Abstract
The aim of this study is to enhance the predictivity power of CoMFA and CoMSIA models by means of different variable selection algorithms. The genetic algorithm (GA), successive projection algorithm (SPA), stepwise multiple linear regression (SW-MLR), and the enhanced replacement method (ERM) were used and tested as variable selection algorithms. Then, the selected variables were used to generate a simple and predictive model by the multilinear regression algorithm. A set of 74 histamine H3 antagonists were split into 40 compounds as a training set, and 17 compounds as a test set, by the Kennard-Stone algorithm. Before splitting the data, 17 compounds were randomly selected from the pool of the whole data set as an evaluation set without any supervision, pretreatment, or visual inspection. Among applied variable selection algorithms, ERM had noticeable improvement on the statistical parameters. The r2 values of training, test, and evaluation sets for the ERM-MLR model using CoMFA fields were 0.9560, 0.8630, and 0.8460 and using the CoMSIA fields were 0.9800, 0.8521, and 0.9080, respectively. In this study, the principles of organization for economic cooperation and development (OECD) for regulatory acceptability of QSARs are considered.
Highlights
One of the most frequently used QSAR techniques is the comparative molecular field analysis (CoMFA) [1,2,3,4,5]
It is possible to select a cluster of variables, rather than a single variable, by a smart region definition (SRD) procedure, which is as advanced as the GOLPE algorithm [10]
The performance of the Improvement of the Prediction Power of the CoMFA and CoMSIA Models on Histamine H3 ... 549 different CoMFA and CoMSIA models were evaluated by modeling a data set of histamine H3 antagonists
Summary
One of the most frequently used QSAR techniques is the comparative molecular field analysis (CoMFA) [1,2,3,4,5]. The CoMFA method was developed to take into account the effect of steric and electrostatic interactions, which are involved in blocking a molecule from its receptor. Thousands of interactions participate in the model These variables consist of two types: some of them have a correlation with biological activity and the others are noisy variables, which are poorly informative and irrelevant to the biological activities [5]. An intelligence variable selection with true judgment between informative and noisy variables could generate an ideal model, which is predictive, robust, and has no molecule labeled as an outlier with it. The new generations of HH3R antagonists are non-imidazole based They contain at least one basic amine, either a piperidine or pyrolidine, which is connected by an alkyl linkage to an aromatic ring. The interaction of the negatively charged carboxylic group of Asp114 on the third helix of the HHR3 and a protonated amine group of an antagonist, is the common point in all of the docking results of HHR3 antagonists by different homology modelling [27,28,29,30,31]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
