DNA Nano array analysis using hierarchical quality threshold clustering

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