Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
P2Rank: Protein-ligand binding site prediction from protein structure based on machine learning.
| Date | Stars |
|---|---|
| 2026-07-31 | 446 |
| 2026-08-04 | 448 |
| 2026-08-06 | 450 |
Today
+2 stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<p align="left">
<img src="https://github.com/rdk/p2rank/blob/develop/misc/img/p2rank_logo.svg?raw=true" width="280" alt="P2Rank" title="logo">
</p>
Ligand-binding site prediction based on machine learning.
<p align="center">
<img src="https://github.com/rdk/p2rank/blob/develop/misc/img/p2rank_sas_points.png?raw=true" width="600" alt="P2Rank illustration">
</p>
<a href="https://github.com/rdk/p2rank/releases" title="go to the release page"><img src="https://img.shields.io/badge/release-2.5.1-green.svg"></img></a>
[](https://github.com/rdk/p2rank/actions)
[](/LICENSE.txt)
### Description
P2Rank is a stand-alone command-line program for fast and accurate prediction of ligand-binding sites from protein structures.
It achieves high prediction success rates without relying on external software for computation of complex features or on a database of known protein-ligand templates.
### ✨ What's new?
* Available in **2.6** (alpha): pocket-grid & per-pocket descriptor exports, [cofactor-as-surface handling](documentation/cofactors.md), [modified-to-canonical residue mapping](documentation/aa-mapping.md), and additional supported methods for rescoring (see [alpha release](https://github.com/rdk/p2rank/releases/tag/2.6-alpha)).
* Version **2.5** brings speed optimizations (~2x faster prediction), ChimeraX visualizations, and improvements to rescoring (`fpocket-rescore` command).
* Version **2.4.2** adds support for BinaryCIF (`.bcif`) input and rescoring of fpocket predictions in `.cif` format.
* Version **2.4** adds support for mmCIF (`.cif`) input and contains a special profile for predictions on AlphaFold models and NMR/cryo-EM structures.
Version 2.6 also brings substantially improved documentation, headlined by a new comprehensive **[User Guide](documentation/user-guide.md)** that covers installation, prediction, rescoring, configuration, performance tuning, and troubleshooting in one place. Several topic-specific docs have been added or expanded alongside it (see the [documentation index](documentation/readme.md)).
### Requirements
* **Runtime**: Java 17 or later (tested up to Java 26)
* **Visualization** (optional): PyMOL or ChimeraX
Runs on Linux, macOS, and Windows. \
On Windows, run from Git Bash to avoid command-line formatting issues.
### Setup
P2Rank requires no installation. Binary packages are available as GitHub Releases.
* **Download**: https://github.com/rdk/p2rank/releases
* Source code: https://github.com/rdk/p2rank
* Datasets: https://github.com/rdk/p2rank-datasets
* **[User Guide](documentation/user-guide.md)**: comprehensive documentation for new and advanced users
* All documentation: [documentation/](documentation/readme.md)
### Usage
<pre>
<b>prank</b> predict -f test_data/1fbl.pdb # predict pockets on a single pdb file
</pre>
See more usage examples below...
### Algorithm
P2Rank makes predictions by scoring and clustering points on the protein's solvent accessible surface.
Ligandability score of individual points is determined by a machine learning model trained on a dataset of known protein-ligand complexes.
For more details, see the slides and publications.
Presentation slides introducing the original version of the algorithm: [Slides (pdf)](https://bit.ly/p2rank-slides)
### Publications
If you use P2Rank, please cite relevant papers: <a href="misc/citations.md" title="go to the BibTex citations" target="_blank"><img align="right" src="https://img.shields.io/badge/BibTeX-eee"></img></a>
* [Software article](https://doi.org/10.1186/s13321-018-0285-8) about P2Rank pocket prediction tool
Krivak R, Hoksza D. ***P2Rank: machine learning based tool for rapid and accurate prediction of ligand binding sExcerpt of 17,165 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:8d0253ed8e9aefd9, topic:bioinformatics, topic:drug-discovery, desc:protein