Abstract
Purpose: Long-term treatment-related toxicities, such as neurologic and metabolic toxicities, are major issues in breast cancer. We investigated the interest of metabolomic profiling to predict toxicities. Experimental Design: Untargeted high-resolution metabolomic profiles of 992 patients with estrogen receptor (ER)+/HER2− breast cancer from the prospective CANTO cohort were acquired (n = 1935 metabolites). A residual-based modeling strategy with discovery and validation cohorts was used to benchmark machine learning algorithms, taking into account confounding variables. Results: Adaptive Least Absolute Shrinkage and Selection (adaptive LASSO) has a good predictive performance, has limited optimism bias, and allows the selection of metabolites of interest for future translational research. The addition of low-frequency metabolites and nonannotated metabolites increases the predictive power. Metabolomics adds extra performance to clinical variables to predict various neurologic and metabolic toxicity profiles. Conclusions: Untargeted high-resolution metabolomics allows better toxicity prediction by considering environmental exposure, metabolites linked to microbiota, and low-frequency metabolites.
Funding Information
  • National Research Agency (ANR-10-COHO-0004)
  • RHU My Probe (ANR-17-RHUS-008)

This publication has 16 references indexed in Scilit: