High-dimensional Microarray Data Research Articles

A feature selection method for classification based on ensemble of penalized logistic models

Classification accuracy of any classifier can be enhanced by performing the classification on selected informative features. Features selection methods are generally approached for the purpose. Combining multiple models known as ensemble method emerged as prominent method for achieving classification accuracy. These techniques can be considered for variable selection for accuracy gain and interpretability of a classifier. we propose an ensemble of penalized logistic models (EPLM) for feature selection. EPLM employs Lasso, adaptive Lasso and elastic net for feature selection. EPLM is applied to high dimensional microarray data sets and simulated data sets. State-of-the-art classifiers, Lasso, Random Forest (RF), Support Vector Machine (SVM) and K- Nearest Neighbors (KNN) are employed for assessment of EPLM. Experimental comparisons reveal that significant improvement in classification accuracy is achieved for all the classifiers considered. The proposed method is also compared to the Ensemble of subset of KNN classifiers (ESKNN). In comparison to ESKNN EPLM achieves better performance accuracy for all the classifiers on simulated and microarray data sets. Moreover, it is also observed that EPLM has selected significantly smaller number of features as compared to the full feature set.

Naive Bayes combined with partial least squares for classification of high dimensional microarray data

Technological advances allow for the measurement of high dimensional data sets with small sample size. When dealing with such high-dimensional data, the consistency of estimations and classification accuracy is called into question. Partial least squares (PLS) scores have traditionally been coupled with linear discriminant analysis, which requires a multivariate normally distributed PLS score. For the classification of high-dimensional data sets, we introduce PLS-NB, a classification strategy that combines PLS with a variant of Naive Bayes (NB). PLS-NB with standard NB, PLS-NB-G with Gaussian(G) kernel NB, PLS-NB-N with non-parametric (N) kernel NB, and PLS-NB-L with Laplace (L) correction are compared to reference approaches PLS coupled with linear discriminate analyses (LDA) and sparse LDA, which are PLS-LDA and SPLS-LDA, respectively, over gene expression data. Cross-validation is used in conjunction with Monte Carlo simulation to avoid over-fitting. The suggested classifier PLS-NB has been validated and calibrated against reference classifiers. PLS-NB-N outperforms when it comes to classifying embryonal cancer with 89.1% accuracy on test data, and it outperforms when it comes to classifying prostate cancer with 92.3% accuracy on test data. The presented method appears to be a viable contender for high-dimensional data classification; its merits can be investigated further, and it can be used to a variety of classification problems.

A Two-Stage Hybrid Adaptive Particle Swarm Optimization (PSO) Based Artificial Bee Colony (ABC) Algorithm for Solving Feature Selection Problems in High-Dimensional Cancer Microarray Data

A Two-Stage Hybrid Adaptive Particle Swarm Optimization (PSO) Based Artificial Bee Colony (ABC) Algorithm for Solving Feature Selection Problems in High-Dimensional Cancer Microarray Data

Gene selection for microarray data classification via multi-objective graph theoretic-based method

In recent decades, the improvement of computer technology has increased the growth of high-dimensional microarray data. Thus, data mining methods for DNA microarray data classification usually involve samples consisting of thousands of genes. One of the efficient strategies to solve this problem is gene selection, which improves the accuracy of microarray data classification and also decreases computational complexity. In this paper, a novel social network analysis-based gene selection approach is proposed. The proposed method has two main objectives of the relevance maximization and redundancy minimization of the selected genes. In this method, on each iteration, a maximum community is selected repetitively. Then among the existing genes in this community, the appropriate genes are selected by using the node centrality-based criterion. The reported results indicate that the developed gene selection algorithm while increasing the classification accuracy of microarray data, will also decrease the time complexity.

Improved Lasso (ILASSO) for Gene Selection and Classification in High Dimensional DNA Microarray Data

<p class="0abstract">Classification and selection of gene in high dimensional microarray data has become a challenging problem in molecular biology and genetics. Penalized Adaptive likelihood method has been employed recently for classification of cancer to address both gene selection consistency and estimation of gene coefficients in high dimensional data simultaneously. Many studies from the literature have proposed the use of ordinary least squares (OLS), maximum likelihood estimation (MLE) and Elastic net as the initial weight in the Adaptive elastic net, but in high dimensional microarray data the MLE and OLS are not suitable. Likewise, considering the Elastic net as the initial weight in Adaptive elastic yields a poor performance, because the ridge penalty in the Elastic net grouped coefficient of highly correlated genes closer to each other. As a result, the estimator fails to differentiate coefficients of highly correlated genes that have different sign being grouped together. To tackle this issue, the present study proposed Improved LASSO (ILASSO) estimator which add the ridge penalty to the original LASSO with an Adaptive weight to both and simultaneously. Results from the real data indicated that ILASSO has a better performance compared to other methods in terms of the number of gene selected, classification precision, Sensitivity and Specificity.</p>

