Identifying prognostic subgroups of luminal-A breast cancer using deep autoencoders and gene expressions

Abstract

Author summaryLuminal-A breast cancer is the most frequently occurring breast cancer subtype. However, it shows high variability in prognosis, and more precise stratification is needed. In this paper, we identified two prognostic subgroups of luminal-A breast cancer, BPS-LumA and WPS-LumA. To this end, we used deep autoencoders which automatically generate informative latent features that represent essential properties of gene expressions. We found that the two subgroups clustered using the latent features are significantly different in prognosis. This prognostic difference was validated with the external luminal-A breast cancer cohort. We showed that only latent features are able to discover the prognostic subgroups compared to gene expression profiles. In addition, we compare our results with the two previous luminal-A breast cancer stratification method which are complementary to each other. Finally, we suggested biological functions associated with the differentially expression genes between the two subgroups as potential molecular mechanisms which results in the differences in the prognosis. We expect that our method could be used for the personalized medicine of luminal-A breast cancer. Luminal-A breast cancer is the most frequently occurring subtype which is characterized by high expression levels of hormone receptors. However, some luminal-A breast cancer patients suffer from intrinsic and/or acquired resistance to endocrine therapies which are considered as first-line treatments for luminal-A breast cancer. This heterogeneity within luminal-A breast cancer has required a more precise stratification method. Hence, our study aims to identify prognostic subgroups of luminal-A breast cancer. In this study, we discovered two prognostic subgroups of luminal-A breast cancer (BPS-LumA and WPS-LumA) using deep autoencoders and gene expressions. The deep autoencoders were trained using gene expression profiles of 679 luminal-A breast cancer samples in the METABRIC dataset. Then, latent features of each samples generated from the deep autoencoders were used for K-Means clustering to divide the samples into two subgroups, and Kaplan-Meier survival analysis was performed to compare prognosis (recurrence-free survival) between them. As a result, the prognosis between the two subgroups were significantly different (p-value = 6.70E-05; log-rank test). This prognostic difference between two subgroups was validated using gene expression profiles of 415 luminal-A breast cancer samples in the TCGA BRCA dataset (p-value = 0.004; log-rank test). Notably, the latent features were superior to the gene expression profiles and traditional dimensionality reduction method in terms of discovering the prognostic subgroups. Lastly, we discovered that ribosome-related biological functions could be potentially associated with the prognostic difference between them. Our stratification method can be contributed to understanding a complexity of luminal-A breast cancer and providing a personalized medicine.