Molearn
Molearn: a Python package streamlining the design of generative models of biomolecular dynamics - Published in JOSS (2023)
Science Score: 95.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
✓DOI references
Found 4 DOI reference(s) in README and JOSS metadata -
✓Academic publication links
Links to: aps.org, joss.theoj.org, zenodo.org -
✓Committers with academic emails
5 of 9 committers (55.6%) from academic institutions -
○Institutional organization owner
-
✓JOSS paper metadata
Published in Journal of Open Source Software
Keywords
Repository
protein conformational spaces meet machine learning
Basic Info
- Host: GitHub
- Owner: Degiacomi-Lab
- License: gpl-3.0
- Language: Python
- Default Branch: master
- Homepage: https://degiacomi.org/software/molearn/
- Size: 226 MB
Statistics
- Stars: 47
- Watchers: 8
- Forks: 15
- Open Issues: 3
- Releases: 8
Topics
Metadata Files
README.md
molearn
protein conformational spaces meet machine learning
molearn is a Python package streamlining the implementation of machine learning models dedicated to the generation of protein conformations from example data obtained via experiment or molecular simulation.
Included in this repository are the following:
* Source code in the molearn folder
* Software documentation (API and FAQ) in the docs folder, also accessible at molearn.readthedocs.io.
* Example training and analysis scripts, along with example data, in the examples folder
Dependencies
The current version of molearn only supports Linux, and has verified to support Python >=3.9.
Required Packages
- numpy
- PyTorch (1.7+)
- Biobox
- MDAnalysis
Optional Packages
To prepare a raw trajectory for training: * mdtraj
To run energy evaluations with OpenMM: * OpenMM * openmmtorchplugin
To evaluate Sinkhorn distances during training: * geomloss
To calculate DOPE and Ramachandran scores during analysis: * Modeller (requires academic license) * cctbx
To run the GUI: * plotly * NGLView
Installation
Anaconda installation from conda-forge
The most recent release can be obtained through Anaconda:
conda install molearn -c conda-forge or the much faster mamba install -c conda-forge molearn
We advise the installation is carried out in a new environment.
Clone the repo and manually install
Manual installation requires the following three steps:
* Clone the repository git clone https://github.com/Degiacomi-Lab/molearn.git
* Install all required packages (see section Dependencies > Required Packages, above). The easiest way is by calling mamba install -c conda-forge --only-deps molearn, where the option --only-deps will install the molearn required dependencies but not molearn itself. Optionally, packages enabling additional molearn functionalities can also be installed. This has to be done manually (see links in Dependencies > Optional Packages).
* Use pip to install molearn from within the molearn directory python -m pip install .
Using molearn without installation
Molearn can used without installation by making the sure the requirements above are met, and adding the src directory to your path at the beginning of every script. For instance, to install all requirements in a new environment molearn_env:
conda env create --file environment.yml -n molearn_env
Then, within this environment, run scripts starting with:
import sys
sys.path.insert(0, 'path/to/molearn/src')
import molearn
Note in case of any installation issue, please consult our FAQ
Usage
- See example scripts in the
examplesfolder. - Jupyter notebook tutorials describing the usage of a trained neural network are available here.
- software API and a FAQ page are available at molearn.readthedocs.io.
References
If you use molearn in your work, please cite: S.C. Musson and M.T. Degiacomi (2023). Molearn: a Python package streamlining the design of generative models of biomolecular dynamics. Journal of Open Source Software, 8(89), 5523
Theory and benchmarks of a neural network training against protein conformational spaces are presented here: V.K. Ramaswamy, S.C. Musson, C.G. Willcocks, M.T. Degiacomi (2021). Learning protein conformational space with convolutions and latent interpolations, Physical Review X 11
Contributing
For information on how to report bugs, request new features, or contribute to the code, please see CONTRIBUTING.md. For any other question please contact matteo.degiacomi@ed.ac.uk.
Owner
- Name: Degiacomi Research Group
- Login: Degiacomi-Lab
- Kind: organization
- Email: matteo.t.degiacomi@durham.ac.uk
- Location: United Kingdom
- Website: www.degiacomi.org
- Twitter: MatteoDegiacomi
- Repositories: 9
- Profile: https://github.com/Degiacomi-Lab
JOSS Publication
Molearn: a Python package streamlining the design of generative models of biomolecular dynamics
Authors
Department of Physics, Durham University, United Kingdom
Department of Physics, Durham University, United Kingdom
Editor
Richard Gowers
Tags
machine learning molecular dynamics proteinsGitHub Events
Total
- Watch event: 5
- Delete event: 1
- Member event: 1
- Issue comment event: 2
- Push event: 27
- Pull request review event: 1
- Pull request event: 16
- Fork event: 4
- Create event: 2
Last Year
- Watch event: 5
- Delete event: 1
- Member event: 1
- Issue comment event: 2
- Push event: 27
- Pull request review event: 1
- Pull request event: 16
- Fork event: 4
- Create event: 2
Committers
Last synced: 7 months ago
Top Committers
| Name | Commits | |
|---|---|---|
| Matteo Degiacomi | d****m | 128 |
| SCM | s****n@d****k | 85 |
| Samuel Musson | w****1@n****k | 66 |
| gwirn | 7****n | 27 |
| Yanchen Zhu | r****u@g****m | 14 |
| rzhu | r****u@n****k | 5 |
| DEGIACOMI | x****5@d****k | 3 |
| Asal Azar | y****l@g****m | 1 |
| Samuel Musson | w****1@g****k | 1 |
Committer Domains (Top 20 + Academic)
Issues and Pull Requests
Last synced: 6 months ago
All Time
- Total issues: 12
- Total pull requests: 28
- Average time to close issues: 26 days
- Average time to close pull requests: 19 days
- Total issue authors: 6
- Total pull request authors: 5
- Average comments per issue: 3.17
- Average comments per pull request: 0.14
- Merged pull requests: 17
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 0
- Pull requests: 18
- Average time to close issues: N/A
- Average time to close pull requests: 5 days
- Issue authors: 0
- Pull request authors: 4
- Average comments per issue: 0
- Average comments per pull request: 0.17
- Merged pull requests: 9
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
- RMeli (4)
- anandojha (2)
- JoaoRodrigues (2)
- ryankzhu (2)
- ABChh26 (1)
Pull Request Authors
- gwirn (18)
- EngAsal (12)
- SCMusson (5)
- ryankzhu (5)
- degiacom (2)
Top Labels
Issue Labels
Pull Request Labels
Packages
- Total packages: 1
- Total downloads: unknown
- Total dependent packages: 0
- Total dependent repositories: 0
- Total versions: 3
conda-forge.org: molearn
This software trains a generative neural network on an ensemble of molecular conformations (typically obtained by molecular dynamics). The trained model can be used to generate new, plausible conformations repesentative of poorly sampled transition states.
- Homepage: https://github.com/Degiacomi-Lab/molearn
- License: GPL-3.0-only
-
Latest release: 1.1.3
published over 3 years ago