DNA Microarray Gene Expression Data Research Articles

Penalized logistic regression with prior information for microarray gene expression classification.

Cancer classification and gene selection are important applications in DNA microarray gene expression data analysis. Since DNA microarray data suffers from the high-dimensionality problem, automatic gene selection methods are used to enhance the classification performance of expert classifier systems. In this paper, a new penalized logistic regression method that performs simultaneous gene coefficient estimation and variable selection in DNA microarray data is discussed. The method employs prior information about the gene coefficients to improve the classification accuracy of the underlying model. The coordinate descent algorithm with screening rules is given to obtain the gene coefficient estimates of the proposed method efficiently. The performance of the method is examined on five high-dimensional cancer classification datasets using the area under the curve, the number of selected genes, misclassification rate and F-score measures. The real data analysis results indicate that the proposed method achieves a good cancer classification performance with a small misclassification rate, large area under the curve and F-score by trading off some sparsity level of the underlying model. Hence, the proposed method can be seen as a reliable penalized logistic regression method in the scope of high-dimensional cancer classification.

Optimizing ANFIS using simulated annealing algorithm for classification of microarray gene expression cancer data.

In the medical field, successful classification of microarray gene expression data is of major importance for cancer diagnosis. However, due to the profusion of genes number, the performance of classifying DNA microarray gene expression data using statistical algorithms is often limited. Recently, there has been an important increase in the studies on the utilization of artificial intelligence methods, for the purpose of classifying large-scale data. In this context, a hybrid approach based on the adaptive neuro-fuzzy inference system (ANFIS), the fuzzy c-means clustering (FCM), and the simulated annealing (SA) algorithm is proposed in this study. The proposed method is applied to classify five different cancer datasets (i.e., lung cancer, central nervous system cancer, brain cancer, endometrial cancer, and prostate cancer). The backpropagation algorithm, hybrid algorithm, genetic algorithm, and the other statistical methods such as Bayesian network, support vector machine, and J48 decision tree are used to compare the proposed approach's performance to other algorithms. The results show that the performance of training FCM-based ANFIS using SA algorithm for classifying all the cancer datasets becomes more successful with the average accuracy rate of 96.28% and the results of the other methods are also satisfactory. The proposed method gives more effective results than the others for classifying DNA microarray cancer gene expression data. Basic structure of proposed method.

Cancer Diagnosis and Disease Gene Identification via Statistical Machine Learning

Diagnosing cancer and identifying the disease gene by using DNA microarray gene expression data are the hot topics in current bioinformatics. This paper is devoted to the latest development in cancer diagnosis and gene selection via statistical machine learning. A support vector machine is firstly introduced for the binary cancer diagnosis. Then, 1-norm support vector machine, doubly regularized support vector machine, adaptive huberized support vector machine and other extensions are presented to improve the performance of gene selection. Lasso, elastic net, partly adaptive elastic net, group lasso, sparse group lasso, adaptive sparse group lasso and other sparse regression methods are also introduced for performing simultaneous binary cancer classification and gene selection. In addition to introducing three strategies for reducing multiclass to binary, methods of directly considering all classes of data in a learning model (multi_class support vector, sparse multinomial regression, adaptive multinomial regression and so on) are presented for performing multiple cancer diagnosis. Limitations and promising directions are also discussed.

A Genome based Detection and Classification of Coronavirus Infection

The Coronavirus (COVID-19) infection has become a global threat in recent time. Many researchers have been dedicated to control COVID-19 pandemic. In this paper, an effective method is presented for detection and classification of COVID-19 infection based on genome sequences. First, the COVID-19 infection is detected based on the induction of changes in the DNA microarray gene expression pattern of the host during and after infection and comparing it with DNA sequences of Coronavirus (SARS-CoV-2). In order to analyse DNA microarray gene expression data, a bi-directional string matching algorithm is used and the analytical result is represented in terms of eight-directional chain code sequence. At the end of the work, an approach for categorization of Coronavirus infection is provided based on the distribution probabilities of eight-directional chain code sequences correspond to DNA microarray gene expression data of different Corona viruses by taking random samples from the GenBank. The categorization of Coronavirus infection will be helpful for forecasting rate of mortality, rate of infection, severity of the infection and other issues related to COVID-19.

