Poké: Fast and Reliable Neural-Network-Based Identification of Protein Ligandable Sites
- 1Sibylla Biotech S.p.A. , Via Lillo del Duca 10 , ,
- 2University of Perugia , , Via del Liceo 1 , ,
- 3University of Naples Federico II , , Via Domenico Montesano, 49 , ,
Abstract
Accurate identification of ligandable pockets is of key relevance for structure-based drug design; however, their identification remains challenging, particularly for cryptic sites that become accessible only upon conformational changes. Here, we introduce Poké, a high-performance pocket scouting tool that combines energetic mapping with a neural-network-based ligandability score, enabling rapid and reliable binding site detection in both static structures and long-timescale molecular dynamics (MD) trajectories. Poké identifies low-energy regions on protein surfaces through probe-based grid energy calculations, expands and clusters these regions into coherent pocket volumes, and computes physicochemical descriptors that are integrated into a learned ligandability estimator. The scoring model is trained on pockets identified across large data sets using docking-derived binding score distributions, allowing robust ranking of candidate sites. Benchmarking on publicly available data sets demonstrates competitive pocket detection accuracy, improved ranking performance, and substantially enhanced computational efficiency compared to widely used pocket detectors. As a representative application, we apply Poké to mixed-solvent MD simulations of TEM-1 β-lactamase, showing efficient tracking of an experimentally validated cryptic pocket and its dynamic ligandability along the trajectory. Overall, Poké enables scalable, high-throughput ligandability assessment across extensive conformational landscapes.
Related
- Multiscale Neural Network Potential with Anisotropic Message Passing for the Fast and Accurate Simulation of Protein Dynamics and Enzymatic Reactions
- Pore-network homogeneity for mechanically reliable powder-compacted solid-electrolyte separators
- Identification of Endonuclease G binding protein using a method which specifically isolates binding partners within subcellular compartments
- Counterfeit Citri Reticulatae Pericarpium Identification: Multi‐Class Detection Using Vis/ NIR Spectroscopy and Residual Neural Networks
- Materials Property Prediction with a Site-Resolved Three-Dimensional Voxel Convolution Neural Network
BibTeX
@article{colasurdo2026poke,
title = {{Poké: Fast and Reliable Neural-Network-Based Identification of Protein Ligandable Sites}},
author = {Enrica Colasurdo and Alberto Boldrini and Luca Terruzzi and Cassiano Langini and Cristina Risueño Fernández and Carmine Varricchio and Erika Primavera and Emilia Cassese and Alexandros Patsilinakos and Giovanni Spagnolli},
journal = {ACS Omega},
year = {2026},
month = oct,
doi = {10.1021/acsomega.6c04816},
url = {https://pubs.acs.org/acsodf/article/doi/10.1021/acsomega.6c04816/5457565/Poke-Fast-and-Reliable-Neural-Network-Based},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Poké: Fast and Reliable Neural-Network-Based Identification of Protein Ligandable Sites
AU - Enrica Colasurdo
AU - Alberto Boldrini
AU - Luca Terruzzi
AU - Cassiano Langini
AU - Cristina Risueño Fernández
AU - Carmine Varricchio
AU - Erika Primavera
AU - Emilia Cassese
AU - Alexandros Patsilinakos
AU - Giovanni Spagnolli
PY - 2026
DA - 2026/10/23
JO - ACS Omega
DO - 10.1021/acsomega.6c04816
UR - https://pubs.acs.org/acsodf/article/doi/10.1021/acsomega.6c04816/5457565/Poke-Fast-and-Reliable-Neural-Network-Based
AB - Accurate identification of ligandable pockets is of key relevance for structure-based drug design; however, their identification remains challenging, particularly for cryptic sites that become accessible only upon conformational changes. Here, we introduce Poké, a high-performance pocket scouting tool that combines energetic mapping with a neural-network-based ligandability score, enabling rapid and reliable binding site detection in both static structures and long-timescale molecular dynamics (MD) trajectories. Poké identifies low-energy regions on protein surfaces through probe-based grid energy calculations, expands and clusters these regions into coherent pocket volumes, and computes physicochemical descriptors that are integrated into a learned ligandability estimator. The scoring model is trained on pockets identified across large data sets using docking-derived binding score distributions, allowing robust ranking of candidate sites. Benchmarking on publicly available data sets demonstrates competitive pocket detection accuracy, improved ranking performance, and substantially enhanced computational efficiency compared to widely used pocket detectors. As a representative application, we apply Poké to mixed-solvent MD simulations of TEM-1 β-lactamase, showing efficient tracking of an experimentally validated cryptic pocket and its dynamic ligandability along the trajectory. Overall, Poké enables scalable, high-throughput ligandability assessment across extensive conformational landscapes.
SN - 2470-1343
ER -