Prediction of partition coefficient based on atom-type electrotopological state indices

The aim of this study was to determine the efficacy of atom-type electrotop ological state indices for estimation of the octanol-water partition coeffi cient (log P) values in a set of 345 drug compounds or related complex chem ical structures. Multilinear regression analysis and artificial neural netw orks were used to construct models based on molecular weights and atom-type electrotopological state indices. Both multilinear regression and artifici al neural networks provide reliable log P estimations. For the same set of parameters, application of neural networks provided better prediction abili ty for training and test sets. The present study indicates that atom-type e lectrotopological state indices offer valuable parameters for fast evaluati on of octanol-water partition coefficients that can be applied to screen la rge databases of chemical compounds, such as combinatorial libraries.