prepare_settings_leave_one_out_characterization: Prepare settings for leave-one-out characterization

In saeyslab/nichenetr: NicheNet: Modeling Intercellular Communication by Linking Ligands to Target Genes

Prepare settings for leave-one-out characterization

Description

prepare_settings_leave_one_out_characterization will generate a list of lists containing the data source weights that need to be used for model construction. Every sub-list will contain the data source weights needed to make so called leave-one-out models in one ligand-signaling data source is or gene regulatory data source is left out.

Usage

prepare_settings_leave_one_out_characterization(lr_network, sig_network, gr_network, source_weights_df)

Arguments

lr_network	A data frame / tibble containing ligand-receptor interactions (required columns: from, to, source)
sig_network	A data frame / tibble containing signaling interactions (required columns: from, to, source)
gr_network	A data frame / tibble containing gene regulatory interactions (required columns: from, to, source)
source_weights_df	A data frame / tibble containing the weights associated to each individual data source. Sources with higher weights will contribute more to the final model performance (required columns: source, weight). Note that only interactions described by sources included here, will be retained during model construction.

Value

A list of lists. Every sub-list contains 2 elements: $model_name: the name of the left-out data source; $source_weights: named numeric vector containing the data source weights that will be used for the construction of leave-one-out models.

saeyslab/nichenetr documentation built on March 26, 2024, 9:22 a.m.