PyVOL: a PyMOL plugin for visualization, comparison, and volume calculation of drug-binding sites
Smith, R. H. B.; Dar, A. C.; Schlessinger, A.
Show abstract
MotivationBinding pocket volumes are a simple yet important predictor of small molecule binding; however, generating visualizations of pocket topology and performing meaningful volume comparisons can be difficult with available tools. Current programs for accurate volume determination rely on extensive user input to define bulk solvent boundaries and to partition cavities into subpockets, increasing inter-user variability in measurements as well as time demands. ResultsWe developed PyVOL, a python package with a PyMOL interface and GUI, to visualize, to characterize, and to compare binding pockets. PyVOLs pocket identification algorithm is designed to maximize reproducibility through minimization of user-provided parameters, avoidance of grid-based methods, and automated subpocket identification. This approach permits efficient, scalable volume calculations. AvailabilityPyVOL is released under the MIT License. Source code and documentation are available through github (https://github.com/schlessingerlab/pyvol/) with distribution through PyPI (bio-pyvol). Contactavner.schlessinger@mssm.edu, arvin.dar@mssm.edu
Matching journals
The top 3 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Fast Local Alignment of Protein Pockets (FLAPP): A system-compiled program for large-scale binding site alignment 94%
- Sampling and ranking of protein conformations using machine learning techniques do not improve quality of rigid protein-protein docking 94%
- ArtiDock: accurate Machine Learning approach to protein-ligand docking optimized for high-throughput virtual screening 94%
Similar papers in this journal
- Robust prediction of relative binding energies for protein-protein complex mutations using free energy perturbation calculations 92%
- ModelCIF: An extension of PDBx/mmCIF data representation for computed structure models 92%
- Prediction of disordered regions in proteins with recurrent Neural Networks and protein dynamics 91%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.