| Name | Voxelium JSON |
| Version |
0.0.2
JSON |
| download |
| home_page | None |
| Summary | Voxelium - a powerful tool for volumetric processing with CUDA support. |
| upload_time | 2025-08-10 22:30:46 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.9 |
| license | GPL-2.0-or-later |
| keywords |
cryoem
cryoet
reconstruction
ml
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# Voxelium Alpha Testing
This repository currently contains the alpha version of the Voxelium library.
## Installation
After you've cloned the repo and `cd` into the project directory you first need to set up the proper Conda environment.
Use the `environment.yml` file to create a new environment called 'voxelium' with the right module installed, by running:
```conda env create -f environment.yml```
### Visualization-Only Installation
If you only need to visualize reconstruction results (e.g. on you local computer) you can skip the building of the torch extensions.
These are only needed on the computational nodes. First activate the new Conda environment:
```conda activate voxelium```
You can now install the voxelium library from inside the project directory by running:
```VOXELIUM_SKIP_EXT=TRUE pip3 install .```
In the above, `VOXELIUM_SKIP_EXT` will skip installation of the torch extensions.
### Full Installation
If you need to run reconstruction (e.g. on a computational node), you need to build and install the torch extensions.
You will need to have a CUDA toolkit installed for this that matches the pytorch version installed.
Once you have that ready you can just run:
```pip3 install .```
## 3D Spectral Heterogeneity Analysis (SHA)
Activate the voxelium conda environment. Then run `voxelium -h` to see a list of modules.
To run the analysis, the sha3D module can be run as follows:
```voxelium SHA3D <input_star_data> <log_directory> --gpu 0```
Here, `<input_star_data>` is an input STAR-file containing all the particles with CTF and pose parameters set.
`<log_directory>` will contain the results of the job.
NOTE: Adding `--preload` speeds things up considerably, assuming the dataset fits in memory.
NOTE: You need to install extension for this, see above.
## SHA3D Visualization
To visualize the results run:
```voxelium sha3D_viwer <log_directory>```
In the above, `<log_directory>` is the path to the directory containing the results of the SHA3D analysis, see above.
## Troubleshoot
If there's an issue with the CUDA environment it can help preventing PYPI building in an isolated environment by running
```pip install --no-build-isolation .```
Raw data
{
"_id": null,
"home_page": null,
"name": "Voxelium",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.9",
"maintainer_email": null,
"keywords": "CryoEM, CryoET, Reconstruction, ML",
"author": null,
"author_email": "Dari Kimanius <dari.kimanius@czii.org>",
"download_url": null,
"platform": null,
"description": "# Voxelium Alpha Testing\n\nThis repository currently contains the alpha version of the Voxelium library.\n\n## Installation\nAfter you've cloned the repo and `cd` into the project directory you first need to set up the proper Conda environment.\nUse the `environment.yml` file to create a new environment called 'voxelium' with the right module installed, by running:\n\n```conda env create -f environment.yml```\n\n### Visualization-Only Installation\nIf you only need to visualize reconstruction results (e.g. on you local computer) you can skip the building of the torch extensions. \nThese are only needed on the computational nodes. First activate the new Conda environment:\n\n```conda activate voxelium```\n\nYou can now install the voxelium library from inside the project directory by running:\n\n```VOXELIUM_SKIP_EXT=TRUE pip3 install .```\n\nIn the above, `VOXELIUM_SKIP_EXT` will skip installation of the torch extensions.\n\n### Full Installation\n\nIf you need to run reconstruction (e.g. on a computational node), you need to build and install the torch extensions.\nYou will need to have a CUDA toolkit installed for this that matches the pytorch version installed. \nOnce you have that ready you can just run: \n\n```pip3 install .```\n\n## 3D Spectral Heterogeneity Analysis (SHA)\nActivate the voxelium conda environment. Then run `voxelium -h` to see a list of modules.