scholarly journals A Hybrid Approach for Biomarker Discovery from Microarray Gene Expression Data for Cancer Classification

2006 ◽  
Vol 2 ◽  
pp. 117693510600200 ◽  
Author(s):  
Yanxiong Peng ◽  
Wenyuan Li ◽  
Ying Liu
Keyword(s):  
Gene Expression ◽  
Biomarker Discovery ◽  
Expression Patterns ◽  
Hybrid Approach ◽  
Microarray Gene Expression Data ◽  
Small Subset ◽  
Microarray Gene Expression ◽  
Simple Method ◽  
Filter Methods ◽  
Wide Range

Microarrays allow researchers to monitor the gene expression patterns for tens of thousands of genes across a wide range of cellular responses, phenotype and conditions. Selecting a small subset of discriminate genes from thousands of genes is important for accurate classification of diseases and phenotypes. Many methods have been proposed to find subsets of genes with maximum relevance and minimum redundancy, which can distinguish accurately between samples with different labels. To find the minimum subset of relevant genes is often referred as biomarker discovery. Two main approaches, filter and wrapper techniques, have been applied to biomarker discovery. In this paper, we conducted a comparative study of different biomarker discovery methods, including six filter methods and three wrapper methods. We then proposed a hybrid approach, FR-Wrapper, for biomarker discovery. The aim of this approach is to find an optimum balance between the precision of the biomarker discovery and the computation cost, by taking advantages of both filter method's efficiency and wrapper method's high accuracy. Our hybrid approach applies Fisher's ratio, a simple method easy to understand and implement, to filter out most of the irrelevant genes, then a wrapper method is employed to reduce the redundancy. The performance of FR-Wrapper approach is evaluated over four widely used microarray datasets. Analysis of experimental results reveals that the hybrid approach can achieve the goal of maximum relevance with minimum redundancy.

SYSTEMATIC VARIATION NORMALIZATION IN MICROARRAY DATA TO GET GENE EXPRESSION COMPARISON UNBIASED

2005 ◽  
Vol 03 (02) ◽  
pp. 225-241 ◽  
Author(s):  
JEFF W. CHOU ◽  
RICHARD S. PAULES ◽  
PIERRE R. BUSHEL
Keyword(s):  
Gene Expression ◽  
Linear Regression ◽  
Microarray Data ◽  
Expression Patterns ◽  
Microarray Gene Expression Data ◽  
Systematic Variation ◽  
Data Sets ◽  
Microarray Gene Expression ◽  
Pixel Intensity ◽  
Non Linear

Normalization removes or minimizes the biases of systematic variation that exists in experimental data sets. This study presents a systematic variation normalization (SVN) procedure for removing systematic variation in two channel microarray gene expression data. Based on an analysis of how systematic variation contributes to variability in microarray data sets, our normalization procedure includes background subtraction determined from the distribution of pixel intensity values from each data acquisition channel and log conversion, linear or non-linear regression, restoration or transformation, and multiarray normalization. In the case when a non-linear regression is required, an empirical polynomial approximation approach is used. Either the high terminated points or their averaged values in the distributions of the pixel intensity values observed in control channels may be used for rescaling multiarray datasets. These pre-processing steps remove systematic variation in the data attributable to variability in microarray slides, assay-batches, the array process, or experimenters. Biologically meaningful comparisons of gene expression patterns between control and test channels or among multiple arrays are therefore unbiased using normalized but not unnormalized datasets.

scholarly journals A performance analysis of clustering based algorithms for the microarray gene expression data

2018 ◽  
Vol 7 (2.21) ◽  
pp. 201 ◽  
Author(s):  
K Yuvaraj ◽  
D Manjula
Keyword(s):  
Gene Expression ◽  
Gene Expression Data ◽  
Dna Sequences ◽  
Clustering Algorithms ◽  
Expression Patterns ◽  
Microarray Gene Expression Data ◽  
Gene Clustering ◽  
Expression Data ◽  
Microarray Gene Expression ◽  
Microarray Gene

Current advancements in microarray technology permit simultaneous observing of the expression levels of huge number of genes over various time points. Microarrays have obtained amazing implication in the field of bioinformatics. It includes an ordered set of huge different Deoxyribonucleic Acid (DNA) sequences that can be used to measure both DNA as well as Ribonucleic Acid (RNA) dissimilarities. The Gene Expression (GE) summary aids in understanding the basic cause of gene activities, the growth of genes, determining recent disorders like cancer and as well analysing their molecular pharmacology. Clustering is a significant tool applied for analyzing such microarray gene expression data.  It has developed into a greatest part of gene expression analysis. Grouping the genes having identical expression patterns is known as gene clustering. A number of clustering algorithms have been applied for the analysis of microarray gene expression data. The aim of this paper is to analyze the precision level of the microarray data by using various clustering algorithms. 

MINIMUM REDUNDANCY FEATURE SELECTION FROM MICROARRAY GENE EXPRESSION DATA

2005 ◽  
Vol 03 (02) ◽  
pp. 185-205 ◽  
Author(s):  
CHRIS DING ◽  
HANCHUAN PENG
Keyword(s):  
Gene Expression ◽  
Feature Selection ◽  
Gene Expression Data ◽  
Microarray Gene Expression Data ◽  
Support Vector ◽  
Small Subset ◽  
Expression Data ◽  
Microarray Gene Expression ◽  
Linear Discriminant ◽  
Selection Framework

How to selecting a small subset out of the thousands of genes in microarray data is important for accurate classification of phenotypes. Widely used methods typically rank genes according to their differential expressions among phenotypes and pick the top-ranked genes. We observe that feature sets so obtained have certain redundancy and study methods to minimize it. We propose a minimum redundancy — maximum relevance (MRMR) feature selection framework. Genes selected via MRMR provide a more balanced coverage of the space and capture broader characteristics of phenotypes. They lead to significantly improved class predictions in extensive experiments on 6 gene expression data sets: NCI, Lymphoma, Lung, Child Leukemia, Leukemia, and Colon. Improvements are observed consistently among 4 classification methods: Naïve Bayes, Linear discriminant analysis, Logistic regression, and Support vector machines. Supplimentary: The top 60 MRMR genes for each of the datasets are listed in . More information related to MRMR methods can be found at .

Sign in / Sign up

Export Citation Format

Share Document