Prediction of a Large-Scale Database of Collision Cross-Section and Retention Time Using Machine Learning to Reduce False Positive Annotations in Untargeted Metabolomics.
Résumé
Download PDF
settings
Order Article Reprints
Open AccessArticle
Prediction of a Large-Scale Database of Collision Cross-Section and Retention Time Using Machine Learning to Reduce False Positive Annotations in Untargeted Metabolomics
by Marie Lenski
1,2,* [ORCID] , Saïd Maallem
1, Gianni Zarcone
1 [ORCID] , Guillaume Garçon
1 [ORCID] , Jean-Marc Lo-Guidice
1, Sébastien Anthérieu
1 [ORCID] and Delphine Allorge
1,2
1
ULR 4483, IMPECS—IMPact de l’Environnement Chimique sur la Santé humaine, CHU Lille, Institut Pasteur de Lille, Université de Lille, F-59000 Lille, France
2
CHU Lille, Unité Fonctionnelle de Toxicologie, F-59037 Lille, France
*
Author to whom correspondence should be addressed.
Metabolites 2023, 13(2), 282; https://doi.org/10.3390/metabo13020282
Submission received: 9 January 2023 / Revised: 7 February 2023 / Accepted: 12 February 2023 / Published: 15 February 2023
(This article belongs to the Special Issue Application of Metabolomics in Toxicology Research)
Download
keyboard_arrow_down
Browse Figures
Versions Notes
Abstract
Metabolite identification in untargeted metabolomics is complex, with the risk of false positive annotations. This work aims to use machine learning to successively predict the retention time (Rt) and the collision cross-section (CCS) of an open-access database to accelerate the interpretation of metabolomic results. Standards of metabolites were tested using liquid chromatography coupled with high-resolution mass spectrometry. In CCSBase and QSRR predictor machine learning models, experimental results were used to generate predicted CCS and Rt of the Human Metabolome Database. From 542 standards, 266 and 301 compounds were detected in positive and negative electrospray ionization mode, respectively, corresponding to 380 different metabolites. CCS and Rt were then predicted using machine learning tools for almost 114,000 metabolites. R2 score of the linear regression between predicted and measured data achieved 0.938 and 0.898 for CCS and Rt, respectively, demonstrating the models’ reliability. A CCS and Rt index filter of mean error ± 2 standard deviations could remove most misidentifications. Its application to data generated from a toxicology study on tobacco cigarettes reduced hits by 76%. Regarding the volume of data produced by metabolomics, the practical workflow provided allows for the implementation of valuable large-scale databases to improve the biological interpretation of metabolomics data.
Origine | Fichiers éditeurs autorisés sur une archive ouverte |
---|