atacnet 0.1.3

Package for building co-accessibility networks from ATAC-seq data.

AtacNet

Description

This repo contains a python package for inferring co-accessibility networks from single-cell ATAC-seq data, using skggm for the graphical lasso and scanpy for data processing.

It is based on the pipeline and hypotheses presented in the manuscript "Cicero Predicts cis-Regulatory DNA Interactions from Single-Cell Chromatin Accessibility Data" by Pliner et al. (2018). The original R package Cicero is available here.

Results may vary between both packages, notably due to the different implementations of graphical lasso.
Currently, scores seem proportional but absolute values differs slightly. (cf comparison plots below)

Installation

The package can be installed using pip:

pip install atacnet

and from github

pip install "git+https://github.com/r-trimbour/atacnet.git"

Minimal example

import anndata as ad
import atacnet as an

atac = ad.read_h5ad('atac_data.h5ad')
an.add_region_infos(atac)
an.compute_atac_network(atac)
an.extract_atac_links(atac)

Comparison to Cicero R package

Toy dataset 1:

On the same metacells obtained from Cicero code.

• Pearson correlation coefficient: 0.99
• Spearman correlation coefficient: 0.98

Coming:

Add stats on similarity on large datasets.
Add stats on runtime, memory usage.
This package can be run on multiple cores.

Usage

It is currently developped to work with AnnData objects. Check Example1.ipynb for a simple usage example.