Medicinal Chemistry Research

, Volume 21, Issue 9, pp 2680–2688 | Cite as

Application of GA–KPLS and L–M ANN calculations for the prediction of the capacity factor of hazardous psychoactive designer drugs

  • Hadi NoorizadehEmail author
  • Abbas Farmany
  • Mehrab Noorizadeh
Original Research


The hazardous psychoactive designer drugs are compounds in which part of the molecular structure of a stimulant or narcotic has been modified. Genetic algorithm and kernel partial least square (GA–KPLS) and Levenberg–Marquardt artificial neural network (L–M ANN) techniques were used to investigate the correlation between capacity factor (k′) and descriptors for 104 hazardous psychoactive designer drugs. These drugs are containing Tryptamine, Phenylethylamine, and Piperazine. The both methods resulted in accurate prediction whereas more accurate results were obtained by L–M ANN model. The best model obtained from L–M ANN showed a good R 2 value (determination coefficient between observed and predicted values) for all compounds, which was superior to GA–KPLS models. The stability and prediction ability of these models were validated using leave-group-out cross-validation, external test set, and Y-randomization techniques. This is the first research on the quantitative structure–retention relationship (QSRR) of the designer drugs using the GA–KPLS and L–M ANN.


Hazardous psychoactive designer drugs Tryptamine Phenylethylamine Piperazine QSRR Genetic algorithm–kernel partial least square Levenberg–Marquardt artificial neural network 


