Package 'NADIA'

Description

Applies BERT batch effect correction to a normalized assay in a SummarizedExperiment. BERT uses hierarchical tree decomposition to handle missing values, making it suitable for pre-imputation batch correction on protein-level proteomics data.

Usage

batch_correct_proteomics(
  se,
  assay_name,
  batch_column = "Batch",
  corrected_assay_name = "BERT",
  algorithm = "ComBat",
  ComBat_mode = 1,
  covariates = NULL,
  qualitycontrol = FALSE,
  verbose = TRUE
)

Arguments

Value

SummarizedExperiment with the new corrected assay added. If BERT returns fewer features than the input, the SE is subsetted to match and a warning is issued.

Examples

data(nadia_dia)

# nadia_dia has no batch information, so the example builds a plausible one:
# two digestion batches crossed with the three conditions.
cov <- data.frame(Column = nadia_dia$metadata$Coding,
                  Batch = rep(c("b1", "b2"),
                              length.out = nrow(nadia_dia$metadata)),
                  stringsAsFactors = FALSE)
res <- process_proteomics(nadia_dia, covariate_df = cov, verbose = FALSE)

# BERT removes the batch effect and adds a "BERT" assay, leaving the
# original one untouched
se <- batch_correct_proteomics(res$se_proc, assay_name = "Impseqrob_min",
                               batch_column = "Batch", verbose = FALSE)
SummarizedExperiment::assayNames(se)

# On a real experiment you would normally pass the biological variable of
# interest in `covariates`, so that ComBat preserves it instead of removing
# it along with the batch effect. `covariates = "Condition"` works on this
# example: the assay is already imputed, so each batch-by-condition cell has
# its two values. Before imputation, with only two samples per cell, BERT
# needs two non-missing values per cell and any protein with a gap there
# stops being adjustable.

Description

Horizontal bar chart of AUC per comparison, colored by value, with a reference line at 0.5.

Usage

benchmark_auc_bars_gg(
  metrics_table,
  title = "AUC by Comparison",
  bar_width = 0.7
)

Arguments

Value

ggplot2 object

Examples

data(nadia_dia)
de <- process_proteomics(nadia_dia, verbose = FALSE)$DEPs_results
sp <- utils::read.delim(system.file("extdata", "nadia_dia_spikein.tsv.gz",
                                    package = "NADIA"))
de$Species <- sp$PG.OrganismId[match(de$Protein.IDs, sp$PG.ProteinGroups)]
ev <- data.frame(Comparison = rep(c("B-A", "D-A"), each = 2),
                 Species = c("ECOLI", "YEAST"),
                 expected_logFC = c(1, -0.58, 2, -3.3))
if (requireNamespace("pROC", quietly = TRUE)) {
  metrics <- compute_benchmark_metrics(de, ev)
  benchmark_auc_bars_gg(metrics)
}

Description

Heatmap of Comparisons x (TP%, FP%, FN%, TN%) with white-to-blue gradient.

Usage

benchmark_confusion_gg(
  confusion_df,
  title = "Confusion Matrix by Comparison x Species",
  text_size = 3.5,
  axis_text_size = 10
)

Arguments

Value

ggplot2 object

Examples

data(nadia_dia)
de <- process_proteomics(nadia_dia, verbose = FALSE)$DEPs_results
sp <- utils::read.delim(system.file("extdata", "nadia_dia_spikein.tsv.gz",
                                    package = "NADIA"))
de$Species <- sp$PG.OrganismId[match(de$Protein.IDs, sp$PG.ProteinGroups)]
ev <- data.frame(Comparison = rep(c("B-A", "D-A"), each = 2),
                 Species = c("ECOLI", "YEAST"),
                 expected_logFC = c(1, -0.58, 2, -3.3))
bench <- benchmarking_proteomics(de, ev, verbose = FALSE)
benchmark_confusion_gg(bench$confusion_by_species)

Description

Heatmap of Comparisons x (TP%, FP%, FN%, TN%) aggregated across all species, with white-to-blue gradient fill by percentage.

