arboreto

Infer gene regulatory networks from expression data using GRNBoost2 and GENIE3.

22|4|Updated May 25, 2026

Search Tags:#single-cell #arboreto #network-inference #distributed-computing #gene-expression #transcription-factor #grn

Ready to run

npx skills add https://github.com/crazymsn/academic-skills --skill arboreto-crazymsn

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: arboreto
Source: https://github.com/crazymsn/academic-skills/tree/main/academic-skills/arboreto
Command: npx skills add https://github.com/crazymsn/academic-skills --skill arboreto-crazymsn

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, arboreto, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Infer gene regulatory networks (GRNs) from gene expression data to reveal transcription factor target gene relationships across samples, conditions, and cell types.

Core Features & Use Cases

Scalable GRN inference using GRNBoost2 and GENIE3 on large datasets
Support for distributed computing with Dask and multi-core setups
Output is a TF-target-importance table ready for downstream analyses (e.g., pySCENIC integration)

Quick Start

Provide an expression matrix to GRNBoost2 to generate the regulatory network.

Frequently Asked Questions about arboreto

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I infer gene regulatory networks from single-cell RNA-seq data?▼

Gene regulatory network inference from single-cell RNA-seq uses algorithms like GRNBoost2 or GENIE3 on an expression matrix. It outputs a TF-target-importance table revealing transcription factor relationships across cell types and conditions.

What is the best way to scale GRN inference for large gene expression datasets?▼

Scaling GRN inference for large gene expression datasets is handled through optional distributed computing with Dask and multi-core setups. This allows GRNBoost2 and GENIE3 to process bulk and single-cell data efficiently across clusters.

Does arboreto work with Dask for distributed computing?▼

Yes, arboreto works with Dask for distributed computing. It supports optional distributed computing with Dask and multi-core setups to scale GRNBoost2 and GENIE3 network inference across large bulk and single-cell RNA-seq datasets.

How do I use GRNBoost2 to identify transcription factor target relationships?▼

You identify transcription factor target relationships with GRNBoost2 by providing a gene expression matrix. The algorithm computes regulatory importance scores and outputs a three-column TF-target-importance table for downstream analysis.

Can I integrate the inferred TF-target-importance network with pySCENIC?▼

Yes, the inferred TF-target-importance network integrates with pySCENIC. The three-column output table is explicitly formatted for downstream pySCENIC analyses to validate and refine transcription factor target relationships.

What is the difference between GRNBoost2 and GENIE3 for transcription factor analysis?▼

Both GRNBoost2 and GENIE3 infer transcription factor target relationships from gene expression data. The Skill implements both algorithms to generate a three-column TF-target-importance network, allowing methodological comparison for downstream analysis.