CoMFA Model and Molecular Design of Anti-excitatory Activity for Benzodiazepinooxazole Derivatives against Mice

A 3D-QSAR study was conducted to analyze the anti-excitatory activity(p E) of benzodiazepinooxazole derivatives to mice by the comparative molecular field analysis(CoMFA) method. Among the 54 active molecules, a training set of 46 compounds was randomly selected to construct the CoMFA model; the remaining compounds, together with template molecule(No. 54) and two newly designed molecules constitute a test set of 17 compounds to validate the model. The obtained cross-validation coefficient(R_(cv)~2), the non-cross validation coefficient(R~2), and the test value F of the CoMFA model for training set are 0.516, 0.899, and 57.57,respectively. The model was used to predict the activities of all compounds in the training and testing sets, and the results indicated that the model had good correlation, strong stability and good predictability. Based on the 3D contour maps, eight novel benzodiazepinooxazole derivatives with higher anti-excitatory activity were designed.However, the effectiveness of these novel benzodiazepinooxazole derivatives is still needed to be verified by the experimental results.     

One- to four-dimensional kernels for virtual screening and the prediction of physical, chemical, and biological properties

Many chemoinformatics applications, including high-throughput virtual screening, benefit from being able to rapidly predict the physical, chemical, and biological properties of small molecules to screen large repositories and identify suitable candidates. When training sets are available, machine learning methods provide an effective alternative to ab initio methods for these predictions. Here, we leverage rich molecular representations including 1D SMILES strings, 2D graphs of bonds, and 3D coordinates to derive efficient machine learning kernels to address regression problems. We further expand the library of available spectral kernels for small molecules developed for classification problems to include 2.5D surface and 3D kernels using Delaunay tetrahedrization and other techniques from computational geometry, 3D pharmacophore kernels, and 3.5D or 4D kernels capable of taking into account multiple molecular configurations, such as conformers. The kernels are comprehensively tested using cross-validation and redundancy-reduction methods on regression problems using several available data sets to predict boiling points, melting points, aqueous solubility, octanol/water partition coefficients, and biological activity with state-of-the art results. When sufficient training data are available, 2D spectral kernels in general tend to yield the best and most robust results, better than state-of-the art. On data sets containing thousands of molecules, the kernels achieve a squared correlation coefficient of 0.91 for aqueous solubility prediction and 0.94 for octanol/water partition coefficient prediction. Averaging over conformations improves the performance of kernels based on the three-dimensional structure of molecules, especially on challenging data sets. Kernel predictors for aqueous solubility (kSOL), LogP (kLOGP), and melting point (kMELT) are available over the Web through: http://cdb.ics.uci.edu.     

Prediction of n-octanol/water partition coefficients from PHYSPROP database using artificial neural networks and E-state indices

A new method, ALOGPS v 2.0 (http://www.lnh.unil.ch/~itetko/logp/), for the assessment of n-octanol/water partition coefficient, log P, was developed on the basis of neural network ensemble analysis of 12 908 organic compounds available from PHYSPROP database of Syracuse Research Corporation. The atom and bond-type E-state indices as well as the number of hydrogen and non-hydrogen atoms were used to represent the molecular structures. A preliminary selection of indices was performed by multiple linear regression analysis, and 75 input parameters were chosen. Some of the parameters combined several atom-type or bond-type indices with similar physicochemical properties. The neural network ensemble training was performed by efficient partition algorithm developed by the authors. The ensemble contained 50 neural networks, and each neural network had 10 neurons in one hidden layer. The prediction ability of the developed approach was estimated using both leave-one-out (LOO) technique and training/test protocol. In case of interseries predictions, i.e., when molecules in the test and in the training subsets were selected by chance from the same set of compounds, both approaches provided similar results. ALOGPS performance was significantly better than the results obtained by other tested methods. For a subset of 12 777 molecules the LOO results, namely correlation coefficient r(2)= 0.95, root mean squared error, RMSE = 0.39, and an absolute mean error, MAE = 0.29, were calculated. For two cross-series predictions, i.e., when molecules in the training and in the test sets belong to different series of compounds, all analyzed methods performed less efficiently. The decrease in the performance could be explained by a different diversity of molecules in the training and in the test sets. However, even for such difficult cases the ALOGPS method provided better prediction ability than the other tested methods. We have shown that the diversity of the training sets rather than the design of the methods is the main factor determining their prediction ability for new data. A comparative performance of the methods as well as a dependence on the number of non-hydrogen atoms in a molecule is also presented.     

