Compressed images for affinity prediction (CIFAP): a study on predicting binding affinities for checkpoint kinase 1 protein inhibitors

• Published in: Journal of chemometrics 2013-06, Vol.27 (6), p.155-164
• Main Authors: Erdas, Ozlem, Andac, Cenk A., Selen Gurkan-Alp, A., Alpaslan, Ferda Nur, Buyukbingol, Erdem
• Format: Article
• Language: English
• Subjects: adaptive neuro-fuzzy inference system; binding affinity; Binding sites; drug-protein interaction; Drugs; Molecules; prediction; Protease inhibitors; Proteins; R&D; Research & development; support vector regression
• ISSN: 0886-9383; 1099-128X
• DOI: 10.1002/cem.2503

Analyses of known protein–ligand interactions play an important role in designing novel and efficient drugs, contributing to drug discovery and development. Recently, machine learning methods have proven useful in the design of novel drugs, which utilize intelligent techniques to predict the outcome of unknown protein–ligand interactions by learning from the physical and geometrical properties of known protein–ligand interactions. The aim of this study is to work through a specific example of a novel computational method, namely compressed images for affinity prediction (CIFAP), in which binding affinities for structurally related ligands in complexes with human checkpoint kinase 1 (CHK1) are predicted. The CIFAP algorithm presented here relates published pIC 50 values of 57 compounds, derived from a thienopyridine pharmacophore, in complexes with CHK1 to their two‐dimensional (2D) electrostatic potential images compressed in orthogonal dimensions. Patterns obtained from the 2D images are then used as inputs in regression and learning algorithms such as support vector regression (SVR) and adaptive neuro‐fuzzy inference system (ANFIS) methods to validate the experimental pIC 50 values. This study revealed that the 2D image pixels in the vicinity of bound ligand surfaces provide more relevant information to make correlations with the empirical pIC 50 values. As compared with ANFIS, SVR gave rise to the lowest root mean square errors and the greatest correlations, suggesting that SVR could be a plausible choice of machine learning methods in predicting binding affinities by CIFAP. Copyright © 2013 John Wiley & Sons, Ltd. A novel data modeling method for prediction of binding affinity of ligands to their receptor, which uses the binding pose of the ligand and the electrostatic potential grid map of the complex, was proposed. The model was tested on a group of ligands based on thienopyridine pharmacophore in complex with the checkpoint kinase 1 protein. A support vector regression (SVR) and an adaptive neuro‐fuzzy inference system were used for predicting binding affinities where SVR gave rise to the finest results.