Wyniki wyszukiwania - BazTech

Ograniczanie wyników

2 Journal of Medical Informatics & Technologies

Powiadomienia systemowe

Sesja wygasła!

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Stability of gene selection methods for multiclass clssification

Student S., Fujarewicz K.

Journal of Medical Informatics & Technologies

2010

Vol. 15

101--107

A big problem in applying DNA microarrays for classification is dimension of the dataset. Recently we proposed a gene selection method based on Partial Least Squares (PLS) for searching best genes for classification. The new idea is to use PLS not only as multiclass approach, but to construct more binary selections that use one versus rest and one versus one approaches. Ranked gene lists are highly instable in the sense, that a small change of the data set often leads to big change of the obtained ordered list. In this article, we take a look at the assessment of stability of our approaches. We compare the variability of the obtained ordered lists from proposed methods with well known Recursive Feature Elimination (RFE) method and classical t-test method. This paper focuses on effective identification of informative genes. As a result, a new strategy to find small subset of significant genes is designed. Our results on real cancer data show that our approach has very high accuracy rate for different combinations of classification methods giving in the same time very stable feature rankings.

Using Multiclass SVM methods for classification of DNA microarray data

Student S.

Journal of Medical Informatics & Technologies

2007

Vol. 11

197--204

One important application of gene expression microarray data is classification of samples into categories, such as the type of tumor. A classifier using Multiclass SVM [4] (Support Vector Machines) is described in this article. Our classifier involves dimension reduction using Multivariate Partial Least Squares (MPLS) for classification more than two classes. We use also two methods based on binary classifications: One-Against-All [5] and One-Against-One [6]. These three methods have been tested on a data set involving 125 tumor/normal thyroid human DNA microarrays samples. There are 66 Papillary throid carcinoma, 32 follicular throid carcinoma and 27 normal tissues. The most important thing is to find small number of genes that discriminate between these three classes with good accuracy. The best genes can be selected for Q-PCR validation. Molecular markers differentiating between throid cancer and normal tissues can help in clinical diagnostics and therapy methods. For error estimation we are use the bootstrap .632 [8] technique. Major issue with bootstrap estimators is their high computational cost. That is why we use a OpenMosix with MPI (Message Passing Interface) cluster technology for this system for parallel computation space.