Integrating the molecular subtypes of breast cancer into a novel prognostic model

Haibe-Kains B, Desmedt C, Rothé F, Piccart MJ, Bontempi G and Sotiriou C

Background: The early gene expression studies in breast cancer have provided a molecular classification of these tumors into at least three clinically relevant subtypes (ER-/HER2-, HER2+ or ER+/HER2). Our group recently introduced a robust method for subtype identification, exhibiting numerous advantages compared to the hierarchical clustering used in the initial publications. From a prognostic point of view, several signatures have been identified in the global population of patients. However, the majority of these only added significant prognostic information in the ER+/HER2-. Here, we propose a novel prognostic model which takes into the account the molecular heterogeneity of breast cancer.

Methods: We developed a two-step prognostic model called GENIUS (Gene Expression progNostic Index Using Subtypes). The first step consists in an accurate assessment of the probabilities for a patient to belong to each of the three breast cancer molecular subtypes. The second step is a combination of these probabilities with subtype specific prognostic signatures, which results in the final GENIUS risk score.

Results: We computed the GENIUS risk score for more than 1000 untreated node-negative breast cancer patients collected from numerous microarray datasets. Compared to current gene signatures, GENIUS yielded significantly better performance in the global population of patients (concordance index of 0.71, superiority test p-values < 0.05) and was very competitive in each subtype (concordance indices of 0.7, 0.66 and 0.66 in the ER+/HER2-, ER-/HER2- and HER2+ subtypes, respectively). Although GENIUS outperformed clinical guidelines (superiority test p-values < 0.05), our results suggest that the combination of GENIUS and these guidelines might improve the predictions.

Conclusions: This novel prognostic model, which considers the molecular heterogeneity of breast cancer, outperforms the current clinical guidelines and gene signatures. GENIUS was the only signature to be highly prognostic in all the molecular subtypes. Additionally, the modular architecture of the model allows plugging in any other gene expression signatures, potentially enlarging its usability.