nichenetr (version 0.1.0)

get_ligand_slope_ligand_prediction_popularity: Regression analysis between popularity of left-out ligands for ligand activity prediction performance

Description

get_ligand_slope_ligand_prediction_popularity: Performs regression analysis to investigate the trend between a particular classficiation evaluation metric and the popularity of left-out ligands for ligand activity prediction performance.

Usage

get_ligand_slope_ligand_prediction_popularity(metric,performances)

Arguments

metric

The name of the performance metric of which the trend with the popularity of the target genes should be calculated.

performances

A data.frame in which the performance measures for target gene predictions of ligands are denoted together with the "popularity index" indicating which percentage of most popular ligands were left out.)

Value

A data.frame in which the regression coefficient estimate, p-value and corresponding R-squared value are shown for the regression analysis to investigate the trend between a particular classficiation evaluation metric and the popularity of the left out ligands.

Examples

# NOT RUN {
library(dplyr)
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))

ligand_activity_popularity_bias = lapply(0:3,ligand_activity_performance_top_i_removed, ligand_importances, ncitations) %>% bind_rows()
slopes_auroc = get_ligand_slope_ligand_prediction_popularity("auroc",ligand_activity_popularity_bias)
slopes_df = ligand_activity_popularity_bias %>% select(-importance_measure,-popularity_index) %>% colnames() %>% lapply(.,get_ligand_slope_ligand_prediction_popularity,ligand_activity_popularity_bias) %>% bind_rows()
# }
# NOT RUN {
# }