Denice van Herwerden
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Denice van Herwerden has a total of 85 co-authors. Here are the top co-authors by number of shared publications:
- Saer Samanipour
University of Amsterdam
15 shared publications - Jake William O'Brien
Queensland Alliance for Environmental Health Sciences (QAEHS), The University of Queensland, 20 Cornwall Street, Woolloongabba, QLD 4103, Australia
8 shared publications - Kevin Victor Thomas
Queensland Alliance for Environmental Health Sciences (QAEHS), The University of Queensland, Woolloongabba, QLD 4102, Australia
7 shared publications - Bob W. J. Pirok
University of Amsterdam
5 shared publications - Alexandros Nikolopoulos
University of Amsterdam
3 shared publications - Viktoriia Turkina
University of Amsterdam
3 shared publications
Latest Publications
- Open Access
- 12 August 2025
- Published by American Chemical Society (ACS) in Analytical Chemistry
- Vol. 97 (33) , 18028-18035
Machine Learning for Enhanced Identification Probability in RPLC/HRMS Nontargeted Workflows
In HRMS-based nontargeted analysis (NTA), spectral matching is crucial for chemical identification, particularly in the absence of retention information. This study introduces class probability of true positives (P(TP)) as an innovative approach, leveraging data from MS/MS spectra and calibrant-free predicted retention time indices (RTIs) through 3 machine learning (ML) models to enhance identification probability (IP). The first model is a molecular fingerprint (MF)-to-RTI model trained on 4713 calibrants. The second model, a cumulative neutral loss (CNL)-to-RTI model, utilized 485,577 experimental spectra. The final model, a binary classification model, was trained using 1,686,319 TP and semisynthetic true negative (TN) spectral matches. High correlations between MF-derived and CNL-derived RTI values (R2 = 0.96 for training; 0.88 for testing) suggest reduced RTI errors in TP spectral matches. Incorporating reference spectral library searches and RTI errors, the k-nearest neighbors algorithm achieved a weighted F1 score of 0.65 and a Matthews correlation coefficient of 0.30 for pesticides at concentrations of 1 to 1000 ppb in blank samples, with a recall of 0.60 in black tea matrices. Compared to solely library matching, the average IPs for pesticides increased by 54.5, 52.1, and 46.7% when spiked in blank, 10× diluted, and 100× diluted tea matrices, respectively. This work demonstrates the effectiveness of ML in enhancing the chemical IPs of annotated compounds within complex matrices.
- 12 August 2025
- Published by American Chemical Society (ACS) in Analytical Chemistry
- Vol. 97 (33) , 18028-18035
Open AccessMachine Learning for Enhanced Identification Probability in RPLC/HRMS Nontargeted Workflows
In HRMS-based nontargeted analysis (NTA), spectral matching is crucial for chemical identification, particularly in the absence of retention information. This study introduces class probability of true positives (P(TP)) as an innovative approach, leveraging data from MS/MS spectra and calibrant-free predicted retention time indices (RTIs) through 3 machine learning (ML) models to enhance identification probability (IP). The first model is a molecular fingerprint (MF)-to-RTI model trained on 4713 calibrants. The second model, a cumulative neutral loss (CNL)-to-RTI model, utilized 485,577 experimental spectra. The final model, a binary classification model, was trained using 1,686,319 TP and semisynthetic true negative (TN) spectral matches. High correlations between MF-derived and CNL-derived RTI values (R2 = 0.96 for training; 0.88 for testing) suggest reduced RTI errors in TP spectral matches. Incorporating reference spectral library searches and RTI errors, the k-nearest neighbors algorithm achieved a weighted F1 score of 0.65 and a Matthews correlation coefficient of 0.30 for pesticides at concentrations of 1 to 1000 ppb in blank samples, with a recall of 0.60 in black tea matrices. Compared to solely library matching, the average IPs for pesticides increased by 54.5, 52.1, and 46.7% when spiked in blank, 10× diluted, and 100× diluted tea matrices, respectively. This work demonstrates the effectiveness of ML in enhancing the chemical IPs of annotated compounds within complex matrices.
