Metadata-Version: 2.1
Name: scyan
Version: 1.3.7
Summary: Single-cell Cytometry Annotation Network
Home-page: https://mics-lab.github.io/scyan/
License: BSD-3-Clause
Author: Blampey Quentin
Author-email: quentin.blampey@gmail.com
Requires-Python: >=3.8,<3.11
Classifier: License :: OSI Approved :: BSD License
Classifier: Operating System :: MacOS :: MacOS X
Classifier: Operating System :: Microsoft :: Windows
Classifier: Operating System :: POSIX :: Linux
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Topic :: Scientific/Engineering
Provides-Extra: dev
Provides-Extra: discovery
Provides-Extra: hydra
Requires-Dist: FlowUtils (>=1.0.0,<2.0.0)
Requires-Dist: anndata (>=0.8.0,<0.9.0)
Requires-Dist: black (>=22.6.0,<23.0.0); extra == "dev"
Requires-Dist: fcsparser (>=0.2.4,<0.3.0)
Requires-Dist: fcswrite (>=0.6.2,<0.7.0)
Requires-Dist: hydra-colorlog (>=1.2.0,<2.0.0); extra == "hydra"
Requires-Dist: hydra-core (>=1.2.0,<2.0.0); extra == "hydra"
Requires-Dist: hydra-optuna-sweeper (>=1.2.0,<2.0.0); extra == "hydra"
Requires-Dist: ipykernel (>=6.15.0,<7.0.0); extra == "dev"
Requires-Dist: ipywidgets (>=7.7.1,<8.0.0); extra == "dev"
Requires-Dist: isort (>=5.10.1,<6.0.0); extra == "dev"
Requires-Dist: leidenalg (>=0.8.10,<0.9.0); extra == "discovery"
Requires-Dist: llvmlite (>=0.38.1,<0.39.0)
Requires-Dist: mkdocs-jupyter (>=0.21.0,<0.22.0); extra == "dev"
Requires-Dist: mkdocs-material (>=8.5.0,<9.0.0); extra == "dev"
Requires-Dist: mkdocstrings (>=0.19.0,<0.20.0); extra == "dev"
Requires-Dist: mkdocstrings-python (>=0.7.1,<0.8.0); extra == "dev"
Requires-Dist: pytest (>=7.1.2,<8.0.0); extra == "dev"
Requires-Dist: pytorch-lightning (>=1.6.4,<2.0.0)
Requires-Dist: seaborn (>=0.12.2,<0.13.0)
Requires-Dist: torch (>=1.13,<2.0)
Requires-Dist: umap-learn (>=0.5.3,<0.6.0)
Requires-Dist: wandb (==0.13.7); extra == "hydra"
Project-URL: Documentation, https://mics-lab.github.io/scyan/
Project-URL: Repository, https://github.com/MICS-Lab/scyan
Description-Content-Type: text/markdown

<p align="center">
  <img src="https://github.com/MICS-Lab/scyan/raw/master/docs/assets/logo.png" alt="scyan_logo" width="500"/>
</p>

[![PyPI](https://img.shields.io/pypi/v/scyan.svg)](https://pypi.org/project/scyan)
[![Downloads](https://pepy.tech/badge/scyan)](https://pepy.tech/project/scyan)
[![Docs](https://img.shields.io/badge/docs-mkdocs-blue)](https://mics-lab.github.io/scyan/)
![Build](https://github.com/MICS-Lab/scyan/workflows/ci/badge.svg)
[![Code Style](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/python/black)
[![License](https://img.shields.io/pypi/l/scyan.svg)](https://github.com/MICS-Lab/scyan/blob/master/LICENSE)
[![Imports: isort](https://img.shields.io/badge/imports-isort-blueviolet)](https://pycqa.github.io/isort/)

Scyan stands for **S**ingle-cell **Cy**tometry **A**nnotation **N**etwork. Based on biological knowledge prior, it provides a fast cell population annotation without requiring any training label. Scyan is an interpretable model that also corrects batch-effect and can be used for debarcoding, cell sampling, and population discovery.

