get_single_ligand_importances: Get ligand importances based on target gene prediction...

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

Get ligand importances based on target gene prediction performance of single ligands.

Description

get_single_ligand_importances Get ligand importance measures for ligands based on how well a single, individual, ligand can predict an observed response. Assess how well every ligand of interest is able to predict the observed transcriptional response in a particular dataset, according to the ligand-target model. It can be assumed that the ligand that best predicts the observed response, is more likely to be the true ligand.

Usage

get_single_ligand_importances(setting,ligand_target_matrix, ligands_position = "cols", known = TRUE)

Arguments

setting	A list containing the following elements: .$name: name of the setting; .$from: name(s) of the ligand(s) of which the predictve performance need to be assessed; .$response: the observed target response: indicate for a gene whether it was a target or not in the setting of interest. $ligand: NULL or the name of the ligand(s) that are known to be active in the setting of interest.
ligand_target_matrix	A matrix of ligand-target probabilty scores (or discrete target assignments).
ligands_position	Indicate whether the ligands in the ligand-target matrix are in the rows ("rows") or columns ("cols"). Default: "cols"
known	Indicate whether the true active ligand for a particular dataset is known or not. Default: TRUE. The true ligand will be extracted from the $ligand slot of the setting.

Value

A data.frame with for each ligand - data set combination, classification evaluation metrics indicating how well the query ligand predicts the response in the particular dataset. Evaluation metrics are the same as in evaluate_target_prediction. In addition to the metrics, the name of the particular setting ($setting), the name of the query ligand($test_ligand), the name of the true active ligand (if known: $ligand).

Examples

## Not run: 
settings = lapply(expression_settings_validation[1:5],convert_expression_settings_evaluation)
settings_ligand_pred = convert_settings_ligand_prediction(settings, all_ligands = unlist(extract_ligands_from_settings(settings,combination = FALSE)), validation = TRUE, single = TRUE)

weighted_networks = construct_weighted_networks(lr_network, sig_network, gr_network, source_weights_df)
ligands = extract_ligands_from_settings(settings_ligand_pred,combination = FALSE)
ligand_target_matrix = construct_ligand_target_matrix(weighted_networks, ligands)
ligand_importances = dplyr::bind_rows(lapply(settings_ligand_pred,get_single_ligand_importances,ligand_target_matrix))
print(head(ligand_importances))

## End(Not run)

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