<img src="easydecon-logo.png" alt="Logo" width=130 style="vertical-align: middle; margin-right: 10px;"/>
[](https://badge.fury.io/py/easydecon)
A package to analyze celltypes on high definition spatial profiling assays
Installation
------------
It is recommended to install the package in a virtual environment or a Conda environment. To create a Conda environment, run the following command:
```bash
conda create -n easydecon python=3.10.14
conda activate easydecon
```
You can install from PyPi:
```bash
pip install easydecon
```
To install directly from GitHub using pip into the active environment, run the following command:
```bash
pip install git+https://github.com/sinanugur/easydecon.git
```
Overview
--------
<img src="easydecon-overview.png" alt="Worfklow Overview"/>
Absolute Minimal Example
---------------
```python
from easydecon.easydecon import *
from easydecon.config import *
from easydecon.extra import *
#read your DESeq table into a markers_df
#sdata is your VisiumHD file in SpatialData format or segmented AnnData object, assumed you QC and etc.
markers_df=read_markers_dataframe(sdata,filename="scanpy_deseq_table.csv")
#run easydecon
ph1, ph2, assigned_labels, posterior_df, proportions_df= easydecon_workflow(sdata,markers_df=markers_df)
#or setting prior genes
ph1, ph2, assigned_labels, posterior_df, proportions_df= easydecon_workflow(sdata,markers_df=markers_df,marker_genes=["gene1","gene2","gene3"])
`assigned_labels` will be added to sdata.obs and contain the celltype assignments
`proportions_df` will contain the estimated proportions for each celltype
```
Usage and Documentation
-----------------------
You may find our example notebooks in the `notebooks` folder.
- Demo notebook for a single-cell Anndata object (demo)[https://github.com/sinanugur/easydecon/blob/main/notebooks/demo.ipynb]
- Demo notebook for macrophage markers (demo_macrophage)[https://github.com/sinanugur/easydecon/blob/main/notebooks/demo_macrophage.ipynb]
- Minimal example notebook (minimal)[https://github.com/sinanugur/easydecon/blob/main/notebooks/demo_minimal_example.ipynb]
Raw data
{
"_id": null,
"home_page": "https://github.com/sinanugur/easydecon",
"name": "easydecon",
"maintainer": null,
"docs_url": null,
"requires_python": null,
"maintainer_email": null,
"keywords": "scRNA single-cell high definition spatial transcriptomics deconvolution",
"author": "Sinan U. Umu",
"author_email": "sinanugur@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/e9/98/3c070b5de493b50d55075239d34a6f6068f21a5c7a326909bbcf79a2073d/easydecon-0.1.2.tar.gz",
"platform": null,
"description": "<img src=\"easydecon-logo.png\" alt=\"Logo\" width=130 style=\"vertical-align: middle; margin-right: 10px;\"/> \n\n[](https://badge.fury.io/py/easydecon) \nA package to analyze celltypes on high definition spatial profiling assays\n\nInstallation\n------------\nIt is recommended to install the package in a virtual environment or a Conda environment. To create a Conda environment, run the following command:\n\n```bash\nconda create -n easydecon python=3.10.14\nconda activate easydecon\n```\n\nYou can install from PyPi:\n\n```bash\npip install easydecon\n```\n\nTo install directly from GitHub using pip into the active environment, run the following command:\n\n```bash\npip install git+https://github.com/sinanugur/easydecon.git\n```\n\nOverview\n--------\n<img src=\"easydecon-overview.png\" alt=\"Worfklow Overview\"/>\n\nAbsolute Minimal Example\n---------------\n```python\nfrom easydecon.easydecon import *\nfrom easydecon.config import *\nfrom easydecon.extra import *\n\n#read your DESeq table into a markers_df\n#sdata is your VisiumHD file in SpatialData format or segmented AnnData object, assumed you QC and etc.