arboreto

To infer gene regulatory networks from single-cell RNA-seq data, you can apply the GRNBoost2 or GENIE3 algorithms to your expression matrix. This process outputs a three-column table mapping transcription factors to targets with importance scores.

Yes, you can scale GRN inference for large-scale expression datasets using distributed computing environments. The implementation supports Dask for local clusters or remote schedulers to handle large single-cell and bulk RNA-seq workflows efficiently.

Both GRNBoost2 and GENIE3 infer gene regulatory networks by calculating feature importance from expression data. GRNBoost2 is optimized for scalability and distributed environments, whereas GENIE3 uses tree-based methods to derive regulatory relationships.

You can filter transcription factors before running GRN inference by providing a predefined TF list. This optional TF filtering step restricts the algorithm to evaluate only specific transcription factors as potential regulators, reducing computation time.

Yes, gene regulatory network inference supports reproducible results through seed-based reproducibility. By setting a specific seed value, you ensure the stochastic elements of the GRNBoost2 or GENIE3 algorithms generate identical network outputs across multiple runs.

Gene regulatory network inference outputs a three-column network table containing the transcription factor, target gene, and importance score. This format enables direct integration with downstream analyses like pySCENIC for further biological interpretation.