Usage

benchmark_confusion_overall_gg(
  confusion_overall_df,
  title = "Confusion Matrix by Comparison (Overall)",
  text_size = 4,
  axis_text_size = 11
)

Arguments

Value

ggplot2 object

Examples

data(nadia_dia)
de <- process_proteomics(nadia_dia, verbose = FALSE)$DEPs_results
sp <- utils::read.delim(system.file("extdata", "nadia_dia_spikein.tsv.gz",
                                    package = "NADIA"))
de$Species <- sp$PG.OrganismId[match(de$Protein.IDs, sp$PG.ProteinGroups)]
ev <- data.frame(Comparison = rep(c("B-A", "D-A"), each = 2),
                 Species = c("ECOLI", "YEAST"),
                 expected_logFC = c(1, -0.58, 2, -3.3))
bench <- benchmarking_proteomics(de, ev, verbose = FALSE)
benchmark_confusion_overall_gg(bench$confusion_overall)

Description

Heatmap of Comparisons x Metrics (AUC, Sensitivity, Specificity, Precision, F1, Accuracy). Gradient red -> yellow -> green.

Usage

benchmark_heatmap_gg(
  metrics_table,
  metrics_to_show = c("AUC", "Sensitivity", "Specificity", "Precision", "F1", "Accuracy"),
  title = "Benchmark Performance Heatmap",
  text_size = 4,
  axis_text_size = 11
)

Arguments

Value

ggplot2 object

Examples

data(nadia_dia)
de <- process_proteomics(nadia_dia, verbose = FALSE)$DEPs_results
sp <- utils::read.delim(system.file("extdata", "nadia_dia_spikein.tsv.gz",
                                    package = "NADIA"))
de$Species <- sp$PG.OrganismId[match(de$Protein.IDs, sp$PG.ProteinGroups)]
ev <- data.frame(Comparison = rep(c("B-A", "D-A"), each = 2),
                 Species = c("ECOLI", "YEAST"),
                 expected_logFC = c(1, -0.58, 2, -3.3))
metrics <- compute_benchmark_metrics(de, ev)
benchmark_heatmap_gg(metrics, metrics_to_show = c("AUC", "F1", "MCC"))

Description

Grouped bar chart: Comparisons x multiple metrics side by side.

Usage

benchmark_metrics_bars_gg(
  metrics_table,
  metrics_to_show = c("Sensitivity", "Specificity", "Precision", "F1", "Accuracy"),
  title = "Benchmark Metrics by Comparison",
  bar_width = 0.7
)

Arguments

Value

ggplot2 object

Examples

data(nadia_dia)
de <- process_proteomics(nadia_dia, verbose = FALSE)$DEPs_results
sp <- utils::read.delim(system.file("extdata", "nadia_dia_spikein.tsv.gz",
                                    package = "NADIA"))
de$Species <- sp$PG.OrganismId[match(de$Protein.IDs, sp$PG.ProteinGroups)]
ev <- data.frame(Comparison = rep(c("B-A", "D-A"), each = 2),
                 Species = c("ECOLI", "YEAST"),
                 expected_logFC = c(1, -0.58, 2, -3.3))
metrics <- compute_benchmark_metrics(de, ev)
benchmark_metrics_bars_gg(metrics, metrics_to_show = c("Sensitivity", "F1"))

Description

Generates ROC curves for each comparison using pROC::ggroc(). Requires the pROC package.

Usage

benchmark_roc_gg(
  classified_df,
  p_col = "adj.P.Val",
  comparisons = NULL,
  title = "ROC Curves by Comparison",
  zoom = FALSE,
  palette = "Set1"
)

Arguments

Value

ggplot2 object or NULL if pROC is not available

Examples

data(nadia_dia)
de <- process_proteomics(nadia_dia, verbose = FALSE)$DEPs_results
sp <- utils::read.delim(system.file("extdata", "nadia_dia_spikein.tsv.gz",
                                    package = "NADIA"))
de$Species <- sp$PG.OrganismId[match(de$Protein.IDs, sp$PG.ProteinGroups)]
ev <- data.frame(Comparison = rep(c("B-A", "D-A"), each = 2),
                 Species = c("ECOLI", "YEAST"),
                 expected_logFC = c(1, -0.58, 2, -3.3))
if (requireNamespace("pROC", quietly = TRUE)) {
  bench <- benchmarking_proteomics(de, ev, verbose = FALSE)
  benchmark_roc_gg(bench$classified_df, comparisons = "B-A")
}

Description

Stacked bar chart of significant proteins by species, faceted by direction (UP/DOWN).

