add_hyperparameters_parameter_settings: Add hyperparameters to existing parameter settings

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

Add hyperparameters to existing parameter settings

Description

add_hyperparameters_parameter_settings will generate a list of lists containing the parameter values that need to be used for model construction.

Usage

add_hyperparameters_parameter_settings(parameter_setting, lr_sig_hub, gr_hub, ltf_cutoff, algorithm, damping_factor, correct_topology)

Arguments

parameter_setting	A list of lists. Sublists contains parameters (like data source weights) and novel sublists will be created by this function by adding additional parameters.
lr_sig_hub	a number between 0 and 1. 0: no correction for hubiness; 1: maximal correction for hubiness.
gr_hub	a number between 0 and 1. 0: no correction for hubiness; 1: maximal correction for hubiness.
ltf_cutoff	Ligand-tf scores beneath the "ltf_cutoff" quantile will be set to 0. Default: 0.99 such that only the 1 percent closest tfs will be considered as possible tfs downstream of the ligand of choice.
algorithm	Selection of the algorithm to calculate ligand-tf signaling probability scores. Different options: "PPR" (personalized pagerank), "SPL" (shortest path length) and "direct"(just take weights of ligand-signaling network as ligand-tf weights). Default and recommended: PPR.
damping_factor	Only relevant when algorithm is PPR. In the PPR algorithm, the damping factor is the probability that the random walker will continue its walk on the graph; 1-damping factor is the probability that the walker will return to the seed node. Default: 0.5.
correct_topology	This parameter indicates whether the PPR-constructed ligand-target matrix will be subtracted by a PR-constructed target matrix. TRUE or FALSE.

Value

A list of lists. Every sub-list contains parameter values for a different parameter.

Examples

## Not run: 
weights_settings_loi = prepare_settings_leave_one_in_characterization(lr_network,sig_network, gr_network, source_weights_df)
weights_settings_loi = lapply(weights_settings_loi,add_hyperparameters_parameter_settings, lr_sig_hub = 0.25,gr_hub = 0.5,ltf_cutoff = 0,algorithm = "PPR",damping_factor = 0.8,correct_topology = TRUE)

## End(Not run)

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