by_isolation_forest     Isolation Forest outlier detection
check_input_data_format
                        Validate required columns of a cohort and
                        (optionally) a ranking
cohort_a_ranking        Protein-importance ranking for plasma cohort
                        "A"
filter_by_occurrence    Keep proteins present in at least a given
                        fraction of samples
log_transform           Log2-transform the intensity column in place
                        (long format)
normalize_medianintensity
                        Per-sample median normalisation (log-space
                        subtraction)
optimize_parameters     Grid-search the cutoff that optimises a chosen
                        performance metric
perform_distance_evaluation_on_ranked_proteins
                        Threshold-based pairwise distance evaluation
plate_correct_residuals_by_protein
                        Regress intensity on plate and replace it with
                        OLS residuals
print.spqrp_train       Print a one-line summary of an spqrp_train
                        object
remove_outlier_samples
                        Remove samples flagged as outliers by Isolation
                        Forest
retrieve_ranking        Convert classifier output to a Protein /
                        Importance ranking
run_clustering          End-to-end clustering pipeline
spqrp_example_data      Load a bundled example data file as a tibble
spqrp_example_path      Filesystem path to a bundled example CSV
train_pairwise_balanced_rand_forest
                        Pairwise balanced random-forest classifier
train_with_normalise    End-to-end ranking pipeline: filter, normalise,
                        optionally plate-correct, train RF