- Open Access
- 13 June 2025
- Published by American Chemical Society (ACS) in ChemRxiv
Ionization Efficiency Prediction of Electrospray Ionization Mass Spectrometry Analytes based on Molecular Fingerprints and Cumulative Neutral Losses
Quantification is a challenge for non-targeted analysis (NTA) with liquid chromatography–high resolution mass spectrometry (LC–HRMS), due to the lack of analytical standards. Quantification via structure-based predicted ionization efficiency (IE) was found to provide the highest accuracy in estimating concentration. However, achieving confident analyte identification is a challenging task, as multiple candidate structures may be likely. This uncertainty in identification limits the reliability of structure-based IE prediction models, since quantification can be severely compromised in cases of wrongly (tentatively) identified chemicals or lack of candidate structures. Here we investigate the possibility of using cumulative neutral losses from fragmentation spectra (i.e. MS2) to predict the logIE. The first model was based on molecular fingerprints and was applied on structurally identified analytes. PubChem fingerprints performed the best with the root-mean-square error (RMSE) of 0.72 logIE units for the test set. The second model was based on the MS2 spectrum, expressed as cumulative neutral losses was used for model training. This approach is applicable to analytes with unknown structures and showed promising results with RMSE of 0.79 logIE units for the test set. The prediction models were compiled in a Julia package, which is publicly available on GitHub, and may be used as part of a quantification workflow to estimate concentrations of identified and unidentified compounds in NTA.
- 13 June 2025
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessIonization Efficiency Prediction of Electrospray Ionization Mass Spectrometry Analytes based on Molecular Fingerprints and Cumulative Neutral Losses
Quantification is a challenge for non-targeted analysis (NTA) with liquid chromatography–high resolution mass spectrometry (LC–HRMS), due to the lack of analytical standards. Quantification via structure-based predicted ionization efficiency (IE) was found to provide the highest accuracy in estimating concentration. However, achieving confident analyte identification is a challenging task, as multiple candidate structures may be likely. This uncertainty in identification limits the reliability of structure-based IE prediction models, since quantification can be severely compromised in cases of wrongly (tentatively) identified chemicals or lack of candidate structures. Here we investigate the possibility of using cumulative neutral losses from fragmentation spectra (i.e. MS2) to predict the logIE. The first model was based on molecular fingerprints and was applied on structurally identified analytes. PubChem fingerprints performed the best with the root-mean-square error (RMSE) of 0.72 logIE units for the test set. The second model was based on the MS2 spectrum, expressed as cumulative neutral losses was used for model training. This approach is applicable to analytes with unknown structures and showed promising results with RMSE of 0.79 logIE units for the test set. The prediction models were compiled in a Julia package, which is publicly available on GitHub, and may be used as part of a quantification workflow to estimate concentrations of identified and unidentified compounds in NTA.
- Open Access
- 28 January 2025
- Published by American Chemical Society (ACS) in ChemRxiv
Machine Learning for Enhanced Identification in RPLC/HRMS Non-Targeted Workflows
In HRMS-based non-targeted analysis (NTA) without access to any retention information of unknown compounds, spectral matching is one of the most employed approaches for the assessment of chemical identification probability (IP). Recently, within the metabolomics community, the use of true positive (TP) probability has been proposed as an alternative to the conventional confidence assessment approaches. In this study, a combination of information extracted from the MS/MS spectra and calibrant-free predicted retention time indices (RTIs) yielded the probability of TP for each chemical annotation by integrating 3 machine learning (ML) models. Firstly, they include a molecular fingerprint (MF)-to-RTI model trained by 4,713 calibrants. Then a cumulative neutral loss (CNL)-to-RTI model was trained by 485,577 experimental spectra. Finally, a binary classification model was trained by 1,686,319 TP and true negative (TN) annotations. Our results demonstrated a high correlation (training: R2 = 0.96; testing: R2 = 0.88) between MF-derived and CNL-derived RTI values, suggesting reduced RTI error for TP annotations. By incorporating the output parameters from a previously developed library search algorithm, monoisotopic mass, and RTI error for TP determination, the k-nearest neighbors algorithm achieved a weighted F1 score of 0.65 and a Matthews correlation coefficient of 0.30 for the annotations with their spectral matching scores ≥50% of total score. The attained ML models were applied to RPLC/HRMS NTA of pesticide mixtures that were spiked in solvent blank and 100× and 10× diluted black tea matrix. The chemical IPs of TP candidates were increased by 54.5%, 52.1%, and 46.7%, respectively. This work demonstrates the application of ML at large-scale model training to enhance chemical IP of unknown compounds.
