Interval based fuzzy systems for identification of important genes from microarray gene expression data: Application to carcinogenic development

Authors:
Rajat K. De;Anupam Ghosh
Affiliations:
Machine Intelligence Unit, Indian Statistical Institute, 203 Barrackpore Trunk Road, Kolkata 700108, West Bengal, India;Department of Computer Science and Engineering, Netaji Subhash Engineering College, Kolkata 700152, India
Venue:
Journal of Biomedical Informatics
Year:
2009

Citing 9
Cited 2

Fuzzy mathematical approach to pattern recognition

Fuzzy mathematical approach to pattern recognition
Linguistic recognition system based on approximate reasoning

Information Sciences: an International Journal
A novel feature selection method to improve classification of gene expression data

APBC '04 Proceedings of the second conference on Asia-Pacific bioinformatics - Volume 29
Mining top-K covering rule groups for gene expression data

Proceedings of the 2005 ACM SIGMOD international conference on Management of data
Detecting clusters of different geometrical shapes in microarray gene expression data

Bioinformatics
Small, fuzzy and interpretable gene expression based classifiers

Bioinformatics
Data-adaptive test statistics for microarray data

Bioinformatics
Gene selection in cancer classification using sparse logistic regression with Bayesian regularization

Bioinformatics
Classification of gene expression data using fuzzy logic

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

A fuzzy intelligent approach to the classification problem in gene expression data analysis

Knowledge-Based Systems
Selection of genes mediating certain cancers, using a neuro-fuzzy approach

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In the present article, we develop two interval based fuzzy systems for identification of some possible genes mediating the carcinogenic development in various tissues. The methodology involves dimensionality reduction, classifying the genes through incorporation of the notion of linguistic fuzzy sets low, medium and high, and finally selection of some possible genes mediating a particular disease, obtained by a rule generation/grouping technique. The effectiveness of the proposed methodology, is demonstrated using five microarray gene expression datasets dealing with human lung, colon, sarcoma, breast cancer and leukemia. Moreover, the superior capability of the methodology in selecting important genes, over five other existing gene selection methods, viz., Significance Analysis of Microarrays (SAM), Signal-to-Noise Ratio (SNR), Neighborhood analysis (NA), Bayesian Regularization (BR) and Data-adaptive (DA) is demonstrated, in terms of the enrichment of each GO category of the important genes based on P-values. The results are appropriately validated by earlier investigations, gene expression profiles and t-test. The proposed methodology has been able to select genes that are more biologically significant in mediating the development of a disease than those obtained by the others.