Usage

benchmark_signif_bars_gg(
  classified_df,
  ev = NULL,
  species_colors = NULL,
  title = "Significant Proteins by Species and Direction"
)

Arguments

Details

Counts every protein the pipeline called significant, whatever the direction. A spike-in found significant with the sign inverted is an FN, so it carries predicted = 0, but it is still a significant protein and belongs in the facet its observed logFC points to – which is precisely the facet that reveals the problem.

Value

ggplot2 object

Examples

data(nadia_dia)
de <- process_proteomics(nadia_dia, verbose = FALSE)$DEPs_results
sp <- utils::read.delim(system.file("extdata", "nadia_dia_spikein.tsv.gz",
                                    package = "NADIA"))
de$Species <- sp$PG.OrganismId[match(de$Protein.IDs, sp$PG.ProteinGroups)]
ev <- data.frame(Comparison = rep(c("B-A", "D-A"), each = 2),
                 Species = c("ECOLI", "YEAST"),
                 expected_logFC = c(1, -0.58, 2, -3.3))
bench <- benchmarking_proteomics(de, ev, verbose = FALSE)
benchmark_signif_bars_gg(bench$classified_df, ev)

Description

Volcano plot colored by Species with plotLines at expected logFC values, dispersion stats in subtitle.

Usage

benchmark_volcano_hc(
  de_res_comp,
  ev_comp,
  disp_comp = NULL,
  alpha = 0.05,
  lfc_thr = 0,
  p_col = "adj.P.Val",
  species_colors = NULL,
  point_size = 3,
  title = NULL,
  height = NULL
)

Arguments

Value

Highchart object

Examples

data(nadia_dia)
de <- process_proteomics(nadia_dia, verbose = FALSE)$DEPs_results
sp <- utils::read.delim(system.file("extdata", "nadia_dia_spikein.tsv.gz",
                                    package = "NADIA"))
de$Species <- sp$PG.OrganismId[match(de$Protein.IDs, sp$PG.ProteinGroups)]
ev <- data.frame(Comparison = rep(c("B-A", "D-A"), each = 2),
                 Species = c("ECOLI", "YEAST"),
                 expected_logFC = c(1, -0.58, 2, -3.3))
disp <- compute_dispersion_metrics(de, ev)
benchmark_volcano_hc(de[de$Comparison == "B-A", ],
                     ev[ev$Comparison == "B-A", ],
                     disp_comp = disp[disp$Comparison == "B-A", ])

Description

Generates one volcano plot per comparison.

Usage

benchmark_volcano_hc_list(
  de_res,
  ev,
  disp = NULL,
  alpha = 0.05,
  lfc_thr = 0,
  p_col = "adj.P.Val",
  comparisons = NULL,
  assay = NULL,
  species_colors = NULL,
  point_size = 3,
  height = NULL,
  species_df = NULL
)

Arguments

Value

Named list of highchart objects

Examples

data(nadia_dia)
de <- process_proteomics(nadia_dia, verbose = FALSE)$DEPs_results
sp <- utils::read.delim(system.file("extdata", "nadia_dia_spikein.tsv.gz",
                                    package = "NADIA"))
de$Species <- sp$PG.OrganismId[match(de$Protein.IDs, sp$PG.ProteinGroups)]
ev <- data.frame(Comparison = rep(c("B-A", "D-A"), each = 2),
                 Species = c("ECOLI", "YEAST"),
                 expected_logFC = c(1, -0.58, 2, -3.3))
volcanoes <- benchmark_volcano_hc_list(de, ev)
names(volcanoes)
volcanoes[["B-A"]]

Description

Orchestrator that imports, ranks, visualizes, and exports results from multiple normalization/imputation method combinations.

