Abstract
We used protein−compound docking simulations to develop a structure‐based quantitative structure−activity relationship (QSAR) model. The prediction model used docking scores as descriptors. The binding free energy was approximated by a weighted average of docking scores for multiple proteins. This approximation was based on a pharmacophore model of receptor pockets and compounds. The weights of the docking scores were restricted to small values to avoid unrealistic weights by a regularization term. Additional outlier elimination improved the results. We applied this method to two groups of targets. The first target was the kinase family. The cross‐validation results of 107 kinase proteins showed that the RMSE of predicted binding free energies was 1.1 kcal/mol. The second target was the matrix metalloproteinase (MMP) family, which has been difficult for docking programs. MMPs require metal‐binding groups in their inhibitor structures in many cases. A quantum effect contributes to the metal−ligand interaction. Despite this difficulty, the present method worked well for the MMPs. This method showed that the RMSE of predicted binding free energies was 1.1 kcal/mol. In comparison, with the original docking method the RMSE was 1.7 kcal/mol. The results suggest that the present QSAR model should be applied to general target proteins.
Highlights
We used proteinÀcompound docking simulations predicted binding free energies was 1.1 kcal/mol
The quantitative structureÀactivity relationship (QSAR) ap- the root-mean-square error (RMSE) was 1.54 kcal/mol for about 97 kinases and 18,491 proach is a useful tool for optimizing leads and predicting compounds selected from the ChEMBL database
We develop a binding-energy prediction method based on the proteinÀcompound docking scores obtained by a docking program; the present method is a modified version of our QSAR method.[18]
Summary
We used proteinÀcompound docking simulations predicted binding free energies was 1.1 kcal/mol. The weights of the docking scores were restricted that the RMSE of predicted binding free energies was to small values to avoid unrealistic weights by a regulariza- 1.1 kcal/mol. We developed QSAR methods for the affinity prediction of a compound by using docking studies against multiple proteins.[17,18,19] We used a proteinÀcompound affinity matrix as the set of descriptors www.molinf.com targets. Either these coefficients should be restricted to a range of realistic values, or the applicability domain should be very restricted around the known experimental data. The method was applied to the kinases and the matrix metalloproteinases (MMPs) of the ChEMBL database.[22,23,24]
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.
