Quantitative structure–mobility relationship study of a diverse set of organic acids using classification and regression trees and adaptive neuro‐fuzzy inference systems

Abstract

A quantitative structure-mobility relationship was developed to accurately predict the electrophoretic mobility of organic acids. The absolute electrophoretic mobilities (mu(0)) of a diverse dataset consisting of 115 carboxylic and sulfonic acids were investigated. A set of 1195 zero- to three-dimensional descriptors representing various structural characteristics was calculated for each molecule in the dataset. Classification and regression trees were successfully used as a descriptor selection method. Four descriptors were selected and used as inputs for adaptive neuro-fuzzy inference system. The root mean square errors for the calibration and prediction sets are 1.61 and 2.27, respectively, compared with 3.60 and 3.93, obtained from a previous mechanistic model.

Prediction of Retention of Pesticides in Reversed-Phase High-Performance Liquid Chromatography Using Classification and Regression Tree Analysis and Adaptive Neuro-Fuzzy Inference Systems

“…[10] The CART is extensively used for modeling and classification in several areas, such as medical diagnosis and prognosis, [11][12][13] ecology, [14] agricultural, [15] and chemistry. [10,[16][17][18] A very interesting advantage of CART is the possibility to deal with large numbers of both categorical and numerical variables. Another advantage is that no assumption about the underlying distribution of the predictor variables is required (even categorical variables can be used).…”

“…The theory and application of CART has been discussed in other references. [10][11][12][13][14][15][16][17][18] The synergism of fuzzy logic (FL) systems and neural networks (NN) has produced a functional system capable of learning, high level thinking, and reasoning. [19] The purpose of a neuro-fuzzy system is to apply neural learning techniques to identify the parameters and=or structure of neuro-fuzzy systems.…”

“…The goal of ANFIS is to find a model or mapping that will correctly associate the inputs (descriptors) with the target (property). [17] EXPERIMENTAL Retention data (log k exp ) at different percentages of water-acetonitrile mobile phase were obtained from the paper by D'Archivio et al [7] and were shown in Table 1. The selected compounds belong to the most widely used pesticide classes and owning to the large differences in terms of molecular complexity and chemical functionalities, as a wide range of structural variability.…”

Classification and Regression Tree Analysis for Molecular Descriptor Selection and Binding Affinities Prediction of Imidazobenzodiazepines in Quantitative Structure-Activity Relationship Studies

“…10 CART is extensively used for modeling and classification in several areas, such as medical diagnosis and prognosis, [11][12][13] ecology, 14 agriculture 15 and chemistry. 10,[16][17] A very interesting advantage of CART is the possibility to deal with large numbers of both categorical and numerical variables. Another advantage is that no assumption about the underlying distribution of the predictor variables is required (even categorical variables can be used).…”

“…In cross validation, some samples are randomly drawn from the data set, to test the tree, which is built with the rest of the data. 10,17 For a ten-fold cross validation, the original data set is divided into ten equal pairs (test sets), each containing a similar distribution for the response variable. A tree is then built using 90% of the observations (learning set), while the remaining 10% (test set) is used to test the tree.…”