ALOGPS 2.1 was developed using ASNN and molecules described in the article:
Estimation of Aqueous Solubility
of Chemical Compounds using E-state Indices
Igor V. Tetko,1,2 Vsevolod Yu. Tanchuk,2 Tamara N. Kasheva,2 Alessandro E. P. Villa1
1Laboratoire de Neuro-Heuristique, Institut
de Physiologie, Rue du Bugnon 7, Lausanne, CH-1005, Switzerland, http://www.lnh.unil.ch2Biomedical
Department, Institute of Bioorganic & Petroleum Chemistry, Murmanskaya
1, Kiev-660, 253660, Ukraine
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 r2=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 this 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 on-line at http://www.vcclab.org/lab/alogps.
Copyright 2001 -- 2016 http://www.vcclab.org. All rights reserved.