Prediction of skin penetration using artificial neural network (ANN) modeling

Artificial neural network (ANN) analysis was used to predict the skin permeability of selected xenobiotics. Permeability coefficients (log k(p)) were obtained from various literature sources. A previously reported equation, which was shown to be useful in the prediction of skin permeability, uses the partial charges of the penetrants, their molecular weight, and their calculated octanol water partition coefficient (log K(oct)). The equation was used to predict the skin permeability for the set of 40 compounds (r(2) = 0.672). A successful ANN was developed and the ANN produced log k(p) values that correlated well with the experimental ones(r(2) = 0.997). The penetration properties of a selection of compounds through human skin that have not been previously investigated, etodolac, famotidine, nimesulide, nizatidine, ranitidine, were investigated. Their permeability coefficients were determined. It was then possible to compare the experimental data with that predicted using the partial charge equation and the trained ANN. ANN modeling for predicting skin permeability was found to be useful for predicting skin permeability coefficients of compounds. In conclusion, the developed and described ANN model in this publication does not require any experimental parameters; it could potentially provide useful and precise prediction of skin penetration for new drugs or toxic penetrants.     

Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research

Artificial neural networks (ANNs) are biologically inspired computer programs designed to simulate the way in which the human brain processes information. ANNs gather their knowledge by detecting the patterns and relationships in data and learn (or are trained) through experience, not from programming. An ANN is formed from hundreds of single units, artificial neurons or processing elements (PE), connected with coefficients (weights), which constitute the neural structure and are organised in layers. The power of neural computations comes from connecting neurons in a network. Each PE has weighted inputs, transfer function and one output. The behavior of a neural network is determined by the transfer functions of its neurons, by the learning rule, and by the architecture itself. The weights are the adjustable parameters and, in that sense, a neural network is a parameterized system. The weighed sum of the inputs constitutes the activation of the neuron. The activation signal is passed through transfer function to produce a single output of the neuron. Transfer function introduces non-linearity to the network. During training, the inter-unit connections are optimized until the error in predictions is minimized and the network reaches the specified level of accuracy. Once the network is trained and tested it can be given new input information to predict the output. Many types of neural networks have been designed already and new ones are invented every week but all can be described by the transfer functions of their neurons, by the learning rule, and by the connection formula. ANN represents a promising modeling technique, especially for data sets having non-linear relationships which are frequently encountered in pharmaceutical processes. In terms of model specification, artificial neural networks require no knowledge of the data source but, since they often contain many weights that must be estimated, they require large training sets. In addition, ANNs can combine and incorporate both literature-based and experimental data to solve problems. The various applications of ANNs can be summarised into classification or pattern recognition, prediction and modeling. Supervised 'associating networks can be applied in pharmaceutical fields as an alternative to conventional response surface methodology. Unsupervised feature-extracting networks represent an alternative to principal component analysis. Non-adaptive unsupervised networks are able to reconstruct their patterns when presented with noisy samples and can be used for image recognition. The potential applications of ANN methodology in the pharmaceutical sciences range from interpretation of analytical data, drug and dosage form design through biopharmacy to clinical pharmacy.     

Prediction of human intestinal absorption using an artificial neural network

An artificial neural network model is developed to predict percent human intestinal absorption (%FA) of compounds from their molecular structural parameters. These parameters are the polar molecular surface area (PSA), the fraction of polar molecular surface area (FPSA, polar molecular surface area/ molecular surface area), the sum of the net atomic charges of oxygen atoms (Q(O)), the sum of the net atomic charges of nitrogen atoms with net negative atomic charges (Q(N)), the sum of the net atomic charges of hydrogen atoms attached to oxygen or nitrogen atoms (Q(H)), and the number of carboxyls (nCOOH). For a training set of 85 compounds anda test set of 10 compounds, root mean squared errors (RMSE) between experimental %FA valuesand calculated/predicted %FA values are 8.86% and 14.1%, respectively.     

