Can this skill handle large-scale single-cell datasets?

Yes, Arboreto is built on Dask, allowing it to scale from a single computer to large multi-node clusters for processing millions of cells.

What is the primary use of the Arboreto skill?

Arboreto is used to infer gene regulatory networks (GRNs) by identifying which transcription factors regulate specific target genes based on expression patterns.

What data formats are required?

It typically accepts gene expression matrices in Pandas DataFrame or NumPy array formats where genes are represented as columns.

Which algorithms does Arboreto support?

It supports GRNBoost2, a fast gradient boosting-based algorithm, and GENIE3, a classic Random Forest-based approach.

Is Arboreto compatible with the SCENIC pipeline?

Yes, Arboreto is a core component of the pySCENIC pipeline, serving as the primary engine for initial GRN inference.

Arboreto GRN Inference

Name: Arboreto GRN Inference
Author: Microck

byMicrock

•

Ciencia de Datos y ML

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

Acerca de

Arboreto is a high-performance computational skill designed for bioinformaticians and data scientists to reconstruct gene regulatory networks (GRNs) from gene expression data. It provides specialized implementations of GRNBoost2 and GENIE3 algorithms, optimized for everything from local machines to multi-node distributed clusters using Dask. This skill is particularly valuable for identifying transcription factor-target gene relationships in large-scale datasets, such as single-cell RNA-seq atlases, and integrates seamlessly into broader workflows like the pySCENIC pipeline.

Características Principales

Distributed computing support via Dask for processing massive transcriptomic datasets.
81 GitHub stars
Scalable GRN inference using high-performance GRNBoost2 and GENIE3 algorithms.
Automated resource management for local multi-core or remote cluster environments.
Targeted regulatory mapping with transcription factor filtering capabilities.
Support for both bulk and single-cell RNA-seq expression matrices.

Casos de Uso

Mapping cell-type-specific transcription factor targets in single-cell RNA-seq studies.
Identifying high-confidence regulatory interactions for systems biology research.
Reconstructing large-scale gene regulatory networks across multiple experimental conditions.

Acerca de

Características Principales

Distributed computing support via Dask for processing massive transcriptomic datasets.
81 GitHub stars
Scalable GRN inference using high-performance GRNBoost2 and GENIE3 algorithms.
Automated resource management for local multi-core or remote cluster environments.
Targeted regulatory mapping with transcription factor filtering capabilities.
Support for both bulk and single-cell RNA-seq expression matrices.

Casos de Uso

Mapping cell-type-specific transcription factor targets in single-cell RNA-seq studies.
Identifying high-confidence regulatory interactions for systems biology research.
Reconstructing large-scale gene regulatory networks across multiple experimental conditions.