ABOUT   |   AIMS and SCOPE   |   AUTHOR INSTRUCTIONS   |   EDITORIAL BOARD   |   ARCHIVE   |   CURRENT ISSUE   |   SUBMIT MANUSCRIPT ONLINE  |
bioinfo issue

This Article

Copyright © 2013 | AIZEON publishers | All rights reserved

 Open Access
 Abstract
 Full Text PDF Free

 

Services

Articles by corresponding author in PubMed

Articles by corresponding author in Google Scholar

 

 

 

aizeon

 



 

International Journal of Computational Bioinformatics and In Silico Modeling
2013: Volume-2 Issue-6
ISSN: 2320-0634

>>Back to Issues

ABSTRACT   REFERENCES  
International Journal of Computational Bioinformatics and In Silico Modeling 2(6) 2013: 257-261

Comparison of Rule Based Classifiers by Pre-Learning for Clustering of Gene Expression Data


Sudhakar Tripathi* and R.B.Mishra

Department of Computer Engineering, IIT(BHU), Varanasi (U.P.), India .

* Corresponding Author

ABSTRACT

Recent advancement in microarray technology has helped to generate huge amount of gene expression data sets very rapidly. Major challenge is to analyze and explore these data sets to find the genes having similar profiles and hence predict their functions and pathways. To achieve this majorly used technique is clustering. Clustering is to find appropriate number of clusters as well as subsets belonging to those clusters. Many clustering techniques have been used to cluster time series as well as sample gene expression data sets but no single one is reported to be best in general conditions. In this research we have performed clustering of gene expression data sets using rule based classifiers (CART, C5, CHAID, QUEST) by training them using train data sets prepared by using some efficient heuristic clustering (we have used k-means).We have shown comparison of these models for testing and validation data sets and then these models can be generalized for clustering gene expression data sets by selecting appropriate model corresponding to preferences. Here we have assumed that all the data is being generated from same or similar source. Main benefit of using these models is simplicity and efficiency in terms of speed and storage. Hence we have used supervised and unsupervised techniques to generate and compare the models for efficient and accurate clustering of gene expression data sets.


Copyright © 2013 | AIZEON publishers | All rights reserved

..........................................................................................................................................................................................................

Citation: S. Tripathi and R.B. Mishra (2013). Comparison of Rule Based Classifiers by Pre-Learning for Clustering of Gene Expression Data Int J Comput Bioinfo In Silico Model 2(6): 257-261

..........................................................................................................................................................................................................