Using Supervised Complexity Measures in the Analysis of Cancer Gene Expression Data Sets

Authors:
Ivan G. Costa;Ana C. Lorena;Liciana R. Peres;Marcilio C. Souto
Affiliations:
Center of Informatics, Federal University of Pernambuco, Recife, Brazil;Center of Mathematics, Computation and Cognition, ABC Fed. Univ., Brazil;Center of Mathematics, Computation and Cognition, ABC Fed. Univ., Brazil;Dept. of Informatics and Applied Mathematics, Fed. Univ. of Rio Grande do Norte,
Venue:
BSB '09 Proceedings of the 4th Brazilian Symposium on Bioinformatics: Advances in Bioinformatics and Computational Biology
Year:
2009

Citing 12
Cited 1

The nature of statistical learning theory

The nature of statistical learning theory
Large margin classification using the perceptron algorithm

COLT' 98 Proceedings of the eleventh annual conference on Computational learning theory
Complexity Measures of Supervised Classification Problems

IEEE Transactions on Pattern Analysis and Machine Intelligence
Machine Learning

Machine Learning
Consensus Clustering: A Resampling-Based Method for Class Discovery and Visualization of Gene Expression Microarray Data

Machine Learning
Introduction to the Special Issue on Meta-Learning

Machine Learning
A comprehensive evaluation of multicategory classification methods for microarray gene expression cancer diagnosis

Bioinformatics
Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)

Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)
Pattern Classifier Design by Linear Programming

IEEE Transactions on Computers
On the Complexity of Gene Expression Classification Data Sets

HIS '08 Proceedings of the 2008 8th International Conference on Hybrid Intelligent Systems
Dataset complexity in gene expression based cancer classification using ensembles of k-nearest neighbors

Artificial Intelligence in Medicine
Modeling Problem Transformations based on Data Complexity

Proceedings of the 2007 conference on Artificial Intelligence Research and Development

Analysis of complexity indices for classification problems: Cancer gene expression data

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Supervised Machine Learning methods have been successfully applied for performing gene expression based cancer diagnosis. Characteristics intrinsic to cancer gene expression data sets, such as high dimensionality, low number of samples and presence of noise makes the classification task very difficult. Furthermore, limitations in the classifier performance may often be attributed to characteristics intrinsic to a particular data set. This paper presents an analysis of gene expression data sets for cancer diagnosis using classification complexity measures. Such measures consider data geometry, distribution and linear separability as indications of complexity of the classification task. The results obtained indicate that the cancer data sets investigated are formed by mostly linearly separable non-overlapping classes, supporting the good predictive performance of robust linear classifiers, such as SVMs, on the given data sets. Furthermore, we found two complexity indices, which were good indicators for the difficulty of gene expression based cancer diagnosis.