DNA Nano array analysis using hierarchical quality threshold clustering

• Published in: 2010 2nd IEEE International Conference on Information Management and Engineering pp. 81 - 85
• Main Authors: Waoo, Nikhilesh, Kashyap, Ramgopal, Jaiswal, Astha
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.04.2010
• Subjects: Bioinformatics; Cancer; Clustering algorithms; Data analysis; Diseases; DNA; Dynamically growing self organizing map; Gene expression; Gene expression profile; Image processing; Monitoring; Nano array; Organizing; QT clustering etc; self-organizing maps
• ISBN: 9781424452637; 1424452635
• DOI: 10.1109/ICIME.2010.5477579

DNA Nano array technology is a challenging area in bioinformatics research, as we have to monitor millions of genes simultaneously. The expression profile of the gene can be useful in cancer disease analysis and its diagnosis. Gene expression data is very voluminous and very difficult to analyze. Several clustering algorithm have been proposed to identify co expressed genes. The Self-organizing-maps (SOM) is a powerful tool for recognizing and classifying features in complex, micro array data. But the interpretation of co-expression of genes are heavily depends on domain knowledge and SOM lacks since the number of clusters must be determined before training. In this work we have proposed dynamically Growing Hierarchical Self Organizing Map (DGHSOM) with Nano array to identify co expressed genes. The DGHSOM overcomes the problem of specifying the number of clusters and total number of iteration before the processing now, we are using QT (quality threshold) clustering is a method of partitioning data, which is invented for gene clustering. It requires more computing power than A-means, but does not require specifying the number of clusters.