Importance of data structure in comparing two dimension reduction methods for classification of microarray gene expression data

Truntzer, Caroline; Mercier, Catherine; Estève, Jacques; Gautier, Christian; Roy, Pascal

doi:10.1186/1471-2105-8-90

Cited by 11 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The lower-performance problem in between-class classification [ 7 ] is herein solved by taking advantage of the information embedded in the testing feature vector.…”

Section: Resultsmentioning

confidence: 99%

“…This can lead to a more complete understanding of molecular variations, in addition to morphologic variations among tumors. A large number of studies have used microarrays to analyze the gene expression for breast cancer, leukemia, colon tissue, and others, demonstrating the potential power of microarray in tumor classification [ 1 - 7 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Using the information embedded in the testing sample to break the limits caused by the small sample size in microarray-based classification

Zhu

Martı́nez

2008

BMC Bioinformatics

View full text Add to dashboard Cite

Background: Microarray-based tumor classification is characterized by a very large number of features (genes) and small number of samples. In such cases, statistical techniques cannot determine which genes are correlated to each tumor type. A popular solution is the use of a subset of prespecified genes. However, molecular variations are generally correlated to a large number of genes. A gene that is not correlated to some disease may, by combination with other genes, express itself.

show abstract

“…The lower-performance problem in between-class classification [ 7 ] is herein solved by taking advantage of the information embedded in the testing feature vector.…”

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Using the information embedded in the testing sample to break the limits caused by the small sample size in microarray-based classification

Zhu

Martı́nez

2008

BMC Bioinformatics

View full text Add to dashboard Cite

show abstract

“…A comparative study of major DR techniques can be seen in [92]. Linear techniques, such as principal component analysis (PCA) [36,44,142,160], linear discriminant analysis (LDA) [44], and multidimensional scaling (MDS) [146], are used in cases of linearly separable points in the feature space. These techniques assume Euclidean distance among the feature points.…”

Section: Histology Image Processing and Analysismentioning

confidence: 99%

Histology image analysis for carcinoma detection and grading

Long

Antani

et al. 2012

Computer Methods and Programs in Biomedicine

306

184

View full text Add to dashboard Cite

This paper presents an overview of the image analysis techniques in the domain of histopathology, specifically, for the objective of automated carcinoma detection and classification. As in other biomedical imaging areas such as radiology, many computer assisted diagnosis (CAD) systems have been implemented to aid histopathologists and clinicians in cancer diagnosis and research, which have been attempted to significantly reduce the labor and subjectivity of traditional manual intervention with histology images. The task of automated histology image analysis is usually not simple due to the unique characteristics of histology imaging, including the variability in image preparation techniques, clinical interpretation protocols, and the complex structures and very large size of the images themselves. In this paper we discuss those characteristics, provide relevant background information about slide preparation and interpretation, and review the application of digital image processing techniques to the field of histology image analysis. In particular, emphasis is given to state-of-the-art image segmentation methods for feature extraction and disease classification. Four major carcinomas of cervix, prostate, breast, and lung are selected to illustrate the functions and capabilities of existing CAD systems.

show abstract

“…For example, to properly use conventional discriminant function analysis (DA), one must have more cases than variables, ideally by a factor of 10 or more. BGA (Dolédec and Chessel 1987) and DA are based on the same principle: find a linear combination of variables that defines a direction in the multidimensional space, along which maximizes the variance between groups (Truntzer et al 2007). However, BGA allows to cope with the limitation related to the number of cases as it can be used when the number of variables exceeds the number of cases (Culhane et al 2002).…”

Section: Between-group (Bga) Analysismentioning

confidence: 99%

Genetic and morphometric characterization of clones of Prosopis alba, Algarobia, selected for salt tolerance

Roser

Ferreyra

Ewens

et al. 2014

Tree Genetics & Genomes

View full text Add to dashboard Cite

Prosopis alba is an important Argentinean species with a great potential for the production of timber and nontimber products. Many studies showed high salt tolerance of this species, which allows it to be used in afforestation and reforestation of saline soils. In this study, we applied the morphometric technique to characterize 21 salt-tolerant clones (ST). Twenty of these clones were studied by inter-simple sequence repeat (ISSR) and simple sequence repeat (SSR), and their molecular patterns were compared with those of 22 individuals selected for salt sensitivity (SS). Most morphological traits revealed highly significant differences among ST clones, and four out of 11 characters showed high heritability. ISSR analysis allowed detecting 89 loci, 91 % of them variable. ST versus SS groups differ significantly from each other by the frequencies of 22 of these loci, from which 12 were significant at the matrix level. Analysis of six SSR loci for the same groups indicated that all of them were polymorphic at the 1 % criterion. Allelic frequencies of SSR also showed highly significant differences between SS and ST groups. Analysis of coancestry between individuals within SS and ST groups and between groups indicated that the molecular differentiation between them cannot be explained solely on relationship grounds. Molecular groupings based on ISSR and SSR showed consistency to each other, as supported by the highly significant coinertia in the distribution of individuals in principal component analysis scatterplots. This work is the first contribution which tends to associate molecular patterns with life history traits and morphological differences in Prosopis clones.

show abstract

Importance of data structure in comparing two dimension reduction methods for classification of microarray gene expression data

Cited by 11 publications

References 21 publications

Using the information embedded in the testing sample to break the limits caused by the small sample size in microarray-based classification

Using the information embedded in the testing sample to break the limits caused by the small sample size in microarray-based classification

Histology image analysis for carcinoma detection and grading

Genetic and morphometric characterization of clones of Prosopis alba, Algarobia, selected for salt tolerance

Contact Info

Product

Resources

About