https://github.com/kavrakilab/ape-gen2.0
https://github.com/kavrakilab/ape-gen2.0
Last synced: 4 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/kavrakilab/ape-gen2.0
- Owner: KavrakiLab
- License: mit
- Created: 2022-01-19T18:57:38.000Z (over 4 years ago)
- Default Branch: main
- Last Pushed: 2025-07-10T15:28:18.000Z (11 months ago)
- Last Synced: 2025-07-10T21:57:00.581Z (11 months ago)
- Language: Python
- Size: 393 MB
- Stars: 3
- Watchers: 1
- Forks: 3
- Open Issues: 5
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# New Ape-Gen version:
## Prelims
To set up APE-Gen2.0 locally, download the repo using `git clone`.
Before you move on to anything else, am important step must be performed: Download the frequency matrices generated using MHCFlurry2.0 through the link below:
https://rice.box.com/s/duxshqxtkykg7u9y3b0tl79j8byc2dp2
These will be crucial for the softawre to run. After these are downloaded, go ahead and put those on the `helper_files` folder. Then you're all set for the installation!
## Installation
We recommend that APE-Gen2.0 is set up with a docker configuration, so the latest version of `docker` should be installed on your system. Setting APE-Gen2.0 through a python virtual env is definitely plausible (check the `environment.yml`and the provided `Dockerfile` for all needed packages), but we'll leave that to you if you want to set it up this way.
Just running:
```
bash build_image.sh
```
should build the docker image After this, just running:
```
bash start_image.sh
```
gets you into the container, APE-Gen2.0 can be run from there.
## Usage
To run APE-Gen2.0 for existing MHC templates in the database, you should be good to go (Ignore the warning message about the MODELLER invalid key). However, for a new MHC not found in the database, you will need to provide a valid MODELLER key. To do that, go to:
```
cd /conda/envs/apegen/lib/modeller-10.4/modlib/modeller/
```
and modify the lines of `config.py` with a valid MODELLER key.
For now, peptide sequence (along with positions with PTM) + an MHC allotype should work! (more inputs to follow...)
```
python New_APE-Gen.py LLGIGSLTV HLA-A*02:01 --verbose
python New_APE-Gen.py LLGIGSLTV HLA-A*02:01 --verbose --score_with_openmm
python New_APE-Gen.py LLGIGpSLTV HLA-A*02:01 --verbose --score_with_openmm
python New_APE-Gen.py LLGpSGpSLTV HLA-A*02:01 --verbose --score_with_openmm
```
Please contact the team should you have any issues with running APE-Gen2.0!
## Citation
```
@article{Fasoulis2024,
title = {APE-Gen2.0: Expanding Rapid Class I Peptide–Major Histocompatibility Complex Modeling to Post-Translational Modifications and Noncanonical Peptide Geometries},
volume = {64},
ISSN = {1549-960X},
url = {http://dx.doi.org/10.1021/acs.jcim.3c01667},
DOI = {10.1021/acs.jcim.3c01667},
number = {5},
journal = {Journal of Chemical Information and Modeling},
publisher = {American Chemical Society (ACS)},
author = {Fasoulis, Romanos and Rigo, Mauricio M. and Lizée, Gregory and Antunes, Dinler A. and Kavraki, Lydia E.},
year = {2024},
month = feb,
pages = {1730–1750}
}
```