Individual Hydrogen-Bond Strength QSPR Modelling with ISIDA Local Descriptors: a Step Towards Polyfunctional Molecules

Mol Inform. 2014 Jun;33(6-7):477-87. doi: 10.1002/minf.201400032. Epub 2014 Jun 17.

Abstract

Here, we introduce new ISIDA fragment descriptors able to describe "local" properties related to selected atoms or molecular fragments. These descriptors have been applied for QSPR modelling of the H-bond basicity scale pKBHX , measured by the 1 : 1 complexation constant of a series of organic acceptors (H-bond bases) with 4-fluorophenol as the reference H-bond donor in CCl4 at 298 K. Unlike previous QSPR studies of H-bond complexation, the models based on these new descriptors are able to predict the H-bond basicity of different acceptor centres on the same polyfunctional molecule. QSPR models were obtained using support vector machine and ensemble multiple linear regression methods on a set of 537 organic compounds including 5 bifunctional molecules. They were validated with cross-validation procedures and with two external test sets. The best model displays good predictive performance on a large test set of 451 mono- and bifunctional molecules: a root-mean squared error RMSE=0.26 and a determination coefficient R(2) =0.91. It is implemented on our website (http://infochim.u-strasbg.fr/webserv/VSEngine.html) together with the estimation of its applicability domain and an automatic detection of potential H-bond acceptors.

Keywords: Equilibrium constants of hydrogen bonding; Fragment descriptors; H-bond; Hydrogen-bond acidity and basicity; ISIDA; QSPR; pKBHX.