  1. Baczek T, Buciński A, Ivanov AP, Kaliszan R (2004) Artificial neural network analysis for evaluation of peptide MS/MS spectra in proteomics. Anal Chem 76(6):1726–1732PubMedCrossRefGoogle Scholar
  2. Ballabio D, Vasighi M, Consonni V, Kompany-Zareh M (2011) Genetic algorithms for architecture optimisation of counter-propagation artificial neural networks. Chemom Intell Lab Syst 105:56–64CrossRefGoogle Scholar
  3. Brandt SD, Freeman S, Fleet IA, McGagh P, Alder JF (2005) Analytical chemistry of synthetic routes to psychoactive tryptamines. Part II. Characterisation of the Speeter and Anthony synthetic route to N,N-dialkylated tryptamines using GC-EI-ITMS. Analyst 130:330–338PubMedCrossRefGoogle Scholar
  4. Buciński A, Wnuk M, Goryński K, Giza A, Kochańczyk J, Nowaczyk A, Bączek T, Nasal A (2009) Artificial neural networks analysis used to evaluate the molecular interactions between selected drugs and human α1-acid glycoprotein. J Pharm Biomed Anal 50:591–596PubMedCrossRefGoogle Scholar
  5. Busam S, McNabb M, Wackwitz A, Senevirathna W, Beggah S, Meer JR, Wells M, Breuer U, Harms H (2007) Artificial neural network study of whole-cell bacterial bioreporter response determined using fluorescence flow cytometry. Anal Chem 79(23):9107–9114PubMedCrossRefGoogle Scholar
  6. Carta D, Villanova L, Costacurta S, Patelli A, Poli I, Vezzu S, Scopece P, Lisi F, Smith-Miles K, Hyndman R, Hill AJ, Paolo F (2011) A new method for optimizing coating properties based on an evolutionary algorithm approach. Anal Chem 83(16):6373–6380PubMedCrossRefGoogle Scholar
  7. Chen BH, Liu JT, Chen WX, Chen HM, Lin CH (2008) A general approach to the screening and confirmation of tryptamines and phenethylamines by mass spectral fragmentation. Talanta 74:512–517PubMedCrossRefGoogle Scholar
  8. Devos O, Duponchel L (2011) Parallel genetic algorithm co-optimization of spectral pre-processing and wavelength selection for PLS regression. Chemom Intell Lab Syst 107:50–58CrossRefGoogle Scholar
  9. Doi K, Miyazawa M, Fujii H, Kojima T (2006) The analysis of the chemical drugs among structural isomer. Yakugaku Zasshi 126:815–823PubMedCrossRefGoogle Scholar
  10. Flieger J (2010) Application of perfluorinated acids as ion-pairing reagents for reversed-phase chromatography and retention-hydrophobicity relationships studies of selected β-blockers. J Chromatogr A 1217:540–549PubMedCrossRefGoogle Scholar
  11. García-Reiriz A, Damiani PC, Olivieri AC (2010) Residual bilinearization combined with kernel-unfolded partial least-squares: a new technique for processing non-linear second-order data achieving the second-order advantage. Chemom Intell Lab Syst 100:127–135CrossRefGoogle Scholar
  12. Gottardo R, Bortolotti F, Paoil G, Pascali JP (2007) Hair analysis for illicit drugs by using capillary zone electrophoresis-electrospray ionization-ion trap mass, spectrometry. J Chromatogr A 1159:185–189PubMedCrossRefGoogle Scholar
  13. Hao M, Li Y, Wang Y, Zhang Sh (2011) Prediction of P2Y12 antagonists using a novel genetic algorithm-support vector machine coupled approach. Anal Chim Acta 690:53–63PubMedCrossRefGoogle Scholar
  14. Jia RD, Mao Zh, Chang Y, Zhang Sh (2010) Kernel partial robust M-regression as a flexible robust nonlinear modeling technique. Chemom Intell Lab Syst 100:91–98CrossRefGoogle Scholar
  15. Kaliszan R (2007) QSRR: quantitative structure-(chromatographic) retention relationships. Chem Rev 107(7):3212–3246PubMedCrossRefGoogle Scholar
  16. Kauppila TJ, Flink A, Haapala M, Laakkonen UM, Aalberg L, Ketola RA, Kostiainen R (2011) Desorption atmospheric pressure photoionization–mass spectrometry in routine analysis of confiscated drugs. Forensic Sci Int 210:206–212PubMedCrossRefGoogle Scholar
  17. Kim K, Lee JM, Lee IB (2005) A novel multivariate regression approach based on kernel partial least squares with orthogonal signal correction. Chemom Intell Lab Syst 79:22–30CrossRefGoogle Scholar
  18. Klopman G, Zhu H (2005) Recent methodologies for the estimation of n-octanol/water partition coefficients and their use in the prediction. Mini Rev Med Chem 5:127–133PubMedGoogle Scholar
  19. Lämmerhofer M (2010) Chiral recognition by enantioselective liquid chromatography: mechanisms and modern chiral stationary phases. J Chromatogr A 1217:814–856PubMedCrossRefGoogle Scholar
  20. Martins LF, Yagles M, Chung H, Wennig R (2006) Rapid and validated gas chromatography/negative ion chemical ionization-mass spectrometry assay including derivatisation with a novel chiral agent for the enantioselective quantification of amphetamine-type stimulants in hair. J Chromatogr B 842:98–105CrossRefGoogle Scholar
  21. Matsumoto T, Kikura-Hanajiri R, Kamakura H, Kawahara N, Goda Y (2006) Identification of N-methyl-4-(3,4-methylenedioxyphenyl)butan-2-amine, distributed as MBDB. J Health Sci 52:805–810CrossRefGoogle Scholar
  22. Noorizadeh H, Noorizadeh M (2011) QSRR-based estimation of the retention time of opiate and sedative drugs by comprehensive two-dimensional gas chromatography. Med Chem Res (in press)Google Scholar
  23. Noorizadeh H, Noorizadeh M, Mumtaz AS (2011) QSRR analysis of capacity factor of nanoparticle compounds. J Saudi Chem Soc (in press)Google Scholar
  24. Petritis K, Kangas LJ, Ferguson PL, Anderson GA, Pasa-Tolic L, Lipton MS, Auberry KJ, Strittmatter EF, Shen Y, Zhao R, Smith RD (2003) Use of artificial neural networks for the accurate prediction of peptide liquid chromatography elution times in proteome analyses. Anal Chem 75(5):1039–1048PubMedCrossRefGoogle Scholar
  25. Postma GJ, Krooshof PWT, Buydens LMC (2011) Opening the kernel of kernel partial least squares and support vector machines. Anal Chim Acta (in press)Google Scholar
  26. Put R, Vander Heyden Y (2007) Review on modeling aspect in reverse-phase liquid chromatographic quantitative structure retention relationship. Anal Chim Acta 602:164–1727PubMedCrossRefGoogle Scholar
  27. Reepmeyer JC, Woodruff JT, d’Avignon DA (2007) Structure elucidation of a novel analogue of sildenafil detected as an adulterant in an herbal dietary supplement. J Pharm Biomed Anal 43(5):1615–1621PubMedCrossRefGoogle Scholar
  28. Sauer Ch, Hoffmann K, Peters USFT (2011) Acute poisoning involving the pyrrolidinophenone-type designer drug 40-methyl-alpha-pyrrolidinohexanophenone (MPHP). Forensic Sci Int 208:20–25CrossRefGoogle Scholar
  29. Spratley TK, Hays PA, Geer LC, Cooper SD, McKibben TD (2005) Analytical profiles for five “designer” tryptamines. Microgram J 3:54–68Google Scholar
  30. Takahashi M, Nagashima M, Suzuki J, Seto T, Yasuda I, Yoshida T (2009) Creation and application of psychoactive designer drugs data library using liquid chromatography with photodiode array spectrophotometry detector and gas chromatography–mass spectrometry. Talanta 77:1245–1272PubMedCrossRefGoogle Scholar
  31. Todeschini R, Consonni V (2000) Handbook of molecular descriptors. Wiley-VCH, WeinheimCrossRefGoogle Scholar
  32. Todeschini R, Consonni V, Mauri A, Pavan M (2003) DRAGON-Software for the calculation of molecular descriptors. Version 3.0 for WindowsGoogle Scholar
  33. Vardakou I, Pistos C, Spiliopoulou Ch (2011) Drugs for youth via Internet and the example of mephedrone. Toxicol Lett 201:191–195PubMedCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2011

Authors and Affiliations

  • Hadi Noorizadeh
    • 1
    Email author
  • Abbas Farmany
    • 1
  • Mehrab Noorizadeh
    • 2
  1. 1.Department of Chemistry, Faculty of Sciences, Ilam BranchIslamic Azad UniversityIlamIran
  2. 2.Young Researchers Club, Ilam BranchIslamic Azad UniversityIlamIran

Personalised recommendations