A fuzzy ARTMAP-based quantitative structure-property relationship (QSPR) for predicting physical properties of organic compounds

A modified fuzzy ARTMAP neural-network-based QSPR for predicting normal boi ling points, critical temperatures, and critical pressures of organic compo unds was developed. Seven or eight molecular descriptors (the sum of atomic numbers; five valence connectivity indices; and the second-order kappa sha pe index, without or with the dipole moment) were used to describe the topo logical and electronic features of a heterogeneous set of 1168 organic comp ounds. Optimal training and testing sets were selected with fuzzy ART. The fuzzy ARTMAP models with eight descriptors as input provided the best predi ctive and extrapolation capabilities compared to optimal back-propagation m odels and group contribution methods. The absolute mean errors of predictio ns for the normal boiling point (1168 compounds), the critical temperature (530 compounds), and the critical pressure (463 compounds) were 2.0 K (0.49 %), 1.4 K (0.24%), and 0.02 MPa (0.52%), respectively. A composite model fo r simultaneously estimating the three properties yielded similar results.