Metabolomics by NMR Combined with Machine Learning to Predict Neoadjuvant Chemotherapy Response for Breast Cancer

Abstract

Neoadjuvant chemotherapy (NACT) is offered to patients with operable or inoperable breast cancer (BC) to downstage the disease. Clinical responses to NACT may vary depending on a few known clinical and biological features, but the diversity of responses to NACT is not fully understood. In this study, 80 women had their metabolite profiles of pre-treatment sera analyzed for potential NACT response biomarker candidates in combination with immunohistochemical parameters using Nuclear Magnetic Resonance (NMR). Sixty-four percent of the patients were resistant to chemotherapy. NMR, hormonal receptors (HR), human epidermal growth factor receptor 2 (HER2), and the nuclear protein Ki67 were combined through machine learning (ML) to predict the response to NACT. Metabolites such as leucine, formate, valine, and proline, along with hormone receptor status, were discriminants of response to NACT. The glyoxylate and dicarboxylate metabolism was found to be involved in the resistance to NACT. We obtained an accuracy in excess of 80% for the prediction of response to NACT combining metabolomic and tumor profile data. Our results suggest that NMR data can substantially enhance the prediction of response to NACT when used in combination with already known response prediction factors.

Predictive analysis of breast cancer response to neoadjuvant chemotherapy through plasma metabolomics

“…Various studies have documented changes in amino acid levels in breast cancer. For instance, prior research indicated a correlation between proline and resistance to neoadjuvant chemotherapy in breast cancer [31]. Additionally, higher levels of arginine were observed in breast cancer patients resistant to treatment compared to those who were sensitive [31,32], and elevated levels of isoleucine were linked to pCR, as con rmed by this study [33].…”

“…For instance, prior research indicated a correlation between proline and resistance to neoadjuvant chemotherapy in breast cancer [31]. Additionally, higher levels of arginine were observed in breast cancer patients resistant to treatment compared to those who were sensitive [31,32], and elevated levels of isoleucine were linked to pCR, as con rmed by this study [33]. The metabolic pathway involving glycine, serine, and threonine has been associated with breast cancer invasion [34] and may serve as a predictor for the response to neoadjuvant chemotherapy, particularly in triple-negative breast cancer [25].…”

Metabolic signature of Mycobacterium avium subsp. paratuberculosis infected and infectious dairy cattle by integrating nuclear magnetic resonance analysis and blood indices

“…The application of LASSO method already showed its utility in multiclass classification of cancer tissues for rapid diagnosis in intra-surgery settings upon integration with mass spectrometry ( 20 , 22 , 23 ). Recently, LASSO showed good performances in classifying biological samples based on the molecular information captured by NMR ( 24 – 26 ). Note that this parsimonious method is less susceptible to the noise linked to the heterogeneity of the samples ( 27 ).…”