Screening unknown novel psychoactive substances using GC–MS based machine learning

van Hout, 2018, Health and social problems associated with recent novel psychoactive substance (NPS) use amongst marginalised, nightlife and online users in six European countries, Int. J. Ment. Health Addict., 16, 480, 10.1007/s11469-017-9824-1 A. Peacock, R. Bruno, N. Gisev, L. Degenhardt, W. Hall, R. Sedefov, J. White, K. v Thomas, M. Farrell, P. Griffiths, New psychoactive substances: challenges for drug surveillance, control, and public health responses, The Lancet 394 (2019) 1668–1684. 10.1016/S0140-6736(19)32231-7. Drummer, 2019, Fatalities caused by novel opioids: a review, Forensic Sci. Res., 4, 95, 10.1080/20961790.2018.1460063 Graddy, 2018, New and emerging illicit psychoactive substances, Med. Clin. North Am., 102, 697, 10.1016/j.mcna.2018.02.010 Underwood, 1979, A new drug war, Science, 347, 469 A. Shafi, A.J. Berry, H. Sumnall, D.M. Wood, D.K. Tracy, New psychoactive substances: a review and updates, Ther. Adv. Psychopharmacol. 10 (2020) 2045125320967197. 10.1177/2045125320967197. L.S.A. Pereira, F.L.C. Lisboa, J. Coelho Neto, F.N. Valladão, M.M. Sena, Screening method for rapid classification of psychoactive substances in illicit tablets using mid infrared spectroscopy and PLS-DA, Forensic Sci. Int. 288 (2018) 227–235. 10.1016/j.forsciint.2018.05.001. H.Z. Shirley Lee, H.B. Koh, S. Tan, B.J. Goh, R. Lim, J.L.W. Lim, T.W. Angeline Yap, Identification of closely related new psychoactive substances (NPS) using solid deposition gas-chromatography infra-red detection (GC–IRD) spectroscopy, Forensic Sci. Int. 299 (2019) 21–33. 10.1016/j.forsciint.2019.03.025. Omar, 2019, Identification of new psychoactive substances (NPS) by Raman spectroscopy, J. Raman Spectrosc., 50, 41, 10.1002/jrs.5496 Muhamadali, 2019, Rapid Detection and Quantification of Novel Psychoactive Substances (NPS) Using Raman Spectroscopy and Surface-Enhanced Raman Scattering, Front. Chem., 7, 10.3389/fchem.2019.00412 Guirguis, 2017, Identification of new psychoactive substances (NPS) using handheld Raman spectroscopy employing both 785 and 1064nm laser sources, Forensic Sci. Int., 273, 113, 10.1016/j.forsciint.2017.01.027 I. Jang, J.U. Lee, J.M. Lee, B.H. Kim, B. Moon, J. Hong, H. bin Oh, LC-MS/MS Software for screening unknown erectile dysfunction drugs and analogues: artificial neural network classification, peak-count scoring, simple similarity search, and hybrid similarity search algorithms, Anal. Chem. 91 (2019) 9119–9128. 10.1021/acs.analchem.9b01643. S.Y. Lee, S.T. Lee, S. Suh, B.J. Ko, H. bin Oh, Revealing unknown controlled substances and new psychoactive substances using high-resolution LC–MS-MS machine learning models and the hybrid similarity search algorithm, J. Anal. Toxicol. 46 (2021) 732-742. 10.1093/jat/bkab098. Moorthy, 2020, Mass spectral similarity mapping applied to fentanyl analogs, Forensic Chem., 19, 10.1016/j.forc.2020.100237 Koshute, 2022, Machine learning model for detecting fentanyl analogs from mass spectra, Forensic Chem., 27, 10.1016/j.forc.2021.100379 Wang, 2021, Accurate prediction of terahertz spectra of molecular crystals of fentanyl and its analogs, Sci. Rep., 11 Bonetti, 2022, Utilization of machine learning for the differentiation of positional NPS Isomers with direct analysis in real time mass spectrometry, Anal. Chem., 94, 5029, 10.1021/acs.analchem.1c04985 