Transcriptome-Based Synthetic Lethality Predictions to Improve Targeted Therapy/Immunotherapy Treatment...

Patients with nonmetastatic triple-negative breast cancer (TNBC) or HER2+ breast cancer do not currently have tools to predict treatment response or prioritize options prior to therapy initiation. Pathologic complete response (pCR) is a proxy that requires neoadjuvant treatment. BC-SELECT leverages genetic interactions [e.g., synthetic lethality (SL)/synthetic rescue (SR)] to predict treatment response via pCR from breast cancer gene expression data. BC-SELECT involves (i) "Training: gene-pair identification" that identifies clinically relevant partner genes from large-scale datasets for a given targeted therapy or immunotherapy target and (ii) "Training: parameter tuning" using clinical trials to predict treatment response. We evaluated BC-SELECT's ability to predict pCR for trastuzumab, poly (ADP-ribose) polymerase (PARP) inhibitors, and immunotherapy, with tuning supported by three trials (n = 86) and validation on nine unseen trials (n = 722). BC-SELECT significantly predicted pCR in 6 of 9 trials, including all PARP inhibitors [ROC-AUCs, 0.6-0.8; odds ratio (OR), 1.9-3.5] and immunotherapy (ROC-AUCs, 0.7-0.8; OR, 3.2-7.1). BC-SELECT significantly distinguished between pCR and residual disease in 8 of 9 trials. No current standard-of-care, pretreatment approaches predict benefit in nonmetastatic TNBC and HER2+ breast cancer. BC-SELECT leverages genetic interactions to predict treatment response from gene expression data. Our findings support development of BC-SELECT toward studying how to prioritize PARP inhibitors and immunotherapy in nonmetastatic breast cancer.

BC-SELECT is an algorithm that uses gene expression to predict pCR in breast cancer using targeted therapy and immunotherapy. BC-SELECT predicted response to PARP inhibitors and immunotherapy, distinguished responders and nonresponders, and identified different response patterns among tumors with low BRCA1/2 gene expression.