- 28 January 2025
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessMachine Learning for Enhanced Identification in RPLC/HRMS Non-Targeted Workflows
In HRMS-based non-targeted analysis (NTA) without access to any retention information of unknown compounds, spectral matching is one of the most employed approaches for the assessment of chemical identification probability (IP). Recently, within the metabolomics community, the use of true positive (TP) probability has been proposed as an alternative to the conventional confidence assessment approaches. In this study, a combination of information extracted from the MS/MS spectra and calibrant-free predicted retention time indices (RTIs) yielded the probability of TP for each chemical annotation by integrating 3 machine learning (ML) models. Firstly, they include a molecular fingerprint (MF)-to-RTI model trained by 4,713 calibrants. Then a cumulative neutral loss (CNL)-to-RTI model was trained by 485,577 experimental spectra. Finally, a binary classification model was trained by 1,686,319 TP and true negative (TN) annotations. Our results demonstrated a high correlation (training: R2 = 0.96; testing: R2 = 0.88) between MF-derived and CNL-derived RTI values, suggesting reduced RTI error for TP annotations. By incorporating the output parameters from a previously developed library search algorithm, monoisotopic mass, and RTI error for TP determination, the k-nearest neighbors algorithm achieved a weighted F1 score of 0.65 and a Matthews correlation coefficient of 0.30 for the annotations with their spectral matching scores ≥50% of total score. The attained ML models were applied to RPLC/HRMS NTA of pesticide mixtures that were spiked in solvent blank and 100× and 10× diluted black tea matrix. The chemical IPs of TP candidates were increased by 54.5%, 52.1%, and 46.7%, respectively. This work demonstrates the application of ML at large-scale model training to enhance chemical IP of unknown compounds.
- Top Cited PapersOpen Access
- 20 June 2024
- Published by American Chemical Society (ACS) in JACS Au
- Vol. 4 (7) , 2412-2425
Exploring the Chemical Space of the Exposome: How Far Have We Gone?
Around two-thirds of chronic human disease can not be explained by genetics alone. The Lancet Commission on Pollution and Health estimates that 16% of global premature deaths are linked to pollution. Additionally, it is now thought that humankind has surpassed the safe planetary operating space for introducing human-made chemicals into the Earth System. Direct and indirect exposure to a myriad of chemicals, known and unknown, poses a significant threat to biodiversity and human health, from vaccine efficacy to the rise of antimicrobial resistance as well as autoimmune diseases and mental health disorders. The exposome chemical space remains largely uncharted due to the sheer number of possible chemical structures, estimated at over 1060 unique forms. Conventional methods have cataloged only a fraction of the exposome, overlooking transformation products and often yielding uncertain results. In this Perspective, we have reviewed the latest efforts in mapping the exposome chemical space and its subspaces. We also provide our view on how the integration of data-driven approaches might be able to bridge the identified gaps.
- 20 June 2024
- Published by American Chemical Society (ACS) in JACS Au
- Vol. 4 (7) , 2412-2425
Top Cited PapersOpen AccessExploring the Chemical Space of the Exposome: How Far Have We Gone?
Around two-thirds of chronic human disease can not be explained by genetics alone. The Lancet Commission on Pollution and Health estimates that 16% of global premature deaths are linked to pollution. Additionally, it is now thought that humankind has surpassed the safe planetary operating space for introducing human-made chemicals into the Earth System. Direct and indirect exposure to a myriad of chemicals, known and unknown, poses a significant threat to biodiversity and human health, from vaccine efficacy to the rise of antimicrobial resistance as well as autoimmune diseases and mental health disorders. The exposome chemical space remains largely uncharted due to the sheer number of possible chemical structures, estimated at over 1060 unique forms. Conventional methods have cataloged only a fraction of the exposome, overlooking transformation products and often yielding uncertain results. In this Perspective, we have reviewed the latest efforts in mapping the exposome chemical space and its subspaces. We also provide our view on how the integration of data-driven approaches might be able to bridge the identified gaps.
