Breast cancer is a heterogeneous disease. Although gene expression profiling has led to\nthe definition of several subtypes of breast cancer, the precise discovery of the subtypes remains\na challenge. Clinical data is another promising source. In this study, clinical variables are utilized\nand integrated to gene expressions for the stratification of breast cancer. We adopt two phases:\ngene selection and clustering, where the integration is in the gene selection phase; only genes\nwhose expressions are most relevant to each clinical variable and least redundant among themselves\nare selected for further clustering. In practice, we simply utilize maximum relevance minimum\nredundancy (mRMR) for gene selection and k-means for clustering. We compare the results of our\nmethod with those of two commonly used only expression-based breast cancer stratification methods:\nprediction analysis of microarray 50 (PAM50) and highest variability (HV). The result is that our\nmethod outperforms them in identifying subtypes significantly associated with five-year survival and\nrecurrence time. Specifically, our method identified recurrence-associated breast cancer subtypes that\nwere not identified by PAM50 and HV. Additionally, our analysis discovered three survival-associated\nluminal-A subgroups and two survival-associated luminal-B subgroups. The study indicates that\nscreening clinically relevant gene expressions yields improved breast cancer stratification.
Loading....