Package index • nichenetr

All Functions

add_hyperparameters_parameter_settings(): Add hyperparameters to existing parameter settings

add_ligand_popularity_measures_to_perfs(): Merge target gene prediction performances with popularity measures of ligands

add_new_datasource(): Add a new data source to the model

alias_to_symbol_seurat(): Convert aliases to official gene symbols in a Seurat Object

annotation_data_sources: Annotation table of all data sources used in the NicheNet model

apply_hub_corrections(): Apply hub corrections to the weighted integrated ligand-signaling and gene regulatory network

assess_influence_source(): Assess the influence of an individual data source on ligand-target probability scores

assess_rf_class_probabilities(): Assess probability that a target gene belongs to the geneset based on a multi-ligand random forest model

assign_ligands_to_celltype(): Assign ligands to cell types

bootstrap_ligand_activity_analysis(): Run ligand activity analysis with bootstrap

calculate_de(): Calculate differential expression of one cell type versus all other cell types

calculate_fraction_top_predicted(): Determine the fraction of genes belonging to the geneset or background and to the top-predicted genes.

calculate_fraction_top_predicted_fisher(): Perform a Fisher's exact test to determine whether genes belonging to the gene set of interest are more likely to be part of the top-predicted targets.

calculate_niche_de(): Calculate differential expression of cell types in one niche versus all other niches of interest.

calculate_niche_de_targets(): Calculate differential expression of receiver cell type in one niche versus all other niches of interest: focus on finding DE genes

calculate_p_value_bootstrap(): Calculate ligand p-values from the bootstrapped ligand activity analysis

calculate_spatial_DE(): Calculate differential expression between spatially different subpopulations of the same cell type

classification_evaluation_continuous_pred_wrapper(): Assess how well classification predictions accord to the expected response

clear_database_cache(): Clear Database Cache

combine_sender_receiver_de(): Combine the differential expression information of ligands in the sender celltypes with the differential expression information of their cognate receptors in the receiver cell types

construct_ligand_target_matrix(): Construct a ligand-target probability matrix for ligands of interest.

construct_ligand_tf_matrix(): Construct a ligand-tf signaling probability matrix for ligands of interest.

construct_model(): Construct a ligand-target model given input parameters.

construct_random_model(): Construct a randomised ligand-target model given input parameters.

construct_tf_target_matrix(): Construct a tf-target matrix.

construct_weighted_networks(): Construct weighted layer-specific networks

convert_alias_to_symbols(): Convert aliases to official gene symbols

convert_cluster_to_settings(): Convert cluster assignment to settings format suitable for target gene prediction.

convert_expression_settings_evaluation(): Convert expression settings to correct settings format for evaluation of target gene prediction.

convert_expression_settings_evaluation_regression(): Convert expression settings to correct settings format for evaluation of target gene log fold change prediction (regression).

convert_gene_list_settings_evaluation(): Convert gene list to correct settings format for evaluation of target gene prediction.

convert_human_to_mouse_symbols(): Convert human gene symbols to their mouse one-to-one orthologs.

convert_mouse_to_human_symbols(): Convert mouse gene symbols to their human one-to-one orthologs.

convert_settings_ligand_prediction(): Convert settings to correct settings format for ligand prediction.

convert_settings_tf_prediction(): Convert settings to correct settings format for TF prediction.

convert_settings_topn_ligand_prediction(): Converts expression settings to format in which the total number of potential ligands is reduced up to n top-predicted active ligands.

convert_single_cell_expression_to_settings(): Prepare single-cell expression data to perform ligand activity analysis

correct_topology_ppr(): Adapt a ligand-target probability matrix construced via PPR by correcting for network topolgoy.

diagrammer_format_signaling_graph(): Prepare extracted ligand-target signaling network for visualization with DiagrammeR.

estimate_source_weights_characterization(): Estimate data source weights of data sources of interest based on leave-one-in and leave-one-out characterization performances.

evaluate_importances_ligand_prediction(): Evaluation of ligand activity prediction based on ligand importance scores.

evaluate_ligand_prediction_per_bin(): Evaluate ligand activity predictions for different bins/groups of targets genes

evaluate_model(): Construct and evaluate a ligand-target model given input parameters.

evaluate_model_application(): Construct and evaluate a ligand-target model given input parameters (for application purposes).

evaluate_model_application_multi_ligand(): Construct and evaluate a ligand-target model given input parameters (for application purposes + multi-ligand predictive model).

evaluate_model_cv(): Construct and evaluate a ligand-target model given input parameters with the purpose of evaluating cross-validation models.

evaluate_multi_ligand_target_prediction(): Evaluation of target gene prediction for multiple ligands.

evaluate_multi_ligand_target_prediction_regression(): Evaluation of target gene value prediction for multiple ligands (regression).

evaluate_random_model(): Construct and evaluate a randomised ligand-target model given input parameters.

evaluate_single_importances_ligand_prediction(): Evaluation of ligand activity prediction performance of single ligand importance scores: aggregate all datasets.