Usage

benchmarking_multiple(
  opdea_combined = NULL,
  confusion_combined = NULL,
  classified_combined = NULL,
  bench_metrics_combined = NULL,
  results_dir = NULL,
  pattern = "benchmark_opdea_metrics\\.tsv$",
  method_names = NULL,
  recursive = TRUE,
  strip_prefix = "benchmark_",
  metrics = .BM_METRICS,
  extended_metrics = .BM_EXTENDED_METRICS,
  p_col = "adj.P.Val",
  plots = "all",
  verbose = TRUE,
  output_dir = NULL,
  export_plots = TRUE,
  export_tables = TRUE,
  plot_width = 12,
  plot_height = 8,
  plot_dpi = 150
)

Arguments

Value

Named list with:

opdea_combined

Combined input data.frame

mean_aggregated

Mean of metrics per Assay

median_aggregated

Median of metrics per Assay

mean_ranking

Ranking table (mean-based)

median_ranking

Ranking table (median-based)

gg_ranking_heatmap_mean

Heatmap of ranks (mean)

gg_ranking_heatmap_median

Heatmap of ranks (median)

gg_ranking_bars_mean

Bar chart of final rank (mean)

gg_ranking_bars_median

Bar chart of final rank (median)

gg_metrics_heatmap_mean

Heatmap of metric values (mean)

gg_metrics_heatmap_median

Heatmap of metric values (median)

gg_metrics_comparison

Boxplot distributions

ranking_by_comparison

Named list of ranking data.frames per comparison

ranking_by_comparison_combined

data.frame with all per-comparison rankings

gg_ranking_heatmap_by_comp

Named list of heatmaps per comparison

gg_ranking_bars_by_comp

Named list of bar charts per comparison

confusion_combined

Combined confusion data.frame (if available)

gg_confusion_stacked

Faceted confusion stacked bars (if available)

gg_confusion_stacked_by_comp

Named list of confusion plots per comparison

classified_combined

Combined classified data.frame (if available)

gg_roc_by_comp

Named list of ROC plots per comparison (if available)

gg_roc_zoom_by_comp

Named list of ROC zoom plots per comparison (if available)

extended_combined

Merged classification + OpDEA data (if bench_metrics available)

extended_mean_aggregated

Mean-aggregated extended metrics per Assay

extended_ranking

Extended ranking table (11 metrics, mean-based)

gg_extended_ranking_bars

Bar chart of extended ranking

gg_extended_ranking_heatmap

Heatmap of extended ranking

parameters

List of parameters used

Examples

data(nadia_dia)
sp <- utils::read.delim(system.file("extdata", "nadia_dia_spikein.tsv.gz",
                                    package = "NADIA"))
ev <- data.frame(Comparison = rep(c("B-A", "D-A"), each = 2),
                 Species = c("ECOLI", "YEAST"),
                 expected_logFC = c(1, -0.58, 2, -3.3))
root <- file.path(tempdir(), "nadia_bench")
for (nm in c("cycloess", "quantile")) {
  de <- process_proteomics(nadia_dia, norm_method = nm,
                           verbose = FALSE)$DEPs_results
  de$Species <- sp$PG.OrganismId[match(de$Protein.IDs, sp$PG.ProteinGroups)]
  benchmarking_proteomics(de, ev, output_dir = file.path(root, nm),
                          verbose = FALSE)
}
result <- benchmarking_multiple(results_dir = root, verbose = FALSE)
result$mean_ranking
result$gg_ranking_bars_mean

Description

Evaluates the reliability of DE results by comparing them against known ground truth (multi-species spike-in experiments). Computes classification metrics, dispersion statistics, and generates visualizations.

Usage

benchmarking_proteomics(
  de_res,
  expected_values,
  alpha = 0.05,
  lfc_thr = 0,
  p_col = "adj.P.Val",
  comparisons = NULL,
  assay = NULL,
  output_dir = NULL,
  verbose = TRUE,
  species_colors = NULL,
  species_df = NULL
)

Arguments

Value

List with:

• metrics_table: Classification metrics per comparison

• confusion_by_species: Confusion matrix per Comparison x Species

• confusion_overall: Confusion matrix aggregated per Comparison

• dispersion_metrics: Dispersion stats per Comparison x Species

• classified_df: Full classified data frame

• gg_heatmap: ggplot2 performance heatmap

• gg_confusion_by_species: ggplot2 confusion matrix heatmap (by species)

