Performance Analysis of Dimensionality Reduction Techniques in Cancer Detection using Microarray Data

Expression profiling: Opportunities and pitfalls and impact on the study and management of allergic diseases

Cancer is a world-famous deadly disease. According to the World Health Organization (WHO), cancer is the second leading cause of death globally and is responsible for an estimated 9.6 million deaths in 2018. One well-known technique for cancer detection is the DNA microarray technique. DNA microarray technology provides an opportunity for researchers to analyze thousands of gene expression profiles at the same time to determine whether a person has cancer or not. However, one of the problems in DNA microarray data is the large number of features that require feature selection. In overcoming these problems, this study will use the feature selection Support Vector Machine-Recursive Feature Elimination (SVM-RFE) and Chi-Square and use the Naive Bayes classification method. The accuracy results from using feature selection with those that are not will be compared. The accuracy between using the two feature selection methods will also be compared to find which feature selection method is better when combined with the Naive Bayes classification method. To get an overall picture of the performance comparison, this study also considers precision, recall, and F1-score. The best accuracy results obtained were 100% lung cancer data with SVM-RFE and Chi-Square, 99.6% ovarian cancer with SVM-RFE, 93.7% breast cancer with SVM-RFE, and 90% colon cancer with SVM- RFE.

DNA Microarray Technique Current Analytical Methods of DNA Microarray Data Advantages and Disadvantages Current Application of DNA Microarray Technique in Medicine A Novel Method for DNA Microarray Data Analysis Future Directions.

The gene expression classification and identification from DNA microarray data is efficient technique for cancer diagnosis and prognosis for specific cancer subtypes. DNA microarray technology has great potential to discover information from expression levels of thousands of gene. The collection of significant genes which can improve the accuracy can give proper direction in early diagnosis of cancer. Cancer may be of different subtypes. Cancer detection from microarray gene expression data has major challenge of low sample size, high dimensionality and complexity of the data. There is a need for fast and computationally efficient method to deal with these kind of challenges. Deep Learning has succeeded in numerous fields such as image, video, speech, and text processing. Gene expression analysis is a unique challenge to Deep Learning for various cancer detection and prediction tasks in order to set specific biomarkers for different cancer subtypes. In this paper, we briefly discuss the strengths of different Deep Learning architectures for a cancer detection and prediction of various types of cancer through gene expression analysis.

Zeroing in on the “holy grail”

Lessons from DNA microarray analysis: the gene expression profile of biofilms

‘‘Genomics in Endocrinology’’ edited by Stuart Handwerger, M.D. and Bruce J. Aronow, Ph.D. presents a series of short articles by hormonal researchers who utilized DNA microarray techniques to analyze the expression of diverse genes in different hormone-producing and hormoneresponsive tissues. In addition, gene expression was monitored in diseased tissues using the DNA microarray approach. This monograph represents a state-of-the-art summary of the present use of DNA microarray analyses in hormonal research for readers interested in this topic. The interesting chapters by 40 some authors represent key DNA microarray findings in the field and provide a useful resource for readers to get an overview of this area of research. In addition, the introductory chapter by the editors provides a useful lead-in to the general approach, including data analyses, statistical consideration, data storage and validation, as well as potential pitfalls. The major advantage of the DNA microarray approach is certainly the high-throughput, genome-wide analyses and the identification of candidate genes important for physiological processes of interest. Although many of the chapters deal with a general survey of the expression of multiple genes, few chapters used DNA microarray data to provide molecular classification of different disease states. Of particular interest, several chapters described more advanced use of DNA microarray data, including analyses of promoter regions of co-expressed genes, identification of candidate genes related to a particular disease, advanced chromatin immuno-precipitation microarray for genes regulated by transcriptional factors, and attempts to reveal gene pathways based on expression data. The overall field is progressing from the straightforward description of gene expression patterns to the formulation of new hypotheses based on gene expression to allow a better understanding of role of genes in physiology and pathophysiology. A more appropriate title for the present monograph is probably ‘‘Transcriptomics of hormone-producing and hormone-responsive tissues’’ due to the emphasis on DNA microarray analyses and a lack of information on genomic topics such as single nucleotide polymorphism, gene copy numbers, genome-wide analyses of the phylogenetic relationship of hormone and receptor genes, identification of new hormone and receptor genes, and other genomic issues.

