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

2013-06-01
Erdas, Ozlem
Andac, Cenk A.
Gurkan-Alp, A. Selen
Alpaslan, Ferda Nur
Buyukbingol, Erdem
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 (c) 2013 John Wiley & Sons, Ltd.
JOURNAL OF CHEMOMETRICS

Suggestions

High-Throughput Screening and Quantitation of Target Compounds in Biofluids by Coated Blade Spray-Mass Spectrometry
Tascon, Marcos; Gomez-Rios, German Augusto; Reyes-Garces, Nathaly; Poole, Justen; Boyacı, Ezel; Pawliszyn, Janusz (American Chemical Society (ACS), 2017-08-15)
Most contemporary methods of screening and quantitating controlled substances and therapeutic drugs in biofluids typically require laborious, time-consuming, and expensive analytical workflows. In recent years, our group has worked toward developing microextraction (mu e)-mass spectrometry (MS) technologies that merge all of the tedious steps of the classical methods into a simple, efficient, and low-cost methodology. Unquestionably, the automation of these technologies allows for faster sample throughput, ...
Modeling and predicting binding affinity of phencyclidine-like compounds using machine learning methods
Erdas, Ozlem; Buyukbingol, Erdem; Alpaslan, Ferda Nur; Adejare, Adeboye (Wiley, 2010-01-01)
Machine learning methods have always been promising in the science and engineering fields, and the use of these methods in chemistry and drug design has advanced especially since the 1990s. In this study, molecular electrostatic potential (MEP) surfaces of phencyclidine-like (PCP-like) compounds are modeled and visualized in order to extract features that are useful in predicting binding affinities. In modeling, the Cartesian coordinates of MEP surface points are mapped onto a spherical self-organizing map ...
Predicting the binding affinities of drug-protein interaction by analyzing the images of binding sites
Erdaş, Özlem; Alpaslan, Ferda Nur; Büyükbingöl, Erdem; Department of Computer Engineering (2013)
Analysis of protein-ligand interactions plays an important role in designing safe and efficient drugs, contributing to drug discovery and development. Recently, machine learning methods have been found useful in drug design, which utilize intelligent techniques to predict unknown protein-ligand interactions by learning from specific properties of known protein-ligand interactions. The aim of this thesis is to propose a novel computational model, Compressed Images for Affinity Prediction (CIFAP), to predict ...
In-Depth Method for the Characterization of Glycosylation in Manufactured Recombinant Monoclonal Antibody Drugs
Song, Ting; Özcan Kabasakal, Süreyya; Becker, Alicia; Lebrilla, Carlito B. (American Chemical Society (ACS), 2014-06-17)
The glycosylation in recombinant monoclonal antibody (rMab) drugs is a major concern in the biopharmaceutical industry as it impacts the drugs' many attributes. Characterization is important but complicated by the intricate structures, microheterogeneity, and the limitations of current tools for structural analysis. In this study, we developed a liquid chromatography-mass spectrometry (LC-MS) N-glycan library based on eight commercial rMab drugs. A library of over 70 structures was developed for the rapid c...
Solid Phase Microextraction-Based Miniaturized Probe and Protocol for Extraction of Neurotransmitters from Brains in Vivo
Lendor, Sofia; Hassani, Seyed-Alireza; Boyacı, Ezel; Singh, Varoon; Womelsdorf, Thilo; Pawliszyn, Janusz (American Chemical Society (ACS), 2019-04-02)
Despite the importance of monitoring and correlating neurotransmitter concentrations in the brain with observable behavior and brain areas in which they act, in vivo measurement of multiple neurochemicals in the brain remains a challenge. Here, we propose an alternative solid phase microextraction-based (SPME) chemical biopsy approach as a viable method for acquirement of quantitative information on multiple neurotransmitters by one device within a single sampling event, with multisite measurement capabilit...
Citation Formats
O. Erdas, C. A. Andac, A. S. Gurkan-Alp, F. N. Alpaslan, and E. Buyukbingol, “Compressed images for affinity prediction (CIFAP): a study on predicting binding affinities for checkpoint kinase 1 protein inhibitors,” JOURNAL OF CHEMOMETRICS, pp. 155–164, 2013, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/42999.