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

The molecular weight and electrotopological E-state indices were used to es timate by Artificial Neural Networks aqueous solubility for a diverse set o f 1291 organic compounds. The neural network with 33-4-1 neurons provided h ighly predictive results with r(2) = 0.91 and RMS = 0.62. The used paramete rs 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 u sed without need of additional indices (the molecular connectivity, shape, flexibility and indicator indices) also considered in the previous study. I n addition, the present neural network contained three times less hidden ne urons. Smaller neural networks and use of one homogeneous set of parameters provides a more robust model for prediction of aqueous solubility of chemi cal 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/similar to itetko/logp.