• gg_confusion_overall: ggplot2 confusion matrix heatmap (aggregated)

• gg_auc_bars: ggplot2 AUC bar chart

• gg_metrics_bars: ggplot2 grouped metrics bar chart

• gg_signif_bars: ggplot2 significant proteins stacked bars (absolute)

• hc_volcano_list: Named list of Highcharter volcano plots

• parameters: List of parameters used

Examples

data(nadia_dia)
de <- process_proteomics(nadia_dia, verbose = FALSE)$DEPs_results
sp <- utils::read.delim(system.file("extdata", "nadia_dia_spikein.tsv.gz",
                                    package = "NADIA"))
species_df <- data.frame(Protein.IDs = sp$PG.ProteinGroups,
                         Species = sp$PG.OrganismId)
ev <- data.frame(Comparison = rep(c("B-A", "D-A"), each = 2),
                 Species = c("ECOLI", "YEAST"),
                 expected_logFC = c(1, -0.58, 2, -3.3))
bench <- benchmarking_proteomics(de, ev, species_df = species_df,
                                 verbose = FALSE)
bench$metrics_table
bench$gg_heatmap

Description

For each of the 11 metrics, averages across comparisons per Assay (mean), then ranks methods in descending order (higher = better for all metrics). Final rank = mean of the 11 individual ranks.

Usage

bm_compute_extended_ranking(
  opdea_combined,
  bench_metrics_combined,
  metrics = .BM_EXTENDED_METRICS
)

Arguments

Details

Note: this extended ranking can drift away from the canonical OpDEA ranking (bm_compute_ranking, based on nMCC/G_mean/pAUC). Performance is collinear with F1 (so F1 effectively counts twice), and in spike-in designs Accuracy/NPV are dominated by the background (TN >> ), hence they have little discriminative power. Use it as a complementary view, not as a substitute for the OpDEA ranking.

Value

Named list with:

extended_combined

Merged data.frame (long format)

mean_aggregated

data.frame of mean metric values per Assay

mean_ranking

data.frame with rank columns and rank_final

n_methods

Number of unique methods

n_comparisons

Number of unique comparisons

metrics_used

Metrics actually used

Examples

data(nadia_dia)
sp <- utils::read.delim(system.file("extdata", "nadia_dia_spikein.tsv.gz",
                                    package = "NADIA"))
ev <- data.frame(Comparison = rep(c("B-A", "D-A"), each = 2),
                 Species = c("ECOLI", "YEAST"),
                 expected_logFC = c(1, -0.58, 2, -3.3))
opdea_all <- NULL
bench_all <- NULL
for (nm in c("cycloess", "quantile")) {
  de <- process_proteomics(nadia_dia, norm_method = nm,
                           verbose = FALSE)$DEPs_results
  de$Species <- sp$PG.OrganismId[match(de$Protein.IDs, sp$PG.ProteinGroups)]
  opdea_all <- rbind(opdea_all, cbind(compute_opdea_metrics(de, ev), Assay = nm))
  bench_all <- rbind(bench_all, cbind(compute_benchmark_metrics(de, ev), Assay = nm))
}
ext <- bm_compute_extended_ranking(opdea_all, bench_all)
ext$mean_ranking[, c("Assay", "rank_final")]

Description

For each metric, aggregates across comparisons (mean and median), then ranks methods in descending order (rank 1 = best). Final rank = average of individual metric ranks.

Usage

bm_compute_ranking(opdea_combined, metrics = .BM_METRICS)

Arguments

Value

Named list with:

mean_aggregated

data.frame of mean metric values per Assay

median_aggregated

data.frame of median metric values per Assay

mean_ranking

data.frame of ranks based on mean aggregation

median_ranking

data.frame of ranks based on median aggregation

opdea_combined

Input combined data.frame

n_methods

Number of methods

n_comparisons

Number of comparisons

metrics_used

Metrics included in ranking

Examples

data(nadia_dia)
sp <- utils::read.delim(system.file("extdata", "nadia_dia_spikein.tsv.gz",
                                    package = "NADIA"))
ev <- data.frame(Comparison = rep(c("B-A", "D-A"), each = 2),
                 Species = c("ECOLI", "YEAST"),
                 expected_logFC = c(1, -0.58, 2, -3.3))
opdea_all <- do.call(rbind, lapply(c("cycloess", "quantile"), function(nm) {
  de <- process_proteomics(nadia_dia, norm_method = nm,
                           verbose = FALSE)$DEPs_results
  de$Species <- sp$PG.OrganismId[match(de$Protein.IDs, sp$PG.ProteinGroups)]
  cbind(compute_opdea_metrics(de, ev), Assay = nm)
}))
ranking <- bm_compute_ranking(opdea_all)
ranking$mean_ranking

Description

For each comparison, ranks methods directly on their metric values (no aggregation needed since there is one value per method per comparison).

