| Attributs | Valeurs |
|---|
| type
| |
| Is Part Of
| |
| Subject
| |
| Title
| - The Comparative Molecular Surface Analysis (COMSA) − A Nongrid 3D QSARMethod by a Coupled Neural Network and PLS System: Predicting pKa Values ofBenzoic and Alkanoic Acids
|
| has manifestation of work
| |
| related by
| |
| Author
| |
| Abstract
| - A self-organizing neural network was used to design a novel method capable of the quantitative predictionof molecular properties. The method is based on the comparison of molecular surfaces performed by thecoupled neural network and PLS system. Unlike CoMFA and related methods it does not compare theproperties describing a discrete set of points but the average property values calculated for a certain area ofthe molecular surface. It has been found that the results of the PLS analysis of the series of the comparativematrices of the molecular electrostatic potential (MEP) are quite stable. Also the results only slightly dependon such parameters as the number of points sampled at the molecular surface (D) or a winning distance(MD) of the self-organizing neurons. The influence of these parameters for modeling the effects limited bysteric and electronic effects was determined and the pKa values of the ortho-, meta-, and para- (o-, m-, p-)analogues of benzoic acid and selected alkanoic acids were predicted. We generally found that for theseries analyzed CoMSA gave better models than CoMFA.
|
| article type
| |
| is part of this journal
| |