- Open Access
- 20 June 2024
- Published by Elsevier in Analytica Chimica Acta
- Vol. 1317, 342869
Exploring the chemical subspace of RPLC: A data driven approach
- 20 June 2024
- Published by Elsevier in Analytica Chimica Acta
- Vol. 1317, 342869
Open AccessExploring the chemical subspace of RPLC: A data driven approach
- Open Access
- 17 June 2024
- Published by American Chemical Society (ACS) in ChemRxiv
Modular Open-access and Open-source julia language Toolbox for Processing of HRMS Data: jHRMSToolBox
There is a growing need for understanding the exposome chemical space. Non-target analysis is, generally, used for the analysis of the thousand of known and unknown chemicals in environmentally and biologically relevant samples. However, algorithm limitations arise with regard to flexibility and suitability for the processing of such data. Hence, the modular open-access and open-source jHRMS toolbox was developed, providing both a user-interface and the freedom to modify and add workflows as required. The default implemented algorithms have been developed for high-resolution mass spectrometry data and can handle MS1 and various data-dependent and data-independent analysis data types both in profile and centroided formats. Moreover, the identification algorithm provides extensive match quality reporting. Besides the data processing workflow, the toolbox comes with built in post processing (i.e., visualization) for individual steps of the workflow and statistical analysis. Finally, the results are reported step-by-step, parameters can be saved, and it is operating system agnostic. To showcase the potential of the jHRMS toolbox, two datasets from different origins environmental and biological were analyzed and reported. For the environmental case study the trends of some pharmaceuticals in river waters were evaluated. While for the biological samples it was possible to differentiate between liver and brain tissues based on the extracted information.
- 17 June 2024
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessModular Open-access and Open-source julia language Toolbox for Processing of HRMS Data: jHRMSToolBox
There is a growing need for understanding the exposome chemical space. Non-target analysis is, generally, used for the analysis of the thousand of known and unknown chemicals in environmentally and biologically relevant samples. However, algorithm limitations arise with regard to flexibility and suitability for the processing of such data. Hence, the modular open-access and open-source jHRMS toolbox was developed, providing both a user-interface and the freedom to modify and add workflows as required. The default implemented algorithms have been developed for high-resolution mass spectrometry data and can handle MS1 and various data-dependent and data-independent analysis data types both in profile and centroided formats. Moreover, the identification algorithm provides extensive match quality reporting. Besides the data processing workflow, the toolbox comes with built in post processing (i.e., visualization) for individual steps of the workflow and statistical analysis. Finally, the results are reported step-by-step, parameters can be saved, and it is operating system agnostic. To showcase the potential of the jHRMS toolbox, two datasets from different origins environmental and biological were analyzed and reported. For the environmental case study the trends of some pharmaceuticals in river waters were evaluated. While for the biological samples it was possible to differentiate between liver and brain tissues based on the extracted information.
- Open Access
- 11 March 2024
- Published by American Chemical Society (ACS) in ChemRxiv
Exploring the Chemical Space of the Exposome: How Far Have We Gone?
Around two-thirds of chronic human disease is not explainable by genetics alone. The Lancet Commission on Pollution and Health estimates that 16% of global premature deaths are linked to pollution. Additionally, it is now thought that humankind has surpassed the safe planetary operating space for introducing human-made chemicals into the Earth System. Direct and indirect exposure to a myriad of chemicals, known and unknown, poses a significant threat to biodiversity and human health, from vaccine efficacy to the rise of antimicrobial resistance as well as autoimmune diseases, and mental health disorders. The exposome chemical space remains largely uncharted due to the sheer number of possible chemical structures, estimated at over 10^60 unique forms. Conventional methods have cataloged only a fraction of the exposome, overlooking transformation products and often yielding uncertain results. In this perspective we have reviewed the latest efforts in mapping the exposome chemical space and its sub-spaces. We also provide our view on how the integration of data driven approaches might be able to bridge the identified gaps.
- 11 March 2024
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessExploring the Chemical Space of the Exposome: How Far Have We Gone?
Around two-thirds of chronic human disease is not explainable by genetics alone. The Lancet Commission on Pollution and Health estimates that 16% of global premature deaths are linked to pollution. Additionally, it is now thought that humankind has surpassed the safe planetary operating space for introducing human-made chemicals into the Earth System. Direct and indirect exposure to a myriad of chemicals, known and unknown, poses a significant threat to biodiversity and human health, from vaccine efficacy to the rise of antimicrobial resistance as well as autoimmune diseases, and mental health disorders. The exposome chemical space remains largely uncharted due to the sheer number of possible chemical structures, estimated at over 10^60 unique forms. Conventional methods have cataloged only a fraction of the exposome, overlooking transformation products and often yielding uncertain results. In this perspective we have reviewed the latest efforts in mapping the exposome chemical space and its sub-spaces. We also provide our view on how the integration of data driven approaches might be able to bridge the identified gaps.
