P-glycoproteins (P-gp) actively transport a wide variety of chemicals out of cells and function as drug efflux pumps that mediate multidrug resistance and limit the efficacy of many drugs. Methods for facilitatingearly elimination of potential P-gp substrates are useful for facilitating new drug discovery. A computational ensemble pharmacophore model has recently been used for the prediction of P-gp substrates with a promising accuracy of 63%. It is desirable to extend the prediction range beyond compounds covered by the known pharmacophore models. For such a purpose, a machine learning method, support vector machine (SVM), was explored for the prediction of P-gp substrates. A set of 201 chemical compounds, including 116 substrates and 85 nonsubstrates of P-gp, was used to train and test a SVM classification system. This SVM system gave a prediction accuracy of at least 81.2% for P-gp substrates based on two different evaluation methods, which is substantially improved against that obtained from the multiple-pharmacophore model. The prediction accuracy for nonsubstrates of P-gp is 79.2% using 5-fold cross-validation. These accuracies are slightly better than those obtained from other statistical classification methods, including k-nearest neighbor (k-NN), probabilistic neural networks (PNN), and C4.5 decision tree, that use the same sets of data and molecular descriptors. Our study indicates the potential of SVM in facilitating the prediction of P-gp substrates.

Statistical-learning methods have been developed for facilitating the prediction of pharmacokinetic and toxicological properties of chemical agents. These methods employ a variety of molecular descriptors to characterize structural and physicochemical properties of molecules. Some of these descriptors are specifically designed for the study of a particular type of properties or agents, and their use for other properties or agents might generate noise and affect the prediction accuracy of a statistical learning system. This work examines to what extent the reduction of this noise can improve the prediction accuracy of a statistical learning system. A feature selection method, recursive feature elimination (RFE), is used to automatically select molecular descriptors for support vector machines (SVM) prediction of P-glycoprotein substrates (P-gp), human intestinal absorption of molecules (HIA), and agents that cause torsades de pointes (TdP), a rare but serious side effect. RFE significantly reduces the number of descriptors for each of these properties thereby increasing the computational speed for their classification. The SVM prediction accuracies of P-gp and HIA are substantially increased and that of TdP remains unchanged by RFE. These prediction accuracies are comparable to those of earlier studies derived from a selective set of descriptors. Our study suggests that molecular feature selection is useful for improving the speed and, in some cases, the accuracy of statistical learning methods for the prediction of pharmacokinetic and toxicological properties of chemical agents.

*: PM3), and ONIOM (MP2/6-31G*: HF/3-21G)-were applied to investigate thermal decomposition mechanisms of four 2-phenoxycarboxylic acids (2-phenoxyacetic acid, 2-phenoxypropionic acid, 2-phenoxybutyric acid, and 2-phenoxyisobutyric acid) in the gas phase. All the transition states and intermediates of the reaction paths were optimized. The reaction pathway of four reactants yielding the phenol, CO, and the corresponding carbonyl compound was characterized on the potential energy surface and found to proceed stepwise. The first step corresponds to the elimination of phenol and the formation of α-lactone intermediate through a five-membered ring transition state, and the second step is the cycloreversion process of α-lactone intermediate to form CO and the corresponding carbonyl compound. The reaction pathway of latter three compounds to produce the carboxylic acid and phenol via a four-membered cyclic transition structure was also examined theoretically. Comparison with experiment indicates that the activation parameters for the fist reaction channel are accurately predicted at the ONIOM (MP2/6-31G*: HF/3-21G) level of theory.

Density functional theory (DFT) and Monte Carlo (MC) simulation with free energy perturbation (FEP) techniques have been used to study the tautomeric proton transfer reaction of 2-amino-2-oxazoline, 2-amino-2-thiazoline, and 2-amino-2-imidazoline in the gas phase and in water. Two reaction pathways were considered: the direct and water-assisted transfers. The optimized structures and thermodynamic properties of stationary points for the title reaction system in the gas phase were calculated at the B3LYP/6-311 G(d, p) level of theory. The potential energy profiles along the minimum energy path in the gas phase and in water were obtained. The study of the solvent effect of water on the proton transfer of 2-amino-2-oxozoline, 2-amino-2-thiazoline, and 2-amino-2-imidazoline indicates that water as a solvent is favorable for the water-assisted process and slows down the rate of the direct transfer pathway.

Toxicity of various compounds has been measured in many studies by their toxic effects against Tetrahymena pyriformis. Efforts have also been made to use computational quantitative structure-activity relationship (QSAR) and statistical learning methods (SLMs) for predicting Tetrahymena pyriformis toxicity (TPT) at impressive accuracies. Because of the diversity of compounds and toxicity mechanisms, it is desirable to explore additional methods and to examine if these methods are applicable to more diverse sets of compounds. We tested several SLMs (logistic regression, C4.5 decision tree, k-nearest neighbor, probabilistic neural network, support vector machines) for their capability in predicting TPT by using 1129 compounds (841 TPT and 288 non-TPT agents) which are more diverse than those in other studies. A feature selection method was used for improving prediction performance and selecting molecular descriptors responsible for distinguishing TPT and non-TPT agents. The prediction accuracies are 86.9% 94.2% for TPT and 71.2% 87.5% for non-TPT agents based on 5-fold cross-validation studies, which are comparable to some of earlier studies despite the use of more diverse sets of compounds. The selected molecular descriptors are consistent with those used in other studies and experimental findings. These suggest that SLMs are useful for predicting TPT potential of diverse sets of compounds and for characterizing the molecular descriptors associated with TPT.