LIBRA-WA: a web application for ligand binding site detection and protein function recognition

Toti, Daniele; Hung, Le Viet; Tortosa, Valentina; Brandi, Valentina; Polticelli, Fabio

doi:10.1093/bioinformatics/btx715

Cited by 26 publications

(25 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides, from a technological standpoint, both DockingApp RF and the original DockingApp [ 27 ] are also planned to be released in the near future as a single server-side web application in a similar fashion to how the authors’ earlier released tools for catalytic site detection and binding site detection, ASSIST [ 59 ] and LIBRA [ 60 ], respectively, were merged and included back then in the LIBRA-WA [ 61 ] web application. This would, on the one hand, provide users with a convenient way of accessing DockingApp RF’s functionalities regardless of the specific platform or operating system while leveraging the computational power of a dedicated server for a more efficient computation of the docking results with respect to a desktop computer.…”

Section: Future Developmentmentioning

confidence: 99%

DockingApp RF: A State-of-the-Art Novel Scoring Function for Molecular Docking in a User-Friendly Interface to AutoDock Vina

Macari

Toti

Pasquadibisceglie

et al. 2020

IJMS

Self Cite

View full text Add to dashboard Cite

Motivation: Bringing a new drug to the market is expensive and time-consuming. To cut the costs and time, computer-aided drug design (CADD) approaches have been increasingly included in the drug discovery pipeline. However, despite traditional docking tools show a good conformational space sampling ability, they are still unable to produce accurate binding affinity predictions. This work presents a novel scoring function for molecular docking seamlessly integrated into DockingApp, a user-friendly graphical interface for AutoDock Vina. The proposed function is based on a random forest model and a selection of specific features to overcome the existing limits of Vina’s original scoring mechanism. A novel version of DockingApp, named DockingApp RF, has been developed to host the proposed scoring function and to automatize the rescoring procedure of the output of AutoDock Vina, even to nonexpert users. Results: By coupling intermolecular interaction, solvent accessible surface area features and Vina’s energy terms, DockingApp RF’s new scoring function is able to improve the binding affinity prediction of AutoDock Vina. Furthermore, comparison tests carried out on the CASF-2013 and CASF-2016 datasets demonstrate that DockingApp RF’s performance is comparable to other state-of-the-art machine-learning- and deep-learning-based scoring functions. The new scoring function thus represents a significant advancement in terms of the reliability and effectiveness of docking compared to AutoDock Vina’s scoring function. At the same time, the characteristics that made DockingApp appealing to a wide range of users are retained in this new version and have been complemented with additional features.

show abstract

Section: Future Developmentmentioning

confidence: 99%

DockingApp RF: A State-of-the-Art Novel Scoring Function for Molecular Docking in a User-Friendly Interface to AutoDock Vina

Macari

Toti

Pasquadibisceglie

et al. 2020

IJMS

Self Cite

View full text Add to dashboard Cite

show abstract

“…A simple solution to the Jmol issue is to use JSmol (10), a JavaScript replacement for Jmol. This is the avenue taken by 3DLigandSite (11), COFACTOR (12,13), COACH (14) ISMBLAB-LIG (15) and LIBRA (16). Though JSmol supports complex visualization options, it suffers from performance issues due to inefficiencies introduced when migrating Jmol code from Java to JavaScript.…”

Section: Introductionmentioning

confidence: 99%

PrankWeb: a web server for ligand binding site prediction and visualization

Jendele

Krivák

Škoda

et al. 2019

Nucleic Acids Research

288

177

View full text Add to dashboard Cite

PrankWeb is an online resource providing an interface to P2Rank, a state-of-the-art method for ligand binding site prediction. P2Rank is a template-free machine learning method based on the prediction of local chemical neighborhood ligandability centered on points placed on a solvent-accessible protein surface. Points with a high ligandability score are then clustered to form the resulting ligand binding sites. In addition, PrankWeb provides a web interface enabling users to easily carry out the prediction and visually inspect the predicted binding sites via an integrated sequence-structure view. Moreover, PrankWeb can determine sequence conservation for the input molecule and use this in both the prediction and result visualization steps. Alongside its online visualization options, PrankWeb also offers the possibility of exporting the results as a PyMOL script for offline visualization. The web frontend communicates with the server side via a REST API. In high-throughput scenarios, therefore, users can utilize the server API directly, bypassing the need for a web-based frontend or installation of the P2Rank application. PrankWeb is available at http://prankweb.cz/, while the web application source code and the P2Rank method can be accessed at https://github.com/jendelel/PrankWebApp and https://github.com/rdk/p2rank, respectively.

show abstract

“…In this work, contacts between fragments and binding site’s residues were analyzed using a starting dataset derived from the ligand binding sites database of LIBRA [24]. The fragments were generated by applying BRICS [14] decomposition as implemented in the Python chemoinformatic library RDKIT (ver.…”

Section: Methodsmentioning

confidence: 99%

“…The fragment-residue contact datasets were derived from LIBRA’s binding site database (whose last update dates back to 2017) [24]. LIBRA’s binding site is a semi-exhaustive binding site database derived from PDB [16] containing 209,431 binding sites.…”

Section: Methodsmentioning

confidence: 99%

Fragment-Based Ligand-Protein Contact Statistics: Application to Docking Simulations

Macari

Toti

Moro

et al. 2019

IJMS

Self Cite

View full text Add to dashboard Cite

In this work, the information contained in the contacts between fragments of small-molecule ligands and protein residues has been collected and its exploitability has been verified by using the scoring of docking simulations as a test case for bringing about a proof of concept. Contact statistics between small-molecule fragments and binding site residues were collected and analyzed using a dataset composed of 200,000+ binding sites and associated ligands, derived from the database of the LIBRA ligand binding site recognition software, as a starting point. The fragments were generated by applying the decomposition algorithm implemented in BRICS. A simple “potential” based on the contact frequencies was tested against the CASF-2013 benchmark; its performance was then evaluated through the rescoring of docking poses generated for the DUD-E dataset. The results obtained indicate that this approach, its simplicity notwithstanding, yields promising results that are comparable, and in some cases, superior, to those obtained with other, more complex scoring functions.

show abstract

LIBRA-WA: a web application for ligand binding site detection and protein function recognition

Abstract: Supplementary data are available at Bioinformatics online.

Cited by 26 publications

References 16 publications

DockingApp RF: A State-of-the-Art Novel Scoring Function for Molecular Docking in a User-Friendly Interface to AutoDock Vina

DockingApp RF: A State-of-the-Art Novel Scoring Function for Molecular Docking in a User-Friendly Interface to AutoDock Vina

PrankWeb: a web server for ligand binding site prediction and visualization

Fragment-Based Ligand-Protein Contact Statistics: Application to Docking Simulations

Contact Info

Product

Resources

About