Premium
Quantitative Structure–Activity Relationship Models for Predicting Biological Properties, Developed by Combining Structure‐ and Ligand‐Based Approaches: An Application to the Human Ether‐a‐go‐go‐Related Gene Potassium Channel Inhibition
Author(s) -
Coi Alessio,
Massarelli Ilaria,
Saraceno Marilena,
Carli Niccolò,
Testai Lara,
Calderone Vincenzo,
Bianucci Anna Maria
Publication year - 2009
Publication title -
chemical biology and drug design
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.59
H-Index - 77
eISSN - 1747-0285
pISSN - 1747-0277
DOI - 10.1111/j.1747-0285.2009.00873.x
Subject(s) - chemical space , biological system , molecular descriptor , quantitative structure–activity relationship , test set , training set , set (abstract data type) , molecular model , chemistry , computer science , computational biology , artificial intelligence , drug discovery , machine learning , stereochemistry , biology , biochemistry , programming language
A strategy for developing accurate quantitative structure–activity relationship models enabling predictions of biological properties, when suitable knowledge concerning both ligands and biological target is available, was tested on a data set where molecules are characterized by high structural diversity. Such a strategy was applied to human ether‐a‐go‐go‐related gene K + channel inhibition and consists of a combination of ligand‐ and structure‐based approaches, which can be carried out whenever the three‐dimensional structure of the target macromolecule is known or may be modeled with good accuracy. Molecular conformations of ligands were obtained by means of molecular docking, performed in a previously built theoretical model of the channel pore, so that descriptors depending upon the three‐dimensional molecular structure were properly computed. A modification of the directed sphere‐exclusion algorithm was developed and exploited to properly splitting the whole dataset into Training/Test set pairs. Molecular descriptors, computed by means of the codessa program, were used for the search of reliable quantitative structure–activity relationship models that were subsequently identified through a rigorous validation analysis. Finally, pIC 50 values of a prediction set, external to the initial dataset, were predicted and the results confirmed the high predictive power of the model within a quite wide chemical space.