle Swarm Clustering K-Means, Cuckoo Search Clustering, Cuckoo Search Clustering with levy flight, harmony search, Fuzzy PSO and Ant Colony Optimization based Clustering for clustering gene expression data. Evaluation measures for clustering gene expression data are also discussed.

Diabetic retinopathy (DR) is a common comorbidity of diabetes involving the formation of abnormal vascular structures in the retina. Tissue inhibitor of metalloproteinases 2 (TIMP2), initially identified as a key mediator of extracellular matrix turnover, is pivotal for inflammatory processes and tissue homeostasis. The current study examined the influence of TIMP2 gene variations on the risk for DR. We investigated the association of TIMP2 gene variations with DR by analyzing four single-nucleotide polymorphisms (SNPs) of the TIMP2 gene (rs16971783, rs2889529, rs7220980, and rs8068674) in a cohort of 672 patients with DR and 919 diabetic controls with normal ophthalmoscopic findings. Our results showed that rs16971783 of TIMP2 gene was associated with a higher risk for DR (TA vs. TT, AOR=1.445, p=0.028; TA+AA vs. TT, AOR=1.179, p=0.046). We further demonstrated that the association of rs16971783 with DR was exclusively observed in diabetic individuals with proliferative DR (TA vs. TT, AOR=1.827, p=0.035; TA+AA vs. TT, AOR=1.351, p=0.027), whereas not detected among those who suffered from non-proliferative DR. In addition, preliminary exploration of gene expression data from public resources reveald that rs16971783 regulated TIMP2 gene expression in various human tissues. Allele-specific expression of TIMP2 gene might contribute to the progression of DR.

Predicting functions of genes is an important issue in biology. Clustering gene expression profiles has been widely used for gene function prediction, but most clustering methods are unstable and sensitive to input parameters such as starting values and number of clusters. In this article, we develop a novel consensus clustering method to address the instability issue and thus improve the performance of clustering methods. The biological function of an unannotated gene is predicted based on the most enriched functional category in its consensus cluster. The MIPS gene annotations are used to evaluate the predictive performance. It is shown that the consensus clustering-based classification method has a significantly better predictive performance than a previously used clustering-based classification method while performing as well as support vector machines (SVMs). In addition to the obvious applicability of consensus clustering to unsupervised learning, the method's advantages in supervised learning include its being a multiclass classifier that can be trained much faster than SVMs, its generality to include any of the many existing clustering algorithms, and its flexibility to be integrated with other predictive models built with other types of data, suggesting its potential for further improved performance. As a concrete example, we consider its combined use with protein-protein interaction data for gene function prediction. It is shown that the combined analysis has a significantly higher predictive accuracy and a much broader functional coverage than using either data source alone.

Advanced Scout is a PC-based data mining application used by National Basketball Association (NBA) coaching staffs to discover interesting patterns in basketball game data. We describe Advanced Scout software from the perspective of data mining and knowledge discovery. This paper highlights the pre-processing of raw data that the program performs, describes the data mining aspects of the software and how the interpretation of patterns supports the process of knowledge discovery. The underlying technique of attribute focusing as the basis of the algorithm is also described. The process of pattern interpretation is facilitated by allowing the user to relate patterns to video tape.

Gene expression (GE) profiles expansively revised to disclose intuition into the multifariousness of cancer furthermore to discover concealed information which provides biological knowledge for the classification of cancer. Precise cancer classification straightly through original GE profiles stays challenging on account of the intrinsic high-dimension feature along with the small magnitude of the data samples. Therefore, choosing high discriminative genes as of the GE data have turn into progressively fascinating in the bioinformatics field. This given paper gives a technique for the GE data classification utilising entropy-based graph classifier. Initially, the proposed technique evaluate the GE data's signal to noise ratio (SNR) values, additionally, selects the relevant features using krill herd (KH) optimization process. The truth is that not all features are helpful for classification, and some redundant together with the irrelevant features might even serve as outlier. To dispose the outliers, feature reduction is done with the assist of Euclidean distance. Classification is made utilising entropy-based graph classifier. The proposed process' effectiveness contrasted with the existing method concerning classifications is established from the experimental outcome.

BackgroundTo better understand the molecular programs of normal and abnormal genital development, clear-cut definition of androgen-dependent gene expression patterns, without the influence of genotype (46, XX vs. 46, XY), is warranted. Previously, we have identified global gene expression profiles in genital-derived fibroblasts that differ between 46, XY males and 46, XY females with complete androgen insensitivity syndrome (CAIS) due to inactivating mutations of the androgen receptor (AR). While these differences could be due to cell autonomous changes in gene expression induced by androgen programming, recent work suggests they could also be influenced by the location from which the fibroblasts were harvested (topology). To minimize the influence of topology, we compared gene expression patterns of fibroblasts derived from identical urogenital anlagen: the scrotum in normally virilized 46, XY males and the labia majora from completely feminized 46, XY individuals with CAIS.Results612 transcripts representing 440 unique genes differed significantly in expression levels between scrotum and CAIS labia majora, suggesting the effects of androgen programming. While some genes coincided with those we had identified previously (TBX3, IGFBP5, EGFR, CSPG2), a significant number did not, implying that topology had influenced gene expression in our previous experiments. Supervised clustering of gene expression data derived from a large set of fibroblast cultures from individuals with partial AIS revealed that the new, topology controlled data set better classified the specimens.ConclusionInactivating mutations of the AR, in themselves, appear to induce lasting changes in gene expression in cultured fibroblasts, independent of topology and genotype. Genes identified are likely to be relevant candidates to decipher androgen-dependent normal and abnormal genital development.