Prediction of human intestinal permeability using artificial membrane permeability

The purpose of the present study was to examine a correlation between the human intestinal permeability (P(eff)) and the bio-mimetic artificial membrane permeability corrected by the paracellular pathway model based on the Renkin function (P(PAMPA-PP-RF)) and to construct a prediction scheme. The effect of the unstirred water layer was incorporated to the prediction scheme. Eighteen P(eff) values of passively absorbed drugs were employed for the analysis. The correlation coefficient (CC) between the predicted and observed logP(eff) was 0.91. P(eff) of furosemide, hydrochlorothiazide and creatinine were underestimated by P(PAMPA-PP-RF). When these compounds were excluded, CC was 0.97. Without the correction for the paracellular pathway, P(eff) of small, cationic and hydrophilic compounds were underestimated. Therefore, P(PAMPA-PP-RF) was found to be an adequate in vitro surrogate for P(eff).     

Clinical application of artificial neural network (ANN) modeling to predict pharmacokinetic parameters of severely ill patients

Artificial neural network (ANN) modeling was used to evaluate the pharmacokinetics of aminoglycosides (arbekacin sulfate and amikacin sulfate) in severely ill patients. The plasma level was predicted by ANN modeling using parameters related to the severity of the patient's condition and the predictive performance was shown to be better than could be achieved using multiple regression analysis. These results indicate that there is a non-linear relationship between the pharmacokinetics of aminoglycosides and the severity of the patient's condition, and this should be taken into account when determining the dose for severely ill patients. Patients whose plasma levels are likely to fall below the effective level can be identified by ANN modeling with a predictive sensitivity and specificity superior to multivariate logistic regression analysis. The predictable range should be inferred from the data structure before the modeling in order to improve the predictive performance. The volume of distribution (Vd) in the normal range was weakly predicted by ANN modeling from the patients' data. Prediction of clearance by ANN modeling was poorer than that obtained from serum creatinine concentration by linear regression analysis. These results suggest that the input-output relationship (linear or non-linear) should be taken into account in selecting the modeling method. Linear modeling can give better predictive performance for linear systems and non-linear modeling can give better predictive performance for non-linear systems. In general, the performance of ANN modeling was superior to linear modeling for PK/PD prediction. For accurate modeling, a predictable range should be inferred from the data structure before the analysis. Restriction of the predictable region, as determined from the data structure, produced an increase in prediction performance. When applying ANN modeling in clinical settings, the predictive performance and predictable region should be investigated in detail to avoid the risk of harm to severely ill patients.     

Prediction of plasma protein binding of cephalosporins using an artificial neural network

An artificial neural network model is developed to predict the fraction of cephalosporins bound to plasma proteins (f(b)) from their molecular structural parameters. These molecular structural parameters are the molecular weight (MW), the surface area occupied by oxygen and nitrogen atoms (S(O),N), and the surface area occupied by hydrogen atoms attached to oxygen or nitrogen atoms (S(H)). For a training set of 20 cephalosporins and a test set of 3 cephalosporins, root mean squared errors (RMSE) between experimental fb values and calculated/predicted fb values are 0.036 and 0.045, respectively.     

Optimisation of the predictive ability of artificial neural network (ANN) models: A comparison of three ANN programs and four classes of training algorithm

The purpose of this study was to determine whether artificial neural network (ANN) programs implementing different backpropagation algorithms and default settings are capable of generating equivalent highly predictive models. Three ANN packages were used: INForm, CAD/Chem and MATLAB. Twenty variants of gradient descent, conjugate gradient, quasi-Newton and Bayesian regularisation algorithms were used to train networks containing a single hidden layer of 3–12 nodes.

All INForm and CAD/Chem models trained satisfactorily for tensile strength, disintegration time and percentage dissolution at 15, 30, 45 and 60 min. Similarly, acceptable training was obtained for MATLAB models using Bayesian regularisation. Training of MATLAB models with other algorithms was erratic. This effect was attributed to a tendency for the MATLAB implementation of the algorithms to attenuate training in local minima of the error surface. Predictive models for tablet capping and friability could not be generated.

The most predictive models from each ANN package varied with respect to the optimum network architecture and training algorithm. No significant differences were found in the predictive ability of these models. It is concluded that comparable models are obtainable from different ANN programs provided that both the network architecture and training algorithm are optimised. A broad strategy for optimisation of the predictive ability of an ANN model is proposed.