Zeranol (Z) is a nonsteroidal mycotoxin with potent estrogenic activity. Z is one of six growth promoters approved by the FDA for use in the U.S. beef industry to accelerate weight gain, improve feed efficiency and increase the lean meat-to-fat ratio. Recently, the safety meat products from Z-implanted beef has been questioned on the basis that increased exposure of bioactive Z residues may have adverse health implications. Our previous study showed that serum, meat and meat extracts derived from beef cattle implanted with Z significantly stimulated the proliferation of primary cultured human normal and cancerous breast epithelial cells, primary cultured human breast pre-adipocytes, and human breast cancer cell lines. However, little is known about the mechanisms of Z stimulation on the growth of different types of breast cells. To systematically investigate gene expression patterns in primary cultured human breast cancer epithelial cells (PCHBCECs) after Z treatment, we performed DNA microarray analysis. After PCHBCECs were isolated from breast cancer tissue, they were treated with 30 nM Z or 0.1% DMSO, as a vehicle control, for 48 hr, and then mRNA was isolated and purified for gene expression analysis using the Human Genome U133 Plus 2.0 Array TM (Affymetrix Co. Ltd) in the Microarray Shared Resources at The Ohio State University Comprehensive Cancer Center. DNA microarray data were generated on the basis of the criteria of signal intensity and signal ratio. Our results showed that 10 genes were down-regulated and 25 genes were up-regulated in PCHBCECs treated with 30 nM Z as compared to the controls. Among the genes regulated by Z were, limb-bud and heart (LBH) and annexin-1 (ANXA1) which were decreased 2.27 and 2 fold, respectively and human HMG-CoA synthase 1 (HMGCS1) and methyltransferase like 7A (METTL7A) which were up-regulated to 3.8 and 3.25 fold, respectively compared with the controls. Our preliminary data also showed that Z decreased the expression of several tumor suppressor genes, such as protein tyrosine phosphatase γ (PTPγ), p16, p21, and increased DNMT1 expression in PCHBCECs which suggests epigenetic modification of Z in their promoter regions. Our results indicate that long term consumption of beef products with low level of Z or its metabolites might have adverse health effects on human breast. Further validation of our DNA microarray results is in progress in our laboratory (Supported by NIH R01Grant ES 015212). Citation Format: {Authors}. {Abstract title} [abstract]. In: Proceedings of the 102nd Annual Meeting of the American Association for Cancer Research; 2011 Apr 2-6; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2011;71(8 Suppl):Abstract nr 33. doi:10.1158/1538-7445.AM2011-33

Class prediction and feature selection is key in the context of diagnostic applications of DNA microarrays. Microarray data is noisy and typically composed of a low number of samples and a large number of genes. Perceptrons can constitute an efficient tool for accurate classification of microarray data. Nevertheless, the large input layers necessary for the direct application of perceptrons and the low samples available for the training process hamper its use. Two strategies can be taken for an optimal use of a perceptron with a favourable balance between samples for training and the size of the input layer: (a) reducing the dimensionality of the data set from thousands to no more than one hundred, highly informative average values, and using the weights of the perceptron for feature selection or (b) using a selection of only few genes that produce an optimal classification with the perceptron. In this case, feature selection is carried out first. Obviously, a combined approach is also possible. In this manuscript we explore and compare both alternatives. We study the informative contents of the data at different levels of compression with a very efficient clustering algorithm (Self Organizing Tree Algorithm). We show how a simple genetic algorithm selects a subset of gene expression values with 100% accuracy in the classification of samples with maximum efficiency. Finally, the importance of dimensionality reduction is discussed in light of its capacity for reducing noise and redundancies in microarray data.

Identification of a possible role of thymine DNA glycosylase (TDG) in epigenome maintenance

Over the past few decades, DNA microarray technology has emerged as a prevailing process for early identification of cancer subtypes. Several feature selection (FS) techniques have been widely applied for identifying cancer from microarray gene data but only very few studies have been conducted on distributing the feature selection process for detecting cancer subtypes. Not all the gene expressions are needed in prediction, this research article objective is to select discriminative biomarkers by using distributed FS method which helps in accurately diagnosis of cancer subtype. Traditional feature selection techniques have several drawbacks like unrelated features that could perform well in terms of classification accuracy with a suitable subset of genes will be left out of the selection. To overcome the issue, in this paper a new filter-based method for gene selection is introduced which can select the highly relevant genes for distinguishing tissues from the gene expression dataset. In addition, it is used to compute the relation between gene-gene and gene-class and simultaneously identify subset of essential genes. Our method is tested on Diffuse Large B cell Lymphoma (DLBCL) dataset by using well-known classification techniques such as support vector machine, naïve Bayes, k-nearest neighbor, and decision tree. Results on biological DLBCL dataset demonstrate that the proposed method provides promising tools for the prediction of cancer type, with the prediction accuracy of 97.62%, precision of 94.23%, sensitivity of 94.12%, F-measure of 90.12%, and ROC value of 99.75%. The experimental results reveal the fact that the proposed method is significantly improved classification accuracy and execution time, compared to existing standard algorithms when applied to the non-partitioned dataset. Furthermore, the extracted genes are biologically sound and agree with the outcome of relevant biomedical studies.

