arboreto

To infer gene regulatory networks from single-cell RNA-seq data, you can use this Skill to predict transcription factor to target gene relationships from your gene expression matrices, generating networks with importance scores via GRNBoost2 or GENIE3.

Yes, you can restrict candidate regulators during GRN inference by providing a specific transcription factor list, which focuses the computation on relevant TF-target relationships and improves the biological accuracy of your inferred network.

Dask supports scalable gene regulatory network inference by enabling distributed execution, allowing you to run GRNBoost2 or GENIE3 locally with multi-core processing or connect to a remote Dask scheduler for large RNA-seq datasets.

GRNBoost2 and GENIE3 are both algorithms used to predict TF-target relationships and produce importance scores from gene expression data, but you can choose either method within this workflow depending on your specific inference requirements.

To ensure reproducible results when inferring gene regulatory networks, you can set a fixed random seed within the GRNBoost2 or GENIE3 execution parameters, guaranteeing identical TF-target-importance outputs across multiple runs.

Yes, you can compare gene regulatory networks across multiple experimental conditions using this Skill, which supports multi-condition comparisons alongside single-condition analysis and TF-restricted inference for bulk and single-cell RNA-seq workflows.