Improving classification of microarray data using prototype-based feature selection

Authors:
Blaise Hanczar;Mélanie Courtine;Arriel Benis;Corneliu Hennegar;Karine Clément;Jean-Daniel Zucker
Affiliations:
EPML-CNRS IAPuces, LIM&BIO -- University Paris, Bobigny;EPML-CNRS IAPuces, LIM&BIO -- University Paris, Bobigny;EPML-CNRS IAPuces, LIM&BIO -- University Paris, Bobigny;EPML-CNRS IAPuces, LIM&BIO -- University Paris, Bobigny;INSERM «Avenir» and EA3502, University Paris, Paris, France;EPML-CNRS IAPuces, LIM&BIO -- University Paris, Bobigny
Venue:
ACM SIGKDD Explorations Newsletter
Year:
2003

Citing 5
Cited 13

Selection of relevant features and examples in machine learning

Artificial Intelligence - Special issue on relevance
Reduction Techniques for Instance-BasedLearning Algorithms

Machine Learning
An introduction to support Vector Machines: and other kernel-based learning methods

An introduction to support Vector Machines: and other kernel-based learning methods
Gene Selection for Cancer Classification using Support Vector Machines

Machine Learning
Gene selection by sequential search wrapper approaches in microarray cancer class prediction

Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology - Challenges for future intelligent systems in biomedicine

On Feature Selection through Clustering

ICDM '05 Proceedings of the Fifth IEEE International Conference on Data Mining
Integrating gene ontology into discriminative powers of genes for feature selection in microarray data

Proceedings of the 2007 ACM symposium on Applied computing
A platform for the selection of genes in DNA microarraydata using evolutionary algorithms

Proceedings of the 9th annual conference on Genetic and evolutionary computation
A Clustering Based Hybrid System for Mass Spectrometry Data Analysis

PRIB '08 Proceedings of the Third IAPR International Conference on Pattern Recognition in Bioinformatics
Efficient multi-class cancer diagnosis algorithm, using a global similarity pattern

Computational Statistics & Data Analysis
Inferring Meta-covariates in Classification

PRIB '09 Proceedings of the 4th IAPR International Conference on Pattern Recognition in Bioinformatics
A clustering based hybrid system for biomarker selection and sample classification of mass spectrometry data

Neurocomputing
Combining feature selection and feature construction to improve concept learning for high dimensional data

SARA'05 Proceedings of the 6th international conference on Abstraction, Reformulation and Approximation
Improving gene selection in microarray data analysis using fuzzy patterns inside a CBR system

ICCBR'05 Proceedings of the 6th international conference on Case-Based Reasoning Research and Development
Using fuzzy patterns for gene selection and data reduction on microarray data

IDEAL'06 Proceedings of the 7th international conference on Intelligent Data Engineering and Automated Learning
Empirical Evidence of the Applicability of Functional Clustering through Gene Expression Classification

IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB)
Fuzzy clustering with biological knowledge for gene selection

Applied Soft Computing
MaskedPainter: Feature selection for microarray data analysis

Intelligent Data Analysis

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper addresses the problem of improving accuracy in the machine-learning task of classification from microarray data. One of the known issues specifically related to microarray data is the large number of inputs (genes) versus the small number of available samples (conditions). A promising direction of research to decrease the generalization error of classification algorithms is to perform gene selection so as to identify those genes which are potentially most relevant for the classification. Classical feature selection methods are based on direct statistical methods. We present a reduction algorithm based on the notion of prototypegene. Each prototype represents a set of similar gene according to a given clustering method. We present experimental evidence of the usefulness of combining prototype-based feature selection with statistical gene selection methods for the task of classifying adenocarcinoma from gene expressions.