A Coherent Pattern Mining Algorithm Based on All Contiguous Column Bicluster
Xiao-Hui Hu, Qiuhua Kuang, Qianhua Cai, Yun Xue, Weixing Zhou, Ying Li
Abstract
Microarray contains a large matrix of information and has been widely used by biologists and bio data scientist for monitoring combinations of genes in different organisms. The coherent patterns in all continuous columns are mined in gene microarray data matrices. It is investigated, in this study, the coherent patterns in all continuous columns in gene microarray data matrix by developing the time series similarity measure for the coherent patterns in all continuous columns, as well as the evaluation function for verifying the proposed algorithm and the corresponding biclusters. The continuous time changes are taken into account in the coherent patterns in all continuous columns, and co-expression patterns in time series are searched. In order to use all the common information between sequences, a similarity measure for the coherent patterns in continuous columns is defined in this paper. To validate the efficiency of the similarity measure to mine biological information at continuous time points, an evaluation function is defined to measure biclusters and an effective algorithm is proposed to mine the biclusters. Simulation experiments are conducted to verify the biological significance of the biclusters, which include synthetic datasets and real gene microarray datasets. The performance of the algorithm is analyzed and the results show that the algorithm is highly efficient.