.. poké documentation master file, created by sphinx-quickstart on Tue Jul 15 12:04:06 2025. You can adapt this file completely to your liking, but it should at least contain the root `toctree` directive. Welcome to the Poké user guide ============================== .. toctree:: :maxdepth: 2 :hidden: Getting Started Descriptors Outputs Filters Structure Preparation CLI Reference Python Package Plugin Tutorials .. image:: img/poke-banner.svg :alt: banner :width: 800px :align: center :class: banner This guide documents Poké |release|. **Poké scouter** is a blazing fast pocket scouter based on CHARMM forcefield. It uses an energy-based approach to identify the low-energy regions of the protein and it is able to compute a set of descriptors for each pocket useful to characterize it. The descriptors are used then by a neural network model to assign a druggability score to the pocket. Designed to be used on long molecular dynamics trajectories, but it can be used also on single frames. **Get Started** If you are new to Poké, start here: * :doc:`Getting Started` to install the package and run it on a structure or a trajectory * :doc:`Tutorials` for a worked example on a cryptic pocket of TEM-1 β-lactamase **How to cite** If you use Poké in your research, please cite: Colasurdo, E., Boldrini, A., Terruzzi, L., Langini, C., Risueño Fernández, C., Varricchio, C., Primavera, E., Cassese, E., Patsilinakos, A. & Spagnolli, G. *Poké: Fast and Reliable Neural-Network-Based Identification of Protein Ligandable Sites.* ACS Omega (2026). https://doi.org/10.1021/acsomega.6c04816 **Code and data** * Source code on GitHub: https://github.com/SibyllaBiotech/poke * Source code archived on Zenodo: https://doi.org/10.5281/zenodo.19634786 * Datasets used in the paper, on Zenodo: https://doi.org/10.5281/zenodo.19635030 **Licence** Poké is free software released under the `MIT licence `_. The text and figures of this guide are released under the `CC BY 4.0 `_ licence.