| Name | fidder JSON |
| Version |
0.0.8
JSON |
| download |
| home_page | |
| Summary | U-Net for 2D fiducial segmentation in cryo-EM |
| upload_time | 2023-05-16 19:24:17 |
| maintainer | |
| docs_url | None |
| author | Alister Burt |
| requires_python | >=3.8 |
| license | BSD 3-Clause License |
| keywords |
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# fidder
[](https://github.com/teamtomo/fidder/raw/main/LICENSE)
[](https://pypi.org/project/fidder)
[](https://python.org)
[](https://github.com/teamtomo/fidder/actions/workflows/ci.yml)
[](https://codecov.io/gh/teamtomo/fidder)
*fidder* is a Python package for detecting and erasing gold fiducials in cryo-EM
images.
<p align="center" width="100%">
<img width="80%" src="https://user-images.githubusercontent.com/7307488/205998768-5808c399-6801-4ade-89ee-771a7202908f.png">
</p>
Fiducials are detected using a pre-trained residual 2D U-Net at 8 Å/px. Segmented regions are replaced with white
noise matching the local mean and global standard deviation of the image.
The package can be used from both
[Python](usage/python.md)
and the
[command line](usage/command_line.md).
---
## Quickstart
### Python
```python
import mrcfile
import torch
from fidder.predict import predict_fiducial_mask
from fidder.erase import erase_masked_region
# load your image
image = torch.tensor(mrcfile.read('my_image_file.mrc'))
# use a pretrained model to predict a mask
mask, probabilities = predict_fiducial_mask(
image, pixel_spacing=1.35, probability_threshold=0.5
)
# erase fiducials
erased_image = erase_masked_region(image=image, mask=mask)
```
### Command Line
```bash
# predict fiducial mask
fidder predict \
--input-image example.mrc \
--probability-threshold 0.5 \
--output-mask mask.mrc
# erase masked region
fidder erase \
--input-image example.mrc \
--input-mask mask.mrc \
--output-image erased.mrc
```
---
## Installation
pip:
```shell
pip install fidder
```
### Compatibility
If trying to use an `10.X` CUDA runtime you may have to install older versions of
`torch` and `pytorch-lightning`, see
[teamtomo/fidder#17](https://github.com/teamtomo/fidder/issues/17) for details.
## Notes
This package provides similar functionality to
[BoxNet](http://www.warpem.com/warp/?page_id=135) from Warp
when
[retrained for gold fiducial segmentation](http://www.warpem.com/warp/?page_id=137).
This package was developed to make this functionality available in a standalone,
easy to install Python package. The architecture and training data
preprocessing are based on the description in the
[Warp paper](https://doi.org/10.1038/s41592-019-0580-y).
Raw data
{
"_id": null,
"home_page": "",
"name": "fidder",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": "",
"keywords": "",
"author": "Alister Burt",
"author_email": "alisterburt@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/59/11/ed509f30ddd9a0eeb1008024fc7c61f216a51659dcb9a20256441ed9cd0c/fidder-0.0.8.tar.gz",
"platform": null,
"description": "# fidder\n\n[](https://github.com/teamtomo/fidder/raw/main/LICENSE)\n[](https://pypi.org/project/fidder)\n[](https://python.org)\n[](https://github.com/teamtomo/fidder/actions/workflows/ci.yml)\n[](https://codecov.io/gh/teamtomo/fidder)\n\n\n*fidder* is a Python package for detecting and erasing gold fiducials in cryo-EM\nimages.\n\n<p align=\"center\" width=\"100%\">\n <img width=\"80%\" src=\"https://user-images.githubusercontent.com/7307488/205998768-5808c399-6801-4ade-89ee-771a7202908f.png\">\n</p>\n\nFiducials are detected using a pre-trained residual 2D U-Net at 8 \u00c5/px. Segmented regions are replaced with white \nnoise matching the local mean and global standard deviation of the image.