Efficient Mining Maximal Variant and Low Usage Rate Biclusters without Candidate Maintenance in Real Function-Resource Matrix: The DeCluster Algorithm

Abstract

The health of the functional layer includes the status of functional components in the hierarchy range and overall health status of the whole functional layer. This paper proposed an efficient bicluster mining algorithm: DeCluster, to effectively mine all biclusters with maximal variant usage rate and maximal low usage rate in the real-valued function-resource matrix. First, a sample weighted graph is constructed, it includes all resource collections between both samples that meet the definition of variant usage rate or low usage rate; then, all biclusters with maximal variant usage rate and low usage rate meeting the definition are mined with the mining method of using depth-first sample-growth in the weight graph made. To improve the mining efficiency of the algorithm, DeCluster algorithm uses multiple pruning strategies to ensure the mining of maximal bicluster without candidate maintenance. The experimental result show our algorithm is efficiently than traditional algorithm.