Gene selection for microarray data classification via dual latent representation learning

With the rapid development of genetic sequencing and DNA microarray technologies, a large number of gene expression data has been generated, which provides an important reference for tumor diagnosis. However, it is challenging to classify these gene expression data due to the high-dimensionality and small number of data samples. In this work, we propose an effective method to select the most discriminative genes from high-dimensional microarray data for benefiting tumor classification. In detail, each gene is regarded as a feature dimension and we build a novel computational model based on dual latent feature representation learning, referred as DLRL briefly, which can capture both the internal association of data samples and the relationship between different genes. Instead of measuring the importance of genes in original data space, we perform gene selection in the learned latent representation space which is more robust to noisy and redundant information. We first construct the affinity matrices for both samples and genes, which can represent the correlation information between data samples and genes, respectively. Then the dual latent representation learning is modelled via non-negative matrix factorization of the two affinity matrices. The low-dimensional latent representation matrix of sample space is treated as a pseudo-label matrix to guide the latent space projection of original data. Meanwhile, the sample projection matrix is unified with the latent representation matrix of gene space. An alternating algorithm is carefully designed to solve the resultant optimization problem. Extensive experiments on six commonly used publicly microarray datasets are conducted to demonstrate that the proposed method can steadily outperform other state-of-the-art methods in terms of microarray data classification. In addition, we also test the proposed model on a face image dataset as well as a digit image dataset to validate its efficacy for general unsupervised feature selection.

Principal Component Analysis in Linear Regression Survival Model with Microarray Data

As a useful alternative to the Cox proportional hazards model, the linear regression survival model assumes a linear relationship between the covariates and a known monotone transformation, for example logarithm, of an event time of interest. In this article, we study the linear regression survival model with right censored survival data, when high-dimensional microarray measurements are present. Such data may arise in studies in vestigating the statistical influence of molecular features on survival risk. We propose using the principal component regression (PCR) technique for model reduction based on the weight least squared Stute estimate. Com pared with other model reduction techniques, the PCR approach is relatively insensitive to the number of covariates and hence suitable for high dimen sional microarray data. Component selection based on the nonparametric bootstrap, and model evaluation using the time-dependent ROC (receiver operating characteristic) technique are investigated. We demonstrate the proposed approach with datasets from two microarray gene expression pro filing studies of lymphoma cancers

Clustering-based hybrid feature selection approach for high dimensional microarray data

The DNA microarrays are used to monitor the expression levels of significant genes. Most of the microarray data are assumed to be high dimensional, redundant, and noisy. This paper proposed a clustering-based hybrid gene selection approach to reduce the high dimensionality and increase the classification accuracy of cancer microarray data. The proposed approach uses the combined method of k-means clustering algorithm and signal-to-noise-ratio ranking method as a primary filtering method to reduce the high dimensionality of the microarray dataset. A cellular learning automaton combined with ant colony optimization is then applied on the reduced dataset as a wrapper method to get the optimized gene subset. The classifiers adopted to evaluate the proposed method are support vector machine, K-nearest neighbor, and Naive Bayes. The experiments showed promising results in gene subset selection and classification.

Swarm Intelligence Algorithms in Gene Selection Profile Based on Classification of Microarray Data: A Review

Microarray data plays a major role in diagnosing and treating cancer. In several microarray data sets, many gene fragments are not associated with the target diseases. A solution to the gene selection problem might become important when analyzing large gene datasets. The key task is to better represent genes through optimum accuracy in classifying the samples. Different gene classification algorithms have been provided in past studies; after all, they suffered due to the selection of several genes mostly in high-dimensional microarray data. This paper aims to review classification and feature selection with different microarray datasets focused on swarm intelligence algorithms. We explain microarray data and its types in this paper briefly. Moreover, our paper presents an introduction to most common swarm intelligence algorithms. A review on swarm intelligence algorithms in gene selection profile based on classification of Microarray Data is presented in this paper.

