Cargando…

Machine Learning for Absolute Quantification of Unidentified Compounds in Non-Targeted LC/HRMS

LC/ESI/HRMS is increasingly employed for monitoring chemical pollutants in water samples, with non-targeted analysis becoming more common. Unfortunately, due to the lack of analytical standards, non-targeted analysis is mostly qualitative. To remedy this, models have been developed to evaluate the r...

Descripción completa

Detalles Bibliográficos
Autores principales: Palm, Emma, Kruve, Anneli
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8840743/
https://www.ncbi.nlm.nih.gov/pubmed/35164283
http://dx.doi.org/10.3390/molecules27031013
_version_ 1784650694916046848
author Palm, Emma
Kruve, Anneli
author_facet Palm, Emma
Kruve, Anneli
author_sort Palm, Emma
collection PubMed
description LC/ESI/HRMS is increasingly employed for monitoring chemical pollutants in water samples, with non-targeted analysis becoming more common. Unfortunately, due to the lack of analytical standards, non-targeted analysis is mostly qualitative. To remedy this, models have been developed to evaluate the response of compounds from their structure, which can then be used for quantification in non-targeted analysis. Still, these models rely on tentatively known structures while for most detected compounds, a list of structural candidates, or sometimes only exact mass and retention time are identified. In this study, a quantification approach was developed, where LC/ESI/HRMS descriptors are used for quantification of compounds even if the structure is unknown. The approach was developed based on 92 compounds analyzed in parallel in both positive and negative ESI mode with mobile phases at pH 2.7, 8.0, and 10.0. The developed approach was compared with two baseline approaches— one assuming equal response factors for all compounds and one using the response factor of the closest eluting standard. The former gave a mean prediction error of a factor of 29, while the latter gave a mean prediction error of a factor of 1300. In the machine learning-based quantification approach developed here, the corresponding prediction error was a factor of 10. Furthermore, the approach was validated by analyzing two blind samples containing 48 compounds spiked into tap water and ultrapure water. The obtained mean prediction error was lower than a factor of 6.0 for both samples. The errors were found to be comparable to approaches using structural information.
format Online
Article
Text
id pubmed-8840743
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-88407432022-02-13 Machine Learning for Absolute Quantification of Unidentified Compounds in Non-Targeted LC/HRMS Palm, Emma Kruve, Anneli Molecules Article LC/ESI/HRMS is increasingly employed for monitoring chemical pollutants in water samples, with non-targeted analysis becoming more common. Unfortunately, due to the lack of analytical standards, non-targeted analysis is mostly qualitative. To remedy this, models have been developed to evaluate the response of compounds from their structure, which can then be used for quantification in non-targeted analysis. Still, these models rely on tentatively known structures while for most detected compounds, a list of structural candidates, or sometimes only exact mass and retention time are identified. In this study, a quantification approach was developed, where LC/ESI/HRMS descriptors are used for quantification of compounds even if the structure is unknown. The approach was developed based on 92 compounds analyzed in parallel in both positive and negative ESI mode with mobile phases at pH 2.7, 8.0, and 10.0. The developed approach was compared with two baseline approaches— one assuming equal response factors for all compounds and one using the response factor of the closest eluting standard. The former gave a mean prediction error of a factor of 29, while the latter gave a mean prediction error of a factor of 1300. In the machine learning-based quantification approach developed here, the corresponding prediction error was a factor of 10. Furthermore, the approach was validated by analyzing two blind samples containing 48 compounds spiked into tap water and ultrapure water. The obtained mean prediction error was lower than a factor of 6.0 for both samples. The errors were found to be comparable to approaches using structural information. MDPI 2022-02-02 /pmc/articles/PMC8840743/ /pubmed/35164283 http://dx.doi.org/10.3390/molecules27031013 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Palm, Emma
Kruve, Anneli
Machine Learning for Absolute Quantification of Unidentified Compounds in Non-Targeted LC/HRMS
title Machine Learning for Absolute Quantification of Unidentified Compounds in Non-Targeted LC/HRMS
title_full Machine Learning for Absolute Quantification of Unidentified Compounds in Non-Targeted LC/HRMS
title_fullStr Machine Learning for Absolute Quantification of Unidentified Compounds in Non-Targeted LC/HRMS
title_full_unstemmed Machine Learning for Absolute Quantification of Unidentified Compounds in Non-Targeted LC/HRMS
title_short Machine Learning for Absolute Quantification of Unidentified Compounds in Non-Targeted LC/HRMS
title_sort machine learning for absolute quantification of unidentified compounds in non-targeted lc/hrms
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8840743/
https://www.ncbi.nlm.nih.gov/pubmed/35164283
http://dx.doi.org/10.3390/molecules27031013
work_keys_str_mv AT palmemma machinelearningforabsolutequantificationofunidentifiedcompoundsinnontargetedlchrms
AT kruveanneli machinelearningforabsolutequantificationofunidentifiedcompoundsinnontargetedlchrms