Modeling of lipophilicity by means of correlation weighting of local graphinvariants

Results of using descriptors calculated with so-called correlation weights (CWs) of local graph invariants for modeling of lipophilicity are reported. Presence of different atoms (i.e. H, C, N, O, F, Cl and Br) in the molecul ar structure and the presence of different values of vertex degrees in labe led hydrogen-filled molecular graphs have been examined as local invariants . By means of Monte Cal lo optimization procedure such values of the CWs wh ich produce as large values as possible of correlation coefficient between lipophilicity and values of the descriptors on training set have been found . The model of lipophilicity obtained by this approach for structures of tr aining set is a reasonable model for the prediction of the parameter values for compounds from test set. (C) 2001 Elsevier Science B.V. All rights res erved.