| Name | scalex JSON |
| Version |
1.0.4
JSON |
| download |
| home_page | None |
| Summary | Online single-cell data integration through projecting heterogeneous datasets into a common cell-embedding space |
| upload_time | 2024-06-02 21:25:09 |
| maintainer | None |
| docs_url | None |
| author | Lei Xiong |
| requires_python | >=3.7 |
| license | MIT |
| keywords |
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
[](https://github.com/jsxlei/scalex/stargazers)
[](https://pypi.org/project/scalex)
[](https://scalex.readthedocs.io/en/latest/?badge=stable)
[](https://pepy.tech/project/scalex)
[](https://zenodo.org/badge/latestdoi/345941713)
# [Online single-cell data integration through projecting heterogeneous datasets into a common cell-embedding space](https://www.nature.com/articles/s41467-022-33758-z)
## News
#### [2022-10-17] SCALEX is online at [Nature Communications](https://www.nature.com/articles/s41467-022-33758-z)
## [Documentation](https://scalex.readthedocs.io/en/latest/index.html)
## [Tutorial](https://scalex.readthedocs.io/en/latest/tutorial/index.html)
## Installation
#### install from PyPI
pip install scalex
#### install from GitHub
install the latest develop version
pip install git+https://github.com/jsxlei/scalex.git
or git clone and install
git clone git://github.com/jsxlei/scalex.git
cd scalex
python setup.py install
SCALEX is implemented in [Pytorch](https://pytorch.org/) framework.
SCALEX can be run on CPU devices, and running SCALEX on GPU devices if available is recommended.
## Getting started
SCALEX can both used under command line and API function in jupyter notebook
Please refer to the [Documentation](https://readthedocs.org/projects/scalex/badge/?version=latest) and [Tutorial](https://scalex.readthedocs.io/en/latest/tutorial/index.html)
### 1. API function
from scalex import SCALEX
adata = SCALEX(data_list, batch_categories)
Function of parameters are similar to command line options.
Output is a Anndata object for further analysis with scanpy.
`data_list` can be
* data_path, file format included txt, csv, h5ad, h5mu/rna, h5mu/atac, dir contains mtx
* list of data_paths
* [Anndata]((https://anndata.readthedocs.io/en/stable/anndata.AnnData.html#anndata.AnnData))
* list of [AnnData]((https://anndata.readthedocs.io/en/stable/anndata.AnnData.html#anndata.AnnData))
* above mixed
`batch_categories` is optional, name of each batch, will be range from 0 to N-1 if not provided
### 2. Command line
#### Standard usage
SCALEX --data_list data1 data2 dataN --batch_categories batch_name1 batch_name2 batch_nameN
`--data_list`: data path of each batch of single-cell dataset, use `-d` for short
`--batch_categories`: name of each batch, batch_categories will range from 0 to N-1 if not specified
#### Output
Output will be saved in the output folder including:
* **checkpoint**: saved model to reproduce results cooperated with option --checkpoint or -c
* **[adata.h5ad](https://anndata.readthedocs.io/en/stable/anndata.AnnData.html#anndata.AnnData)**: preprocessed data and results including, latent, clustering and imputation
* **umap.png**: UMAP visualization of latent representations of cells
* **log.txt**: log file of training process
### Other Common Usage
#### Use h5ad file storing `anndata` as input, one or multiple separated files
SCALEX --data_list <filename.h5ad>
#### Specify batch in `anadata.obs` using `--batch_name` if only one concatenated h5ad file provided, batch_name can be e.g. conditions, samples, assays or patients, default is `batch`
SCALEX --data_list <filename.h5ad> --batch_name <specific_batch_name>
#### Integrate heterogenous scATAC-seq datasets, add option `--profile` ATAC
SCALEX --data_list <filename.h5ad> --profile ATAC
#### Inputation simultaneously along with Integration, add option `--impute`, results are stored at anndata.layers['impute']
SCALEX --data_list <atac_filename.h5ad> --profile ATAC --impute True
#### Custom features through `--n_top_features` a filename contains features in one column format read
SCALEX --data_list <filename.h5ad> --n_top_features features.txt
#### Use preprocessed data `--processed`
SCALEX --data_list <filename.h5ad> --processed
#### Option
* --**data_list**
A list of matrices file (each as a `batch`) or a single batch/batch-merged file.
* --**batch_categories**
Categories for the batch annotation. By default, use increasing numbers if not given
* --**batch_name**
Use this annotation in anndata.obs as batches for training model. Default: 'batch'.
* --**profile**
Specify the single-cell profile, RNA or ATAC. Default: RNA.
* --**min_features**
Filtered out cells that are detected in less than min_features. Default: 600 for RNA, 100 for ATAC.
* --**min_cells**
Filtered out genes that are detected in less than min_cells. Default: 3.
* --**n_top_features**
Number of highly-variable genes to keep. Default: 2000 for RNA, 30000 for ATAC.
* --**outdir**
Output directory. Default: 'output/'.
* --**projection**
Use for new dataset projection. Input the folder containing the pre-trained model. Default: None.