- Open Access
- 22 January 2024
- Published by American Chemical Society (ACS) in ChemRxiv
Exploring the Chemical Subspace of RPLC: a Data Driven Approach
The chemical space is comprised of a vast number of possible structures, of which an unknown portion comprises the human and environmental exposome. Such samples are frequently analyzed using non-targeted analysis via liquid chromatography (LC) coupled to high-resolution mass spectrometry often employing a reversed phase (RP) column. However, prior to analysis, the contents of these samples are unknown and could be comprised of thousands of known and unknown chemical constituents. Moreover, it is unknown which part of the chemical space is sufficiently retained and eluted using RPLC. Therefore, we present a generic framework that uses a data driven approach to predict whether molecules fall "inside", "maybe" inside, or "outside" of the RPLC subspace. Firstly, three retention index random forest (RF) regression models were constructed that showed that molecular fingerprints are able to predict RPLC retention behavior. Secondly, these models were used to setup the dataset for building a RPLC RF classification model. The RPLC classification model was able to correctly predict whether a chemical belonged to the RPLC subspace with an accuracy of 92% for the testing set. Finally, applying this model to the 91737 small molecules (i.e., <=1000 Da) in NORMAN SusDat showed that 19.1% fall "outside" of the RPLC subspace. Knowing which chemicals are outside of the RPLC subspace can assist in reducing potential candidates for library searching and avoid screening for chemicals that will not be present in RPLC data.
- 22 January 2024
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessExploring the Chemical Subspace of RPLC: a Data Driven Approach
The chemical space is comprised of a vast number of possible structures, of which an unknown portion comprises the human and environmental exposome. Such samples are frequently analyzed using non-targeted analysis via liquid chromatography (LC) coupled to high-resolution mass spectrometry often employing a reversed phase (RP) column. However, prior to analysis, the contents of these samples are unknown and could be comprised of thousands of known and unknown chemical constituents. Moreover, it is unknown which part of the chemical space is sufficiently retained and eluted using RPLC. Therefore, we present a generic framework that uses a data driven approach to predict whether molecules fall "inside", "maybe" inside, or "outside" of the RPLC subspace. Firstly, three retention index random forest (RF) regression models were constructed that showed that molecular fingerprints are able to predict RPLC retention behavior. Secondly, these models were used to setup the dataset for building a RPLC RF classification model. The RPLC classification model was able to correctly predict whether a chemical belonged to the RPLC subspace with an accuracy of 92% for the testing set. Finally, applying this model to the 91737 small molecules (i.e., <=1000 Da) in NORMAN SusDat showed that 19.1% fall "outside" of the RPLC subspace. Knowing which chemicals are outside of the RPLC subspace can assist in reducing potential candidates for library searching and avoid screening for chemicals that will not be present in RPLC data.
- Open Access
- 7 August 2023
- Published by American Chemical Society (ACS) in Analytical Chemistry
- Vol. 95 (33) , 12247-12255
Cumulative Neutral Loss Model for Fragment Deconvolution in Electrospray Ionization High-Resolution Mass Spectrometry Data
Clean high-resolution mass spectra (HRMS) are essential to a successful structural elucidation of an unknown feature during nontarget analysis (NTA) workflows. This is a crucial step, particularly for the spectra generated during data-independent acquisition or during direct infusion experiments. The most commonly available tools only take advantage of the time domain for spectral cleanup. Here, we present an algorithm that combines the time domain and mass domain information to perform spectral deconvolution. The algorithm employs a probability-based cumulative neutral loss (CNL) model for fragment deconvolution. The optimized model, with a mass tolerance of 0.005 Da and a scoreCNL threshold of 0.00, was able to achieve a true positive rate (TPr) of 95.0%, a false discovery rate (FDr) of 20.6%, and a reduction rate of 35.4%. Additionally, the CNL model was extensively tested on real samples containing predominantly pesticides at different concentration levels and with matrix effects. Overall, the model was able to obtain a TPr above 88.8% with FD rates between 33 and 79% and reduction rates between 9 and 45%. Finally, the CNL model was compared with the retention time difference method and peak shape correlation analysis, showing that a combination of correlation analysis and the CNL model was the most effective for fragment deconvolution, obtaining a TPr of 84.7%, an FDr of 54.4%, and a reduction rate of 51.0%.
