摘要：Breast cancer encompasses a group of heterogeneous diseases, each associated with distinct clinical implications. Dozens of molecular biomarkers capable of categorizing tumors into clinically relevant subgroups have been proposed which, though considerably contribute in precision medicine, complicate our understandings toward breast cancer subtyping and its clinical translation. To decipher the networking of markers with diagnostic roles on breast carcinomas, we constructed the diagnostic networks by incorporating 6 publically available gene expression datasets with protein interaction data retrieved from BioGRID on previously identified 1015 genes with breast cancer subtyping roles. The Greedy algorithm and mutual information were used to construct the integrated diagnostic network, resulting in 37 genes enclosing 43 interactions. Four genes, FAM134B, KIF2C, ALCAM, KIF1A, were identified having comparable subtyping efficacies with the initial 1015 genes evaluated by hierarchical clustering and cross validations that deploy support vector machine and k nearest neighbor algorithms. Pathway, Gene Ontology, and proliferation marker enrichment analyses collectively suggest 5 primary cancer hallmarks driving breast cancer differentiation, with those contributing to uncontrolled proliferation being the most prominent. Our results propose a 37-gene integrated diagnostic network implicating 5 cancer hallmarks that drives breast cancer heterogeneity and, in particular, a 4-gene panel with clinical diagnostic translation potential.
