Skip to main content
Fig. 1 | BMC Bioinformatics

Fig. 1

From: Regularized logistic regression with network-based pairwise interaction for biomarker identification in breast cancer

Fig. 1

Identification of an edge biomarker using the regularized logistic regression with network-based pairwise interaction via adaptive elastic net. a The available data, including expression data and PPI network data. b A line graph G (V ,E ,W ) is constructed based on the similarities S(e ik ,e jk ) which are treated as the weights for the new edges of graph, where the elements of the new node set V are the interactions in the biological network. c The expression of each gene is mapped to the edge of the network in different conditions by integrating both the network and expression information. d If the expression of the interaction change in the different states of a biological system, the edge is labeled in red, while green if not. e The informative edges identified by our model. The genes with differential expression is marked in purple, while blue if with non-differential expression

Back to article page