\n\nThe package can be used from both\n[Python](usage/python.md)\nand the\n[command line](usage/command_line.md).\n\n---\n\n## Quickstart\n\n### Python\n\n```python\nimport mrcfile\nimport torch\nfrom fidder.predict import predict_fiducial_mask\nfrom fidder.erase import erase_masked_region\n\n# load your image\nimage = torch.tensor(mrcfile.read('my_image_file.mrc'))\n\n# use a pretrained model to predict a mask\nmask, probabilities = predict_fiducial_mask(\n image, pixel_spacing=1.35, probability_threshold=0.5\n)\n\n# erase fiducials\nerased_image = erase_masked_region(image=image, mask=mask)\n```\n### Command Line\n\n```bash\n# predict fiducial mask\nfidder predict \\\n--input-image example.mrc \\\n--probability-threshold 0.5 \\\n--output-mask mask.mrc\n\n# erase masked region\nfidder erase \\\n--input-image example.mrc \\\n--input-mask mask.mrc \\\n--output-image erased.mrc\n\n```\n\n---\n\n## Installation\n\npip:\n\n```shell\npip install fidder\n```\n\n### Compatibility\n\nIf trying to use an `10.X` CUDA runtime you may have to install older versions of \n`torch` and `pytorch-lightning`, see \n[teamtomo/fidder#17](https://github.com/teamtomo/fidder/issues/17) for details.\n\n## Notes\n\nThis package provides similar functionality to \n[BoxNet](http://www.warpem.com/warp/?page_id=135) from Warp\nwhen \n[retrained for gold fiducial segmentation](http://www.warpem.com/warp/?page_id=137).\n\nThis package was developed to make this functionality available in a standalone, \neasy to install Python package. The architecture and training data \npreprocessing are based on the description in the \n[Warp paper](https://doi.org/10.1038/s41592-019-0580-y).\n",
"bugtrack_url": null,
"license": "BSD 3-Clause License",
"summary": "U-Net for 2D fiducial segmentation in cryo-EM",
"version": "0.0.8",
"project_urls": {
"homepage": "https://github.com/teamtomo/fidder",
"repository": "https://github.com/teamtomo/fidder"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "759b01f49d68f1b18f28bef2569050924d0b0427fe3a0a50b122dc6e02bfcc97",
"md5": "c653aa802a4d6d4b07bfd01d63da5cab",
"sha256": "b4ebbdd89f1e7cefde0d06779d3216b6370996989c68caffc3ca2f4efd8fabc4"
},
"downloads": -1,
"filename": "fidder-0.0.8-py3-none-any.whl",
"has_sig": false,
"md5_digest": "c653aa802a4d6d4b07bfd01d63da5cab",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 24931,
"upload_time": "2023-05-16T19:24:07",
"upload_time_iso_8601": "2023-05-16T19:24:07.138030Z",
"url": "https://files.pythonhosted.org/packages/75/9b/01f49d68f1b18f28bef2569050924d0b0427fe3a0a50b122dc6e02bfcc97/fidder-0.0.8-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "5911ed509f30ddd9a0eeb1008024fc7c61f216a51659dcb9a20256441ed9cd0c",
"md5": "818808a0697f1da2ec3dd44760a22804",
"sha256": "09a3c82006b719a43250a72aa48c046b39459da529266336dcf0c8ebc010b5c2"
},
"downloads": -1,
"filename": "fidder-0.0.8.tar.gz",
"has_sig": false,
"md5_digest": "818808a0697f1da2ec3dd44760a22804",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 20982,
"upload_time": "2023-05-16T19:24:17",
"upload_time_iso_8601": "2023-05-16T19:24:17.806925Z",
"url": "https://files.pythonhosted.org/packages/59/11/ed509f30ddd9a0eeb1008024fc7c61f216a51659dcb9a20256441ed9cd0c/fidder-0.0.8.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-05-16 19:24:17",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "teamtomo",
"github_project": "fidder",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "fidder"
}
