Skip to content

gandrianov/LUNA

 
 

Repository files navigation

Documentation Status Build Status Code Coverage Package on PyPi License

LUNA [1] is an object-oriented Python 3 toolkit for drug design that makes it easy to analyze very large data sets of 3D molecular structures and complexes, and that allows identifying, filtering, and visualizing atomic interactions.

LUNA also implements three hashed interaction fingerprints (IFP): Extended Interaction FingerPrint (EIFP), Functional Interaction FingerPrint (FIFP), and Hybrid Interaction FingerPrint (HIFP) -- inspired by ECFP [2], FCFP [2], and E3FP [3]. These IFPs encode molecular interactions at different levels of detail, provide several functionalities to trace individual bits back to their original atomic substructures in the context of the binding site, and are RDKit-compatible.

Documentation is hosted by ReadTheDocs, and development occurs on GitHub.

Installation and Usage

The latest stable release (and required dependencies) can be installed as follows:

  1. Download LUNA’s environment.yml file.

  2. Create the Conda environment using the downloaded file:

    conda env create -f <LUNA-ENV-FILE>

  3. After creating the Conda environment, activate it:

    conda activate luna-env

  4. Finally, install LUNA from Pip:

    pip install luna

For additional installation options and usage instructions, refer to the documentation.

License

LUNA is available under the MIT License.

References

[1]Fassio, A. V.; Shub, L.; Ponzoni, L.; McKinley, J.; O’Meara, M. J.; Ferreira, R. S.; Keiser, M. J.; de Melo Minardi, R. C. Prioritizing Virtual Screening with Interpretable Interaction Fingerprints. J. Chem. Inf. Model. 2022. Access the paper Access the preprint on bioRxiv
[2](1, 2) Rogers, D.; Hahn, M. Extended-Connectivity Fingerprints. J. Chem. Inf. Model. 2010, 50 (5), 742–754. Access the paper
[3]Axen, S. D.; Huang, X.-P.; Cáceres, E. L.; Gendelev, L.; Roth, B. L.; Keiser, M. J. A Simple Representation of Three-Dimensional Molecular Structure. J. Med. Chem. 2017, 60 (17), 7393–7409. Access the paper Access the preprint on bioRxiv Access the recommendation on F1000Prime

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 53.0%
  • Python 47.0%