DNA Microarray Gene Expression Data Classification Using SVM, MLP, and RF with Feature Selection Methods Relief and LASSO

DNA microarray technology is a novel method to monitor expression levels of large number of genes simultaneously. These gene expressions can be and is being used to detect various forms of diseases. Using multiple microarray datasets, this paper cross compares two different methods for classification and feature selection. Since individual gene count in microarray datas are too many, most informative genes should be selected and used. For this selection, we have tried Relief and LASSO feature selection methods. After selecting informative genes from microarray data, classification is performed with Support Vector Machines (SVM) and Multilayer Perceptron Networks (MLP) which both are widely used in multiple classification tasks. The overall accuracy with LASSO and SVM outperforms most of the approaches proposed.

Missing value imputation in DNA microarray gene expression data: a comparative study of an improved collaborative filtering method with decision tree based approach

DNA microarray is used to study the expression levels of thousands of genes under various conditions simultaneously. Unfortunately, microarray experiments can generate datasets with multiple missing values. In this work, the approach proposed first (CFBRSTFDV), uses fuzzy difference vector (FDV) along with rough set based collaborative filtering that helps to estimate the missing values. Later on, we have also proposed a decision tree based approach combined with genetic algorithm GADTreeImpute to impute the same missing values. We have applied our proposed algorithms on three benchmark datasets, i.e., yeast gene expression data, human tumour cell and prostate cancer dataset. We have first measured the performance of both these proposed approaches by using RMSE metric. Later on the estimation is also validated by using classification process and the performance is measured by the metrics like % of classification accuracy, precision, recall, etc.

Missing value imputation in DNA microarray gene expression data: a comparative study of an improved collaborative filtering method with decision tree based approach

Missing value imputation in DNA microarray gene expression data: a comparative study of an improved collaborative filtering method with decision tree based approach

Stellar-Mass Black Hole Optimization for Biclustering Microarray Gene Expression Data

DNA microarray gene expression data analysis has provided new insights into gene function, disease pathophysiology, disease classification, and drug development. Biclustering in gene expression data is a subset of the genes demonstrating consistent patterns over a subset of the conditions. The proposed work finds the significant biclusters in large expression data using a novel optimization technique called stellar-mass black hole optimization (SBO). This optimization algorithm is inspired from the property of the relentless pull of a black hole’s gravity that is present in the Universe. The proposed work is tested on benchmark optimization test functions and gene expression benchmark datasets, and the results are compared with swarm intelligence techniques such as particle swarm optimization (PSO), and cuckoo search (CK). The experimental results show that the SBO outperforms PSO and CK.

Gene Expression Mining for Predicting Survivability of Patients in Earlystages of Lung Cancer

After numerous breakthroughs in medicine, microbiology, and pathology in the past century, lung cancer still remains as a leading cause of cancer-related death even in the developed countries. Lung cancer accounts roughly for 30% of all cancer-related deaths in the world. Diagnosis and treatments are still based on traditional histopathology. It is of paramount importance to predict the survivability of patients in early stages of lung cancer so that specific treatments can be sought. Nonetheless, histopathology has been shown by previous studies to be inadequate in predicting lung cancer development and clinical outcome. The microarray technology allows researchers to examine the expression of thousands of genes simultaneously. This paper describes a state-of-the-art machine learning based approach called averaged one-dependence estimators with subsumption resolution to tackle the problem of predicting whether a patient in early stages of lung cancer will survive by mining DNA microarray gene expression data. To lower the computational complexity, we employ an entropy-based gene selection approach to select relevant genes that are directly responsible for lung cancer survivability prognosis. The proposed system has achieved an average accuracy of 92.31% in predicting lung cancer survivability over 2 independent datasets. The experimental results provide confirmation that gene expression mining can be used to predict survivability of patients in early stages of lung cancer.