An Efficient SVM-Based Feature Selection Model for Cancer Classification Using High-Dimensional Microarray Data

An Efficient SVM-Based Feature Selection Model for Cancer Classification Using High-Dimensional Microarray Data

A Novel Hybrid Filter/Wrapper Feature Selection Approach Based on Improved Fruit Fly Optimization Algorithm and Chi-square Test for High Dimensional Microarray Data

Background: Microarray data is widely utilized for disease analysis and diagnosis. However, it is hard to process them directly and achieve high classification accuracy due to the intrinsic characteristics of high dimensionality and small size samples. As an important data preprocessing technique, feature selection is usually used to reduce the dimensionality of some datasets. Methods: Given the limitations of employing filter or wrapper approaches individually for feature selection, in the study, a novel hybrid filter-wrapper approach, CS_IFOA, is proposed for high dimensional datasets. First, the Chi-square Test is utilized to filter out some irrelevant or redundant features. Next, an improved binary Fruit Fly Optimization algorithm is conducted to further search the optimal feature subset without degrading the classification accuracy. Here, the KNN classifier with the 10-fold-CV is utilized to evaluate the classification accuracy. Results: Extensive experimental results on six benchmark biomedical datasets show that the proposed CS-IFOA can achieve superior performance compared with other state-of-the-art methods. The CS-IFOA can get a smaller number of features while achieving higher classification accuracy. Furthermore, the standard deviation of the experimental results is relatively small, which indicates that the proposed algorithm is relatively robust. Conclusion: The results confirmed the efficiency of our approach in identifying some important genes for high-dimensional biomedical datasets, which can be used as an ideal pre-processing tool to help optimize the feature selection process, and improve the efficiency of disease diagnosis.

An efficient multivariate feature ranking method for gene selection in high-dimensional microarray data

Classification of microarray data plays a significant role in the diagnosis and prediction of cancer. However, its high-dimensionality (>tens of thousands) compared to the number of observations (<tens of hundreds) may lead to poor classification accuracy. In addition, only a fraction of genes is really important for the classification of a certain cancer, and thus feature selection is very essential in this field. Due to the time and memory burden for processing the high-dimensional data, univariate feature ranking methods are widely-used in gene selection. However, most of them are not that accurate because they only consider the relevance of features to the target without considering the redundancy among features. In this study, we propose a novel multivariate feature ranking method to improve the quality of gene selection and ultimately to improve the accuracy of microarray data classification. The method can be efficiently applied to high-dimensional microarray data. We embedded the formal definition of relevance into a Markov blanket (MB) to create a new feature ranking method. Using a few microarray datasets, we demonstrated the practicability of MB-based feature ranking having high accuracy and good efficiency. The method outperformed commonly-used univariate ranking methods and also yielded the better result even compared with the other multivariate feature ranking method due to the advantage of data efficiency.

Maximal Covariance Complexity-Based Penalized Likelihood Method in High Dimensional Data

Classification of cancer and selection of genes is one of the most important application of DNA microarray data. As a result of the higher dimensionality of microarray data, classification and selection of gene techniques are frequently employed to support the professional systems in the diagnosing ability of cancer with higher precision in classification. Least absolute shrinkage and selection operator (LASSO) is one of the most popular method for cancer classification and gene selection in high dimensional data. However, Lasso has limitations of being biased and cannot select variables more than the sample size (n) in gene selection and classification of high dimensional microarray data. To address this problems, LASSO-C1F was proposed using scale invariant measure of maximal information complexity of covariance matrix denoted with weight modifications as data-adaptive alternative to the fairly arbitrary choice of the regularization term in the least absolute shrinkage and selection operator (LASSO). The results indicated the effectiveness of the proposed method LASSO-C1F over the classical LASSO. The evaluation criteria result shows that the proposed method, LASSO-C1F has a better performance in terms of AUC and number of genes selected.

Effects of Random Forest Parameters in the Selection of Biomarkers

Abstract A microarray dataset contains thousands of DNA spots covering almost every gene in the genome. Microarray-based gene expression helps with the diagnosis, prognosis and treatment of cancer. The nature of diseases frequently changes, which in turn generates a considerable volume of data. The main drawback of microarray data is the curse of dimensionality. It hinders useful information and leads to computational instability. The main objective of feature selection is to extract and remove insignificant and irrelevant features to determine the informative genes that cause cancer. Random forest is a well-suited classification algorithm for microarray data. To enhance the importance of the variables, we proposed out-of-bag (OOB) cases in every tree of the forest to count the number of votes for the exact class. The incorporation of random permutation in the variables of these OOB cases enables us to select the crucial features from high-dimensional microarray data. In this study, we analyze the effects of various random forest parameters on the selection procedure. ‘Variable drop fraction’ regulates the forest construction. The higher variable drop fraction value efficiently decreases the dimensionality of the microarray data. Forest built with 800 trees chooses fewer important features under any variable drop fraction value that reduces microarray data dimensionality.