药物水溶解度的QSAR研究和VolSurf参数

药物的水溶解度与其吸收密切相关。本文利用一种新的计算方法,VolSurf,预测药物的水溶解度并测定有利于药物水溶解度的主要分子特征。被测化合物包括26个结构不同的药物,通过偏最小二乘分析法,对药物水溶解度实验值与分子特征进行相关,得到较好的模型(r2=0.90,q2=0.77)。将化合物分为训练集和预测集进行相关分析,结果表明以18个化合物所建立的训练集模型对其余8个化合物有较好的预测能力,预测的标准偏差(SDEP)为0.59。参数分析表明分子与水相互作用的3个局部能量最小值越小,且它们之间的距离越大,对其水溶解度越有利;亲水性占主导因素的分子有高的水溶解度;分子的疏水性越强,在水中的溶解性越弱;大分子的溶解度较小分子溶解度低。     

Continuum polarizable force field within the Poisson-Boltzmann framework

We have developed and tested a complete set of nonbonded parameters for a continuum polarizable force field. Our analysis shows that the new continuum polarizable model is consistent with B3LYP/cc-pVTZ in modeling electronic response upon variation of dielectric environment. Comparison with experiment also shows that the new continuum polarizable model is reasonable, with accuracy similar to that of B3LYP/cc-pVTZ in reproduction of dipole moments of selected organic molecules in the gas phase. We have further tested the validity to interchange the Amber van der Waals parameters between the explicit and continuum polarizable force fields with a series of dimers. It can be found that the continuum polarizable model agrees well with MP2/cc-pVTZ, with deviations in dimer binding energies less than 0.9 kcal/mol in the aqueous dielectric environment. Finally, we have optimized atomic cavity radii with respect to experimental solvation free energies of 177 training molecules. To validate the optimized cavity radii, we have tested these parameters against 176 test molecules. It is found that the optimized Poisson-Boltzmann atomic cavity radii transfer well from the training set to the test set, with an overall root-mean-square deviation of 1.30 kcal/mol, an unsigned average error of 1.07 kcal/mol, and a correlation coefficient of 92% for all 353 molecules in both the training and test sets. Given the development documented here, the next natural step is the construction of a full protein/nucleic acid force field within the new continuum polarization framework.     

Prediction of pH-dependent aqueous solubility of Histone Deacetylase (HDAC) inhibitors1

Recently we developed a model for prediction of pH-dependent aqueous solubility of drugs and drug like molecules. In the present work, the model was applied on a series of novel Histone Deacetylases (HDAC) inhibitors discovered at TopoTarget. The applicability of our model was evaluated on the series of HDAC inhibitors by use of Self-Organizing Maps (SOM) and 2D-projection of the HDAC inhibitors on the chemical space of the training data set of the artificial neural network (ANN) module. The model was refined for the particular chemical space of interest, which led to two modifications in the training data set of the ANN. The performance of the original and the two modified versions of the model were evaluated against the commercial software from Simulations-plus and pH-dependent solubility measurements for representative compounds of the series. The results of the evaluation indicate that one can develop models that are more accurate in predicting differences in the solubility of structurally very similar compounds than models that have been trained on structurally unbiased, diverse data sets. Such ‘tailor-made’ models have the potential to become trustworthy enough to replace time-consuming and expensive medium- and high-throughput solubility experiments by providing results of similar or even better quality.     

