Prediction of octanol–water partition coefficients of organic compounds by multiple linear regression, partial least squares, and artificial neural network

Abstract

A quantitative structure-property relationship (QSPR) study was performed to develop models those relate the structure of 141 organic compounds to their octanol-water partition coefficients (log P(o/w)). A genetic algorithm was applied as a variable selection tool. Modeling of log P(o/w) of these compounds as a function of theoretically derived descriptors was established by multiple linear regression (MLR), partial least squares (PLS), and artificial neural network (ANN). The best selected descriptors that appear in the models are: atomic charge weighted partial positively charged surface area (PPSA-3), fractional atomic charge weighted partial positive surface area (FPSA-3), minimum atomic partial charge (Qmin), molecular volume (MV), total dipole moment of molecule (mu), maximum antibonding contribution of a molecule orbital in the molecule (MAC), and maximum free valency of a C atom in the molecule (MFV). The result obtained showed the ability of developed artificial neural network to prediction of partition coefficients of organic compounds. Also, the results revealed the superiority of ANN over the MLR and PLS models.

QSPR studies for predicting gas to acetone and gas to acetonitrile solvation enthalpies using support vector machine

“…A neuron has an input, an output and a transfer function. A detailed description of the theory behind a neural network has been adequately described in our previous works [34][35][36][37][38].…”

Application of QSPR for the prediction of gas to 1-octanol solvation enthalpy using support vector regression

“…They have the aptitude to capture the relationship between input and an output variable from given outlines and this facilitates their ability to solve large-scale complex problems. A detailed description of the theory behind a neural network has been adequately described in our previous publications [37][38][39][40][41].…”

Prediction of Superoxide Quenching Activity of Fullerene (C60) Derivatives by Genetic Algorithm-Support Vector Machine

“…This method is based on electronegativity scale and represents the molecular electronegativity as geometrics mean of atomic electronegativity. This descriptor also is demanding the affinity of compounds in electrostatic interaction (50). This descriptor has a positive sign in linear equation (2); therefore increasing the charge distribution and affinity in electrostatic positions of a molecule leads to increase in its pIC 50 value.…”

“…This descriptor is related to valance of H atom. Since this descriptor has negative sign, decreasing the descriptor value or decreasing the valence of hydrogen atoms for each molecule leads to increase in its pIC 50 value.…”