Construction and validation of a gene expression classifier to predict immunotherapy response in primary triple-negative breast cancer

Abstract Background: Immune checkpoint inhibitors (ICI) improve clinical outcomes in triple-negative breast cancer (TNBC) patients. However, a subset of patients does not respond to treatment. Biomarkers that show ICI predictive potential in other solid tumors, such as levels of PD-L1 and the tumor mutational burden, among others, show a modest predictive performance in patients with TNBC. Methods: We built machine learning models based on pre-ICI treatment gene expression profiles, to construct gene expression classifiers to identify primary TNBC ICI-responder patients. This study involved 132 ICI-naïve and 721 specimens treated with ICI plus chemotherapy, including TNBC tumors, HR+/HER2- breast tumors, and other solid non-breast tumors. Results: A 37-gene TNBC ICI predictive (TNBC-ICI) classifier showed a high performance in predicting pathological complete response (pCR) to ICI plus chemotherapy on an independent TNBC validation cohort (AUC=0.86). The TNBC-ICI classifier showed better performance than other previously established molecular signatures, including PD-1 (PDCD1) and PD-L1 (CD274) gene expression (AUC=0.67). Integrating molecular signatures did not improve the efficiency of the classifier (AUC=0.75). TNBC-ICI displayed a modest accuracy in predicting ICI response in two different cohorts of HR+/HER2- breast cancer patients (AUC: 0.72-0.76). Evaluation of six cohorts of patients with non-breast solid tumors treated with ICI plus chemotherapy showed overall poor performance (median AUC=0.67). Conclusion: TNBC-ICI predicts pCR to ICI plus chemotherapy in patients with primary TNBC. The study provides a guide to implementing the TNBC-ICI classifier in clinical studies. Further validations will consolidate a novel predictive panel to improve the treatment decision-making for patients with TNBC.