SpaDecon: cell-type deconvolution in spatial transcriptomics with semi-supervised learning
Project description
SpaDecon: cell-type deconvolution in spatial transcriptomics with semi-supervised learning
Kyle Coleman, Jian Hu, Amelia Schroeder, Edward B. Lee, Mingyao Li*
SpaDecon is a semi-supervised learning-based method developed to perform cell-type deconvolution on spatially resolved transcriptomics (SRT) datasets. SpaDecon has been shown to provide accurate cell-type deconvolution results for both Spatial Transcriptomics (ST) and 10X Visium SRT datasets. Annotated scRNA-seq gene expression data from the same type of tissue as the SRT data are required for deconvolution.
SpaDecon Installation
- SpaDecon installation requires a python version of at least 3.6. The version of python can be checked by:
import platform
platform.python_version()
'3.7.11'
We recommend creating and activating a new conda environment when installing the SpaDecon package. For instance,
conda create -n SpaDecon python=3.7
conda activate SpaDecon
There are mulitple ways to install SpaDecon:
- Install SpaDecon using PyPI:
pip3 install SpaDecon
- Download and install SpaDecon package from GitHub:
git clone https://github.com/kpcoleman/SpaDecon
cd SpaDecon/
python3 setup.py install --user
Tutorial
A markdown tutorial file can be found here: https://github.com/kpcoleman/SpaDecon/blob/main/tutorial/Tutorial.md
A tutorial in the form of a jupyter notebook can be found here: https://github.com/kpcoleman/SpaDecon/blob/main/tutorial/tutorial.ipynb
Software Requirements
python >= 3.6
keras==2.2.4
pandas==1.2.4
numpy==1.20.1
scipy==1.6.2
scanpy==1.7.0
anndata==0.7.6
sklearn
tensorflow==1.14.0
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file SpaDecon-1.1.2.tar.gz
.
File metadata
- Download URL: SpaDecon-1.1.2.tar.gz
- Upload date:
- Size: 18.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.7.4
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 38c17cc1ef206628a01d5c2f29cd04c2e07a7c6a8a97d48f82c2d66bc392c44b |
|
MD5 | 46c5b3bccb52c2fb76c55aaa757479ec |
|
BLAKE2b-256 | faa096e2f8fba0e577948f7e7e948f31aa619968bd1ce0861f94ff392c341826 |
File details
Details for the file SpaDecon-1.1.2-py3-none-any.whl
.
File metadata
- Download URL: SpaDecon-1.1.2-py3-none-any.whl
- Upload date:
- Size: 20.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.7.4
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | b418db83b1b43f9dbc374ff0b4a59e1a809b870790788ca023c842a06a20dd6b |
|
MD5 | 84509b0a3cb360b8249fbe0853bfae65 |
|
BLAKE2b-256 | 3f35388a969c51e8552f40f5c081a845b8f8a722ec8f0d245bc8026e2ee1ebe5 |