MammaTyper®: molecular predictor of response to neoadjuvant therapy in HER2-positive breast cancer

Introduction. Neoadjuvant therapy (NAT) has become the standard of care for most HER2-positive early breast cancer (BC). However, 25 to 50% of patients fail to achieve a pathological complete response (pCR). The study aims to assess the clinical utility of the CE/IVD MammaTyper® kit (Cerca Biotech) as a predictor of response in this setting. Methods. One-hundred and sixty-one HER2-positive/3+ IHC-score invasive BC patients were enrolled. All patients underwent trastuzumab-based NAT combined with a taxane backbone. Ethical approval was obtained. Three patients were excluded due to insufficient RNA amount, along with 4 patients treated with dual anti-HER2 blockade. Thus, 154 FFPE preoperatory core-biopsies were tested: 79 were hormone-positive (HR+) and 75 hormone-negative (HR-). Ninety-one subjects achieved a pCR while 63 attained a pathological partial response (pPR). MammaTyper®, a molecular in vitro diagnostic RT-qPCR test, was used to assess the relative mRNA expression levels of the ERBB2, ESR1, PGR and MKI67 genes. A machine-learning, Python-based Decision Tree Algorithm was used to predict pCR from the ΔΔCq values of the four genes alongside tumor size and nodal status (MTClin). Samples were stratified by MammaTyper® hormone receptor (ER and/or PgR) status. To balance interpretability and generalizability, key hyperparameters were tuned and GridSearchCV with a 5-fold cross-validation was used. Analytical accuracy was evaluated in terms of sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV). Funding: PNRR - M4.C2 - Tuscany Health Ecosystem - Spoke n.6, CUP I53C22000780001 (C.S., A.G.N.); PNRR - M4C2-I1.3 Project PE00000019 HEAL ITALIA, CUP E63C22002080006 (F.M., P.V.). Results. Two Decision Trees were selected showing high specificity and sensitivity, and plausible biomarker hierarchy. In detail, the tree for HR+ tumors showed 90.2% sensitivity, 86.8% specificity, 88.1% PPV, and 89.2% NPV. The decision tree for HR- tumors had a sensitivity of 96%, a specificity of 88%, a PPV of 94.1% and a NPV of 91.7%. Conclusions. MTClin may discriminate patients with HER2-positive BC who will achieve pCR from those who will not, representing a powerful decision tool in terms of escalation/de-escalation of treatment approaches.