Estimation of ADME Properties with Substructure Pattern Recognition

Abstract

Over the past decade, absorption, distribution, metabolism, and excretion (ADME) property evaluation has become one of the most important issues in the process of drug discovery and development. Since in vivo and in vitro evaluations are costly and laborious, in silico techniques had been widely used to estimate ADME properties of chemical compounds. Traditional prediction methods usually try to build a functional relationship between a set of molecular descriptors and a given ADME property. Although traditional methods have been successfully used in many cases, the accuracy and efficiency of molecular descriptors must be concerned. Herein, we report a new classification method based on substructure pattern recognition, in which each molecule is represented as a substructure pattern fingerprint based on a predefined substructure dictionary, and then a support vector machine (SVM) algorithm is applied to build the prediction model. Therefore, a direct connection between substructures and molecular properties is built. The most important substructure patterns can be identified via the information gain analysis, which could help to interpret the models from a medicinal chemistry perspective. Afterward, this method was verified with two data sets, one for blood-brain barrier (BBB) penetration and the other for human intestinal absorption (HIA). The results demonstrated that the overall predictive accuracies of the best HIA model for the training and test sets were 98.5 and 98.8%, and the overall predictive accuracies of the best BBB model for the training and test sets were 98.8 and 98.4%, which confirmed the reliability of our method. In the additional validations, the predictive accuracies were 94 and 69.5% for the HIA and the BBB models, respectively. Moreover, some of the representative key substructure patterns which significantly correlated with the HIA and BBB penetration properties were also presented.

Untitled

“…A close observation on the naturally occurring protein complexes 12 , the hotspot of the target with a preferential binding possibility is identified as GLY15, LYS16 and GLY60 (Fig. 2 and Table 1).…”

Predicting human intestinal absorption with modified random forest approach: a comprehensive evaluation of molecular representation, unbalanced data, and applicability domain issues

“…25 Based on the same dataset, Hou et al and Shen et al also built HIA classication models in 2007 and 2010 respectively (ACC ¼ 0.97/0.98 for training set; ACC ¼ 0.98/0.99 for test set). 12,36 In addition, there have also been several QSAR models with similar statistical results for HIA classication in the last few years.…”

“…For these classication models, the number of compounds ranges from 202 to 685. Other than these descriptors used in regression models, 1,13,35,36 chargerelated descriptors such as hydrogen bonding capacity and charged partial surface were proposed to improve the predictive ability for HIA models. 37 In regard to statistical methods, linear discriminant analysis, 1,30 SVM 35,36 and Bayesian 37 are the most commonly used ones in all the published classication models studies.…”

“…Other than these descriptors used in regression models, 1,13,35,36 chargerelated descriptors such as hydrogen bonding capacity and charged partial surface were proposed to improve the predictive ability for HIA models. 37 In regard to statistical methods, linear discriminant analysis, 1,30 SVM 35,36 and Bayesian 37 are the most commonly used ones in all the published classication models studies. In 2012, Taravat explained the impact of data distributions for modelling of passive intestinal absorption and attempted to address this problem of unbalanced data distribution by creating a training set through under-sampling the highly absorbed compounds.…”

In silicoADME/T modelling for rational drug design

“…Recently, Shen et al proposed a substructure pattern recognition approach to build a support vector machine (SVM)-based classification model for HIA prediction, in which each molecule is represented by a set of substructure fingerprints based on a predefined substructure dictionary (Shen et al 2010). The most influential substructure patterns are recognized by an information gain analysis, which may contribute to an indirect interpretation of the models from a medicinal chemistry perspective.…”