A New Biclustering Algorithm for Time-Series Gene Expression Data Analysis

Biclustering algorithm is used to find local patterns as an important tool in the analysis of gene expression data. However, most of the biclusters found by existing biclustering algorithms consist of non-continuous columns. It is not suitable for time series gene expression data, which has not been extensively studied. This paper presents an efficient exact algorithm to search contiguous column coherent evolution biclusters in time-series data. The first step of the algorithm is to transform the original matrix into the difference matrix, then starting from the column pattern consisting of continuous k columns, gradually obtain longer patterns composed of more columns by using the prefix tree and nodes-update-strategy to improve the efficiency of the algorithm. Experimental results on real data show that the algorithm can find biclusters with statistically significance and strong biological relevance.