# SNPmanifold
SNPmanifold is a Python package that learns a representative manifold for single cells based on their SNPs (Single-Nucleotide Polymorphisms) using VAE (Variational AutoEncoder) and UMAP (Uniform Manifold Approximation and Projection). It takes AD matrix, DP matrix, and VCF (or variant_name.tsv) as inputs. You can compile them from bam file(s) either conveniently by cellSNP-lite or by your custom scripts.
SNPmanifold first performs simple filtering on AD matrix and DP matrix for high-quality cells and SNPs. It then trains VAE and UMAP to learn a representative manifold for single cells according to their allele frequency of different SNPs (AF = AD/DP). Finally, it classifies cells into clones and infer their phylogeny based on the manifold.
## Installation
Quick install can be achieved via pip
```bash
# for published version
pip install -U SNPmanifold
# or developing version
pip install -U git+https://github.com/StatBiomed/SNPmanifold
```
Or set a conda environment before installing (credits to Xinyi Lin).
Replace `$myenv` with the environment name you prefer.
```bash
conda create -n $myenv python=3.8
conda activate $myenv
pip install -U git+https://github.com/StatBiomed/SNPmanifold
```
## Quick Usage
Full documentation is at https://SNPmanifold.readthedocs.io.
Here is a quick start:
1. Import SNPmanifold and create an object of the class SNP_VAE.
```python
from SNPmanifold import SNP_VAE
```
2. Run 4 methods (filtering, training, clustering, phylogeny) in order.
Each method can rerun sperately without reruning prior methods.
* The [demo page](https://snpmanifold.readthedocs.io/en/latest/SNPmanifold_demo.html)
and notebook [SNPmanifold_demo.ipynb](./SNPmanifold_demo.ipynb) show
a demo for quick usage of SNPmanifold on MKN45 cancer cell line using
mitochondrial SNPs.
* See how to use it via the [API page](https://snpmanifold.readthedocs.io/en/latest/API.html#main-object).
Raw data
{
"_id": null,
"home_page": "https://github.com/StatBiomed/SNPmanifold",
"name": "SNPmanifold",
"maintainer": null,
"docs_url": null,
"requires_python": null,
"maintainer_email": null,
"keywords": "Manifold learning, Variational autoencoder, Single-cell single-nucleotide variations, Phylogenetic reconstruction",
"author": "['Kevin Chung', 'Yuanhua Huang']",
"author_email": "u3570318@connect.hku.hk",
"download_url": "https://files.pythonhosted.org/packages/56/91/d27f20fa6fedc0ca0c20d069cb701ec71f59a6add10fbc18a695a54e01a8/snpmanifold-0.0.6.tar.gz",
"platform": null,
"description": "# SNPmanifold\n\nSNPmanifold is a Python package that learns a representative manifold for single cells based on their SNPs (Single-Nucleotide Polymorphisms) using VAE (Variational AutoEncoder) and UMAP (Uniform Manifold Approximation and Projection). It takes AD matrix, DP matrix, and VCF (or variant_name.tsv) as inputs. You can compile them from bam file(s) either conveniently by cellSNP-lite or by your custom scripts.\n\nSNPmanifold first performs simple filtering on AD matrix and DP matrix for high-quality cells and SNPs. It then trains VAE and UMAP to learn a representative manifold for single cells according to their allele frequency of different SNPs (AF = AD/DP). Finally, it classifies cells into clones and infer their phylogeny based on the manifold. \n\n## Installation\n\nQuick install can be achieved via pip\n\n```bash\n# for published version\npip install -U SNPmanifold\n\n# or developing version\npip install -U git+https://github.com/StatBiomed/SNPmanifold\n```\n\nOr set a conda environment before installing (credits to Xinyi Lin).\nReplace `$myenv` with the environment name you prefer.\n\n```bash\nconda create -n $myenv python=3.8\nconda activate $myenv\n\npip install -U git+https://github.com/StatBiomed/SNPmanifold\n```\n\n## Quick Usage\n\nFull documentation is at https://SNPmanifold.readthedocs.io. \n\nHere is a quick start:\n\n1. Import SNPmanifold and create an object of the class SNP_VAE.\n\n```python\nfrom SNPmanifold import SNP_VAE\n```\n\n2. Run 4 methods (filtering, training, clustering, phylogeny) in order.\n\n Each method can rerun sperately without reruning prior methods. \n\n* The [demo page](https://snpmanifold.readthedocs.io/en/latest/SNPmanifold_demo.html) \n and notebook [SNPmanifold_demo.ipynb](./SNPmanifold_demo.ipynb) show \n a demo for quick usage of SNPmanifold on MKN45 cancer cell line using \n mitochondrial SNPs.\n\n* See how to use it via the [API page](https://snpmanifold.readthedocs.io/en/latest/API.html#main-object).\n",
"bugtrack_url": null,
"license": "Apache-2.0",
"summary": "SNPmanifold: Manifold learning for single-cell SNVs",
"version": "0.0.6",
"project_urls": {
"Homepage": "https://github.com/StatBiomed/SNPmanifold"
},
"split_keywords": [
"manifold learning",
" variational autoencoder",
" single-cell single-nucleotide variations",
" phylogenetic reconstruction"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "5691d27f20fa6fedc0ca0c20d069cb701ec71f59a6add10fbc18a695a54e01a8",
"md5": "cdc41d482f0ac5b878083a66949cd75e",
"sha256": "71e60825e5ad89fc3e76b45daaabc4848f4083859c2e2e301c9ebfdb09837d65"
},
"downloads": -1,
"filename": "snpmanifold-0.0.6.tar.gz",
"has_sig": false,
"md5_digest": "cdc41d482f0ac5b878083a66949cd75e",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 20128,
"upload_time": "2024-09-22T17:27:36",
"upload_time_iso_8601": "2024-09-22T17:27:36.941938Z",
"url": "https://files.pythonhosted.org/packages/56/91/d27f20fa6fedc0ca0c20d069cb701ec71f59a6add10fbc18a695a54e01a8/snpmanifold-0.0.6.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-09-22 17:27:36",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "StatBiomed",
"github_project": "SNPmanifold",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [
{
"name": "anndata",
"specs": [
[
">=",
"0.6"
]
]
},
{
"name": "scanpy",
"specs": []
},
{
"name": "leidenalg",
"specs": []
},
{
"name": "numpy",
"specs": [
[
">=",
"1.18.0"
]
]
},
{
"name": "scipy",
"specs": [
[
">=",
"1.4.1"
]
]
},
{
"name": "pandas",
"specs": [
[
">=",
"0.23.0"
]
]
},
{
"name": "networkx",
"specs": []
},
{
"name": "matplotlib",
"specs": [
[
">=",
"3.1.2"
]
]
},
{
"name": "seaborn",
"specs": [
[
">=",
"0.10.0"
]
]
},
{
"name": "torch",
"specs": []
},
{
"name": "scikit-learn",
"specs": [
[
">=",
"0.23"
]
]
},
{
"name": "umap-learn",
"specs": [
[
">=",
"0.5.3"
]
]
},
{
"name": "tqdm",
"specs": []
}
],
"lcname": "snpmanifold"
}
JSON