* --**impute**
If True, calculate the imputed gene expression and store it at adata.layers['impute']. Default: False.
* --**chunk_size**
Number of samples from the same batch to transform. Default: 20000.
* --**ignore_umap**
If True, do not perform UMAP for visualization and leiden for clustering. Default: False.
* --**join**
Use intersection ('inner') or union ('outer') of variables of different batches.
* --**batch_key**
Add the batch annotation to obs using this key. By default, batch_key='batch'.
* --**batch_size**
Number of samples per batch to load. Default: 64.
* --**lr**
Learning rate. Default: 2e-4.
* --**max_iteration**
Max iterations for training. Training one batch_size samples is one iteration. Default: 30000.
* --**seed**
Random seed for torch and numpy. Default: 124.
* --**gpu**
Index of GPU to use if GPU is available. Default: 0.
* --**verbose**
Verbosity, True or False. Default: False.
#### Help
Look for more usage of SCALEX
SCALEX.py --help
## Release notes
See the [changelog](https://github.com/jsxlei/SCALEX/CHANGELOG.md).
## Citation
Xiong, L., Tian, K., Li, Y., Ning, W., Gao, X., & Zhang, Q. C. (2022). Online single-cell data integration through projecting heterogeneous datasets into a common cell-embedding space. Nature Communications, 13(1), 6118. https://doi.org/10.1038/s41467-022-33758-z
Raw data
{
"_id": null,
"home_page": null,
"name": "scalex",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.7",
"maintainer_email": null,
"keywords": null,
"author": "Lei Xiong",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/4d/45/4c58807fcdc3408ca94fdf8daeb6879a8ebd2ada42f64b3214380dbf4932/scalex-1.0.4.tar.gz",
"platform": null,
"description": "[](https://github.com/jsxlei/scalex/stargazers)\n[](https://pypi.org/project/scalex)\n[](https://scalex.readthedocs.io/en/latest/?badge=stable)\n[](https://pepy.tech/project/scalex)\n[](https://zenodo.org/badge/latestdoi/345941713)\n# [Online single-cell data integration through projecting heterogeneous datasets into a common cell-embedding space](https://www.nature.com/articles/s41467-022-33758-z)\n\n\n\n\n## News\n#### [2022-10-17] SCALEX is online at [Nature Communications](https://www.nature.com/articles/s41467-022-33758-z)\n\n## [Documentation](https://scalex.readthedocs.io/en/latest/index.html) \n## [Tutorial](https://scalex.readthedocs.io/en/latest/tutorial/index.html) \n## Installation \t\n#### install from PyPI\n\n pip install scalex\n \n#### install from GitHub\ninstall the latest develop version\n\n pip install git+https://github.com/jsxlei/scalex.git\n\nor git clone and install\n\n git clone git://github.com/jsxlei/scalex.git\n cd scalex\n python setup.py install\n \nSCALEX is implemented in [Pytorch](https://pytorch.org/) framework. \nSCALEX can be run on CPU devices, and running SCALEX on GPU devices if available is recommended. \n\n## Getting started\n\nSCALEX can both used under command line and API function in jupyter notebook \nPlease refer to the [Documentation](https://readthedocs.org/projects/scalex/badge/?version=latest) and [Tutorial](https://scalex.readthedocs.io/en/latest/tutorial/index.html)\n\n\n### 1. API function\n\n from scalex import SCALEX\n adata = SCALEX(data_list, batch_categories)\n \nFunction of parameters are similar to command line options. \nOutput is a Anndata object for further analysis with scanpy. \n`data_list` can be \n* data_path, file format included txt, csv, h5ad, h5mu/rna, h5mu/atac, dir contains mtx\n* list of data_paths\n* [Anndata]((https://anndata.readthedocs.io/en/stable/anndata.AnnData.html#anndata.AnnData))\n* list of [AnnData]((https://anndata.readthedocs.io/en/stable/anndata.AnnData.html#anndata.AnnData))\n* above mixed\n\n`batch_categories` is optional, name of each batch, will be range from 0 to N-1 if not provided\n\n### 2. Command line\n#### Standard usage\n\n\n SCALEX --data_list data1 data2 dataN --batch_categories batch_name1 batch_name2 batch_nameN \n \n \n`--data_list`: data path of each batch of single-cell dataset, use `-d` for short\n\n`--batch_categories`: name of each batch, batch_categories will range from 0 to N-1 if not specified\n\n \n#### Output\nOutput will be saved in the output folder including:\n* **checkpoint**: saved model to reproduce results cooperated with option --checkpoint or -c\n* **[adata.h5ad](https://anndata.readthedocs.io/en/stable/anndata.AnnData.html#anndata.AnnData)**: preprocessed data and results including, latent, clustering and imputation\n* **umap.png**: UMAP visualization of latent representations of cells \n* **log.txt**: log file of training process\n\n### Other Common Usage\n#### Use h5ad file storing `anndata` as input, one or multiple separated files\n\n SCALEX --data_list <filename.h5ad>\n\n#### Specify batch in `anadata.obs` using `--batch_name` if