| Abstract
| - The molecular weight and electrotopological E-state indices were used to estimate by Artificial NeuralNetworks aqueous solubility for a diverse set of 1291 organic compounds. The neural network with 33-4-1neurons provided highly predictive results with r2 = 0.91 and RMS = 0.62. The used parameters includedseveral combinations of E-state indices with similar properties. The calculated results were similar to thosepublished for these data by Huuskonen (2000). However, in the current study only E-state indices wereused 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 lesshidden neurons. Smaller neural networks and use of one homogeneous set of parameters provides a morerobust model for prediction of aqueous solubility of chemical compounds. Limitations of the developedmethod for prediction of large compounds are discussed. The developed approach is available online athttp://www.lnh.unil.ch/∼itetko/logp.
|