- 7 August 2023
- Published by American Chemical Society (ACS) in Analytical Chemistry
- Vol. 95 (33) , 12247-12255
Open AccessCumulative Neutral Loss Model for Fragment Deconvolution in Electrospray Ionization High-Resolution Mass Spectrometry Data
Clean high-resolution mass spectra (HRMS) are essential to a successful structural elucidation of an unknown feature during nontarget analysis (NTA) workflows. This is a crucial step, particularly for the spectra generated during data-independent acquisition or during direct infusion experiments. The most commonly available tools only take advantage of the time domain for spectral cleanup. Here, we present an algorithm that combines the time domain and mass domain information to perform spectral deconvolution. The algorithm employs a probability-based cumulative neutral loss (CNL) model for fragment deconvolution. The optimized model, with a mass tolerance of 0.005 Da and a scoreCNL threshold of 0.00, was able to achieve a true positive rate (TPr) of 95.0%, a false discovery rate (FDr) of 20.6%, and a reduction rate of 35.4%. Additionally, the CNL model was extensively tested on real samples containing predominantly pesticides at different concentration levels and with matrix effects. Overall, the model was able to obtain a TPr above 88.8% with FD rates between 33 and 79% and reduction rates between 9 and 45%. Finally, the CNL model was compared with the retention time difference method and peak shape correlation analysis, showing that a combination of correlation analysis and the CNL model was the most effective for fragment deconvolution, obtaining a TPr of 84.7%, an FDr of 54.4%, and a reduction rate of 51.0%.
- Open Access
- 1 March 2023
- Published by American Chemical Society (ACS) in ChemRxiv
Cumulative Neutral Loss Model for Fragment Deconvolution in Electrospray Ionization High-Resolution Mass Spectrometry Data
Fragment deconvolution is a crucial step during componentization of non-targeted analysis (NTA) high-resolution mass spectrometry (HRMS) data, aiming to filter out false positive (FP) signals that do not belong to the component. Moreover, inclusion of FP fragments could lead to, for example, wrong identification further down the workflow. Commonly used methods for deconvolution of fragment signals rely on the presence of a time domain (e.g., peak apex retention time difference and correlation analysis). However, when there is no or insufficient MS2 information in the time domain, these methods are unusable and only the mass domain remains. A probability based cumulative neutral loss (CNL) model for fragment deconvolution using the mass domain information was thus developed to allow deconvolution for such cases. The optimized model, with a mass tolerance of 0.005 Da and a CNL score threshold of -0.95, was able to achieve true positive rate (TPr) of 95.0%, a false discovery rate (FDr) of 25.6%, and a reduction rate of 39.9%. Additionally, the CNL model was extensively tested on real samples containing predominantly pesticides at different concentration levels and with matrix effects. Overall, the model was able to obtain a TPr above 95% with FD rates between 45% and 77% and reduction rates between 10% and 24%. Finally, the CNL model was compared with the retention time difference method and peak shape correlation analysis, showing that a combination of correlation analysis and the CNL model was the most effective for fragment deconvolution, obtaining a TPr of 93.1%, a FDr of 57.2%, and a reduction rate of 42.6%.
- 1 March 2023
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessCumulative Neutral Loss Model for Fragment Deconvolution in Electrospray Ionization High-Resolution Mass Spectrometry Data
Fragment deconvolution is a crucial step during componentization of non-targeted analysis (NTA) high-resolution mass spectrometry (HRMS) data, aiming to filter out false positive (FP) signals that do not belong to the component. Moreover, inclusion of FP fragments could lead to, for example, wrong identification further down the workflow. Commonly used methods for deconvolution of fragment signals rely on the presence of a time domain (e.g., peak apex retention time difference and correlation analysis). However, when there is no or insufficient MS2 information in the time domain, these methods are unusable and only the mass domain remains. A probability based cumulative neutral loss (CNL) model for fragment deconvolution using the mass domain information was thus developed to allow deconvolution for such cases. The optimized model, with a mass tolerance of 0.005 Da and a CNL score threshold of -0.95, was able to achieve true positive rate (TPr) of 95.0%, a false discovery rate (FDr) of 25.6%, and a reduction rate of 39.9%. Additionally, the CNL model was extensively tested on real samples containing predominantly pesticides at different concentration levels and with matrix effects. Overall, the model was able to obtain a TPr above 95% with FD rates between 45% and 77% and reduction rates between 10% and 24%. Finally, the CNL model was compared with the retention time difference method and peak shape correlation analysis, showing that a combination of correlation analysis and the CNL model was the most effective for fragment deconvolution, obtaining a TPr of 93.1%, a FDr of 57.2%, and a reduction rate of 42.6%.