only one concatenated h5ad file provided, batch_name can be e.g. conditions, samples, assays or patients, default is `batch`\n\n SCALEX --data_list <filename.h5ad> --batch_name <specific_batch_name>\n \n \n#### Integrate heterogenous scATAC-seq datasets, add option `--profile` ATAC\n \n SCALEX --data_list <filename.h5ad> --profile ATAC\n \n#### Inputation simultaneously along with Integration, add option `--impute`, results are stored at anndata.layers['impute']\n\n SCALEX --data_list <atac_filename.h5ad> --profile ATAC --impute True\n \n \n#### Custom features through `--n_top_features` a filename contains features in one column format read\n\n SCALEX --data_list <filename.h5ad> --n_top_features features.txt\n \n#### Use preprocessed data `--processed`\n\n SCALEX --data_list <filename.h5ad> --processed\n\n#### Option\n\n* --**data_list** \n A list of matrices file (each as a `batch`) or a single batch/batch-merged file.\n* --**batch_categories** \n Categories for the batch annotation. By default, use increasing numbers if not given\n* --**batch_name** \n Use this annotation in anndata.obs as batches for training model. Default: 'batch'.\n* --**profile** \n Specify the single-cell profile, RNA or ATAC. Default: RNA.\n* --**min_features** \n Filtered out cells that are detected in less than min_features. Default: 600 for RNA, 100 for ATAC.\n* --**min_cells** \n Filtered out genes that are detected in less than min_cells. Default: 3.\n* --**n_top_features** \n Number of highly-variable genes to keep. Default: 2000 for RNA, 30000 for ATAC.\n* --**outdir** \n Output directory. Default: 'output/'.\n* --**projection** \n Use for new dataset projection. Input the folder containing the pre-trained model. Default: None. \n* --**impute** \n If True, calculate the imputed gene expression and store it at adata.layers['impute']. Default: False.\n* --**chunk_size** \n Number of samples from the same batch to transform. Default: 20000.\n* --**ignore_umap** \n If True, do not perform UMAP for visualization and leiden for clustering. Default: False.\n* --**join** \n Use intersection ('inner') or union ('outer') of variables of different batches. \n* --**batch_key** \n Add the batch annotation to obs using this key. By default, batch_key='batch'.\n* --**batch_size** \n Number of samples per batch to load. Default: 64.\n* --**lr** \n Learning rate. Default: 2e-4.\n* --**max_iteration** \n Max iterations for training. Training one batch_size samples is one iteration. Default: 30000.\n* --**seed** \n Random seed for torch and numpy. Default: 124.\n* --**gpu** \n Index of GPU to use if GPU is available. Default: 0.\n* --**verbose** \n Verbosity, True or False. Default: False.\n \n\n\t\n \n#### Help\nLook for more usage of SCALEX\n\n\tSCALEX.py --help \n \n \n## Release notes\n\nSee the [changelog](https://github.com/jsxlei/SCALEX/CHANGELOG.md). \n\n\n## Citation\n\nXiong, L., Tian, K., Li, Y., Ning, W., Gao, X., & Zhang, Q. C. (2022). Online single-cell data integration through projecting heterogeneous datasets into a common cell-embedding space. Nature Communications, 13(1), 6118. https://doi.org/10.1038/s41467-022-33758-z\n\n ",
"bugtrack_url": null,
"license": "MIT",
"summary": "Online single-cell data integration through projecting heterogeneous datasets into a common cell-embedding space",
"version": "1.0.4",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "ab9b6745a16efe50a2cba607d70cddaa15b7772332f3a8dc05c0e5290f724d14",
"md5": "4773ad518ae1157aa4ce16867d375dbe",
"sha256": "a98fe01cd89601675fd198c75e2afbd28ed2c7124eb40e1b4d9208bbd627e006"
},
"downloads": -1,
"filename": "scalex-1.0.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "4773ad518ae1157aa4ce16867d375dbe",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7",
"size": 25946,
"upload_time": "2024-06-02T21:25:07",
"upload_time_iso_8601": "2024-06-02T21:25:07.066221Z",
"url": "https://files.pythonhosted.org/packages/ab/9b/6745a16efe50a2cba607d70cddaa15b7772332f3a8dc05c0e5290f724d14/scalex-1.0.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "4d454c58807fcdc3408ca94fdf8daeb6879a8ebd2ada42f64b3214380dbf4932",
"md5": "2cd7f07a52ee29bd18018457da3d58e2",
"sha256": "af821d3c8dd98416376f20d9ab30554c7d182107f3d45d43ca4a819bf002427a"
},
"downloads": -1,
"filename": "scalex-1.0.4.tar.gz",
"has_sig": false,
"md5_digest": "2cd7f07a52ee29bd18018457da3d58e2",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.7",
"size": 4047711,
"upload_time": "2024-06-02T21:25:09",
"upload_time_iso_8601": "2024-06-02T21:25:09.440030Z",
"url": "https://files.pythonhosted.org/packages/4d/45/4c58807fcdc3408ca94fdf8daeb6879a8ebd2ada42f64b3214380dbf4932/scalex-1.0.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-06-02 21:25:09",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "scalex"
}
