Bypassing the Identification: MS2Quant for Concentration Estimations of Chemicals Detected with Nontarget LC-HRMS from MS2 Data

Nontarget analysisby liquid chromatography-high-resolutionmass spectrometry (LC-HRMS) is now widely used to detect pollutantsin the environment. Shifting away from targeted methods has led todetection of previously unseen chemicals, and assessing the risk posedby these newly detected chemicals is an important challenge. Assessingexposure and toxicity of chemicals detected with nontarget HRMS ishighly dependent on the knowledge of the structure of the chemical.However, the majority of features detected in nontarget screeningremain unidentified and therefore the risk assessment with conventionaltools is hampered. Here, we developed MS2Quant, a machine learningmodel that enables prediction of concentration from fragmentation(MS2) spectra of detected, but unidentified chemicals.MS2Quant is an xgbTree algorithm-based regressionmodel developed using ionization efficiency data for 1191 unique chemicalsthat spans 8 orders of magnitude. The ionization efficiency valuesare predicted from structural fingerprints that can be computed fromthe SMILES notation of the identified chemicals or from MS2 spectra of unidentified chemicals using SIRIUS+CSI:FingerID software.The root mean square errors of the training and test sets were 0.55(3.5x) and 0.80 (6.3x) log-units, respectively. In comparison,ionization efficiency prediction approaches that depend on assigningan unequivocal structure typically yield errors from 2x to 6x.The MS2Quant quantification model was validated on a set of 39 environmentalpollutants and resulted in a mean prediction error of 7.4x, ageometric mean of 4.5x, and a median of 4.0x. For comparison,a model based on PaDEL descriptors that depends on unequivocal structuralassignment was developed using the same dataset. The latter approachyielded a comparable mean prediction error of 9.5x, a geometricmean of 5.6x, and a median of 5.2x on the validation setchemicals when the top structural assignment was used as input. Thisconfirms that MS2Quant enables to extract exposure information forunidentified chemicals which, although detected, have thus far beendisregarded due to lack of accurate tools for quantification. TheMS2Quant model is available as an R-package in GitHub for improvingdiscovery and monitoring of potentially hazardous environmental pollutantswith nontarget screening.