Deep Learning-Enabled MS/MS Spectrum Prediction Facilitates Automated Identification Of Novel Psychoactive Substances
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Deep Learning-Enabled MS/MS Spectrum Prediction Facilitates Automated Identification Of Novel Psychoactive Substances. / Wang, Fei; Pasin, Daniel; Skinnider, Michael A.; Liigand, Jaanus; Kleis, Jan Niklas; Brown, David; Oler, Eponine; Sajed, Tanvir; Gautam, Vasuk; Harrison, Stephen; Greiner, Russell; Foster, Leonard J.; Dalsgaard, Petur Weihe; Wishart, David S.
In: Analytical Chemistry, Vol. 95, No. 50, 2023, p. 18326-18334.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Deep Learning-Enabled MS/MS Spectrum Prediction Facilitates Automated Identification Of Novel Psychoactive Substances
AU - Wang, Fei
AU - Pasin, Daniel
AU - Skinnider, Michael A.
AU - Liigand, Jaanus
AU - Kleis, Jan Niklas
AU - Brown, David
AU - Oler, Eponine
AU - Sajed, Tanvir
AU - Gautam, Vasuk
AU - Harrison, Stephen
AU - Greiner, Russell
AU - Foster, Leonard J.
AU - Dalsgaard, Petur Weihe
AU - Wishart, David S.
N1 - Publisher Copyright: © 2023 The Authors. Published by American Chemical Society.
PY - 2023
Y1 - 2023
N2 - 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.
AB - 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.
U2 - 10.1021/acs.analchem.3c02413
DO - 10.1021/acs.analchem.3c02413
M3 - Journal article
C2 - 38048435
AN - SCOPUS:85180094019
VL - 95
SP - 18326
EP - 18334
JO - Industrial And Engineering Chemistry Analytical Edition
JF - Industrial And Engineering Chemistry Analytical Edition
SN - 0003-2700
IS - 50
ER -
ID: 380204121