Prediction of Retention Time and Collision Cross Section (CCS_H+, CCS_H–, and CCS_Na+) of Emerging Contaminants Using Multiple Adaptive Regression Splines

Abstract

Ultra-high performance liquid chromatography coupled to ion mobility separation and high-resolution mass spectrometry instruments have proven very valuable for screening of emerging contaminants in the aquatic environment. However, when applying suspect or nontarget approaches (i.e., when no reference standards are available), there is no information on retention time (RT) and collision cross-section (CCS) values to facilitate identification. In silico prediction tools of RT and CCS can therefore be of great utility to decrease the number of candidates to investigate. In this work, Multiple Adaptive Regression Splines (MARS) were evaluated for the prediction of both RT and CCS. MARS prediction models were developed and validated using a database of 477 protonated molecules, 169 deprotonated molecules, and 249 sodium adducts. Multivariate and univariate models were evaluated showing a better fit for univariate models to the experimental data. The RT model (R 2 = 0.855) showed a deviation between predicted and experimental data of ±2.32 min (95% confidence intervals). The deviation observed for CCS data of protonated molecules using the CCSH model (R 2 = 0.966) was ±4.05% with 95% confidence intervals. The CCSH model was also tested for the prediction of deprotonated molecules, resulting in deviations below ±5.86% for the 95% of the cases. Finally, a third model was developed for sodium adducts (CCSNa, R 2 = 0.954) with deviation below ±5.25% for 95% of the cases. The developed models have been incorporated in an open-access and user-friendly online platform which represents a great advantage for third-party research laboratories for predicting both RT and CCS data.

Prediction of a Large-Scale Database of Collision Cross-Section and Retention Time Using Machine Learning to Reduce False Positive Annotations in Untargeted Metabolomics

“…Most prediction models or workflows previously reported discuss one or the other predicted property (CCS or Rt), while only a few associate multi-dimensional information for metabolite annotation [ 47 , 48 , 49 , 50 ]. Interestingly, all of them are dedicated to lipids or exogenous compounds, while our workflow predicted a database including small molecules found in the human body, including water-soluble or lipid-soluble endogenous metabolites and exogenous compounds.…”

Collision cross section measurement and prediction methods in omics

“…Interestingly, a few studies had been reported on a prediction model with multiple prediction functions, allowing prediction in multiple dimensions 148,157 . One of which was conducted by Celma et al 157 in which prediction of RT and CCS was performed simultaneously for suspect screening (SS) and nontarget screening (NTS).…”

“…This study was based on two algorithms (support vector machine Interestingly, a few studies had been reported on a prediction model with multiple prediction functions, allowing prediction in multiple dimensions. 148,157 One of which was conducted by Celma et al 157 in which prediction of RT and CCS was performed simultaneously for suspect screening (SS) and nontarget screening (NTS). Three individual models were built for RT, CCS for (de)protonated molecules (CCS H ), and CCS for sodiated molecules (CCS Na ), all based on the multivariate adaptive regression splines (MARS) model.…”

Application of deep learning to support peak picking during non-target high resolution mass spectrometry workflows in environmental research

“…For example, ML has been demonstrated to accurately predict t R across multiple environmental matrices, collision cross section in ion mobility spectrometry and to support identication and annotation of compounds during non-target HRMS. 28,[31][32][33] These predictive models would complement the CNN developed here to improve annotation of unknown compounds. Moreover, the advantage of HRMS enables retrospective analysis to improve current knowledge related to exposure and risk.…”