Abstract
Neoadjuvant chemotherapy is the current standard of care for large, advanced, and/or inoperable tumors, including triple-negative breast cancer. Although the clinical benefits of neoadjuvant chemotherapy have been illustrated through numerous clinical trials, more than half of the patients do not experience therapeutic benefit and needlessly suffer from side effects. Currently, no clinically applicable biomarkers are available for predicting neoadjuvant chemotherapy response in triple-negative breast cancer; the discovery of such a predictive biomarker or marker profile is an unmet need. In this study, we introduce a generic computational framework to calculate a response-probability score (RPS), based on patient transcriptomic profiles, to predict their response to neoadjuvant chemotherapy. We first validated this framework in ER-positive breast cancer patients and showed that it predicted neoadjuvant chemotherapy response with equal performance to several clinically used gene signatures, including Oncotype DX and MammaPrint. Then, we applied this framework to triple-negative breast cancer data and, for each patient, we calculated a response probability score (TNBC-RPS). Our results indicate that the TNBC-RPS achieved the highest accuracy for predicting neoadjuvant chemotherapy response compared to previously proposed 143 gene signatures. When combined with additional clinical factors, the TNBC-RPS achieved a high prediction accuracy for triple-negative breast cancer patients, which was comparable to the prediction accuracy of Oncotype DX and MammaPrint in ER-positive patients. In conclusion, the TNBC-RPS accurately predicts neoadjuvant chemotherapy response in triple-negative breast cancer patients and has the potential to be clinically used to aid physicians in stratifying patients for more effective neoadjuvant chemotherapy.