International Scholarly Research Network ISRN Chromatography Volume 2012, Article ID 838432, 9 pages doi:10.5402/2012/838432 Research Article A QSRR Modeling of Hazardous Psychoactive Designer Drugs Using GA-PlS and L-M ANN Hamzeh Karimi,1 Hadi Noorizadeh,2 and Abbas Farmany2 1 Faculty of Sciences, Islamic Azad University, South Tehran Branch, Tehran, Iran 2 Faculty of Science, Islamic Azad University, Ilam Branch, Ilam, Iran Correspondence should be addressed to Hamzeh Karimi, h [email protected] Received 29 January 2012; Accepted 5 March 2012 Academic Editors: I. Brondz and D. Gavril Copyright © 2012 Hamzeh Karimi et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. The hazardous psychoactive designer drugs are compounds in which part of the molecular structure of a stimulant or narcotic has been modified. A quantitative structure-retention relationship (QSRR) study based on a Levenberg-Marquardt artificial neural network (L-M ANN) was carried out for the prediction of the capacity factor (k) of hazardous psychoactive designer drugs that contain Tryptamine, Phenylethylamine and Piperazine. The genetic algorithm-partial least squares (GA-PLS) method was used as a variable selection tool. A PLS method was used to select the best descriptors and the selected descriptors were used as input neurons in neural network model. For choosing the best predictive model from among comparable models, square correlation coefficient (R2) for the whole set is suggested to be a good criterion. Finally, to improve the results, structure-retention relationships were followed by nonlinear approach using artificial neural networks and consequently better results were obtained. Also this demonstrates the advantages of L-M ANN. This is the first research on the QSRR of the designer drugs using the GA-PLS and L-M ANN. 1. Introduction rapid onset of affect (1 to 4 minutes) and a short duration of action (generally 30–90 minutes, and no more than a Designer drugs (sometimes also referred to as club drugs) few hours). They are sold as tablets or capsules, and often are a particular class of synthetic drugs most often associated produce feelings of stimulation and euphoria, a sense of well- with underground youth dance parties called raves, wherein being, and various sensory distortions. Higher doses can lead participants listen to techno music and experiment with to paranoia, hallucinations, violent or otherwise irrational psychoactive substances. These drugs have been created by behavior, and fatal overdosing. Some designer drugs are changing the molecular structure of other existing drugs, to depressants, so they are used when an individual is coming create something new with similar pharmacological effects, down from a stimulant like Ecstasy. hence, the name designer drug. They are plentiful, cheap, In general, the physical symptoms common among users and dangerous. For example, the pharmaceutical drug am- of psychoactive designer drugs include hypertension, in- phetamine (which was originally created as an anesthetic) creased heart rate, clenched teeth, blurred vision, uncon- has been modified to be 80 to 1,000 times more potent than trolled tremors, anorexia, nausea and vomiting, impaired heroin. Prepared by underground, amateur chemists known speech, seizures, permanent brain damage, and death. as cookers, designer drugs can be injected, smoked, snorted, Some common psychological side effects include con- or ingested. These synthetic drugs can be easily obtained on fusion, irritability, severe anxiety, extreme emotional, sensi- the street or on the Internet. tivity, depression, amnesia, violent behavior, insomnia, and Once changed, they become known by a variety of street hallucinations [1–4]. names, for example, XTC, Ecstasy, Adam, Lover’s Speed, As shown in Figure 1, these hazardous psychoactive Special K, Fantasy, and Nature’s Quaalude. Most have a designer drugs have I, II, and III basic skeletons. Type I 2 ISRN Chromatography NH2 NH2 N H I II N N H III Figure 1: Structures of basic skeletons. I: phenylethylamine; II: tryptamine; III: phenylpiperazine. structure is phenylethylamine-(PEA-) related compounds system partition is of major importance in physicochemical, with structural similarities to both amphetamine and the environmental, and life sciences. Chemical distribution psychedelic PEA, mescaline. Type II structure is trypta- phenomena depend not only on molecular structure but also mines-(T-) related compounds with structural similarities to on the properties of the system in question [12]. Quantitative hallucinogenic psilocin. Type III structure is phenylpiper- structure-retention relationship (QSRR) techniques based azine-(PP-) related compounds with