An Efficient Filter-Based Feature Selection Model to Identify Significant Features from High-Dimensional Microarray Data

Subset feature selection for microarray data is intended to reduce the number of irrelevant features in order to extract significant features from the dataset. Simultaneously, choosing the appropriate features from the high-dimensional dataset may enhance the learning algorithm’s classification precision. Relief algorithms and their variants are successful attribute estimators. MultiSURF is the latest descendant of relief-based approaches; it estimates the feature by preserving target instance-centric neighborhood determination. However, the large number of redundant features can lead to the degraded performance of MultiSURF’s ability to select relevant features from the datasets. In order to select an informative feature from extremely redundant data, we suggest an innovative feature weighting algorithm called boundary margin relief (BMR). BMR’s main concept is to predict the feature weights through the measurement of the local hyperplane, which is typically used in I-Relief techniques. The weights of the features in the proposed methods are very robust in terms of removing redundant features. To show the efficiency of the method, comprehensive studies involving classification tests were conducted on benchmark microarray datasets by combining the suggested technique with conventional classifiers, including support vector machine, k-nearest neighbor, and Naive Bayes. Extensive studies have shown that the proposed method has three notable features: (1) elevated classification accuracy, (2) outstanding redundant robustness, and (3) good stability about different classification algorithms.

Gene Selection Using Hybrid Multi-Objective Cuckoo Search Algorithm With Evolutionary Operators for Cancer Microarray Data

Microarray data play a huge role in recognizing a proper cancer diagnosis and classification. In most microarray data set consist of thousands of genes, but the majority number of genes are irrelevant to the diseases. An efficient algorithm for gene selection becomes important to deal with large microarray data. The main challenge is to analyze and select the relevant genes with maximum classification accuracy. Various algorithms were proposed for gene classification in previous studies, however, limited success was succeeded due to the selection of many genes in the high-dimensional microarray data. This study proposed and developed a hybrid multi-objective cuckoo search with evolutionary operators for gene selection. Evolutionary operators that are used in this article were double mutation and single crossover operators. The motivation behind this research is to improve the dimensions’ values and explorative search abilities. Multi-objective cuckoo search with evolutionary operators employed the selection of informative genes among the high-dimensional cancer microarray data. Experiments were conducted on seven publicly available and high-dimensional cancer microarray data sets. These microarray data sets consist of approximately 2000 to 15000 genes. The results from the experiments concluded that the developed algorithm, multi-objective cuckoo search with evolutionary operators outperforms cuckoo search and multi-objective cuckoo search algorithms with a smaller number of selected significant genes.

Ensemble Neighborhood Search (ENS) for biclustering of gene expression microarray data and single cell RNA sequencing data

Background Ensemble biclustering comprises a class of biclustering algorithms that generates a consensus, better-quality partition/s as output. This concept has emerged from the fusion of existing biclustering methods hybridized upon selected aspects. The design of the methodology enriches the existing methods furnishing with new properties. Usually biclustering of gene expression microarray data indulges in simultaneous clustering of the expression profiles under specific conditions and determines local two-way clustering models. In general, biclustering solutions rely upon different parameters like biclusters numbers, random initialization etc. However ensemble techniques are proposed to either reduce or eliminate the impact of such parameters on the output bicluster. Methods In this paper, the authors propose a novel ensemble biclustering approach “Ensemble Neighborhood search (ENS)” based on the concept of neighborhood search. Simulation results verify that the proposed approach appears to be more flexible and adaptive in comparison to the existing competitive methods on high-dimensional gene expression microarray data as well as on scRNA-seq datasets. Conclusion The performance of the proposed framework demonstrates its effectiveness with the other state-of-the-art schemes. The proposed framework is tested on five different microarray datasets and one single cell RNA sequence(scRNA-seq) dataset. Experimental results reveal that the proposed architecture achieves the prevention of unusual data loss and delivers the output refined as the per user standards. Also this framework preforms effectively on high sparsity scRNA-seq data where most of the algorithms fail to do so as these datasets contain massive zeros within. BicAT analysis of the ENS output validates ENS method as computationally effective and can be used to improve the quality of the biclusters. Finally, the results are statistically significant as shown in the ANOVA table. Hence this ENS method can be considered as a reliable framework and can be preferable over the traditional biclustering approaches to analyze the gene expression microarray data and high sparsity scRNA-seq data. The source code of the ENS algorithm can be accessed at https://github.com/c114002/Research/blob/master/ENS_Code.zip .

