Estimation of aqueous solubility of chemical compounds using E-state indices.

The molecular weight and electrotopological E-state indices were used to estimate by Artificial Neural Networks aqueous solubility for a diverse set of 1291 organic compounds. The neural network with 33-4-1 neurons provided highly predictive results with r(2) = 0.91 and RMS = 0.62. The used parameters included several combinations of E-state indices with similar properties. The calculated results were similar to those published for these data by Huuskonen (2000). However, in the current study only E-state indices were used without need of additional indices (the molecular connectivity, shape, flexibility and indicator indices) also considered in the previous study. In addition, the present neural network contained three times less hidden neurons. Smaller neural networks and use of one homogeneous set of parameters provides a more robust model for prediction of aqueous solubility of chemical compounds. Limitations of the developed method for prediction of large compounds are discussed. The developed approach is available online at http://www.lnh.unil.ch/~itetko/logp.     

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.     

新型原子类型拓扑指数模拟含氧化合物气相色谱保留指数

Quantitative structure-retention relationship (QSRR) model for the estimation of retention indices (RIs)of 39 oxygen-containing compounds containing ketones and esters was established by our newly introduced distance-based atom-type indices DAI. The useful application of the novel DAI indices has been demonstrated by developing accurate predictive equations for gas chromatographic retention indices. The statistical results of the multiple linear regression for the final model are r=0.9973 and s=8.23. Furthermore, an external test set of 10 oxo-containing compounds can be accurately predicted with the final equation giving the following statistical results: r pred=0.9966 and s pred=8.56.     

The predicting study for chromatographic retention index of saturated alcohols by MLR and ANN

A QSRR method was followed to relate the observed Kovats retention indexes of saturated alcohol compounds with their molecular connectivity indices by means of multilinear regression analysis and artificial neural networks technique. The alcohols included linear, branched with hydroxyl group on a primary, secondary, or tertiary carbon atom. At first, models were generated for six OV (Ohio Valley) series columns separately, with high value of R and F statistics. Then a combined model, added a polarity term of stationary phase (M), was also developed for all these columns, and the result was satisfactory. For comparison, the neural network of BP algorithm was applied, and it was found that the neural network could exceed the level of the multiple regression method. The stability and validity of both models were tested by cross-validation technique and by prediction response values for the prediction set.     

Prediction of quantitative calibration factors of some organic compounds in gas chromatography

A quantitative structure-property relationship (QSPR) methodology that involves multilinear (Hansch-type) and nonlinear (radial basis function neural network (RBFNN)) approaches was performed to correlate the quantitative molar calibration factors (f(M)) of 140 organic compounds against structural factors. The statistical characteristics provided by the multiple linear model (R(2) = 0.963; RMS = 0.089; AARD = 3.86% for test set) indicated satisfactory stability and predictive ability, while the predictive ability of the RBFNN model is somewhat superior (R(2) = 0.983; RMS = 0.075; AARD = 3.19% for test set). The multilinear model provided some insight into the main structure factors that modulate the quantitative calibration factor of the investigated compounds.