Conference Paper

M@CBETH: Optimizing Clinical Microarray Classification.

Dept. of Electr. Eng., Katholieke Univ., Leuven, Belgium
DOI: 10.1109/CSBW.2005.86 Conference: Fourth International IEEE Computer Society Computational Systems Bioinformatics Conference Workshops & Poster Abstracts (CSB 2005 Workshops), 8-11 August 2005, Stanford, CA, USA
Source: DBLP


The M@CBETH (microarray classification bench-marking tool on host server) web service, available at, offers a simple tool for making optimal two-class predictions in a clinical setting. This web service compares different classifiers and selects the best in terms of randomized test set performances. The M@CBETH website offers two services: benchmarking and prediction. Benchmarking involves selection and training of an optimal model based on a benchmarking dataset. This model is stored for immediate or later use on prospective data. The prediction service offers a way for later evaluation of prospective data by reusing an existing optimal prediction model, which is useful for classifying new unseen patients. Nine different classification methods are considered. Application of the M@CBETH benchmarking service on two binary classification problems in ovarian cancer confirms that it is important to select and train an optimal model for each microarray dataset.

Download full-text


Available from: Nathalie Pochet, Oct 01, 2015
4 Reads
  • [Show abstract] [Hide abstract]
    ABSTRACT: We investigated whether prognostic information is reflected in the expression patterns of ovarian carcinoma samples. RNA obtained from seven FIGO stage I without recurrence, seven platin-sensitive advanced-stage (III or IV), and six platin-resistant advanced-stage ovarian tumors was hybridized on a complementary DNA microarray with 21,372 spotted clones. The results revealed that a considerable number of genes exhibit nonaccidental differential expression between the different tumor classes. Principal component analysis reflected the differences between the three tumor classes and their order of transition. Using a leave-one-out approach together with least squares support vector machines, we obtained an estimated classification test accuracy of 100% for the distinction between stage I and advanced-stage disease and 76.92% for the distinction between platin-resistant versus platin-sensitive disease in FIGO stage III/IV. These results indicate that gene expression patterns could be useful in clinical management of ovarian cancer.
    International Journal of Gynecological Cancer 02/2006; 16 Suppl 1(S1):147-51. DOI:10.1111/j.1525-1438.2006.00321.x · 1.96 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Microarrays are capable of determining the expression levels of thousands of genes simultaneously. In combination with classification methods, this technology can be useful to support clinical management decisions for individual patients, e.g. in oncology. The aim of this paper is to systematically benchmark the role of non-linear versus linear techniques and dimensionality reduction methods. A systematic benchmarking study is performed by comparing linear versions of standard classification and dimensionality reduction techniques with their non-linear versions based on non-linear kernel functions with a radial basis function (RBF) kernel. A total of 9 binary cancer classification problems, derived from 7 publicly available microarray datasets, and 20 randomizations of each problem are examined. Three main conclusions can be formulated based on the performances on independent test sets. (1) When performing classification with least squares support vector machines (LS-SVMs) (without dimensionality reduction), RBF kernels can be used without risking too much overfitting. The results obtained with well-tuned RBF kernels are never worse and sometimes even statistically significantly better compared to results obtained with a linear kernel in terms of test set receiver operating characteristic and test set accuracy performances. (2) Even for classification with linear classifiers like LS-SVM with linear kernel, using regularization is very important. (3) When performing kernel principal component analysis (kernel PCA) before classification, using an RBF kernel for kernel PCA tends to result in overfitting, especially when using supervised feature selection. It has been observed that an optimal selection of a large number of features is often an indication for overfitting. Kernel PCA with linear kernel gives better results.
    Bioinformatics 12/2004; 20(17):3185-95. DOI:10.1093/bioinformatics/bth383 · 4.98 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Microarray classification can be useful to support clinical management decisions for individual patients in, for example, oncology. However, comparing classifiers and selecting the best for each microarray dataset can be a tedious and non-straightforward task. The M@CBETH (a MicroArray Classification BEnchmarking Tool on a Host server) web service offers the microarray community a simple tool for making optimal two-class predictions. M@CBETH aims at finding the best prediction among different classification methods by using randomizations of the benchmarking dataset. The M@CBETH web service intends to introduce an optimal use of clinical microarray data classification.
    Bioinformatics 08/2005; 21(14):3185-6. DOI:10.1093/bioinformatics/bti495 · 4.98 Impact Factor