\nmarkers_df=read_markers_dataframe(sdata,filename=\"scanpy_deseq_table.csv\")\n\n#run easydecon\nph1, ph2, assigned_labels, posterior_df, proportions_df= easydecon_workflow(sdata,markers_df=markers_df)\n\n#or setting prior genes\nph1, ph2, assigned_labels, posterior_df, proportions_df= easydecon_workflow(sdata,markers_df=markers_df,marker_genes=[\"gene1\",\"gene2\",\"gene3\"])\n\n`assigned_labels` will be added to sdata.obs and contain the celltype assignments\n`proportions_df` will contain the estimated proportions for each celltype\n\n```\n\nUsage and Documentation\n-----------------------\nYou may find our example notebooks in the `notebooks` folder.\n\n- Demo notebook for a single-cell Anndata object (demo)[https://github.com/sinanugur/easydecon/blob/main/notebooks/demo.ipynb]\n- Demo notebook for macrophage markers (demo_macrophage)[https://github.com/sinanugur/easydecon/blob/main/notebooks/demo_macrophage.ipynb]\n- Minimal example notebook (minimal)[https://github.com/sinanugur/easydecon/blob/main/notebooks/demo_minimal_example.ipynb]\n",
"bugtrack_url": null,
"license": null,
"summary": "easydecon",
"version": "0.1.2",
"project_urls": {
"Homepage": "https://github.com/sinanugur/easydecon"
},
"split_keywords": [
"scrna",
"single-cell",
"high",
"definition",
"spatial",
"transcriptomics",
"deconvolution"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "e9983c070b5de493b50d55075239d34a6f6068f21a5c7a326909bbcf79a2073d",
"md5": "1479dc08e81a83f8126ac27587416be5",
"sha256": "e3bac48d5c7f228a75c07a183c28c024976207cacfc140d093d8c54480185a06"
},
"downloads": -1,
"filename": "easydecon-0.1.2.tar.gz",
"has_sig": false,
"md5_digest": "1479dc08e81a83f8126ac27587416be5",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 1399262,
"upload_time": "2025-10-20T12:26:32",
"upload_time_iso_8601": "2025-10-20T12:26:32.129227Z",
"url": "https://files.pythonhosted.org/packages/e9/98/3c070b5de493b50d55075239d34a6f6068f21a5c7a326909bbcf79a2073d/easydecon-0.1.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-10-20 12:26:32",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "sinanugur",
"github_project": "easydecon",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [
{
"name": "scipy",
"specs": []
},
{
"name": "regex",
"specs": []
},
{
"name": "matplotlib",
"specs": []
},
{
"name": "pandas",
"specs": [
[
"==",
"2.2.2"
]
]
},
{
"name": "anndata",
"specs": [
[
"==",
"0.10.9"
]
]
},
{
"name": "numpy",
"specs": []
},
{
"name": "stardist",
"specs": [
[
"==",
"0.9.1"
]
]
},
{
"name": "bin2cell",
"specs": [
[
"==",
"0.3.0"
]
]
},
{
"name": "spatialdata",
"specs": [
[
"==",
"0.2.2"
]
]
},
{
"name": "spatialdata-io",
"specs": [
[
"==",
"0.1.4"
]
]
},
{
"name": "spatialdata-plot",
"specs": [
[
"==",
"0.2.4"
]
]
},
{
"name": "xarray-spatial",
"specs": [
[
"==",
"0.4.0"
]
]
},
{
"name": "xarray",
"specs": [
[
"==",
"2024.7.0"
]
]
},
{
"name": "dask",
"specs": [
[
"==",
"2024.11.2"
]
]
},
{
"name": "ipykernel",
"specs": []
},
{
"name": "squidpy",
"specs": []
},
{
"name": "joblib",
"specs": []
},
{
"name": "xlrd",
"specs": [
[
"==",
"2.0.1"
]
]
},
{
"name": "tensorflow-macos",
"specs": [
[
"==",
"2.9.0"
]
]
},
{
"name": "tensorflow-metal",
"specs": [
[
"==",
"0.5.0"
]
]
},
{
"name": "tensorflow",
"specs": [
[
"==",
"2.9.0"
]
]
}
],
"lcname": "easydecon"
}
JSON