Cancer Recurrence Prediction Using Machine Learning

Cancer is one of the deadliest diseases in the world and is responsible for around 13% of all deaths world-wide. Cancer incidence rate is growing at an alarming rate in the world. Despite the fact that cancer is preventable and curable in early stages, the vast majority of patients are diagnosed with cancer very late. Furthermore, cancer commonly comes back after years of treatment. Therefore, it is of paramount importance to predict cancer recurrence so that specific treatments can be sought. Nonetheless, conventional methods of predicting cancer recurrence rely solely on histopathology and the results are not very reliable. The microarray gene expression technology is a promising technology that could predict cancer recurrence by analyzing the gene expression of sample cells. The microarray technology allows researchers to examine the expression of thousands of genes simultaneously. This paper describes a state-of-the-art machine learning based approach called averaged one-dependence estimators with subsumption resolution to tackle the problem of predicting, from DNA microarray gene expression data, whether a particular cancer will recur within a specific timeframe, which is usually 5 years. To lower the computational complexity, we employ an entropy-based gene selection approach to select relevant prognostic genes that are directly responsible for recurrence prediction. This proposed system has achieved an average accuracy of 98.9% in predicting cancer recurrence over 3 datasets. The experimental results demonstrate the efficacy of our framework.

Cancer Recognition From DNA Microarray Gene Expression Data Using Averaged One - Dependence Estimators

Cancer is a major leading cause of death and responsible for around 13% of all deaths world-wide. Cancer incidence rate is growing at an alarming rate in the world. Despite the fact that cancer is preventable and curable in early stages, the vast majority of patients are diagnosed with cancer very late. Therefore, it is of paramount importance to prevent and detect cancer early. Nonetheless, conventional methods of detecting and diagnosing cancer rely solely on skilled physicians, with the help of medical imaging, to detect certain symptoms that usually appear in the late stages of cancer. The microarray gene expression technology is a promising technology that can detect cancerous cells in early stages of cancer by analyzing gene expression of tissue samples. The microarray technology allows researchers to examine the expression of thousands of genes simultaneously. This paper describes a state-of-the-art machine learning based approach called averaged one-dependence estimators with subsumption resolution to tackle the problem of recognizing cancer from DNA microarray gene expression data. To lower the computational complexity and to increase the generalization capability of the system, we employ an entropy-based gene selection approach to select relevant gene that are directly responsible for cancer discrimination. This proposed system has achieved an average accuracy of 98.94% in recognizing and classifying cancer over 11 benchmark cancer datasets. The experimental results demonstrate the efficacy of our framework.

A feature selection method using fixed-point algorithm for DNA microarray gene expression data

As the performance of hardware is limited, the focus has been to develop objective, optimized and computationally efficient algorithms for a given task. To this extent, fixed-point and approximate algorithms have been developed and successfully applied in many areas of research. In this paper we propose a feature selection method based on fixed-point algorithm and show its application in the field of human cancer classification using DNA microarray gene expression data. In the fixed-point algorithm, we utilize between-class scatter matrix to compute the leading eigenvector. This eigenvector has been used to select genes. In the computation of the eigenvector, the eigenvalue decomposition of the scatter matrix is not required which significantly reduces its computational complexity and memory requirement.

Dynamic regulatory network reconstruction for Alzheimer's disease based on matrix decomposition techniques.