DNA microarray technology is a fundamental tool in gene expression data analysis. The collection of datasets from the technology has underscored the need for quantitative analytical tools to examine such data. Due to the large number of genes and complex gene regulation networks, clustering is a useful exploratory technique for analyzing these data. Many clustering algorithms have been proposed to analyze microarray gene expression data, but very few of them evaluate the quality of the clusters. In this paper, a novel cluster analysis technique has been proposed without considering number of clusters a priori. The method computes a similarity measurement function based on which the clusters are merged and subsequently splits a cluster by computing the degree of separation of the cluster. The process of splitting and merging performs iteratively until the cluster validity index (i.e. DB index) degrades. The experimental result shows that the proposed cluster analysis technique gives comparable results on gene cancer dataset with existing methods. This study may help raise relevant issues in the extraction of meaningful biological information from microarray expression data. Keywords- DNA microarray data, Clustering technique, Cluster validity index, Similarity measurement, Splitting and Merging, Cancer data analysis

We investigate discrete structures and combinatoric modeling of weighted prefix trees for managing and analyzing DNA microarray data. We describe the algorithms to construct the weighted trees for these data. Using these weighted trees with our algorithms, we propose methods to compute the appearance probability of a DNA microarray, to compare the informational distances in the expression of genes between the DNA microarrays, to search the characteristic microarrays and the group of candidate genes suggestive of a pathology.

Microarray is a powerful tool used widely to characterize tumors and has greatly improved the ability to subclassify tumors according to shared molecular characteristics and clinical behavior. It is a method to measure the expression of a large number of genes in any specimen simultaneously. Researchers at Stanford University were the first to describe and use DNA microarray to study gene expression in various diseases including cancer. Breast cancer is the second most common cancer among Indian women. Multiple factors like age, diet, obesity, parity, age at first childbirth, oral contraceptives, exogenous estrogens, genetics, environment, geographic location influence the development of this heterogeneous disease. Gene expression in these cancers by microarray is fast gaining in popularity in providing better prognostic and predictive information on the disease. This review is an attempt to look at the recent advances in breast cancer research with DNA microarray technology.

The aim of the study was to develop a multiplex PCR-based DNA microarray technology for simultaneous detection and species identification of seven human herpes viruses, namely herpes simplex virus type 1, type 2 (HSV-1, HSV-2), varicella-zoster virus (VZV), Epstein-Barr virus (EBV), cytomegalovirus (CMV), and human herpes virus 6 (HHV-6A, HHV-6B), and to apply this technology to accurate diagnosis of herpesvirus-associated diseases. Primers and oligonucleotide probes were designed and synthesized based on the highly conserved regions of the DNA polymerase gene in human herpes viruses. DNA microarrays were made by printing the oligonucleotide probes onto special glass slides. After amplification and labeling with CY5, the PCR products were hybridized with the DNA microarrays and species identified. Sixty-one cerebrospinal fluid (CSF) and 132 blood specimens were analyzed by this technique, and the results were compared with those of TaqMan PCR. Several specimens were sequenced further after cloning. The PCR products of the seven human herpes viruses ranged from 224 to 252 bp, and could be species identified with DNA microarrays. The detection limits were 10(1) copies/microl for each virus. And the test showed no cross-reaction to DNA extracted from S. aureus, E. coli, hepatitis B virus, Cryptococcus neoformans, Candida albicans and human genome. Among 132 blood and 61 CSF specimens, 55 were tested positive for human herpes virus DNA. Compared with the results of TaqMan PCR, the sensitivity and specificity of the DNA microarray technology was 96.2% and 99.3%, respectively. This multiplex PCR-based DNA microarray technology, which is rapid, specific and sensitive, serves as an effective technique for simultaneous detection and species identification of seven human herpes viruses.