Deep Learning-Enabled MS/MS Spectrum Prediction Facilitates Automated Identification Of Novel Psychoactive Substances
- PMID: 38048435
- PMCID: PMC10733899
- DOI: 10.1021/acs.analchem.3c02413
Deep Learning-Enabled MS/MS Spectrum Prediction Facilitates Automated Identification Of Novel Psychoactive Substances
Abstract
The market for illicit drugs has been reshaped by the emergence of more than 1100 new psychoactive substances (NPS) over the past decade, posing a major challenge to the forensic and toxicological laboratories tasked with detecting and identifying them. Tandem mass spectrometry (MS/MS) is the primary method used to screen for NPS within seized materials or biological samples. The most contemporary workflows necessitate labor-intensive and expensive MS/MS reference standards, which may not be available for recently emerged NPS on the illicit market. Here, we present NPS-MS, a deep learning method capable of accurately predicting the MS/MS spectra of known and hypothesized NPS from their chemical structures alone. NPS-MS is trained by transfer learning from a generic MS/MS prediction model on a large data set of MS/MS spectra. We show that this approach enables a more accurate identification of NPS from experimentally acquired MS/MS spectra than any existing method. We demonstrate the application of NPS-MS to identify a novel derivative of phencyclidine (PCP) within an unknown powder seized in Denmark without the use of any reference standards. We anticipate that NPS-MS will allow forensic laboratories to identify more rapidly both known and newly emerging NPS. NPS-MS is available as a web server at https://nps-ms.ca/, which provides MS/MS spectra prediction capabilities for given NPS compounds. Additionally, it offers MS/MS spectra identification against a vast database comprising approximately 8.7 million predicted NPS compounds from DarkNPS and 24.5 million predicted ESI-QToF-MS/MS spectra for these compounds.
Conflict of interest statement
The authors declare no competing financial interest.
Figures
![Figure 1](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/10733899/bin/ac3c02413_0001.gif)
![Figure 2](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/10733899/bin/ac3c02413_0002.gif)
![Figure 3](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/10733899/bin/ac3c02413_0003.gif)
Similar articles
-
PS2MS: A Deep Learning-Based Prediction System for Identifying New Psychoactive Substances Using Mass Spectrometry.Anal Chem. 2024 Mar 26;96(12):4835-4844. doi: 10.1021/acs.analchem.3c05019. Epub 2024 Mar 15. Anal Chem. 2024. PMID: 38488022 Free PMC article.
-
Application of a simultaneous screening method for the detection of new psychoactive substances in various matrix samples using liquid chromatography/electrospray ionization tandem mass spectrometry and liquid chromatography/quadrupole time-of-flight mass spectrometry.Rapid Commun Mass Spectrom. 2021 May 30;35(10):e9067. doi: 10.1002/rcm.9067. Rapid Commun Mass Spectrom. 2021. PMID: 33656207
-
Simultaneous determination of new psychoactive substances and illicit drugs in sewage: Potential of micro-liquid chromatography tandem mass spectrometry in wastewater-based epidemiology.J Chromatogr A. 2019 Sep 27;1602:300-309. doi: 10.1016/j.chroma.2019.05.051. Epub 2019 May 30. J Chromatogr A. 2019. PMID: 31171357
-
The targeted analysis of New Psychoactive Substances in oral fluid through chromatographic-spectrometric methods: review of recent findings.Eur Rev Med Pharmacol Sci. 2022 Feb;26(3):750-754. doi: 10.26355/eurrev_202202_27982. Eur Rev Med Pharmacol Sci. 2022. PMID: 35179740 Review.
-
Recent advances in analysis of new psychoactive substances by means of liquid chromatography coupled with low-resolution tandem mass spectrometry.Anal Bioanal Chem. 2024 Jan;416(1):107-124. doi: 10.1007/s00216-023-05057-z. Epub 2023 Nov 25. Anal Bioanal Chem. 2024. PMID: 38001373 Review.
Cited by
-
Accurate Prediction of 1H NMR Chemical Shifts of Small Molecules Using Machine Learning.Metabolites. 2024 May 19;14(5):290. doi: 10.3390/metabo14050290. Metabolites. 2024. PMID: 38786767 Free PMC article.
-
Target and Nontarget Screening to Support Capacity Scaling for Substance Use Assessment through a Statewide Wastewater Surveillance Network in New York.Environ Sci Technol. 2024 May 14;58(19):8518-8530. doi: 10.1021/acs.est.4c01251. Epub 2024 May 1. Environ Sci Technol. 2024. PMID: 38693060 Free PMC article.
-
PS2MS: A Deep Learning-Based Prediction System for Identifying New Psychoactive Substances Using Mass Spectrometry.Anal Chem. 2024 Mar 26;96(12):4835-4844. doi: 10.1021/acs.analchem.3c05019. Epub 2024 Mar 15. Anal Chem. 2024. PMID: 38488022 Free PMC article.
References
-
- Varì M. R.; Mannocchi G.; Tittarelli R.; Campanozzi L. L.; Nittari G.; Feola A.; Umani Ronchi F.; Ricci G. New Psychoactive Substances: Evolution in the Exchange of Information and Innovative Legal Responses in the European Union. Int. J. Environ. Res. Public Health 2020, 17 (22), 8704.10.3390/ijerph17228704. - DOI - PMC - PubMed
Publication types
MeSH terms
Substances
LinkOut - more resources
Full Text Sources
Miscellaneous