LINGER

Introduction

LINGER (LIfelong neural Network for GEne Regulation) is a novel method to infer GRNs from single-cell multiome data built on top of PyTorch.

LINGER incorporates both 1) atlas-scale external bulk data across diverse cellular contexts and 2) the knowledge of transcription factor (TF) motif matching to cis-regulatory elements as a manifold regularization to address the challenge of limited data and extensive parameter space in GRN inference.

Analysis tasks for single cell multiome data

• Infer gene regulatory network
• Benchmark gene regulatory network
• Explainable dimensionality reduction (transcription factor activity, availiable for single cell or bulk RNA-seq data)
• In silico pertubation

In the user guide, we provide an overview of each task.

Basic installation

LINGER can be installed by pip (Time cost: 1min 39s):

conda create -n LINGER python==3.10.0
conda activate LINGER
pip install LingerGRN==1.110
conda install bioconda::bedtools # Requirment

Documentation

We provide several tutorials and user guide. The PBMC tutorial serves as a comprehensive demonstration of the entire workflow.

User guide	PBMCs tutorial (notebook)	H1 cell line tutorial
GRN benchmark	In silico perturbation	Other species
Downstream analysis-Module detection	Downstream analysis-TF Driver score	post network processing

Reference

If you use LINGER, please cite:

Yuan, Qiuyue, and Zhana Duren. "Inferring gene regulatory networks from single-cell multiome data using atlas-scale external data." Nature Biotechnology (2024): 1-11.

License

This project is covered by the MIT license.