Classifying the gene expression levels of normal and cancerous cells and identifying the genes most contributing to this distinction propose an alternative means of diagnosis. We have investigated the effect of feature extraction and feature selection on clustering of the expression data on two different data sets for ovarian cancer. One data set consisted of 2176 transcripts from 30 samples, nine from normal ovarian epithelial cells and 21 from cancerous ones. The other data set had 7129 transcripts coming from 27 tumor and four normal ovarian tissues. Hierarchical clustering algorithms employing complete-link, average-link and Ward's method were implemented for comparative evaluation. Principal component analysis was applied for feature extraction and resulted in 100% segregation. Feature selection was performed to identify the most distinguishing genes using CART/spl reg/ software. Selected features were able to cluster the data with 100% success. The results suggest that adoption of feature extraction and selection enhances the quality of clustering of gene expression data for ovarian cancer. Identification of distinguishing genes is a more complex problem that requires incorporating pathway knowledge with statistical and machine learning methods.

Clustering of gene expression data simplifies subsequent data analyses and forms the basis of numerous approaches for biomarker identification, prediction of clinical outcome, and personalized therapeutic strategies. The most popular clustering methods such as K-means and hierarchical clustering are intuitive and easy to use, but they require arbitrary choices on their various parameters (number of clusters for K-means, and a threshold to cut the tree for hierarchical clustering). Human disease gene expression data are in general more difficult to cluster efficiently due to background (genotype) heterogeneity, disease stage and progression differences and disease subtyping; all of which cause gene expression datasets to be more heterogeneous. Spectral clustering has been recently introduced in many fields as a promising alternative to standard clustering methods. The idea is that pairwise comparisons can help reveal global features through the eigen techniques. In this paper, we developed a new recursive K-means spectral clustering method (ReKS) for disease gene expression data. We benchmarked ReKS on three large-scale cancer datasets and we compared it to different clustering methods with respect to execution time, background models and external biological knowledge. We found ReKS to be superior to the hierarchical methods and equally good to K-means, but much faster than them and without the requirement for a priori knowledge of K. Overall, ReKS offers an attractive alternative for efficient clustering of human disease data.

One of the most significant research topics in bioinformatics is the classification of gene expression. Gene expression data commonly have a large number of features and a small number of samples. The gene expression data are very different from one to another, this differentiation among data and the feature's large number make the classification for gene expression data challenging. In this study, for classification we assessed the accuracy for most powerful deep learning's algorithms such as Deep Neural Network, Recurrent Neural Network, Convolutional Neural Network and improved Deep Neural Network with the preprocessing technique. The DNN was improved by adding Dropout to it by which the overfitting problem was overcame. Our results showed that the proposed improved-DNN outperforms the other algorithms among all used datasets.

Computational scientists must understand results from experimental, observational and computational simulation generated data to gain insights and perform knowledge discovery. As systems approach the petascale range, problems that were unimaginable a few years ago are within reach. With the increasing volume and complexity of data produced by ultra-scale simulations and high-throughput experiments, understanding the science is largely hampered by the lack of comprehensive I/O, storage, acceleration of data manipulation, analysis, and mining tools. Scientists require techniques, tools and infrastructure to facilitate better understanding of their data, in particular the ability to effectively perform complex data analysis, statistical analysis and knowledge discovery. The goal of this work is to enable more effective analysis of scientific datasets through the integration of enhancements in the I/O stack, from active storage support at the file system layer to MPI-IO and high-level I/O library layers. We propose to provide software components to accelerate data analytics, mining, I/O, and knowledge discovery for large-scale scientific applications, thereby increasing productivity of both scientists and the systems. Our approaches include 1) design the interfaces in high-level I/O libraries, such as parallel netCDF, for applications to activate data mining operations at the lower I/O layers; 2) Enhance MPI-IO runtime systems to incorporate the functionality developed as a part of the runtime system design; 3) Develop parallel data mining programs as part of runtime library for server-side file system in PVFS file system; and 4) Prototype an active storage cluster, which will utilize multicore CPUs, GPUs, and FPGAs to carry out the data mining workload.

To achieve knowledge management (KM), we need to integrate information system strategies with business strategies. The implementation of e-commerce provides conditions for KM of enterprises. This article suggests using data mining (DM) as a technique to support knowledge management in e-commerce. We discuss the process of knowledge management in e-commerce and present a reference model. A general architecture of collecting and mining data out of an e-commerce platform is designed to facilitate user discovering valuable knowledge. We detail the four functional modules, namely data collection, data pre-processing, pattern discovery, and knowledge analysis of the integrated architecture. Finally, some challenges in the process of implementing KM using data mining are summarized.

Clustering is an important data exploration technique with many applications in different areas of engineering, including engineering design, manufacturing system design, quality assurance, production planning and process planning, modelling, monitoring, and control. The clustering problem has been addressed by researchers from many disciplines. However, efforts to perform effective and efficient clustering on large data sets only started in recent years with the emergence of data mining. The current paper presents an overview of clustering algorithms from a data mining perspective. Attention is paid to techniques of scaling up these algorithms to handle large data sets. The paper also describes a number of engineering applications to illustrate the potential of clustering algorithms as a tool for handling complex real-world problems.