Metabolomic Prediction of Breast Cancer Treatment-Induced Neurologic and Metabolic Toxicities.

IF 10 1区医学 Q1 ONCOLOGY

Clinical Cancer Research Pub Date : 2024-10-15 DOI:10.1158/1078-0432.CCR-24-0195

Max Piffoux, Jérémie Jacquemin, Mélanie Pétéra, Stéphanie Durand, Angélique Abila, Delphine Centeno, Charlotte Joly, Bernard Lyan, Anne-Laure Martin, Sibille Everhard, Sandrine Boyault, Barbara Pistilli, Marion Fournier, Philippe Rouanet, Julie Havas, Baptiste Sauterey, Mario Campone, Carole Tarpin, Marie-Ange Mouret-Reynier, Olivier Rigal, Thierry Petit, Christine Lasset, Aurélie Bertaut, Paul Cottu, Fabrice André, Ines Vaz-Luis, Estelle Pujos-Guillot, Youenn Drouet, Olivier Trédan

{"title":"Metabolomic Prediction of Breast Cancer Treatment-Induced Neurologic and Metabolic Toxicities.","authors":"Max Piffoux, Jérémie Jacquemin, Mélanie Pétéra, Stéphanie Durand, Angélique Abila, Delphine Centeno, Charlotte Joly, Bernard Lyan, Anne-Laure Martin, Sibille Everhard, Sandrine Boyault, Barbara Pistilli, Marion Fournier, Philippe Rouanet, Julie Havas, Baptiste Sauterey, Mario Campone, Carole Tarpin, Marie-Ange Mouret-Reynier, Olivier Rigal, Thierry Petit, Christine Lasset, Aurélie Bertaut, Paul Cottu, Fabrice André, Ines Vaz-Luis, Estelle Pujos-Guillot, Youenn Drouet, Olivier Trédan","doi":"10.1158/1078-0432.CCR-24-0195","DOIUrl":null,"url":null,"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.","PeriodicalId":10279,"journal":{"name":"Clinical Cancer Research","volume":null,"pages":null},"PeriodicalIF":10.0000,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Clinical Cancer Research","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1158/1078-0432.CCR-24-0195","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ONCOLOGY","Score":null,"Total":0}

引用次数: 0

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.

查看原文本刊更多论文

乳腺癌治疗引起的神经和代谢毒性的代谢组学预测。

背景：长期治疗相关毒性，如神经和代谢毒性，是乳腺癌的主要问题。我们研究了代谢组学图谱对预测毒性的兴趣：方法：我们从前瞻性CANTO队列中获取了992名ER+/HER2-乳腺癌患者的非靶向高分辨率代谢组图谱（代谢物数=1935）。在考虑混杂变量的情况下，采用基于残差的建模策略，以发现队列和验证队列作为机器学习算法的基准：结果：自适应 LASSO 具有良好的预测性能，乐观偏差有限，可以为未来的转化研究选择感兴趣的代谢物。增加低频代谢物和非注释代谢物可提高预测能力。代谢组学为临床变量增加了额外的性能，以预测各种神经和代谢毒性特征：非靶向高分辨率代谢组学通过考虑环境暴露、与微生物群相关的代谢物和低频代谢物，可以更好地预测毒性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Clinical Cancer Research 医学-肿瘤学

CiteScore

20.10

自引率

1.70%

发文量

1207

审稿时长

2.1 months

期刊介绍： Clinical Cancer Research is a journal focusing on groundbreaking research in cancer, specifically in the areas where the laboratory and the clinic intersect. Our primary interest lies in clinical trials that investigate novel treatments, accompanied by research on pharmacology, molecular alterations, and biomarkers that can predict response or resistance to these treatments. Furthermore, we prioritize laboratory and animal studies that explore new drugs and targeted agents with the potential to advance to clinical trials. We also encourage research on targetable mechanisms of cancer development, progression, and metastasis.