alterlab-arboreto

# Arboreto ## Overview Arboreto is a computational library for inferring gene regulatory networks (GRNs) from gene expression data using parallelized algorithms that scale from single machines to multi-node clusters. **Core capability**: Identify which transcription factors (TFs) regulate which target genes based on expression patterns across observations (cells, samples, conditions). ## When to Use This Skill Use this skill when the user wants to: - Infer a TF → target-gene regulatory network from a bulk or single-cell expression matrix. - Run the GRN-inference step (step 1) of a SCENIC / pySCENIC pipeline. - Compare GRNBoost2 against GENIE3, or build a consensus network across random seeds. - Scale GRN inference across cores or a Dask cluster. ### Does NOT Trigger | Scenario | Use Instead | |----------|-------------| | Differential expression between conditions (counts → padj) | `alterlab-pydeseq2` | | Clustering, UMAP, or QC of a single-cell dataset | `alterlab-scanpy` | | Deep-learning latent space / batch integration of scRNA-seq | `alterlab-scvi-tools` | | Generic graph analysis or centrality on an existing network | `alterlab-networkx` | | Tuning the Dask cluster itself rather than running GRN inference | `alterlab-dask` | ## Quick Start Install arboreto: ```bash uv pip install arboreto ``` Arboreto 0.1.6 is from 2021 and its internals use `dask.delayed` plus `dask.dataframe.from_delayed`. Those APIs still exist in current dask, but if a run fails inside dask...