A fuzzy ARTMAP based on quantitative structure-property relationships (QSPRs) for predicting aqueous solubility of organic compounds

Quantitative structure-property relationships (QSPRs) for estimating aqueou s solubility of organic compounds at 25 degreesC were developed based on a fuzzy ARTMAP and a back-propagation neural networks using a heterogeneous s et of 515 organic compounds. A set of molecular descriptors, developed from PM3 semiempirical MO-theory and topological descriptors (first-, second-, third-, and fourth-order molecular connectivity indices), were used as inpu t parameters to the neural networks. Quantum chemical input descriptors inc luded average polarizability, dipole moment, resonance energy, exchange ene rgy, electron-nuclear attraction energy, and nuclear-nuclear (core-core) re pulsion energy. The fuzzy ARTMAP/QSPR correlated aqueous solubility (S, mol /L) for a range of -11.62 to 4.31 logS with average absolute errors of 0.02 and 0.14 logS units for the overall and validation data sets, respectively . The optimal 11 - 13 -1 back-propagation/QSPR model was less accurate, for the same solubility range, and exhibited larger average absolute errors of 0.29 and 0.28 logS units for the overall and validation sets, respectively . The fuzzy ARTMAP-based QSPR approach was shown to be superior to other ba ck-propagation and multiple linear regression/QSPR models for aqueous solub ility of organic compounds.