We are presenting the results obtained by computing different toxicity indices for some of the newest JWH synthetic cannabinoids, by using (Q)SAR models, ADME(T) predictions, simulations of NMR spectral techniques and other different computational dedicated software packages and forensic analytical tools. We have examined the main physical and chemical properties and evaluated the behavioral neurotoxicity and pharmacokinetic profile of 16 aminoalkylindole class-derived synthetic cannabinoids JWH as compared to the Delta-9-tetrahydrocannabinol (Δ9-THC), which was chosen as a standard compound. For this purpose, the geometries of the molecules have been optimized by using the AM1 semi-empirical quantum method. The conclusions of a comparative analysis of the toxicities of synthetic and natural cannabinoids are presented.

We are presenting a convolutional neural network (CNN) application recognizing the class identity of synthetic cannabinoids based on their Attenuated Total Reflection-Fourier Transform Infrared (ATR-FTIR) spectra. The results indicate that this CNN system can be efficiently used to distinguish JWH synthetic cannabinoids from other substances of forensic interest, but also from other types of synthetic cannabinoids. One of the main advantages of the system is that it can also operate on mobile ATR-FTIR spectrometers used in field operations.

An Artificial Neural Networks (ANN) model identifying JWH Synthetic Cannabinoids, that we have developed based on a combination of topological, 3D-MoRSE (Molecule Representation of Structure based on Electron diffraction) and ADMET (Absorption, Distribution, Metabolism, Excretion and Toxicity) molecular descriptors, is described and analyzed. The validation results indicate that this computerized system has a very high potential for efficiently predicting the class membership of JWH and discriminating them from a large variety of (non-JWH) substances of forensic interest.

This paper presents the alternative training strategies we tested for an Artificial Neural Network (ANN) designed to detect JWH synthetic cannabinoids. In order to increase the model performance in terms of output sensitivity, we used the Neural Designer data science and machine learning platform combined with the programming language Python. We performed a comparative analysis of several optimization algorithms, error parameters and regularization methods. Finally, we performed a new goodness-of-fit analysis between the testing samples in the data set and the corresponding ANN outputs in order to investigate their sensitivity. The effectiveness of the new methods combined with the optimization algorithms is discussed.

No abstract