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.
©2024 American Association for Cancer Research.