FCD

Name	FCD JSON
Version	1.2 JSON
	download
home_page	https://github.com/bioinf-jku/FCD
Summary	Fréchet ChEMNet Distance
upload_time	2023-08-23 09:48:59
maintainer
docs_url	None
author	Philipp Renz
requires_python
license	LGPLv3
keywords
VCS
bugtrack_url
requirements	No requirements were recorded.
Travis-CI	No Travis.
coveralls test coverage	No coveralls.

            # Fréchet ChemNet Distance

Code for the paper "Fréchet ChemNet Distance: A Metric for Generative Models for Molecules in Drug Discovery"
[JCIM](https://pubs.acs.org/doi/10.1021/acs.jcim.8b00234) /
[ArXiv](https://arxiv.org/abs/1803.09518)


## Installation
You can install the FCD using
```
pip install fcd
```

# Requirements
```
numpy
torch
scipy
rdkit
```

# Updates
## Version 1.1 changes
- Got rid of unneeded imports
- `load_ref_model` doesn't need an argument any more to load a model.
- `canonical` and `canonical_smiles` now return `None` for invalid smiles.
- Added `get_fcd` as a quick way to get a the fcd score from two lists of smiles.

## Version 1.2 changes
- Ported the package to pytorch with the help of https://github.com/insilicomedicine/fcd_torch
- pytorch allows a lighter package and is more popular than Tensorflow which saves an additional install

            

Raw data

            {
    "_id": null,
    "home_page": "https://github.com/bioinf-jku/FCD",
    "name": "FCD",
    "maintainer": "",
    "docs_url": null,
    "requires_python": "",
    "maintainer_email": "",
    "keywords": "",
    "author": "Philipp Renz",
    "author_email": "renz.ph@gmail.com",
    "download_url": "https://files.pythonhosted.org/packages/71/80/ab1868cc301426ddffa927976f72918cabe694c2907403b4f27b9eb0de7b/FCD-1.2.tar.gz",
    "platform": null,
    "description": "# Fr\u00e9chet ChemNet Distance\n\nCode for the paper \"Fr\u00e9chet ChemNet Distance: A Metric for Generative Models for Molecules in Drug Discovery\"\n[JCIM](https://pubs.acs.org/doi/10.1021/acs.jcim.8b00234) /\n[ArXiv](https://arxiv.org/abs/1803.09518)\n\n\n## Installation\nYou can install the FCD using\n```\npip install fcd\n```\n\n# Requirements\n```\nnumpy\ntorch\nscipy\nrdkit\n```\n\n# Updates\n## Version 1.1 changes\n- Got rid of unneeded imports\n- `load_ref_model` doesn't need an argument any more to load a model.\n- `canonical` and `canonical_smiles` now return `None` for invalid smiles.\n- Added `get_fcd` as a quick way to get a the fcd score from two lists of smiles.\n\n## Version 1.2 changes\n- Ported the package to pytorch with the help of https://github.com/insilicomedicine/fcd_torch\n- pytorch allows a lighter package and is more popular than Tensorflow which saves an additional install\n",
    "bugtrack_url": null,
    "license": "LGPLv3",
    "summary": "Fr\u00e9chet ChEMNet Distance",
    "version": "1.2",
    "project_urls": {
        "Homepage": "https://github.com/bioinf-jku/FCD"
    },
    "split_keywords": [],
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "019ceff17f2803737b36b5f98c4d471b799a02dd14898639e97635005e09db10",
                "md5": "93eea0de8326de362860fc039818c4a1",
                "sha256": "4aa98e839e2f5f50b7c695a5e5c7b1a9c4a83bc8b014099627950e4918bc24f8"
            },
            "downloads": -1,
            "filename": "FCD-1.2-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "93eea0de8326de362860fc039818c4a1",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": null,
            "size": 5242629,
            "upload_time": "2023-08-23T09:48:57",
            "upload_time_iso_8601": "2023-08-23T09:48:57.303861Z",
            "url": "https://files.pythonhosted.org/packages/01/9c/eff17f2803737b36b5f98c4d471b799a02dd14898639e97635005e09db10/FCD-1.2-py3-none-any.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "7180ab1868cc301426ddffa927976f72918cabe694c2907403b4f27b9eb0de7b",
                "md5": "0fd728e20b6b6d4f55caabd1e9b080d5",
                "sha256": "6cc56a5c9d4ec6d6ee480b3ed94d858ba8d6d20db70319ff802c51737d166e32"
            },
            "downloads": -1,
            "filename": "FCD-1.2.tar.gz",
            "has_sig": false,
            "md5_digest": "0fd728e20b6b6d4f55caabd1e9b080d5",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 5244243,
            "upload_time": "2023-08-23T09:48:59",
            "upload_time_iso_8601": "2023-08-23T09:48:59.583106Z",
            "url": "https://files.pythonhosted.org/packages/71/80/ab1868cc301426ddffa927976f72918cabe694c2907403b4f27b9eb0de7b/FCD-1.2.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2023-08-23 09:48:59",
    "github": true,
    "gitlab": false,
    "bitbucket": false,
    "codeberg": false,
    "github_user": "bioinf-jku",
    "github_project": "FCD",
    "travis_ci": false,
    "coveralls": false,
    "github_actions": false,
    "lcname": "fcd"
}