# AIDD Codebase
[](https://colab.research.google.com/drive/1jlyEd1yxhvFCN82YqEFI82q2n0k_y06F?usp=sharing)
A high-level codebase for deep learning development in drug discovery applications using PyTorch-Lightning.
## Dependencies
The codebase requires the following additional dependencies
- CUDA >= 11.4
- PyTorch >= 1.9
- Pytorch-Lightning >= 1.5
- RDKit
- Optionally supports: tensorboard and/or wandb
## Installation
The codebase can be installed from PyPI using `pip`, or your package manager of choice, with
```bash
$ pip install aidd-codebase
```
## Usage
1. __*Configuration*__: The coding framework has a number of argument dataclasses in the file *arguments.py*. This file contains all standard arguments for each of the models. Because they are dataclasses, you can easily adapt them to your own needs.
<br>
Does your Seq2Seq adaptation need an extra argument? Import the Seq2SeqArguments from arguments.py, create your own dataclass which inherits it and add your extra argument. <br> <br>
*It is important to note that the order of supplying arguments to a script goes as follows:* <br>
- --flags override config.yaml <br>
- config.yaml overrides default values in arguments.py <br>
- default values from arguments.py are used when no other values are supplied<br>
At the end, it stores all arguments in config.yaml
<br><br>
2. __*Use*__: The coding framework has four main parts: <br>
- utils
- data_utils
- models
- interpretation
These parts should be used
3. __*File Setup*__: The setup of the files in the system is best used as followed:<br>
coding_framework<br>
|-- ..<br>
ESR X<br>
|-- project 1<br>
|-- data<br>
|-- ..<br>
|-- Arguments.py<br>
|-- config.yaml<br>
|-- main.py<br>
|-- datamodule.py<br>
|-- pl_framework.py<br>
## Contributors
All fellows of the AIDD consortium have contributed to the packaged.
## Code of Conduct
Everyone interacting in the codebase, issue trackers, chat rooms, and mailing lists is expected to follow the [PyPA Code of Conduct](https://www.pypa.io/en/latest/code-of-conduct/).
Raw data
{
"_id": null,
"home_page": "https://github.com/aidd-msca/aidd-codebase",
"name": "aidd-codebase",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.7,<4.0",
"maintainer_email": "",
"keywords": "aidd,drug discovery,deep learning",
"author": "Peter Hartog",
"author_email": "peter.hartog@hotmail.nl",
"download_url": "https://files.pythonhosted.org/packages/ac/e2/6762d0cc4873ea1e17a116a87720d0e91045dd5f256c6b219a32b79124c7/aidd-codebase-0.2.0.tar.gz",
"platform": null,
"description": "# AIDD Codebase\n\n\n\n\n[](https://colab.research.google.com/drive/1jlyEd1yxhvFCN82YqEFI82q2n0k_y06F?usp=sharing)\n\nA high-level codebase for deep learning development in drug discovery applications using PyTorch-Lightning.\n\n## Dependencies\n\nThe codebase requires the following additional dependencies\n- CUDA >= 11.4\n- PyTorch >= 1.9\n- Pytorch-Lightning >= 1.5 \n- RDKit \n- Optionally supports: tensorboard and/or wandb\n\n\n## Installation\n\nThe codebase can be installed from PyPI using `pip`, or your package manager of choice, with\n\n```bash\n$ pip install aidd-codebase\n```\n\n## Usage\n\n1. __*Configuration*__: The coding framework has a number of argument dataclasses in the file *arguments.py*. This file contains all standard arguments for each of the models. Because they are dataclasses, you can easily adapt them to your own needs. \n<br> \nDoes your Seq2Seq adaptation need an extra argument? Import the Seq2SeqArguments from arguments.py, create your own dataclass which inherits it and add your extra argument. <br> <br>\n*It is important to note that the order of supplying arguments to a script goes as follows:* <br>\n- --flags override config.yaml <br>\n- config.yaml overrides default values in arguments.py <br>\n- default values from arguments.py are used when no other values are supplied<br>\nAt the end, it stores all arguments in config.yaml\n<br><br>\n\n2. __*Use*__: The coding framework has four main parts: <br>\n- utils\n- data_utils\n- models\n- interpretation\n\nThese parts should be used \n \n\n3. __*File Setup*__: The setup of the files in the system is best used as followed:<br>\ncoding_framework<br> \n|-- ..<br> \nESR X<br> \n|-- project 1<br> \n |-- data<br> \n |-- ..<br> \n |-- Arguments.py<br> \n |-- config.yaml<br> \n |-- main.py<br>\n |-- datamodule.py<br>\n |-- pl_framework.py<br>\n\n## Contributors\n\nAll fellows of the AIDD consortium have contributed to the packaged.\n\n## Code of Conduct\n\nEveryone interacting in the codebase, issue trackers, chat rooms, and mailing lists is expected to follow the [PyPA Code of Conduct](https://www.pypa.io/en/latest/code-of-conduct/).\n\n \n",
"bugtrack_url": null,
"license": "MIT",
"summary": "High-level codebase for deep learning development in drug discovery.",
"version": "0.2.0",
"split_keywords": [
"aidd",
"drug discovery",
"deep learning"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "2cb0146bb2364191370a41157221f41042ce86175b85058de100d2bc79646621",
"md5": "5365b4a6953c7babc76893ad673ad24d",
"sha256": "5806856691676f0708135c1a98b82bc3f398f0465a433afe94edc7d91bebe1a4"
},
"downloads": -1,
"filename": "aidd_codebase-0.2.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "5365b4a6953c7babc76893ad673ad24d",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7,<4.0",
"size": 12835,
"upload_time": "2022-11-03T15:14:56",
"upload_time_iso_8601": "2022-11-03T15:14:56.463037Z",
"url": "https://files.pythonhosted.org/packages/2c/b0/146bb2364191370a41157221f41042ce86175b85058de100d2bc79646621/aidd_codebase-0.2.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "ace26762d0cc4873ea1e17a116a87720d0e91045dd5f256c6b219a32b79124c7",
"md5": "a91f9f77756d8f81232eca0e754facda",
"sha256": "b71c5a92905947e809c2429ca8a876c690922c3b9d980e3f53a0c46fa2f64c3a"
},
"downloads": -1,
"filename": "aidd-codebase-0.2.0.tar.gz",
"has_sig": false,
"md5_digest": "a91f9f77756d8f81232eca0e754facda",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.7,<4.0",
"size": 9409,
"upload_time": "2022-11-03T15:14:54",
"upload_time_iso_8601": "2022-11-03T15:14:54.866294Z",
"url": "https://files.pythonhosted.org/packages/ac/e2/6762d0cc4873ea1e17a116a87720d0e91045dd5f256c6b219a32b79124c7/aidd-codebase-0.2.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2022-11-03 15:14:54",
"github": true,
"gitlab": false,
"bitbucket": false,
"github_user": "aidd-msca",
"github_project": "aidd-codebase",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "aidd-codebase"
}
JSON