Prediction of pH-dependent aqueous solubility of Histone Deacetylase (HDAC) inhibitors

Recently we developed a model for prediction of pH-dependent aqueous solubility of drugs and drug like molecules. In the present work, the model was applied on a series of novel Histone Deacetylases (HDAC) inhibitors discovered at TopoTarget. The applicability of our model was evaluated on the series of HDAC inhibitors by use of Self-Organizing Maps (SOM) and 2D-projection of the HDAC inhibitors on the chemical space of the training data set of the artificial neural network (ANN) module. The model was refined for the particular chemical space of interest, which led to two modifications in the training data set of the ANN. The performance of the original and the two modified versions of the model were evaluated against the commercial software from Simulations-plus and pH-dependent solubility measurements for representative compounds of the series. The results of the evaluation indicate that one can develop models that are more accurate in predicting differences in the solubility of structurally very similar compounds than models that have been trained on structurally unbiased, diverse data sets. Such 'tailor-made' models have the potential to become trustworthy enough to replace time-consuming and expensive medium- and high-throughput solubility experiments by providing results of similar or even better quality.     

Solubility prediction of anthracene in mixed solvents using a minimum number of experimental data

Numerical methods to predict the solubility of anthracene in mixed solvents have been proposed. A minimum number of 3 solubility data points in sub-binary solvents has been employed to calculate the solvent-solute interaction terms of a well established colsolvency model, i.e. the combined nearly ideal binary solvent/Redlich-Kister model. The calculated interaction terms were used to predict the solubility in binary and ternary solvent systems. The predicted solubilities have been compared with experimental solubility data and the absolute percentage mean deviation (APMD) has been computed as a criterion of prediction capability. The overall APMD for 25 anthracene data sets in binary solvents is 0.40%. In order to provide a predictive method, which is based fully on theoretical calculations, the quantitative relationships between sub-binary interaction terms and physicochemical properties of the solvents have been presented. The overall APMD value for 41 binary data sets is 9.19%. The estimated binary interaction terms using a minimum number of data points and the quantitative relationships have then been used to predict anthracene solubility data in 30 ternary solvent systems. The produced APMD values are 3.72 and 15.79%, respectively. To provide an accurate correlation for solubility in ternary solvent systems, an extension to the combined nearly ideal multicomponenet solvent/Redlich-Kister (CNIMS/R-K) model was proposed and the corresponding overall AMPD is 0.38%.     

Studies on a Series of Coumarin Derivatives for Anticancer Activity against Breast Carcinoma Cell Line MCF-7 and Their Molecular Design

Breast cancer is one of the most common malignant tumors in women, and is also the focus of researchers. In this article, 3D-QSAR(three-dimensional quantitative structure-activity relationship) was performed on 24 molecules which are a series of coumarin derivatives for their anticancer activity. Our team divided these compounds randomly into the training and test sets to build the CoMFA(comparative molecular field analysis) and CoMSIA(comparative molecular similarity index analysis) models. The coefficients of cross-validation Q~2 and non cross-validation R~2 for CoMFA model were 0.684 and 0.949, and 0.579 and 0.930 for the CoMSIA model, respectively. The result demonstrates that the model has strong stability and satisfactory predictability. 3D contour maps suggest that the electrostatic factor has the greatest impact on activity followed by the H-bonding acceptor and hydrophilic factors. Taking the above results into account, we designed several molecules with high anticancer activity against breast carcinoma cell line MCF-7.     

New LSER Model Based on Solvent Empirical Parameters for the Prediction and Description of the Solubility of Buckminsterfullerene in Various Solvents

Because of the importance of the solubility of buckminsterfullerene, C₆₀, as the most well-known carbon nanomaterial, a multiparameter linear model is proposed for C₆₀ solubility in different solvents using solvent empirical parameters. The obtained model covers more than 81 and 87 % of the variance in the training and test sets, respectively. On the other hand, because of the potential of solvent empirical parameters for probing different aspects of the solvent–solute interactions, some information about the solubility of C₆₀ in solution phase was obtained. The results showed that hydrogen bond donation ability, basicity scale and dispersion interactions were some of the effective parameters for correlating the solubility of C₆₀ in various solvents.