Abstract
Gene expressions play a crucial role in analyzing gene products and related functionalities. Based on the gene expression, similar cellular functions can be predicted successfully. However, gene samples are very small, and a large number of genes may have varied functionalities, so, this issue leads to create difficulties while selecting the genes from the huge database. Therefore, in this study, map reducing and clustering techniques are used for effectively evaluating gene structures and functions. Initially, map reduction is applied to all gene data to analyze gene functions in parallel. Then, correlation-based clustering is applied to group similar gene patterns. According to the grouped patterns, various structures and functions can be applied in future research. The system efficiency is evaluated using the yeast gene expression dataset in terms of the error rate, F-measure, precision, recall and clustering accuracy.