Usage

bm_compute_ranking_by_comparison(opdea_combined, metrics = .BM_METRICS)

Arguments

Value

Named list with:

by_comparison

Named list where each key is a comparison and each value is a data.frame with metric values, ranks, and rank_final

ranking_combined

data.frame with all comparisons in long format (includes Comparison column)

Examples

data(nadia_dia)
sp <- utils::read.delim(system.file("extdata", "nadia_dia_spikein.tsv.gz",
                                    package = "NADIA"))
ev <- data.frame(Comparison = rep(c("B-A", "D-A"), each = 2),
                 Species = c("ECOLI", "YEAST"),
                 expected_logFC = c(1, -0.58, 2, -3.3))
opdea_all <- do.call(rbind, lapply(c("cycloess", "quantile"), function(nm) {
  de <- process_proteomics(nadia_dia, norm_method = nm,
                           verbose = FALSE)$DEPs_results
  de$Species <- sp$PG.OrganismId[match(de$Protein.IDs, sp$PG.ProteinGroups)]
  cbind(compute_opdea_metrics(de, ev), Assay = nm)
}))
by_comp <- bm_compute_ranking_by_comparison(opdea_all)
by_comp$by_comparison[["B-A"]]

Description

Horizontal stacked bars showing confusion matrix counts per method. If comparison is NULL, generates a faceted plot with all comparisons.

Usage

bm_plot_confusion_stacked(confusion_combined, comparison = NULL, title = NULL)

Arguments

Value

ggplot2 object

Examples

data(nadia_dia)
sp <- utils::read.delim(system.file("extdata", "nadia_dia_spikein.tsv.gz",
                                    package = "NADIA"))
ev <- data.frame(Comparison = rep(c("B-A", "D-A"), each = 2),
                 Species = c("ECOLI", "YEAST"),
                 expected_logFC = c(1, -0.58, 2, -3.3))
bench_all <- do.call(rbind, lapply(c("cycloess", "quantile"), function(nm) {
  de <- process_proteomics(nadia_dia, norm_method = nm,
                           verbose = FALSE)$DEPs_results
  de$Species <- sp$PG.OrganismId[match(de$Protein.IDs, sp$PG.ProteinGroups)]
  cbind(compute_benchmark_metrics(de, ev), Assay = nm)
}))
bm_plot_confusion_stacked(bench_all)
bm_plot_confusion_stacked(bench_all, comparison = "B-A")

Description

Horizontal bar chart of extended combined ranking

Usage

bm_plot_extended_ranking_bars(extended_ranking, title = NULL)

Arguments

Value

ggplot object

Examples

data(nadia_dia)
sp <- utils::read.delim(system.file("extdata", "nadia_dia_spikein.tsv.gz",
                                    package = "NADIA"))
ev <- data.frame(Comparison = rep(c("B-A", "D-A"), each = 2),
                 Species = c("ECOLI", "YEAST"),
                 expected_logFC = c(1, -0.58, 2, -3.3))
opdea_all <- NULL
bench_all <- NULL
for (nm in c("cycloess", "quantile")) {
  de <- process_proteomics(nadia_dia, norm_method = nm,
                           verbose = FALSE)$DEPs_results
  de$Species <- sp$PG.OrganismId[match(de$Protein.IDs, sp$PG.ProteinGroups)]
  opdea_all <- rbind(opdea_all, cbind(compute_opdea_metrics(de, ev), Assay = nm))
  bench_all <- rbind(bench_all, cbind(compute_benchmark_metrics(de, ev), Assay = nm))
}
ext <- bm_compute_extended_ranking(opdea_all, bench_all)
bm_plot_extended_ranking_bars(ext)

