process_characterization_popularity_slopes_ligand_prediction: Process the output of model evaluation for data source...

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

Process the output of model evaluation for data source characterization purposes on the popularity bias assessment of ligand activity performance

Description

process_characterization_popularity_slopes_ligand_prediction will process output formed by model evaluation to get a data frame containing popularity bias measures in performance of ligand activity prediction.

Usage

process_characterization_popularity_slopes_ligand_prediction(output_characterization)

Arguments

output_characterization

a list of lists containing the results of evaluation of different models (e.g. after execution of evaluate_model. Every sublist should contain at least the following elements: $model_name and $performances_target_prediction.

Value

A data frame containing the popularity bias slopes in ligand activity prediction performances.

Examples

## Not run: 
library(dplyr)
settings = lapply(expression_settings_validation, convert_expression_settings_evaluation)
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)
doMC::registerDoMC(cores = 8)
output_characterization = parallel::mclapply(weights_settings_loi[1:3],evaluate_model,lr_network,sig_network, gr_network,settings,calculate_popularity_bias_target_prediction = TRUE, calculate_popularity_bias_ligand_prediction = TRUE, ncitations, mc.cores = 3)
popularity_slopes_ligand_prediction_performances = process_characterization_popularity_slopes_ligand_prediction(output_characterization)

## End(Not run)

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