# Documentation

The [complete documentation can be found here](https://mics-lab.github.io/scyan/). It contains installation guidelines, tutorials, a description of the API, etc.

# Overview

Scyan is a Bayesian probabilistic model composed of a deep invertible neural network called a normalizing flow (the function $f_{\phi}$). It maps a latent distribution of cell expressions into the empirical distribution of cell expressions. This cell distribution is a mixture of gaussian-like distributions representing the sum of a cell-specific and a population-specific term. Also, interpretability and batch effect correction are based on the model latent space — more details in the article's Methods section.

<p align="center">
  <img src="https://github.com/MICS-Lab/scyan/raw/master/docs/assets/overview.png" alt="overview_image"/>
</p>

# Getting started

Scyan can be installed on every OS with `pip` or [`poetry`](https://python-poetry.org/docs/).

On macOS / Linux, `python>=3.8,<3.11` is required, while `python>=3.8,<3.10` is required on Windows. The preferred Python version is `3.9`.

## Install from PyPI (recommended)

```bash
pip install scyan
```

## Install locally (if you want to contribute)

> Advice (optional): We advise creating a new environment via a package manager (except if you use Poetry, which will automatically create the environment). For instance, you can create a new `conda` environment:
>
> ```bash
> conda create --name scyan python=3.9
> conda activate scyan
> ```

Clone the repository and move to its root:

```bash
git clone https://github.com/MICS-Lab/scyan.git
cd scyan
```

Choose one of the following, depending on your needs (it should take at most a few minutes):

```bash
pip install .                            # pip minimal installation (library only)
pip install -e .                         # pip installation in editable mode
pip install -e '.[dev,hydra,discovery]'  # pip installation with all the extras
poetry install -E 'dev hydra discovery'  # poetry installation with all the extras
```

## Basic usage / Demo

```py
import scyan

adata, table = scyan.data.load("aml")

model = scyan.Scyan(adata, table)
model.fit()
model.predict()
```

This code should run in approximately 40 seconds (once the dataset is loaded).
For more usage demo, read the [tutorials](https://mics-lab.github.io/scyan/tutorials/usage/) or the complete [documentation](https://mics-lab.github.io/scyan/).

# Technical description

Scyan is a **Python** library based on:

- [_Pytorch_](https://pytorch.org/), a deep learning framework
- [_AnnData_](https://anndata.readthedocs.io/en/latest/), a data library that works nicely with single-cell data
- [_Pytorch Lighning_](https://www.pytorchlightning.ai/), for model training
- [_Hydra_](https://hydra.cc/docs/intro/), for project configuration (optional)
- [_Weight & Biases_](https://wandb.ai/site), for model monitoring (optional)

# Project layout

    .github/      # Github CI and templates
    config/       # Hydra configuration folder (optional use)
    data/         # Data folder containing adata files and csv tables
    docs/         # The folder used to build the documentation
    scripts/      # Scripts to reproduce the results from the article
    tests/        # Folder containing tests
    scyan/                    # Library source code
        data/                 # Folder with data-related functions and classes
            datasets.py       # Load and save datasets
            tensors.py        # Pytorch data-related classes for training
        module/               # Folder containing neural network modules
            coupling_layer.py # Coupling layer
            distribution.py   # Prior distribution (called U in the article)
            real_nvp.py       # Normalizing Flow
            scyan_module      # Core module
        plot/                 # Plots
            ...
        tools/
            ...               # Tools (umap, subclustering, ...)
        model.py              # Scyan model class
        _io.py                # Input / output functions
        preprocess.py         # Preprocessing functions
        utils.py              # Misc functions
    .gitattributes
    .gitignore
    CONTRIBUTING.md   # To read before contributing
    LICENSE
    mkdocs.yml        # The docs configuration file
    poetry.lock
    pyproject.toml    # Dependencies, project metadata, and more
    README.md
    setup.py          # Setup file, see `pyproject.toml`

# Cite us

Our paper is not published yet. Meanwhile, you can [read our preprint on arXiv](https://arxiv.org/abs/2208.05745).