Description

Heatmap of extended ranking (11 metrics)

Usage

bm_plot_extended_ranking_heatmap(extended_ranking, title = NULL)

Arguments

Value

ggplot object

Examples

data(nadia_dia)
sp <- utils::read.delim(system.file("extdata", "nadia_dia_spikein.tsv.gz",
                                    package = "NADIA"))
ev <- data.frame(Comparison = rep(c("B-A", "D-A"), each = 2),
                 Species = c("ECOLI", "YEAST"),
                 expected_logFC = c(1, -0.58, 2, -3.3))
opdea_all <- NULL
bench_all <- NULL
for (nm in c("cycloess", "quantile")) {
  de <- process_proteomics(nadia_dia, norm_method = nm,
                           verbose = FALSE)$DEPs_results
  de$Species <- sp$PG.OrganismId[match(de$Protein.IDs, sp$PG.ProteinGroups)]
  opdea_all <- rbind(opdea_all, cbind(compute_opdea_metrics(de, ev), Assay = nm))
  bench_all <- rbind(bench_all, cbind(compute_benchmark_metrics(de, ev), Assay = nm))
}
ext <- bm_compute_extended_ranking(opdea_all, bench_all)
bm_plot_extended_ranking_heatmap(ext)

Description

Faceted boxplot showing the distribution of each metric across comparisons for every method.

Usage

bm_plot_metrics_comparison(opdea_combined, metrics = .BM_METRICS, title = NULL)

Arguments

Value

ggplot2 object

Examples

data(nadia_dia)
sp <- utils::read.delim(system.file("extdata", "nadia_dia_spikein.tsv.gz",
                                    package = "NADIA"))
ev <- data.frame(Comparison = rep(c("B-A", "D-A"), each = 2),
                 Species = c("ECOLI", "YEAST"),
                 expected_logFC = c(1, -0.58, 2, -3.3))
opdea_all <- do.call(rbind, lapply(c("cycloess", "quantile"), function(nm) {
  de <- process_proteomics(nadia_dia, norm_method = nm,
                           verbose = FALSE)$DEPs_results
  de$Species <- sp$PG.OrganismId[match(de$Protein.IDs, sp$PG.ProteinGroups)]
  cbind(compute_opdea_metrics(de, ev), Assay = nm)
}))
bm_plot_metrics_comparison(opdea_all)

Description

Shows the actual metric values per method, with per-column color scaling.

Usage

bm_plot_metrics_heatmap(ranking_result, type = "mean", title = NULL)

Arguments

Value

ggplot2 object

Examples

data(nadia_dia)
sp <- utils::read.delim(system.file("extdata", "nadia_dia_spikein.tsv.gz",
                                    package = "NADIA"))
ev <- data.frame(Comparison = rep(c("B-A", "D-A"), each = 2),
                 Species = c("ECOLI", "YEAST"),
                 expected_logFC = c(1, -0.58, 2, -3.3))
opdea_all <- do.call(rbind, lapply(c("cycloess", "quantile"), function(nm) {
  de <- process_proteomics(nadia_dia, norm_method = nm,
                           verbose = FALSE)$DEPs_results
  de$Species <- sp$PG.OrganismId[match(de$Protein.IDs, sp$PG.ProteinGroups)]
  cbind(compute_opdea_metrics(de, ev), Assay = nm)
}))
ranking <- bm_compute_ranking(opdea_all)
bm_plot_metrics_heatmap(ranking)

Description

Horizontal bars of rank_final by Assay, ordered best to worst.

