# GCNdesign
A neural network model for prediction of amino-acid probability from a protein backbone structure.
### Built with
- pytorch
- numpy
- pandas
- tqdm
## Getting Started
### Install
To install gcndesgn through [pip](https://pypi.org/project/gcndesign)
```bash
pip install gcndesign
```
## Usage
### Quick usage as a python module
```python
from gcndesign.predictor import Predictor
gcndes = Predictor(device='cpu') # 'cuda' can also be applied
gcndes.predict(pdb='pdb-file-path') # returns list of amino-acid probabilities
```
### Usage of scripts
```gcndesign_predict.py```
To predict amino-acid probabilities for each residue-site
```bash
gcndesign_predict.py YOUR_BACKBONE_STR.pdb
```
```gcndesign_autodesign.py```
To design 20 sequences in a completely automatic fashion
```bash
gcndesign_autodesign.py YOUR_BACKBONE_STR.pdb -n 20
```
For more detailed usage, please run the following command
```bash
gcndesign_autodesign.py -h
```
> Note
>
> The gcndesign_autodesign script requires **pyrosetta** software.
> Installation & use of **pyrosetta** must be in accordance with their license.
## External Packages
- gcndesign_autodesign.py: [**PyRosetta**](https://www.pyrosetta.org/)
## Documents
- [Method summary](documents/Method_Summary.pdf)
> Note
>
> A critical issue has fixed and the parameters were re-trained on a new dataset (CATH v4.3 S40 dataset).
> This change has stabilized the prediction, but has not been reflected in the document above. So there are inaccuracies in the description and figures.
## Dataset
The dataset used for training GCNdesign is available [here](https://zenodo.org/record/6650679#.YqvTp-yZNeg)
- dataset.tar.gz: Training/T500/TS50 dataset
- dataset_cath40.tar.bz2: CATH-v4.3 S40 dataset (used for the latest parameter training)
## Lisence
Distributed under [MIT](https://choosealicense.com/licenses/mit/) license.
## Acknowledgments
The author was supported by Grant-in-Aid for JSPS Research Fellows (PD, 17J02339).
Koga Laboratory of Institutes for Molecular Science (NINS, Japan) has provided a part of the computational resources.
Koya Sakuma ([yakomaxa](https://github.com/yakomaxa)) gave a critical idea for neural net architecture design in a lot of deep discussions.
Naoya Kobayashi ([naokob](https://github.com/naokob)) created excellent applications to help broader needs,
[ColabGCNdesign](https://github.com/naokob/ColabGCNdesign.git) and [FolditStandalone_Sequence_Design](https://github.com/naokob/FolditStandalone_Sequence_Design.git).
Raw data
{
"_id": null,
"home_page": "https://github.com/ShintaroMinami/GCNdesign",
"name": "gcndesign",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "gcndesign,autodesign",
"author": "Shintaro Minami",
"author_email": "",
"download_url": "",
"platform": null,
"description": "# GCNdesign\n\nA neural network model for prediction of amino-acid probability from a protein backbone structure.\n\n### Built with\n- pytorch\n- numpy\n- pandas\n- tqdm\n\n## Getting Started\n\n### Install\nTo install gcndesgn through [pip](https://pypi.org/project/gcndesign)\n```bash\npip install gcndesign\n```\n\n## Usage\n\n### Quick usage as a python module\n```python\nfrom gcndesign.predictor import Predictor\n\ngcndes = Predictor(device='cpu') # 'cuda' can also be applied\ngcndes.predict(pdb='pdb-file-path') # returns list of amino-acid probabilities\n```\n\n### Usage of scripts\n\n```gcndesign_predict.py```\n\nTo predict amino-acid probabilities for each residue-site\n```bash\ngcndesign_predict.py YOUR_BACKBONE_STR.pdb\n```\n\n```gcndesign_autodesign.py```\n\nTo design 20 sequences in a completely automatic fashion\n\n```bash\ngcndesign_autodesign.py YOUR_BACKBONE_STR.pdb -n 20\n```\n\nFor more detailed usage, please run the following command\n```bash\ngcndesign_autodesign.py -h\n```\n\n> Note\n>\n> The gcndesign_autodesign script requires **pyrosetta** software.\n> Installation & use of **pyrosetta** must be in accordance with their license.\n\n## External Packages\n- gcndesign_autodesign.py: [**PyRosetta**](https://www.pyrosetta.org/)\n\n## Documents\n- [Method summary](documents/Method_Summary.pdf)\n> Note\n>\n> A critical issue has fixed and the parameters were re-trained on a new dataset (CATH v4.3 S40 dataset).\n> This change has stabilized the prediction, but has not been reflected in the document above. So there are inaccuracies in the description and figures.\n\n## Dataset\nThe dataset used for training GCNdesign is available [here](https://zenodo.org/record/6650679#.YqvTp-yZNeg)\n- dataset.tar.gz: Training/T500/TS50 dataset\n- dataset_cath40.tar.bz2: CATH-v4.3 S40 dataset (used for the latest parameter training)\n\n## Lisence\nDistributed under [MIT](https://choosealicense.com/licenses/mit/) license.\n\n## Acknowledgments\nThe author was supported by Grant-in-Aid for JSPS Research Fellows (PD, 17J02339).\nKoga Laboratory of Institutes for Molecular Science (NINS, Japan) has provided a part of the computational resources.\nKoya Sakuma ([yakomaxa](https://github.com/yakomaxa)) gave a critical idea for neural net architecture design in a lot of deep discussions.\nNaoya Kobayashi ([naokob](https://github.com/naokob)) created excellent applications to help broader needs,\n[ColabGCNdesign](https://github.com/naokob/ColabGCNdesign.git) and [FolditStandalone_Sequence_Design](https://github.com/naokob/FolditStandalone_Sequence_Design.git).\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Neural network model for predicting amino-acid sequence from a protein backbone structure",
"version": "2.3.2",
"split_keywords": [
"gcndesign",
"autodesign"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "542301bd83e6db020712eb926b8b617405bd4d208fbda8f27026236b2fdc2ff2",
"md5": "8402a1af906949884f581136778c610c",
"sha256": "4a8967fc52b7bf3c8b4b6c988fff0fa7a5a961c466606b8ee0c31be132ecd380"
},
"downloads": -1,
"filename": "gcndesign-2.3.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "8402a1af906949884f581136778c610c",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 37201432,
"upload_time": "2023-04-06T23:52:13",
"upload_time_iso_8601": "2023-04-06T23:52:13.049277Z",
"url": "https://files.pythonhosted.org/packages/54/23/01bd83e6db020712eb926b8b617405bd4d208fbda8f27026236b2fdc2ff2/gcndesign-2.3.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-04-06 23:52:13",
"github": true,
"gitlab": false,
"bitbucket": false,
"github_user": "ShintaroMinami",
"github_project": "GCNdesign",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [],
"lcname": "gcndesign"
}
JSON
