Data

Tools

Indexes

Applications

Experiments

Open Source Science

desc

Deep Embedding for Single-cell Clustering

https://github.com/eleozzr/desc

Science Score: 36.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ○
    .zenodo.json file
  • ✓
    DOI references
    Found 3 DOI reference(s) in README
  • ✓
    Academic publication links
    Links to: biorxiv.org, nature.com
  • ○
    Committers with academic emails
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (12.6%) to scientific vocabulary

Keywords

batch-remove clustering deep-learning desc scrna-seq
Last synced: 9 months ago · JSON representation

Repository

Deep Embedding for Single-cell Clustering

Basic Info
Statistics
  • Stars: 86
  • Watchers: 4
  • Forks: 25
  • Open Issues: 41
  • Releases: 1
Topics
batch-remove clustering deep-learning desc scrna-seq
Created over 7 years ago · Last pushed about 2 years ago
Metadata Files
Readme

README.md

Deep Embedding for Single-cell Clustering (DESC)

DESC is an unsupervised deep learning algorithm for clustering scRNA-seq data. The algorithm constructs a non-linear mapping function from the original scRNA-seq data space to a low-dimensional feature space by iteratively learning cluster-specific gene expression representation and cluster assignment based on a deep neural network. This iterative procedure moves each cell to its nearest cluster, balances biological and technical differences between clusters, and reduces the influence of batch effect. DESC also enables soft clustering by assigning cluster-specific probabilities to each cell, which facilitates the identification of cells clustered with high-confidence and interpretation of results.

DESC workflow

For thorough details, see our paper: https://www.nature.com/articles/s41467-020-15851-3

Usage

The desc package is an implementation of deep embedding for single-cell clustering. With desc, you can:

  • Preprocess single cell gene expression data from various formats.
  • Build a low-dimensional representation of the single-cell gene expression data.
  • Obtain soft-clustering assignments of cells.
  • Visualize the cell clustering results and the gene expression patterns.

Because of the difference between tensorflow 1* and tensorflow 2*, we updated our desc algorithm into two version such that it can be compatible with tensorflow 1* and tensorflow 2*, respectively.

  1. For tensorflow 1*, we released desc(2.0.3). Please see our jupyter notebook example desc2.0.3paul.ipynb
  2. For tensorflow 2*, we released desc(2.1.1). Please see our jupyter notebook example desc2.1.1paul.ipynb


Installation

To install desc package you must make sure that your python version is either 3.5.x or 3.6.x. If you dont know the version of python you can check it by: ```python

import platform platform.python_version()

3.5.3

import tensorflow as tf tf.version

1.7.0

`` **Note:** Because desc depend ontensorflow, you should make sure the version oftensorflowis lower than2.0if you want to get the same results as the results in our paper. Now you can install the current release ofdesc` by the following three ways.

  • PyPI
    Directly install the package from PyPI.

bash $ pip install desc Note: you need to make sure that the pip is for python3or we should install desc by ```bash python3 -m pip install desc

or

pip3 install desc ```

If you do not have permission (when you get a permission denied error), you should install desc by

bash $ pip install --user desc

  • Github
    Download the package from Github and install it locally:

bash git clone https://github.com/eleozzr/desc cd desc pip install .

  • Anaconda

If you do not have Python3.5 or Python3.6 installed, consider installing Anaconda (see Installing Anaconda). After installing Anaconda, you can create a new environment, for example, DESC (you can change to any name you like):

```bash conda create -n DESC python=3.5.3

activate your environment

source activate DESC git clone https://github.com/eleozzr/desc cd desc python setup.py build python setup.py install

now you can check whether desc installed successfully!

```

Please check desc Tutorial for more details. And we also provide a simple example for reproducing the results of Paul's data in our paper.


Contributing

Souce code: Github

We are continuing adding new features. Bug reports or feature requests are welcome.


References

Please consider citing the following reference:

  • Xiangjie Li, Yafei Lyu, Jihwan Park, Jingxiao Zhang, Dwight Stambolian, Katalin Susztak, Gang Hu, Mingyao Li. Deep learning enables accurate clustering and batch effect removal in single-cell RNA-seq analysis. 2019. bioRxiv 530378; doi: https://doi.org/10.1101/530378

Owner

  • Name: Xiangjie Li
  • Login: eleozzr
  • Kind: user

GitHub Events

Total
  • Watch event: 4
  • Pull request event: 2
  • Fork event: 4
Last Year
  • Watch event: 4
  • Pull request event: 2
  • Fork event: 4

Committers

Last synced: over 2 years ago

All Time
  • Total Commits: 98
  • Total Committers: 3
  • Avg Commits per committer: 32.667
  • Development Distribution Score (DDS): 0.633
Past Year
  • Commits: 0
  • Committers: 0
  • Avg Commits per committer: 0.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
eleozzr e****r@g****m 36
Xiangjie Li e****7@1****m 34
Yafei Lyu l****i@g****m 28
Committer Domains (Top 20 + Academic)
163.com: 1

Issues and Pull Requests

Last synced: 9 months ago

All Time
  • Total issues: 53
  • Total pull requests: 10
  • Average time to close issues: 6 months
  • Average time to close pull requests: 15 days
  • Total issue authors: 48
  • Total pull request authors: 4
  • Average comments per issue: 1.57
  • Average comments per pull request: 0.3
  • Merged pull requests: 4
  • Bot issues: 0
  • Bot pull requests: 3
Past Year
  • Issues: 0
  • Pull requests: 2
  • Average time to close issues: N/A
  • Average time to close pull requests: less than a minute
  • Issue authors: 0
  • Pull request authors: 1
  • Average comments per issue: 0
  • Average comments per pull request: 0.0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • 123kfl (3)
  • kongfengling (2)
  • Cumol (2)
  • MediciPrime (2)
  • Dan-121 (1)
  • cdiaz45 (1)
  • HelloWorldLTY (1)
  • dm8000 (1)
  • DovahCoding (1)
  • amssljc (1)
  • byee4 (1)
  • zhumengyan (1)
  • NathanSkene (1)
  • linzhangTuesday (1)
  • jhu99 (1)
Pull Request Authors
  • Yafei611 (4)
  • dependabot[bot] (3)
  • Jakerson22 (2)
  • johnarevalo (1)
Top Labels
Issue Labels
Pull Request Labels
dependencies (3)

Packages

  • Total packages: 1
  • Total downloads:
    • pypi 729 last-month
  • Total dependent packages: 2
  • Total dependent repositories: 9
  • Total versions: 16
  • Total maintainers: 2
pypi.org: desc

Deep Embedded Single-cell RNA-seq Clustering

  • Versions: 16
  • Dependent Packages: 2
  • Dependent Repositories: 9
  • Downloads: 729 Last month
Rankings
Dependent packages count: 3.1%
Dependent repos count: 4.9%
Stargazers count: 7.7%
Average: 7.9%
Forks count: 8.1%
Downloads: 15.4%
Maintainers (2)
eleozzr Yafei
Last synced: 9 months ago

Dependencies

setup.py pypi
  • h5py *
  • keras ==2.1
  • louvain *
  • matplotlib >=2.2
  • pandas *
  • pydot *
  • python-igraph *
  • scanpy *
  • tensorflow *