evaluate_target_prediction(): Evaluation of target gene prediction.

evaluate_target_prediction_interprete(): Evaluation of target gene prediction.

evaluate_target_prediction_per_bin(): Evaluate target gene predictions for different bins/groups of targets genes

evaluate_target_prediction_regression(): Evaluation of target gene value prediction (regression).

expression_settings_validation: Expression datasets for validation

extract_ligands_from_settings(): Extract ligands of interest from settings

extract_top_fraction_ligands(): Get the predicted top n percentage ligands of a target of interest

extract_top_fraction_targets(): Get the predicted top n percentage target genes of a ligand of interest

extract_top_n_ligands(): Get the predicted top n ligands of a target gene of interest

extract_top_n_targets(): Get the predicted top n target genes of a ligand of interest

geneinfo_2022: Gene annotation information: version 2 - january 2022

geneinfo_alias_human: Gene annotation information: version 2 - january 2022 - suited for alias conversion

geneinfo_alias_mouse: Gene annotation information: version 2 - january 2022 - suited for alias conversion

geneinfo_human: Gene annotation information

generate_info_tables(): Generate tables used for generate_prioritization_tables

generate_prioritization_tables(): Perform a prioritization of cell-cell interactions (similar to MultiNicheNet).

get_active_ligand_receptor_network(): Get active ligand-receptor network for cellular interaction between a sender and receiver cell.

get_active_ligand_target_df(): Get active ligand-target network in data frame format.

get_active_ligand_target_matrix(): Get active ligand-target matrix.

get_active_regulatory_network(): Get active gene regulatory network in a receiver cell.

get_active_signaling_network(): Get active signaling network in a receiver cell.

get_database_cache_stats(): Get Cache Statistics

get_expressed_genes(): Determine expressed genes of a cell type from an input object

get_exprs_avg(): Calculate average of gene expression per cell type.

get_lfc_celltype(): Get log fold change values of genes in cell type of interest

get_ligand_activities_targets(): Calculate the ligand activities and infer ligand-target links based on a list of niche-specific genes per receiver cell type

get_ligand_signaling_path(): Get ligand-target signaling paths between ligand(s) and target gene(s) of interest

get_ligand_signaling_path_with_receptor(): Get ligand-target signaling paths between ligand(s), receptors, and target gene(s) of interest

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

get_ligand_target_links_oi(): Get ligand-target links of interest

get_multi_ligand_importances(): Get ligand importances from a multi-ligand classfication model.

get_multi_ligand_importances_regression(): Get ligand importances from a multi-ligand regression model.

get_multi_ligand_rf_importances(): Get ligand importances from a multi-ligand trained random forest model.

get_multi_ligand_rf_importances_regression(): Get ligand importances from a multi-ligand trained random forest regression model.

get_ncitations_genes(): Get the number of times of gene is mentioned in the pubmed literature

get_non_spatial_de(): Makes a table similar to the output of `calculate_spatial_DE` and `process_spatial_de`, but now in case you don't have spatial information for the sender and/or receiver celltype. This is needed for comparability reasons.

get_optimized_parameters_nsga2(): Get optimized parameters from the output of run_nsga2R_cluster.

get_prioritization_tables(): Use the information from the niche- and spatial differential expression analysis of ligand-senders and receptor-receivers pairs, in addition to the ligand activity prediction and ligand-target inferernce, in order to make a final ligand-receptor and ligand-target prioritization table.

get_single_ligand_importances(): Get ligand importances based on target gene prediction performance of single ligands.

get_single_ligand_importances_regression(): Get ligand importances based on target gene value prediction performance of single ligands (regression).

get_slope_ligand_popularity(): Regression analysis between ligand popularity and target gene predictive performance

get_slope_target_gene_popularity(): Regression analysis between target gene popularity and target gene predictive performance

get_slope_target_gene_popularity_ligand_prediction(): Regression analysis between target gene popularity and ligand activity predictive performance

get_target_genes_ligand_oi(): Get a set of predicted target genes of a ligand of interest

get_top_predicted_genes(): Find which genes were among the top-predicted targets genes in a specific cross-validation round and see whether these genes belong to the gene set of interest as well.

get_weighted_ligand_receptor_links(): Get the weighted ligand-receptor links between a possible ligand and its receptors

get_weighted_ligand_target_links(): Infer weighted active ligand-target links between a possible ligand and target genes of interest

hyperparameter_list: Optimized hyperparameter values

infer_supporting_datasources(): Get the data sources that support the specific interactions in the extracted ligand-target signaling subnetwork

ligand_activity_performance_top_i_removed(): Calculate ligand activity performance without considering evaluation datasets belonging to the top i most frequently cited ligands

make_circos_lr(): make_circos_lr

make_circos_plot(): Draw a circos plot

make_discrete_ligand_target_matrix(): Convert probabilistic ligand-target matrix to a discrete one.

make_heatmap_bidir_lt_ggplot(): Make a ggplot heatmap object from an input ligand-target matrix.

