externelly/p2rank repository overview

⁠P2Rank

This is an unofficial Docker image running the P2Rank protein pocket prediction method.
See the official GitHub repository for additional information (https://github.com/rdk/p2rank⁠) or use the PrankWeb (https://prankweb.cz/⁠) web server.

⁠Setup

Pull the P2Rank Docker image and build a container using the following command:
docker run -v ${PWD}/mount/:/p2rank/mount -it externelly/p2rank:latest

Once the Docker container is running, it will create a persistant mount folder in your current working directory.
Create a mount/pdbs/ folder and copy all the PDB files you want to be analyzed by P2Rank.

⁠Run

# Create a dataset.ds file containing the path to all PDB files 
find mount/pdbs/ -type f > dataset.ds

# Run P2Rank on all PDB files and save results to mount/output/
./prank.sh predict dataset.ds -o mount/output/

⁠Comments

Leave a message or open an issue regarding the Docker image at:
https://github.com/eporetsky/PlantDiffusion/tree/main/docker/P2Rank⁠

⁠Cite

• Krivák, R., & Hoksza, D. (2018). P2Rank: machine learning based tool for rapid and accurate prediction of ligand binding sites from protein structure. Journal of cheminformatics, 10, 1-12.
• Jendele, L., Krivak, R., Skoda, P., Novotny, M., & Hoksza, D. (2019). PrankWeb: a web server for ligand binding site prediction and visualization. Nucleic acids research, 47(W1), W345-W349.