Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/irrationone/cellassign
Automated, probabilistic assignment of cell types in scRNA-seq data
https://github.com/irrationone/cellassign
Last synced: 23 days ago
JSON representation
Automated, probabilistic assignment of cell types in scRNA-seq data
- Host: GitHub
- URL: https://github.com/irrationone/cellassign
- Owner: Irrationone
- License: other
- Created: 2018-07-08T18:55:41.000Z (almost 6 years ago)
- Default Branch: master
- Last Pushed: 2023-01-09T17:19:34.000Z (over 1 year ago)
- Last Synced: 2024-05-22T18:11:59.863Z (about 1 month ago)
- Language: R
- Homepage:
- Size: 14.9 MB
- Stars: 187
- Watchers: 13
- Forks: 78
- Open Issues: 47
-
Metadata Files:
- Readme: README.md
- License: LICENSE.md
- Code of conduct: CODE_OF_CONDUCT.md
Lists
- awesome_single_cell - cellassign - [R] - Automated, probabilistic assignment of scRNA-seq to known types. `cellassign` automatically assigns single-cell RNA-seq data to known cell types across thousands of cells accounting for patient and batch specific effects. Information about a priori known markers for cell types is provided as input to the model. cellassign then probabilistically assigns each cell to a cell type, removing subjective biases from typical unsupervised clustering workflows. [bioRxiv](https://www.biorxiv.org/content/early/2019/01/16/521914) (Software packages / Cell type identification and classification)
README
# cellassign
[](https://travis-ci.com/Irrationone/cellassign) [](http://bioconda.github.io/recipes/r-cellassign/README.html)
`cellassign` automatically assigns single-cell RNA-seq data to known cell types across thousands of cells accounting for patient and batch specific effects. Information about *a priori* known markers cell types is provided as input to the model in the form of a (binary) marker gene by cell-type matrix. `cellassign` then probabilistically assigns each cell to a cell type, removing subjective biases from typical unsupervised clustering workflows.
# Getting started
## Installation
### Installing from GitHub
`cellassign` is built using Google's Tensorflow, and as such requires installation of the R package `tensorflow`:
``` r
install.packages("tensorflow")
tensorflow::install_tensorflow(extra_packages='tensorflow-probability', version = "2.1.0")
```
Please ensure this installs version 2 of tensorflow. You can check this by calling
```r
tensorflow::tf_config()
```
```
TensorFlow v2.1.0 (/usr/local/lib/python3.7/site-packages/tensorflow)
```
`cellassign` can then be installed from github:
``` r
install.packages("devtools") # If not already installed
devtools::install_github("Irrationone/cellassign")
```
### Installing from conda
With [conda](https://conda.io/miniconda.html), install the current release version of `cellassign` as follows:
``` r
conda install -c conda-forge -c bioconda r-cellassign
```
## Documentation
Package documentation can be found [here](https://irrationone.github.io/cellassign/index.html). This includes the following vignettes:
- [Assigning single-cells to known cell types with CellAssign](https://irrationone.github.io/cellassign/articles/introduction-to-cellassign.html)
- [Constructing marker genes from purified bulk/scRNA-seq data](https://irrationone.github.io/cellassign/articles/constructing-markers-from-purified-data.html)
## Basic usage
`cellassign` requires the following inputs:
* `exprs_obj`: Cell-by-gene matrix of raw counts (or SingleCellExperiment with `counts` assay)
* `marker_gene_info`: Binary gene-by-celltype marker gene matrix or list relating cell types to marker genes
* `s`: Size factors
* `X`: Design matrix for any patient/batch specific effects
The model can be run as follows:
``` r
cas <- cellassign(exprs_obj = gene_expression_data,
marker_gene_info = marker_gene_info,
s = s,
X = X)
```
An example set of markers for the human tumour microenvironment can be loaded by calling
``` r
data(example_TME_markers)
```
Please see the package vignette for details and caveats.
# Paper
[Probabilistic cell-type assignment of single-cell RNA-seq for tumor microenvironment profiling, _Nature Methods 2019_](https://www.nature.com/articles/s41592-019-0529-1)
# Code of Conduct
Please note that the 'cellassign' project is released with a
[Contributor Code of Conduct](CODE_OF_CONDUCT.md).
By contributing to this project, you agree to abide by its terms.
# Authors
Allen W Zhang, University of British Columbia
Kieran R Campbell, University of British Columbia