Metadata-Version: 2.1
Name: autogenes
Version: 1.0.1
Summary: Automatic Gene Selection for Bulk Deconvolution
Home-page: https://github.com/theislab/AutoGeneS
Author: Hananeh Aliee, Maxim Schmidt
Author-email: author@helmholtz-muenchen.de
License: BSD
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.6
Description-Content-Type: text/markdown
Requires-Dist: pandas (>=0.25.1)
Requires-Dist: anndata (>=0.6.22.post1)
Requires-Dist: numpy (>=1.17.2)
Requires-Dist: dill (>=0.3.1.1)
Requires-Dist: deap (>=1.3.0)
Requires-Dist: scipy (==1.3)
Requires-Dist: cachetools (>=3.1.1)
Requires-Dist: scikit-learn (>=0.21.3)
Requires-Dist: matplotlib (==3.0.*)

# AutoGeneS

AutoGeneS **automatically** extracts informative genes and reveals the cellular heterogeneity of bulk RNA samples. AutoGeneS requires no prior knowledge about marker genes and selects genes by **simultaneously optimizing multiple criteria**: minimizing the correlation and maximizing the distance between cell types. It can be applied to reference profiles from various sources like single-cell experiments or sorted cell populations.

![Workflow of AutoGeneS](./images/overview.png)

For a multi-objective optimization problem, there usually exists no single solution that simultaneously optimizes all objectives. In this case, the objective functions are said to be conflicting, and there exists a (possibly infinite) number of **Pareto-optimal solutions**. Pareto-(semi)optimal solutions are a set of all solutions that are not dominated by any other explored solution. Pareto-optimal solutions offer a set of equally good solutions from which to select, depending on the dataset

## Installation

1. PyPI only <br/> 
```pip install --user autogenes```<br/>

2. Development Version (latest version on github) <br/>
```git clone https://github.com/theislab/AutoGeneS```<br/>
```pip install --user dist/autogenes-1.0-py3-none-any.whl```<br/>

## Example

[Example on pseudo bulks](https://github.com/theislab/AutoGeneS/blob/master/deconv_example/bulkDeconvolution_using_singleCellReferenceProfiles.ipynb)

## Documentation

[Documentation](https://autogenes.readthedocs.io/en/latest/)

[Getting Started](https://autogenes.readthedocs.io/en/latest/getting_started.html)

## Dependencies

* python >=3.6
* anndata
* deap
* cachetools


