Disease classification based on the activities of interacting molecular modules with condition-responsive correlation

Genome-wide expression profiles of diseased samples have been exploited to predict disease states. Recently, network-based approaches utilizing molecular interaction networks integrated with gene expression profiles have been proposed to address challenges which arise from smaller number of samples compared to the large number of predictors, and genetic heterogeneity of samples in complex diseases such as cancer. However, previous network-based methods only focus on expression levels of proteins, nodes in the network though the identification of condition-responsive interactions, edges under the phenotype of interest must enlighten another aspect of pathogenic processes. Thus, we propose a novel network-based classification which focuses on both nodes with discriminative expression levels and edges with condition-responsive correlations across two phenotypes. The extracted modules with conditionresponsive interactions not only provide candidate molecular models for disease, and their activities inferred from a subset of member genes serve as better predictors in classification compared to the conventional gene-centric method.