Artificial Neural Networks and the Study of the Psychoactivity of Cannabinoid Compounds

Abstract

Cannabinoid compounds have widely been employed because of its medicinal and psychotropic properties. These compounds are isolated from Cannabis sativa (or marijuana) and are used in several medical treatments, such as glaucoma, nausea associated to chemotherapy, pain and many other situations. More recently, its use as appetite stimulant has been indicated in patients with cachexia or AIDS. In this work, the influence of several molecular descriptors on the psychoactivity of 50 cannabinoid compounds is analyzed aiming one obtain a model able to predict the psychoactivity of new cannabinoids. For this purpose, initially, the selection of descriptors was carried out using the Fisher's weight, the correlation matrix among the calculated variables and principal component analysis. From these analyses, the following descriptors have been considered more relevant: E LUMO (energy of the lowest unoccupied molecular orbital), Log P (logarithm of the partition coefficient), VC4 (volume of the substituent at the C4 position) and LP1 (Lovasz-Pelikan index, a molecular branching index). To follow, two neural network models were used to construct a more adequate model for classifying new cannabinoid compounds. The first model employed was multi-layer perceptrons, with algorithm back-propagation, and the second model used was the Kohonen network. The results obtained from both networks were compared and showed that both techniques presented a high percentage of correctness to discriminate psychoactive and psychoinactive compounds. However, the Kohonen network was superior to multi-layer perceptrons.

Machine Learning Techniques and Drug Design

“…To plot the results and improve the physical interpretation, the Kohonen network was employed. Both MLP and SOM techniques showed reliable results and allowed good interpretation and visualization of the outcomes [24].…”

“…The problem of local convergence associated to the back propagation algorithm indicate the desirability of training with stochastic optimization methods, such as simulated evolution, which can provide convergence to globally optimal solutions [69,70]. An example that can be cited is the study of 50 cannabinoid compounds classified experimentally into psychoactives and psychoinactives [24]. In that study, the authors employed SOM and MLP techniques with the aim to predict the class of studied compounds (actives and inactives) and the obtained results indicated 96% of correct information.…”

“…A certain number of computational techniques have been found useful for the establishment of these relationships such as multiple linear regression (MLR) [11][12][13][14] and partial least squares (PLS) [15][16][17][18][19][20]. Recently, there is also a growing interest in the application of artificial neural networks (ANNs) and support vector machines (SVM) in the field of QSAR, as well as other molecular modeling approaches have been recognized as important tools in drug discovery [21][22][23][24][25][26][27][28][29]. The most common machine learning techniques (MLT) can be classified as supervised (such as Multilayer Perceptrons, Bayesian Neural Network, and Support Vector Machines), unsupervised (for example, Self-Organizing Maps) and hybrid models, such as Counter Propagation Neural Network (CPN), which comprises the advantages of supervised and unsupervised learning techniques.…”

Applications of Artificial Neural Networks in Chemical Problems

“…In general, the neighborhood of an output neuron is defined as square or hexagonal and this means that each neuron has 4 or 6 nearest neighbors, respectively [51][52][53]. Figure 4 exemplifies the output layers of a SOM model using square and hexagonal neurons for a combinatorial design of purinergic receptor antagonists [54] and cannabinoid compounds [30], respectively. Example of output layers of SOM models using square and hexagonal neurons for the combinatorial design of (a) purinergic receptor antagonists [54] and (b) cannabinoid compounds [30], respectively.…”

“…The main advantages of ANN techniques include learning and generalization ability of data, fault tolerance and inherent contextual information processing in addition to fast computation capacity [25]. It is important to mention that since 90's many studies have related advantages of applying ANN techniques when compared to other statistical methods [23,[26][27][28][29][30][31].…”