A deep learning-based tool for alignment and integration of single cell genomic data across multiple datasets, species, conditions and batches

First follow the install instructions below, at the bottom of the page, before following the tutorials.

Unsupervised alignment and projection of HSCs

Multiway alignment using all pairs method

Supervised/Semi-supervised alignment

Chang Kim

Bioconductor for now will only support the Linux version of scAlign.

The latest version of scAlign for all systems can always be found at github.

install.packages('devtools')
devtools::install_github(repo = 'quon-titative-biology/scAlign')
library(scAlign)

scAlign has three dependencies: Python 3, tensorflow (the R package), and tensorflow (the Python package). This is a guide to installing python and Tensorflow on different operating systems.

1. Download install binaries for Python 3 here

1. Download Python 3
2. Make sure pip is included in the installation.

1. sudo apt update
2. sudo apt install python3-dev python3-pip

1. /usr/bin/ruby -e "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/master/install)"
2. export PATH="/usr/local/bin:/usr/local/sbin:$PATH"
3. brew update
4. brew install python # Python 3

In an R session:

install.packages('tensorflow') #install the tensorflow R package (that sits on top of the TensorFlow python package)
library(tensorflow)