Gene selection for microarray data classification via adaptive hypergraph embedded dictionary learning

Due to the rapid development of DNA microarray technology, a large number of microarray data come into being and classifying these data has been verified useful for cancer diagnosis, treatment and prevention. However, microarray data classification is still a challenging task since there are often a huge number of genes but a small number of samples in gene expression data. As a result, a computational method for reducing the dimension of microarray data is necessary. In this paper, we introduce a computational gene selection model for microarray data classification via adaptive hypergraph embedded dictionary learning (AHEDL). Specifically, a dictionary is learned from the feature space of original high dimensional microarray data, and this learned dictionary is used to represent original genes with a reconstruction coefficient matrix. Then we use a l2, 1-norm regularization to impose the row sparsity on the coefficient matrix for selecting discriminate genes. Meanwhile, in order to capture the localmanifold geometrical structure of original microarray data in a high-order manner, a hypergraph is adaptively learned and embedded into the model. An iterative updating algorithm is designed for solving the optimization problem. In order to validate the efficacy of the proposed model, we have conducted experiments on six publicly available microarray data sets and the results demonstrate that AHEDL outperforms other state-of-the-art methods in terms of microarray data classification. AbbreviationsUnlabelled TableAHEDLAdaptive Hypergraph Embedded Dictionary LearningADMMAlternating Direction method of MultipliersSVMSupport Vector MachineRFRandom Forestk-NNk-Nearest NeighborCVcross validationMSVM-RFMulticlass Support Vector Machine-Recursive Feature EliminationKernelPLSKernel Partial Least SquaresWLMGSWeight Local Modularity based Gene SelectionGRSL-GSGene Selection via Subspace Learning and Manifold RegularizationLNNFWLocal-Nearest-Neighbors-based Feature Weighting for Gene SelectionRLRRegularized Logistic RegressionACCaccuracySDstandard deviationsANOVAAnalysis of VarianceDFDegrees of FreedomSSSum-of-SquareMSMean Sum-of-SquareFF-valueSigstatistical significanceSRBCTSmall Round Blue Cell TumorsGCMGlobal Cancer MapCLL_SUB_111B-cell chronic lymphocytic leukemia

A Hybrid Gene Selection Method for Microarray Data Based on Geodesic Distance and Binary Particle Swarm Optimization

To obtain the most predictive genes subsets without filtering out critical genes, a method for gene selection based on binary particle swarm optimization (BPSO) and geodesic distance is proposed in this paper. In this approach, to preserve the intrinsic geometry of high dimensional microarray data, geodesic distance is calculated as the measurement between genes for cluster, and by combining with clustering method, BPSO is used to perform gene selection to reduce redundancy. With experiments conducted on several public microarray data by ELM classifiers, the results confirm that it is efficient to use the proposed method for gene selection compared to the relevant gene selection method.

Novel machine learning approach for classification of high-dimensional microarray data

Independent component analysis (ICA) is a powerful concept for reducing the dimension of big data in many applications. It has been used for the feature extraction of microarray gene expression data in numerous works. One of the merits of ICA is that a number of extracted features are always equal to the number of samples. When ICA is applied to microarray data, whenever, it faces the challenges of how to find the best subset of genes (features) from extracted features. To resolve this problem, in this paper, we propose a new (artificial bee colony) ABC-based feature selection approach for microarray data. Our approach is based on two stages: ICA-based extraction approach to reduce the size of data and ABC-based wrapper approach to optimize the reduced feature vectors. To validate our proposed approach, extensive experiments were conducted to compare the performance of ICA + ABC with the results obtained from recently published and other previously suggested methods of gene selection for Naive Bayes (NB) classifier. To compare the performance of the proposed approach with other algorithms, a statistical hypothesis test was employed with six benchmark cancer classification datasets of the microarray. The experimental result shows that the proposed approach demonstrates an improvement over all the algorithms for NB classifier with a certain level of significance.