Does this skill require specific data formats?

It works best with gene expression matrices provided as Pandas DataFrames or NumPy arrays, where genes are represented as columns and observations as rows.

Is Arboreto compatible with the SCENIC pipeline?

Absolutely; Arboreto serves as a core component for the initial gene regulatory network inference step in the pySCENIC workflow.

Can Arboreto handle large single-cell datasets?

Yes, Arboreto is specifically designed for scalability and utilizes Dask to distribute computations across multi-core processors or multi-node clusters.

What algorithms does Arboreto support?

Arboreto primarily supports GRNBoost2 (Gradient Boosting) and GENIE3 (Random Forest) for inferring regulatory links between genes.

Arboreto Gene Regulatory Network Inference

Name: Arboreto Gene Regulatory Network Inference
Author: Zehong-Wang

byZehong-Wang

0•

Data Science & ML

Infers gene regulatory networks from transcriptomics data using scalable algorithms like GRNBoost2 and GENIE3.

Arboreto is a high-performance computational library designed to reconstruct gene regulatory networks (GRNs) from large-scale gene expression datasets, such as bulk or single-cell RNA-seq. By leveraging parallelized algorithms including GRNBoost2 (gradient boosting) and GENIE3 (random forest), it identifies relationships between transcription factors and target genes across diverse biological conditions. This skill is essential for bioinformaticians needing to scale complex regulatory analyses from local machines to multi-node Dask clusters while maintaining high accuracy and computational efficiency.

Key Features

01Scalable GRN inference using GRNBoost2 and GENIE3 algorithms

020 GitHub stars

03Seamless integration with the pySCENIC pipeline for single-cell analysis

04Identification of transcription factor (TF) to target gene relationships

05Support for both bulk and single-cell RNA-seq expression matrices

06Distributed computing support via Dask for large-scale datasets

Use Cases

01Analyzing gene expression patterns to find transcription factor targets in bulk RNA-seq

02Performing comparative regulatory network analysis across multiple experimental conditions

03Identifying cell-type-specific regulatory interactions in single-cell RNA-seq data

Key Features

01Scalable GRN inference using GRNBoost2 and GENIE3 algorithms

020 GitHub stars

03Seamless integration with the pySCENIC pipeline for single-cell analysis

04Identification of transcription factor (TF) to target gene relationships

05Support for both bulk and single-cell RNA-seq expression matrices

06Distributed computing support via Dask for large-scale datasets

Use Cases

01Analyzing gene expression patterns to find transcription factor targets in bulk RNA-seq

02Performing comparative regulatory network analysis across multiple experimental conditions

03Identifying cell-type-specific regulatory interactions in single-cell RNA-seq data