make_heatmap_ggplot(): Make a ggplot heatmap object from an input matrix (2-color).

make_ligand_activity_target_exprs_plot(): make_ligand_activity_target_exprs_plot

make_ligand_receptor_lfc_plot(): make_ligand_receptor_lfc_plot

make_ligand_receptor_lfc_spatial_plot(): make_ligand_receptor_lfc_spatial_plot

make_line_plot(): Make a line plot

make_mushroom_plot(): Make a "mushroom plot" of ligand-receptor interactions

make_threecolor_heatmap_ggplot(): Make a ggplot heatmap object from an input matrix (3-color).

mlrmbo_optimization(): Optimization of objective functions via model-based optimization (mlrMBO).

model_based_ligand_activity_prediction(): Prediction of ligand activity prediction by a model trained on ligand importance scores.

model_evaluation_hyperparameter_optimization_mlrmbo(): Construct and evaluate a ligand-target model given input parameters with the purpose of hyperparameter optimization using mlrMBO.

model_evaluation_optimization_application(): Construct and evaluate a ligand-target model given input parameters with the purpose of parameter optimization for multi-ligand application.

model_evaluation_optimization_mlrmbo(): Construct and evaluate a ligand-target model given input parameters with the purpose of parameter optimization with mlrMBO.

model_evaluation_optimization_nsga2(): Construct and evaluate a ligand-target model with the purpose of parameter optimization with NSGA-II.

mutate_cond(): Change values in a tibble if some condition is fulfilled.

ncitations: Number of citations for genes

nichenet_seuratobj_aggregate(): Perform NicheNet analysis on Seurat object: explain DE between conditions

nichenet_seuratobj_aggregate_cluster_de(): Perform NicheNet analysis on Seurat object: explain DE between two cell clusters from separate conditions

nichenet_seuratobj_cluster_de(): Perform NicheNet analysis on Seurat object: explain DE between two cell clusters

normalize_single_cell_ligand_activities(): Normalize single-cell ligand activities

optimized_source_weights_df: Optimized data source weights

predict_ligand_activities(): Predict activities of ligands in regulating expression of a gene set of interest

predict_single_cell_ligand_activities(): Single-cell ligand activity prediction

prepare_circos_visualization(): Prepare circos visualization

prepare_ligand_receptor_visualization(): Prepare ligand-receptor visualization

prepare_ligand_target_visualization(): Prepare heatmap visualization of the ligand-target links starting from a ligand-target tibble.

prepare_settings_leave_one_in_characterization(): Prepare settings for leave-one-in characterization

prepare_settings_leave_one_out_characterization(): Prepare settings for leave-one-out characterization

prepare_settings_one_vs_one_characterization(): Prepare settings for one-vs-one characterization

process_characterization_ligand_prediction(): Process the output of model evaluation for data source characterization purposes on the ligand prediction performance

process_characterization_ligand_prediction_single_measures(): Process the output of model evaluation for data source characterization purposes on the ligand prediction performance (for every importance score individually)

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

process_characterization_popularity_slopes_target_prediction(): Process the output of model evaluation for data source characterization purposes on the popularity bias assessment of target prediction performance

process_characterization_target_prediction(): Process the output of model evaluation for data source characterization purposes on the target prediction performance

process_characterization_target_prediction_average(): Process the output of model evaluation for data source characterization purposes on the target prediction performance (average)

process_mlrmbo_nichenet_optimization(): Process the output of mlrmbo multi-objective optimization to extract optimal parameter values.

process_niche_de(): Process the DE output of `calculate_niche_de`

process_receiver_target_de(): Processing differential expression output of the receiver cell types

process_spatial_de(): Process the spatialDE output

process_table_to_ic(): Process DE or expression information into intercellular communication focused information.

randomize_complete_network_source_specific(): Randomize an integrated network by shuffling its source networks

randomize_datasource_network(): Randomize a network of a particular data source.

randomize_network(): Randomize a network

run_nsga2R_cluster(): Run NSGA-II for parameter optimization.

scale_quantile(): Cut off outer quantiles and rescale to a [0, 1] range

scale_quantile_adapted(): Normalize values in a vector by quantile scaling and add a pseudovalue of 0.001

scaling_modified_zscore(): Normalize values in a vector by the modified z-score method.

scaling_zscore(): Normalize values in a vector by the z-score method

single_ligand_activity_score_classification(): Assess how well cells' ligand activities predict a binary property of interest of cells.

single_ligand_activity_score_regression(): Perform a correlation and regression analysis between cells' ligand activities and property scores of interest

source_weights_df: Data source weights

visualize_parameter_values(): Visualize parameter values from the output of run_nsga2R_cluster.

visualize_parameter_values_across_folds(): Visualize parameter values from the output of run_nsga2R_cluster across cross-validation folds.

wrapper_average_performances(): Calculate average performance of datasets of a specific ligand.

wrapper_evaluate_single_importances_ligand_prediction(): Evaluation of ligand activity prediction performance of single ligand importance scores: each dataset individually.