Silverstein, 1962, Spectrometric identification of organic compounds, J. Chem. Educ., 39, 546, 10.1021/ed039p546 Samokhin, 2015, Evaluation of mass spectral library search algorithms implemented in commercial software, J. Mass Spectrom., 50, 820, 10.1002/jms.3591 A.S. Moorthy, W.E. Wallace, A.J. Kearsley, D. v. Tchekhovskoi, S.E. Stein, Combining fragment-ion and neutral-loss matching during mass spectral library searching: A new general purpose algorithm applicable to illicit drug identification, Anal. Chem. 89 (2017) 13261–13268. 10.1021/acs.analchem.7b03320. Skinnider, 2021, A deep generative model enables automated structure elucidation of novel psychoactive substances, Nat. Mach. Intell., 3, 973, 10.1038/s42256-021-00407-x Ji, 2020, Predicting a molecular fingerprint from an electron ionization mass spectrum with deep neural networks, Anal. Chem., 92, 8649, 10.1021/acs.analchem.0c01450 Nan, 2020, Investigation of fragmentation pathways of fentanyl analogues and novel synthetic opioids by electron ionization high-resolution mass spectrometry and electrospray ionization high-resolution tandem mass spectrometry, J. Am. Soc. Mass Spectrom., 31, 277, 10.1021/jasms.9b00112 Broséus, 2010, The differentiation of fibre- and drug type Cannabis seedlings by gas chromatography/mass spectrometry and chemometric tools, Forensic Sci. Int., 200, 87, 10.1016/j.forsciint.2010.03.034 Scientific Working Group for the Analysis of Seized Drugs. SWGDRUG Mass Spectral Library. Version 3.11. URL https://www.swgdrug.org/ms.htm. Cayman Chemical (2020) Version CaymanSpectralLibrary_v09222020. URL https://www.caymanchem.com/forensics/publications/csl. German, 2014, Bath salts and synthetic cathinones: An emerging designer drug phenomenon, Life Sci., 97, 2, 10.1016/j.lfs.2013.07.023 Castaneto, 2014, Synthetic cannabinoids: Epidemiology, pharmacodynamics, and clinical implications, Drug Alcohol Depend., 144, 12, 10.1016/j.drugalcdep.2014.08.005 King, 2014, New phenethylamines in Europe, Drug Test Anal., 6, 808, 10.1002/dta.1570 Elliott, 2011, Current awareness of piperazines: pharmacology and toxicology, Drug Test Anal., 3, 430, 10.1002/dta.307 Araújo, 2015, The hallucinogenic world of tryptamines: an updated review, Arch. Toxicol., 89, 1151, 10.1007/s00204-015-1513-x Armenian, 2018, Fentanyl, fentanyl analogs and novel synthetic opioids: A comprehensive review, Neuropharmacology, 134, 121, 10.1016/j.neuropharm.2017.10.016 Skarysz, 2018, Convolutional neural networks for automated targeted analysis of raw gas chromatography-mass spectrometry data, 1 O.I. Abiodun, A. Jantan, A.E. Omolara, K.V. Dada, N.A. Mohamed, H. Arshad, State-of-the-art in artificial neural network applications: A survey, Heliyon 4 (2018) e00938. 10.1016/j.heliyon.2018.e00938. Li, 2021, A survey of convolutional neural networks: Analysis, applications, and prospects, IEEE Trans. Neural. Netw. Learn Syst., 1, 10.1109/TNNLS.2021.3132836 Lemaître, 2017, Imbalanced-learn: A python toolbox to tackle the curse of imbalanced datasets in machine learning, J. Mach. Learn. Res., 18, 559 Kranenburg, 2020, Revealing hidden information in GC–MS spectra from isomeric drugs: Chemometrics based identification from 15 eV and 70 eV EI mass spectra, Forensic Chem., 18, 10.1016/j.forc.2020.100225 Fawcett, 2006, An introduction to ROC analysis, Pattern Recognit. Lett., 27, 861, 10.1016/j.patrec.2005.10.010