Alzheimer's disease (AD) is the most common form of dementia and leads to irreversible neurodegenerative damage of the brain. Finding the dynamic responses of genes, signaling proteins, transcription factor (TF) activities, and regulatory networks of the progressively deteriorative progress of AD would represent a significant advance in discovering the pathogenesis of AD. However, the high throughput technologies of measuring TF activities are not yet available on a genome-wide scale. In this study, based on DNA microarray gene expression data and a priori information of TFs, network component analysis (NCA) algorithm is applied to determining the TF activities and regulatory influences on TGs of incipient, moderate, and severe AD. Based on that, the dynamical gene regulatory networks of the deteriorative courses of AD were reconstructed. To select significant genes which are differentially expressed in different courses of AD, independent component analysis (ICA), which is better than the traditional clustering methods and can successfully group one gene in different meaningful biological processes, was used. The molecular biological analysis showed that the changes of TF activities and interactions of signaling proteins in mitosis, cell cycle, immune response, and inflammation play an important role in the deterioration of AD.

Incorporating feature ranking and evolutionary methods for the classification of high-dimensional DNA microarray gene expression data

DNA microarray gene expression classification poses a challenging task to the machine learning domain. Typically, the dimensionality of gene expression data sets could go from several thousands to over 10,000 genes. A potential solution to this issue is using feature selection to reduce the dimensionality. The aim of this paper is to investigate how we can use feature quality information to improve the precision of microarray gene expression classification tasks. We propose two evolutionary machine learning models based on the eXtended Classifier System (XCS) and a typical feature selection methodology. The first one, which we call FS-XCS, uses feature selection for feature reduction purposes. The second model is GRD-XCS, which uses feature ranking to bias the rule discovery process of XCS. The results indicate that the use of feature selection/ranking methods is essential for tackling highdimensional classification tasks, such as microarray gene expression classification. However, the results also suggest that using feature ranking to bias the rule discovery process performs significantly better than using the feature reduction method. In other words, using feature quality information to develop a smarter learning procedure is more efficient than reducing the feature set. Our findings have shown that extracting feature quality information can assist the learning process and improve classification accuracy. On the other hand, relying exclusively on the feature quality information might potentially decrease the classification performance (e.g., using feature reduction). Therefore, we recommend a hybrid approach that uses feature quality information to direct the learning process by highlighting the more informative features, but at the same time not restricting the learning process to explore other features.

Fine mapping of the Bmgr5 quantitative trait locus for allogeneic bone marrow engraftment in mice.

To identify novel mechanisms regulating allogeneic hematopoietic cell engraftment, we used forward genetics and previously described identification, in mice, of a bone marrow (BM) engraftment quantitative trait locus (QTL), termed Bmgr5. This QTL confers dominant and large allele effects for engraftment susceptibility. It was localized to chromosome 16 by quantitative genetic techniques in a segregating backcross bred from susceptible BALB.K and resistant B10.BR mice. We now report verification of the Bmgr5 QTL using reciprocal chromosome 16 consomic strains. The BM engraftment phenotype in these consomic mice shows that Bmgr5 susceptibility alleles are not only sufficient but also indispensable for conferring permissiveness for allogeneic BM engraftment. Using panels of congenic mice, we resolved the Bmgr5 QTL into two separate subloci, termed Bmgr5a (Chr16:14.6-15.8 Mb) and Bmgr5b (Chr16:15.8-17.6 Mb), each conferring permissiveness for the engraftment phenotype and both fine mapped to an interval amenable to positional cloning. Candidate Bmgr5 genes were then prioritized using whole exome DNA sequencing and microarray gene expression data. Further studies are warranted to elucidate the genetic interaction between the Bmgr5a and Bmgr5b QTL and identify causative genes and underlying gene variants. This may lead to new approaches for overcoming the problem of graft rejection in clinical hematopoietic cell transplantation.

