Skip to main content
Fig. 1 | BMC Bioinformatics

Fig. 1

From: TLGP: a flexible transfer learning algorithm for gene prioritization based on heterogeneous source domain

Fig. 1

Overview of TLGP, which consists of the affinity matrix construction, dimension reduction in source domain, fusion network construction and gene ranking. Affinity matrix quantifies the similarity of genes between source and target domain. Dimension reduction learns the expression representation of source cancer, where cancer and non-cancer genes are well separated. The fusion network is based on the integration of source and target data. The gene ranking is performed via exploring fusion matrix

Back to article page