Microarray data integration is an important yet challenging problem. Usually, direct integration of microarrays after normalization is ineective because of the diverse types of experiment specic variations. To address this issue, two novel integration approaches were proposed in recent microarray studies. Therst study presented a cancer classication technique which identies gene pairs whose expression orders are consistent within class and dierent across classes. The other study presented a promising gene expression analysis technique which utilizes pairwise correlations of gene expressions across dierent microarray datasets. Interestingly, we observe that both of the independently developed techniques rely on inter-gene nformation and noise ltering strategy to achieve satisfactory performance in microarray integration. Motivated by this observation, we propose in this paper a formal data model for microarray integration using inter-gene information and effective ltering, which generalizes the previous two frameworks. We also show how the proposed model can handle a broader range of problems than the previous frameworks.