# scGraphNE: a novel scRNA-seq representation learning method based on graph node embedding
## Overview
scGraphNE is a graph autoencoder network where the encoder based on multi-layer graph convolutional networks extracts high-order representations of cells and genes from the cell-gene bipartite graph, and the decoder based on the ZINB model uses these representations to reconstruct the gene expression matrix. By virtue of a model-driven self-supervised training paradigm, scGraphNE can effectively learn low-dimensional representations of both cells and genes, amenable to diverse downstream analytical tasks.
## Installation
Please install `scGraphNE` from pypi with:
```bash
pip install scgraphne
```
Or clone this repository and use
```bash
pip install -e .
```
in the root of this repository.
## Quick start
Load the data to be analyzed:
```python
import scanpy as sc
adata = sc.AnnData(data)
```
Perform data pre-processing:
```python
# Basic filtering
sc.pp.filter_genes(adata, min_cells=3)
sc.pp.filter_cells(adata, min_genes=200)
adata.raw = adata.copy()
# Total-count normlize, logarithmize the data, calculate the gene size factor
sc.pp.normalize_per_cell(adata)
adata.obs['cs_factor'] = adata.obs.n_counts / np.median(adata.obs.n_counts)
sc.pp.log1p(adata)
adata.var['gs_factor'] = np.max(adata.X, axis=0, keepdims=True).reshape(-1)
```
Run the scGraphNE method:
```python
from scgraphne import run_scgraphne
adata = run_scgraphne(adata)
```
The output adata contains the cell embeddings in `adata.obsm['feat']` and the gene embeddings in `adata.obsm['feat']`. The embeddings can be used as input of other downstream analyses.
Please refer to `tutorial.ipynb` for a detailed description of scGraphNE's usage.
Raw data
{
"_id": null,
"home_page": "https://github.com/sldyns/scGraphNE",
"name": "scgraphne",
"maintainer": "Kun Qian",
"docs_url": null,
"requires_python": "",
"maintainer_email": "kun_qian@foxmail.com",
"keywords": "single-cell RNA-sequencing,Graph node embedding,Dimensionality reduction",
"author": "Kun Qian, Ting Li",
"author_email": "kun_qian@foxmail.com",
"download_url": "https://files.pythonhosted.org/packages/cc/80/ccbe44c9fcd9f9d1d28b8814a8bb1a68a233e1166581104f9a800357681d/scgraphne-0.1.1.tar.gz",
"platform": "any",
"description": "# scGraphNE: a novel scRNA-seq representation learning method based on graph node embedding\n\n## Overview\n\n\n\nscGraphNE is a graph autoencoder network where the encoder based on multi-layer graph convolutional networks extracts high-order representations of cells and genes from the cell-gene bipartite graph, and the decoder based on the ZINB model uses these representations to reconstruct the gene expression matrix. By virtue of a model-driven self-supervised training paradigm, scGraphNE can effectively learn low-dimensional representations of both cells and genes, amenable to diverse downstream analytical tasks.\n\n## Installation\n\nPlease install `scGraphNE` from pypi with:\n\n```bash\npip install scgraphne\n```\n\nOr clone this repository and use\n\n```bash\npip install -e .\n```\n\nin the root of this repository.\n\n## Quick start\n\nLoad the data to be analyzed:\n\n```python\nimport scanpy as sc\n\nadata = sc.AnnData(data)\n```\n\n\n\nPerform data pre-processing:\n\n```python\n# Basic filtering\nsc.pp.filter_genes(adata, min_cells=3)\nsc.pp.filter_cells(adata, min_genes=200)\n\nadata.raw = adata.copy()\n\n# Total-count normlize, logarithmize the data, calculate the gene size factor \nsc.pp.normalize_per_cell(adata)\nadata.obs['cs_factor'] = adata.obs.n_counts / np.median(adata.obs.n_counts)\nsc.pp.log1p(adata)\nadata.var['gs_factor'] = np.max(adata.X, axis=0, keepdims=True).reshape(-1)\n```\n\nRun the scGraphNE method:\n\n```python\nfrom scgraphne import run_scgraphne\nadata = run_scgraphne(adata)\n```\n\nThe output adata contains the cell embeddings in `adata.obsm['feat']` and the gene embeddings in `adata.obsm['feat']`. The embeddings can be used as input of other downstream analyses.\n\nPlease refer to `tutorial.ipynb` for a detailed description of scGraphNE's usage.\n\n",
"bugtrack_url": null,
"license": "MIT Licence",
"summary": "scGraphNE: a novel scRNA-seq representation learning method based on graph node embedding",
"version": "0.1.1",
"project_urls": {
"Homepage": "https://github.com/sldyns/scGraphNE"
},
"split_keywords": [
"single-cell rna-sequencing",
"graph node embedding",
"dimensionality reduction"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "fdefc25e192e697dd3754da71342a550574c4533b9dc342309dabfd7c263fea3",
"md5": "d7187fa701ec8b406a6b9d0b1aa968d3",
"sha256": "1924bf18fdfbb828502d83e97e4a5edb610d0e2050769b98e0d304ffd102379a"
},
"downloads": -1,
"filename": "scgraphne-0.1.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "d7187fa701ec8b406a6b9d0b1aa968d3",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 16719,
"upload_time": "2023-08-05T08:06:54",
"upload_time_iso_8601": "2023-08-05T08:06:54.282403Z",
"url": "https://files.pythonhosted.org/packages/fd/ef/c25e192e697dd3754da71342a550574c4533b9dc342309dabfd7c263fea3/scgraphne-0.1.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "cc80ccbe44c9fcd9f9d1d28b8814a8bb1a68a233e1166581104f9a800357681d",
"md5": "ea783a8d34e02a2a05b9a12552cbe086",
"sha256": "ded6821d1e61ba7b097f7e08095fed995bebb801b2be34083eb4527672c6ab08"
},
"downloads": -1,
"filename": "scgraphne-0.1.1.tar.gz",
"has_sig": false,
"md5_digest": "ea783a8d34e02a2a05b9a12552cbe086",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 13847,
"upload_time": "2023-08-05T08:06:57",
"upload_time_iso_8601": "2023-08-05T08:06:57.258946Z",
"url": "https://files.pythonhosted.org/packages/cc/80/ccbe44c9fcd9f9d1d28b8814a8bb1a68a233e1166581104f9a800357681d/scgraphne-0.1.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-08-05 08:06:57",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "sldyns",
"github_project": "scGraphNE",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "scgraphne"
}
JSON