structural similarities on different molecular descriptors have been successfully to stimulus effects 1-(3-trifluoromethylphenyl)piperazine used to model organic chemicals properties [13]. A number (TFMPP). of reports, deal with QSRR calculation of several com- Most of the best known research chemicals are structural pounds, have been published in the literature [14–16]. The analogues of tryptamines or phenethylamines, but there are QSRR models apply to partial least squares (PLSs) methods also many other completely unrelated chemicals which can often combined with genetic algorithms (GAs) for feature be considered as part of the group. It is very difficult to selection [17–19]. Because of the complexity of relationships determine psychoactivity or other pharmaceutical properties between the property of molecules and structures, nonlinear of these compounds based strictly upon structural exami- models are also used to model the structure-property rela- nation. Many of the substances have common effects whilst tionships. Levenberg-Marquardt artificial neural network (L- structurally different and vice versa. As a result of no real M ANN) is nonparametric nonlinear modeling technique official naming for some of these compounds, as well as that has attracted increasing interest. In the present study, regional naming, this can all lead to (and is anecdotally GA-PLS and L-M ANN were employed to generate QSRR known to have led to) potentially hazardous mix-ups for models that correlate the structure of hazardous psychoactive users. designer drugs, with observed k. This is the first research on In order to prevent damage resulting from drug abuse, the QSRR of the designer drugs using the GA-PLS and L-M it is necessary to analyze the active ingredients, publicize ANN. the risks of these compounds, and, if illegal, quickly act to regulate them. For that, the library required the screening 2. Computational of these compounds, while there were a few of data for gas chromatography-mass spectrometry (GC/MS) [5–7]and 2.1. Data Set. Capacity factor (k) of 104 hazardous psy- liquid chromatography-mass spectrometry (LC/MS) [8, 9] choactive designer drugs taken from the literature [20]is and there was little data on hazardous psychoactive designer presented in Table 1. There are 51 types of PEA compounds drugs. Also, there were few library systems for the liquid with a type I structure, where these have a PEA skeleton such chromatography with photodiode array spectrophotometry as 3,4,5-trimethoxyamphetamine (TMA), 2,5-dimethoxy- (LC/PDA) [10, 11]. In order to eliminate the impact of the 4-ethylthiophenethylamine (2C-T-2), 2,5-dimethoxy-4-pro- dead volume of the chromatographic system, the capacity pylthiophenethylamine (2C-T-7), and 4-bromo-2,5-dime- factor (k ) was calculated according to thoxyphenethylamine (2C-B). There are 32 types of T t − t compounds with a type II structure, where these have a k = ( r 0) t ,(1)T skeleton such as bis(methylethyl)[2-(5-methoxyindol- 0 3-yl)ethyl]amine (5-MeO-DIPT) and 1-indol-3-ylprop-2- where tr is the retention time of the designer drugs, and t0 ylamine (AMT), and there are 21 types of PP compounds is column void volume time of a nonretained compound with a type III structure, where these have a piperazine or the dead time. It is known that the capacity factor (k) skeleton such as 1-(3-chlorophenyl)piperazine (3CPP), 1-(4- of a substance is related to the partition process, adsorption methoxyphenyl)piperazine (4MPP), and TFMPP. These are process, or both. tested using LC/PDA and GC/electron ionization (EI)/MS, Using chemometrics tools to predict drugs and chemical and a library is created based on the analysis data obtained. tissue distribution, membrane permeability or biphasic The data registered into the library consisted of the capacity ISRN Chromatography 3 Table 1: The data set, structure, and the corresponding observed k values. k No. Name Structure EXP Calibration set 1 N-[2-(5-Methoxyindol-3-yl)ethyl]acetamide (Melatonin) C13H16N2O2 0.09 2 2-Amino-3-(5- hydroxyindolin-3-yl)propanoic acid,5-hydroxy-tryptophan (5-HO-TP) C11H12N2O3 0.31 3 3-Methoxy-tyramine (3-MT) C9H13NO2 0.39 4 3-(2-Aminoethyl)indol-5-ol (5-HO-T) C10H12N2O0.46 5 (Dimethylaminoethyl)- 1H-indol-5-ol (Bufotenin) C12H16N2O0.50 6 p-Methoxyphen ethylamine C9H13NO 0.53 7 2-(3,4-Dimethoxyphenyl)ethylamine (DMPEA) C10H15NO2 0.59 8 1-Methyl-3,4-dihydrobeta-carbolin-7-ol (Hannalol) C12H12N2O0.68 9 2-(3,4-Dimethoxyphenyl)-N-methylethylamine (N-Me-DMPEA) C11H17NO2 0.69 10 1-Methylbeta-carbolin-7-ol (Harmol) C12H10N2O0.71 11 2-(Methylamino)-1-phenylpropan-1-one (Methcathinone) C10H12NO 0.85 12 1-(p-Fluorophenyl)piperazine (4FPP) C10H13FN2 0.87 13 2-Phenylethylamine