Improving the Accuracy of Protein‐Ligand Binding Mode Prediction Using a Molecular Dynamics‐Based Pocket Generation Approach. Issue 32 (4th December 2018)

• Record Type: Journal Article
• Authors: Araki, Mitsugu; Iwata, Hiroaki; Ma, Biao; Fujita, Atsuto; Terayama, Kei; Sagae, Yukari; Ono, Fumie; Tsuda, Koji; Kamiya, Narutoshi; Okuno, Yasushi
• Is Part Of: Journal of computational chemistry. Volume 39:Issue 32(2018)
• Page Start: 2679
• Page End: 2689
• Publication Date: 2018-12-04
• Subjects: protein -- in‐silico drug discovery -- molecular docking -- molecular dynamics simulation -- the binding free energy; Chemistry -- Data processing -- Periodicals; 542.85
• DOI: 10.1002/jcc.25715
• Languages: English
• ISSNs: 0192-8651

Abstract

Abstract : Protein‐drug binding mode prediction from the apo‐protein structure is challenging because drug binding often induces significant protein conformational changes. Here, the authors report a computational workflow that incorporates a novel pocket generation method. First, the closed protein pocket is expanded by repeatedly filling virtual atoms during molecular dynamics (MD) simulations. Second, after ligand docking toward the prepared pocket structures, binding mode candidates are ranked by MD/Molecular Mechanics Poisson‐Boltzmann Surface Area. The authors validated our workflow using CDK2 kinase, which has an especially‐closed ATP‐binding pocket in the apo‐form, and several inhibitors. The crystallographic pose coincided with the top‐ranked docking pose for 59% (34/58) of the compounds and was within the top five‐ranked ones for 88% (51/58), while those estimated by a conventional prediction protocol were 9% (5/58) and 50% (29/58), respectively. Our study demonstrates that the prediction accuracy is significantly improved by preceding pocket expansion, leading to generation of conformationally‐diverse binding mode candidates. © 2018 Wiley Periodicals, Inc. Abstract : In the drug discovery process, structural information about the binding mode of drug candidates toward their target protein is useful for optimizing the chemical structure of promising lead compounds. This article reports a computational workflow for predicting the protein‐ligand binding mode from the apo‐protein structure, which consists of the following steps: (1) expansion of the closed protein pocket by the virtual ligand, (2) ligand docking, and (3) ranking of binding mode candidates based on MD/MM‐PBSA.