\nTo run the analysis, the sha3D module can be run as follows:\n\n```voxelium SHA3D <input_star_data> <log_directory> --gpu 0```\n\nHere, `<input_star_data>` is an input STAR-file containing all the particles with CTF and pose parameters set.\n`<log_directory>` will contain the results of the job. \n\nNOTE: Adding `--preload` speeds things up considerably, assuming the dataset fits in memory.\n\nNOTE: You need to install extension for this, see above.\n\n## SHA3D Visualization\n\nTo visualize the results run:\n\n```voxelium sha3D_viwer <log_directory>```\n\nIn the above, `<log_directory>` is the path to the directory containing the results of the SHA3D analysis, see above.\n\n## Troubleshoot\n\nIf there's an issue with the CUDA environment it can help preventing PYPI building in an isolated environment by running\n\n```pip install --no-build-isolation .```\n",
"bugtrack_url": null,
"license": "GPL-2.0-or-later",
"summary": "Voxelium - a powerful tool for volumetric processing with CUDA support.",
"version": "0.0.2",
"project_urls": null,
"split_keywords": [
"cryoem",
" cryoet",
" reconstruction",
" ml"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "2408cd39fa0774ef1e7db83a52210db3de05f26e9765b478a199ce5a1ef4fe12",
"md5": "3de4ff85bc2112075e38432ef0a86501",
"sha256": "fc72b4554873c9e10d1a801eba9bc389b6cf0cd05bb57006c7f09047cc8682bb"
},
"downloads": -1,
"filename": "voxelium-0.0.2-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl",
"has_sig": false,
"md5_digest": "3de4ff85bc2112075e38432ef0a86501",
"packagetype": "bdist_wheel",
"python_version": "cp310",
"requires_python": ">=3.9",
"size": 20176707,
"upload_time": "2025-08-10T22:30:46",
"upload_time_iso_8601": "2025-08-10T22:30:46.962184Z",
"url": "https://files.pythonhosted.org/packages/24/08/cd39fa0774ef1e7db83a52210db3de05f26e9765b478a199ce5a1ef4fe12/voxelium-0.0.2-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "733181400867c98c60e370921edc2925bb4a81332636ccf957c9795381296743",
"md5": "e71760d2d76493cb6e94efbb0760814f",
"sha256": "c09d7c8270d0625836d5f83acdaf6671e82c24bf33fe682e5b98d4dc64c9129e"
},
"downloads": -1,
"filename": "voxelium-0.0.2-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl",
"has_sig": false,
"md5_digest": "e71760d2d76493cb6e94efbb0760814f",
"packagetype": "bdist_wheel",
"python_version": "cp311",
"requires_python": ">=3.9",
"size": 20238207,
"upload_time": "2025-08-10T22:32:12",
"upload_time_iso_8601": "2025-08-10T22:32:12.806535Z",
"url": "https://files.pythonhosted.org/packages/73/31/81400867c98c60e370921edc2925bb4a81332636ccf957c9795381296743/voxelium-0.0.2-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "903aa393a3f5a50278e16ce5bb3ef229271d7494d740b94337ab2f504357b60a",
"md5": "0c69f9163389914fbf8fe266006d9651",
"sha256": "c26d07353959efe76bab7667195e907f4c665fed6fd026e4897e024b4313e0c4"
},
"downloads": -1,
"filename": "voxelium-0.0.2-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl",
"has_sig": false,
"md5_digest": "0c69f9163389914fbf8fe266006d9651",
"packagetype": "bdist_wheel",
"python_version": "cp312",
"requires_python": ">=3.9",
"size": 20331408,
"upload_time": "2025-08-10T22:30:40",
"upload_time_iso_8601": "2025-08-10T22:30:40.903647Z",
"url": "https://files.pythonhosted.org/packages/90/3a/a393a3f5a50278e16ce5bb3ef229271d7494d740b94337ab2f504357b60a/voxelium-0.0.2-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "7471aac22962277ab18f2e239246d69dcd8252b3ef0db33abce22efb54867c39",
"md5": "3d178d64421a6fa88dec944c0478d03f",
"sha256": "4b333aaed3525fb66f4a690e7c155460414a27e729ae01cd1b7160a476c1eeb5"
},
"downloads": -1,
"filename": "voxelium-0.0.2-cp39-cp39-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl",
"has_sig": false,
"md5_digest": "3d178d64421a6fa88dec944c0478d03f",
"packagetype": "bdist_wheel",
"python_version": "cp39",
"requires_python": ">=3.9",
"size": 20128825,
"upload_time": "2025-08-10T22:32:39",
"upload_time_iso_8601": "2025-08-10T22:32:39.163267Z",
"url": "https://files.pythonhosted.org/packages/74/71/aac22962277ab18f2e239246d69dcd8252b3ef0db33abce22efb54867c39/voxelium-0.0.2-cp39-cp39-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-10 22:30:46",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "voxelium"
}
