Can Arboreto handle single-cell RNA-seq data?

Yes, it is specifically designed to handle the high volume of observations found in single-cell datasets and is a core component of the SCENIC pipeline.

Does this skill require a specific environment to run?

It requires a Python environment with Dask and Pandas. It is critical to use the 'if __name__ == "__main__":' guard when running scripts to support Dask's multi-processing.

How do I scale Arboreto to a computing cluster?

You can scale by connecting to a remote Dask scheduler. Simply instantiate a distributed Client with the scheduler's address and pass it to the inference function.

What is the main difference between GRNBoost2 and GENIE3?

GRNBoost2 uses gradient boosting and is optimized for speed and large datasets, while GENIE3 uses random forests and follows the original regression approach for inference.

Is it possible to filter by specific transcription factors?

Yes, Arboreto allows you to provide a list of transcription factor names to restrict the regulators considered during the network inference process.

Arboreto Gene Regulatory Network Inference

Name: Arboreto Gene Regulatory Network Inference
Author: Microck

byMicrock

•

Ciencia de Datos y ML

Infers gene regulatory networks from transcriptomics data using scalable gradient boosting and random forest algorithms.

Acerca de

Arboreto is a high-performance computational library designed to reconstruct gene regulatory networks (GRNs) from large-scale gene expression data, such as bulk or single-cell RNA-seq. By leveraging parallelized algorithms like GRNBoost2 and GENIE3, it identifies regulatory relationships between transcription factors and target genes with exceptional speed. This skill is particularly valuable for bioinformaticians needing to scale analyses from local machines to distributed clusters using Dask, providing a robust foundation for downstream systems biology workflows like the pySCENIC pipeline.

Características Principales

81 GitHub stars
Distributed computing support via Dask for large-scale datasets
Identification of transcription factor-target gene interactions
Scalable GRN inference using GRNBoost2 and GENIE3 algorithms
Optimized performance for datasets with 10k+ observations
Seamless integration with single-cell and bulk RNA-seq workflows

Casos de Uso

Identifying cell-type-specific regulatory networks in single-cell RNA-seq data
Performing comparative regulatory analysis across multiple experimental conditions
Mapping transcription factor targets in bulk transcriptomics studies

Acerca de

Características Principales

81 GitHub stars
Distributed computing support via Dask for large-scale datasets
Identification of transcription factor-target gene interactions
Scalable GRN inference using GRNBoost2 and GENIE3 algorithms
Optimized performance for datasets with 10k+ observations
Seamless integration with single-cell and bulk RNA-seq workflows

Casos de Uso

Identifying cell-type-specific regulatory networks in single-cell RNA-seq data
Performing comparative regulatory analysis across multiple experimental conditions
Mapping transcription factor targets in bulk transcriptomics studies