PockDrug: A Model for Predicting Pocket Druggability That Overcomes Pocket Estimation Uncertainties
- PMID: 25835082
- DOI: 10.1021/ci5006004
PockDrug: A Model for Predicting Pocket Druggability That Overcomes Pocket Estimation Uncertainties
Abstract
Predicting protein druggability is a key interest in the target identification phase of drug discovery. Here, we assess the pocket estimation methods' influence on druggability predictions by comparing statistical models constructed from pockets estimated using different pocket estimation methods: a proximity of either 4 or 5.5 Å to a cocrystallized ligand or DoGSite and fpocket estimation methods. We developed PockDrug, a robust pocket druggability model that copes with uncertainties in pocket boundaries. It is based on a linear discriminant analysis from a pool of 52 descriptors combined with a selection of the most stable and efficient models using different pocket estimation methods. PockDrug retains the best combinations of three pocket properties which impact druggability: geometry, hydrophobicity, and aromaticity. It results in an average accuracy of 87.9% ± 4.7% using a test set and exhibits higher accuracy (∼5-10%) than previous studies that used an identical apo set. In conclusion, this study confirms the influence of pocket estimation on pocket druggability prediction and proposes PockDrug as a new model that overcomes pocket estimation variability.
Similar articles
-
PockDrug-Server: a new web server for predicting pocket druggability on holo and apo proteins.Nucleic Acids Res. 2015 Jul 1;43(W1):W436-42. doi: 10.1093/nar/gkv462. Epub 2015 May 8. Nucleic Acids Res. 2015. PMID: 25956651 Free PMC article.
-
Combining global and local measures for structure-based druggability predictions.J Chem Inf Model. 2012 Feb 27;52(2):360-72. doi: 10.1021/ci200454v. Epub 2012 Jan 5. J Chem Inf Model. 2012. PMID: 22148551
-
Drug-like density: a method of quantifying the "bindability" of a protein target based on a very large set of pockets and drug-like ligands from the Protein Data Bank.J Chem Inf Model. 2010 Nov 22;50(11):2029-40. doi: 10.1021/ci100312t. Epub 2010 Oct 26. J Chem Inf Model. 2010. PMID: 20977231
-
Structure-based computational analysis of protein binding sites for function and druggability prediction.J Biotechnol. 2012 Jun 15;159(3):123-34. doi: 10.1016/j.jbiotec.2011.12.005. Epub 2011 Dec 14. J Biotechnol. 2012. PMID: 22197384 Review.
-
Investigating drug-target association and dissociation mechanisms using metadynamics-based algorithms.Acc Chem Res. 2015 Feb 17;48(2):277-85. doi: 10.1021/ar500356n. Epub 2014 Dec 12. Acc Chem Res. 2015. PMID: 25496113 Review.
Cited by
-
The druggable genome: Twenty years later.Front Bioinform. 2022 Sep 30;2:958378. doi: 10.3389/fbinf.2022.958378. eCollection 2022. Front Bioinform. 2022. PMID: 36304325 Free PMC article.
-
Proteome level analysis of drug-resistant Prevotella melaninogenica for the identification of novel therapeutic candidates.Front Microbiol. 2023 Sep 22;14:1271798. doi: 10.3389/fmicb.2023.1271798. eCollection 2023. Front Microbiol. 2023. PMID: 37808310 Free PMC article.
-
Structural Impacts of Drug-Resistance Mutations Appearing in HIV-2 Protease.Molecules. 2021 Jan 25;26(3):611. doi: 10.3390/molecules26030611. Molecules. 2021. PMID: 33503916 Free PMC article.
-
Toward physics-based precision medicine: Exploiting protein dynamics to design new therapeutics and interpret variants.Protein Sci. 2024 Mar;33(3):e4902. doi: 10.1002/pro.4902. Protein Sci. 2024. PMID: 38358129 Free PMC article. Review.
-
Inhibition of the hexamerization of SARS-CoV-2 endoribonuclease and modeling of RNA structures bound to the hexamer.Sci Rep. 2022 Mar 9;12(1):3860. doi: 10.1038/s41598-022-07792-2. Sci Rep. 2022. PMID: 35264667 Free PMC article.
MeSH terms
Substances
LinkOut - more resources
Full Text Sources
Medical
