PrankWeb 3: accelerated ligand-binding site predictions for experimental and modelled protein structures

By David Jakubec, Petr Skoda, Radoslav Krivák, Marián Novotný, David Hoksza. 2022

49 citations recorded by the source corpus.

Abstract Knowledge of protein–ligand binding sites (LBSs) enables research ranging from protein function annotation to structure-based drug design. To this end, we have previously developed a stand-alone tool, P2Rank, and the web server PrankWeb (https://prankweb.cz/) for fast and accurate LBS prediction. Here, we present significant enhancements to PrankWeb. First, a new, more accurate evolutionary conservation estimation pipeline based on the UniRef50 sequence database and the HMMER3 package is introduced. Second, PrankWeb now allows users to enter UniProt ID to carry out LBS predictions in situations where no experimental structure is available by utilizing the AlphaFold model database. Additionally, a range of minor improvements has been implemented. These include the ability to deploy PrankWeb and P2Rank as Docker containers, support for the mmCIF file format, improved public REST API access, or the ability to batch download the LBS predictions for the whole PDB archive and parts of the AlphaFold database.

Subfields: Computational Theory and Mathematics, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

1. Jianzhu Ma
2. Jian Peng
3. Bonnie Berger
4. Shitong Luo
5. Sheng Wang
6. Jinbo Xu

In Molecular Biology

1. Jianzhu Ma
2. Jian Peng
3. Jinbo Xu
4. Bonnie Berger
5. Shitong Luo
6. Sheng Wang
7. Shiwang Liu
8. Siqi Sun

Citations in the corpus

• High-resolution de novo structure prediction from primary sequence (2022, background): “One of the successful pre-trained models in biology is the pre-trained protein language models, which has been demonstrated to be able to extract biologically meaningful representations for various tasks such as protein contact prediction (11–14), protein function prediction (15,16), zero-shot mutat”