istar: A Web Platform for Large-Scale Protein-Ligand Docking

Abstract

Protein-ligand docking is a key computational method in the design of starting points for the drug discovery process. We are motivated by the desire to automate large-scale docking using our popular docking engine idock and thus have developed a publicly-accessible web platform called istar. Without tedious software installation, users can submit jobs using our website. Our istar website supports 1) filtering ligands by desired molecular properties and previewing the number of ligands to dock, 2) monitoring job progress in real time, and 3) visualizing ligand conformations and outputting free energy and ligand efficiency predicted by idock, binding affinity predicted by RF-Score, putative hydrogen bonds, and supplier information for easy purchase, three useful features commonly lacked on other online docking platforms like DOCK Blaster or iScreen. We have collected 17,224,424 ligands from the All Clean subset of the ZINC database, and revamped our docking engine idock to version 2.0, further improving docking speed and accuracy, and integrating RF-Score as an alternative rescoring function. To compare idock 2.0 with the state-of-the-art AutoDock Vina 1.1.2, we have carried out a rescoring benchmark and a redocking benchmark on the 2,897 and 343 protein-ligand complexes of PDBbind v2012 refined set and CSAR NRC HiQ Set 24Sept2010 respectively, and an execution time benchmark on 12 diverse proteins and 3,000 ligands of different molecular weight. Results show that, under various scenarios, idock achieves comparable success rates while outperforming AutoDock Vina in terms of docking speed by at least 8.69 times and at most 37.51 times. When evaluated on the PDBbind v2012 core set, our istar platform combining with RF-Score manages to reproduce Pearson's correlation coefficient and Spearman's correlation coefficient of as high as 0.855 and 0.859 respectively between the experimental binding affinity and the predicted binding affinity of the docked conformation. istar is freely available at http://istar.cse.cuhk.edu.hk/idock.

In silico prediction and in vitro and in vivo validation of acaricide fluazuron as a potential inhibitor of FGFR3 and a candidate anticancer drug for bladder carcinoma

“…The free and open‐source docking software idock v2.2.1 was executed to predict the binding conformations and the binding affinities of the 3,167 compounds upon docking against the FGFR3 structure. Program settings were tuned to make the conformational searching procedure more exhaustive than the default settings.…”

“…We used the free and open‐source protein–ligand docking software idock together with the binding affinity prediction software RF‐Score‐v3 to virtually screen and rank worldwide approved small‐molecule drugs (including but not limited to those approved by US FDA) with potential ability to inhibit FGFR3, and then used the molecular visualization tool iview to inspect and analyze putative interactions. Among the high‐scoring compounds shortlisted computationally, six were purchased for experimental validation in vitro in BC cell lines RT112 and RT4 via cell viability assays, cell apoptosis assays, Western blotting and immunoprecipitation experiments.…”

The Importance of the Regression Model in the Structure-Based Prediction of Protein-Ligand Binding

“…Now because this study focuses on co-crystallized ligands, there is only one conformer per molecule (k=1) and thus the intramolecular contribution cancels out giving: [9] for an explanation of how this conversion factor is derived). The values for the six weights were found by minimising the difference between predicted and measured binding affinity using a nonlinear optimisation algorithm (this process was not detailed in the original publication [13]).…”

“…RF-Score has recently been used [2] to discover a large number of innovative binders of antibacterial targets. This machine-learning scoring function has now been incorporated [9] into a large-scale docking tool for prospective virtual screening, which is freely available at http://istar.cse.cuhk.edu.hk/idock/. There is also a recent version of RF-Score [1] incorporating interatomic distance-dependent features to improve the characterization of the complex.…”

Machine‐Learning Techniques Applied to Antibacterial Drug Discovery

“…In practice, most of the generalized receptor-based machine-learning scoring functions described in the literature have not been publically released, and so are mere proofs of concept. To our knowledge, only NNScore 1.0 (26), NNScore 2.0 (27), and RF-Score (52, 59) are publically available. Nevertheless, though still in its infancy, the application of machine learning to antibiotic research specifically, and drug design generally, clearly has a bright future.…”