add_mirrors             Add custom download mirrors
annotate_clones         Annotate cells with clone IDs via Seurat
                        clustering
build_clone_counts      Build clone abundance table from cell-clone
                        mapping
build_clone_key         Build a clone key from patient and clone id
build_on_BULK_v2        Build PERCEPTIONx model on bulk expression data
clone_mean_expression   Compute clone-level mean expression from
                        single-cell data
compare_performance     Compare performance of multiple trained models
cor.test_trimmed_v0     Fast correlation test (generic)
each_patient_pseudo_bulk
                        Compute pseudo-bulk expression for a patient
export_plot_cairo       Export plot to file via Cairo device
fdrcorr                 FDR correction for multiple testing
feature_ranking_bulk    Feature ranking for a single drug using bulk
                        expression
get_cellLine_list       Determine training and test cell-lines for a
                        given drug
get_depmap              Get the DepMap dataset
get_mirrors             Get current download mirrors
get_performance         Load performance metrics from a saved model
                        file
get_response_matrix     Get specific drug response data for cell-lines
get_significant_models
                        Get best performing models
hypergeometric_test_for_twolists
                        Hypergeometric test for gene list overlap
list_mirrors            List current download mirrors
load_depmap             Download filtered DepMap data
load_model              Load pre-built model of provided drugs
parse_clone_keys        Parse clone keys in "Patient@Clone" format
plot_clone_distribution
                        Plot clone distribution as stacked bar
plot_clone_umap         Plot UMAP colored by clone identity
plot_clone_viability    Plot clone-level viability (lollipop plot)
plot_model_performance
                        Plot model performance across datasets
plot_model_roc          Plot validation ROC curves for trained models
plot_patient_response_panel
                        Complete patient response visualization
                        pipeline
plot_response_boxplot   Plot predicted vs observed response boxplot
plot_roc_curve          Plot ROC curve with AUC annotation
plot_seurat_clustering
                        Run Seurat clustering and plot 2D embedding
plot_tsne_biomarker_viability
                        Plot UMAP side-by-side for biomarker and
                        viability
plot_tsne_response      Plot UMAP with drug response overlay
predict_drugs           Predict drug response for cells or clones
predict_patients        Predict drug response at patient level
prepare_data            Prepare patient data for PERCEPTIONx prediction
range01                 Change range to 0-1
rank_normalization_mat
                        Rank-normalize each column of a matrix
reset_mirrors           Reset mirrors to default
run_parallel_feature_ranking_bulk
                        Parallel feature ranking for multiple drugs
run_perception_app      Launch PERCEPTIONx Shiny Dashboard
train_models            Train PERCEPTIONx models for multiple drugs
zscore_viability        Z-score scale viability values across patients