Mixed PCA and Wavelet Transform based Effective Feature Extraction for Efficient Tumor Classification using DNA Microarray Gene Expression Data

Cancer classification is an emerging research area in the field of bioinformatics. Gene expression profiles using microarray data play important role in accurate tumor diagnosis. Hence correlation between gene expression profiles to disease through microarray data and its analysis has been an intensive task in molecular biology. As the microarray data have thousands of genes and very few samples, it is crucial to develop techniques to effectively exploit the huge quantity of data produced. Thus efficient feature extraction and computational method development is indispensible for the analysis. In this paper a mixed feature extraction method by combining principal component analysis (PCA) and discrete wavelet transform (DWT) has been proposed to detect informative genes effectively. The PCA is a dimensionality reduction algorithm which aims to map high dimensional data to a lower dimensional space. The reduced data represents the most important variables underlying the original data. Further a feature extraction method based on the DWT is proposed. The approximation coefficients obtained by the decomposition at a particular level is used as the features for further study. Radial basis function neural network (RBFNN) classifier is used to efficiently predict the sample class which has a low complexity than other classifier. The potential of the proposed approach is evaluated through an exhaustive study by many benchmark datasets. The experimental results show that the proposed method can be a useful approach for cancer classification with low computational complexity and high accuracy.

A GRASP metaheuristic for microarray data analysis

The Weighted Gene Regulatory Network (WGRN) problem consists in pruning a regulatory network obtained from DNA microarray gene expression data, in order to identify a reduced set of candidate elements which can explain the expression of all other genes. Since the problem appears to be particularly hard for general-purpose solvers, we develop a Greedy Randomized Adaptive Search Procedure (GRASP) and refine it with three alternative Path Relinking procedures. For comparison purposes, we also develop a Tabu Search algorithm with a self-adapting tabu tenure. The experimental results show that GRASP performs better than Tabu Search and that Path Relinking significantly contributes to its effectiveness.

A Filter Based Feature Selection Algorithm Using Null Space of Covariance Matrix for DNA Microarray Gene Expression Data

We propose a new filter based feature selection algorithm for classification based on DNA microarray gene expression data. It utilizes null space of covariance matrix for feature selection. The algorithm can perform bulk reduction of features (genes) while maintaining the quality information in the reduced subset of features for discriminative purpose. Thus, it can be used as a pre-processing step for other feature selection algorithms. The algorithm does not assume statistical independency among the features. The algorithm shows promising classification accuracy when compared with other existing techniques on several DNA microarray gene expression datasets.

Clustering approach to detect mRNA-degradation patterns from DNA–microarray gene-expression data

Clustering approach to detect mRNA-degradation patterns from DNA–microarray gene-expression data

Comprehensive evaluation of matrix factorization methods for the analysis of DNA microarray gene expression data

BackgroundClustering-based methods on gene-expression analysis have been shown to be useful in biomedical applications such as cancer subtype discovery. Among them, Matrix factorization (MF) is advantageous for clustering gene expression patterns from DNA microarray experiments, as it efficiently reduces the dimension of gene expression data. Although several MF methods have been proposed for clustering gene expression patterns, a systematic evaluation has not been reported yet.ResultsHere we evaluated the clustering performance of orthogonal and non-orthogonal MFs by a total of nine measurements for performance in four gene expression datasets and one well-known dataset for clustering. Specifically, we employed a non-orthogonal MF algorithm, BSNMF (Bi-directional Sparse Non-negative Matrix Factorization), that applies bi-directional sparseness constraints superimposed on non-negative constraints, comprising a few dominantly co-expressed genes and samples together. Non-orthogonal MFs tended to show better clustering-quality and prediction-accuracy indices than orthogonal MFs as well as a traditional method, K-means. Moreover, BSNMF showed improved performance in these measurements. Non-orthogonal MFs including BSNMF showed also good performance in the functional enrichment test using Gene Ontology terms and biological pathways.ConclusionsIn conclusion, the clustering performance of orthogonal and non-orthogonal MFs was appropriately evaluated for clustering microarray data by comprehensive measurements. This study showed that non-orthogonal MFs have better performance than orthogonal MFs and K-means for clustering microarray data.