Usage

bm_plot_ranking_bars(ranking_result, type = "mean", title = NULL)

Arguments

Value

ggplot2 object

Examples

data(nadia_dia)
sp <- utils::read.delim(system.file("extdata", "nadia_dia_spikein.tsv.gz",
                                    package = "NADIA"))
ev <- data.frame(Comparison = rep(c("B-A", "D-A"), each = 2),
                 Species = c("ECOLI", "YEAST"),
                 expected_logFC = c(1, -0.58, 2, -3.3))
opdea_all <- do.call(rbind, lapply(c("cycloess", "quantile"), function(nm) {
  de <- process_proteomics(nadia_dia, norm_method = nm,
                           verbose = FALSE)$DEPs_results
  de$Species <- sp$PG.OrganismId[match(de$Protein.IDs, sp$PG.ProteinGroups)]
  cbind(compute_opdea_metrics(de, ev), Assay = nm)
}))
ranking <- bm_compute_ranking(opdea_all)
bm_plot_ranking_bars(ranking)

Description

Bar chart of final ranks for a single comparison

Usage

bm_plot_ranking_bars_by_comp(ranking_by_comp, comparison, title = NULL)

Arguments

Value

ggplot2 object

Examples

data(nadia_dia)
sp <- utils::read.delim(system.file("extdata", "nadia_dia_spikein.tsv.gz",
                                    package = "NADIA"))
ev <- data.frame(Comparison = rep(c("B-A", "D-A"), each = 2),
                 Species = c("ECOLI", "YEAST"),
                 expected_logFC = c(1, -0.58, 2, -3.3))
opdea_all <- do.call(rbind, lapply(c("cycloess", "quantile"), function(nm) {
  de <- process_proteomics(nadia_dia, norm_method = nm,
                           verbose = FALSE)$DEPs_results
  de$Species <- sp$PG.OrganismId[match(de$Protein.IDs, sp$PG.ProteinGroups)]
  cbind(compute_opdea_metrics(de, ev), Assay = nm)
}))
by_comp <- bm_compute_ranking_by_comparison(opdea_all)
bm_plot_ranking_bars_by_comp(by_comp, comparison = "D-A")

Description

Rows = Assay (ordered by rank_final), columns = metrics. Fill color = rank value (green = best, red = worst).

Usage

bm_plot_ranking_heatmap(ranking_result, type = "mean", title = NULL)

Arguments

Value

ggplot2 object

Examples

data(nadia_dia)
sp <- utils::read.delim(system.file("extdata", "nadia_dia_spikein.tsv.gz",
                                    package = "NADIA"))
ev <- data.frame(Comparison = rep(c("B-A", "D-A"), each = 2),
                 Species = c("ECOLI", "YEAST"),
                 expected_logFC = c(1, -0.58, 2, -3.3))
opdea_all <- do.call(rbind, lapply(c("cycloess", "quantile"), function(nm) {
  de <- process_proteomics(nadia_dia, norm_method = nm,
                           verbose = FALSE)$DEPs_results
  de$Species <- sp$PG.OrganismId[match(de$Protein.IDs, sp$PG.ProteinGroups)]
  cbind(compute_opdea_metrics(de, ev), Assay = nm)
}))
ranking <- bm_compute_ranking(opdea_all)
bm_plot_ranking_heatmap(ranking)

Description

Heatmap of metric ranks for a single comparison

Usage

bm_plot_ranking_heatmap_by_comp(ranking_by_comp, comparison, title = NULL)

Arguments

Value

ggplot2 object

Examples

data(nadia_dia)
sp <- utils::read.delim(system.file("extdata", "nadia_dia_spikein.tsv.gz",
                                    package = "NADIA"))
ev <- data.frame(Comparison = rep(c("B-A", "D-A"), each = 2),
                 Species = c("ECOLI", "YEAST"),
                 expected_logFC = c(1, -0.58, 2, -3.3))
opdea_all <- do.call(rbind, lapply(c("cycloess", "quantile"), function(nm) {
  de <- process_proteomics(nadia_dia, norm_method = nm,
                           verbose = FALSE)$DEPs_results
  de$Species <- sp$PG.OrganismId[match(de$Protein.IDs, sp$PG.ProteinGroups)]
  cbind(compute_opdea_metrics(de, ev), Assay = nm)
}))
by_comp <- bm_compute_ranking_by_comparison(opdea_all)
bm_plot_ranking_heatmap_by_comp(by_comp, comparison = "B-A")

Description

Generates ROC (or ROC zoom) plot where each curve represents a different method (Assay) for one comparison.

Usage

bm_plot_roc(
  classified_combined,
  comparison,
  p_col = "adj.P.Val",
  zoom = FALSE,
  palette = "Set2"
)

Arguments

Value

ggplot2 object or NULL if pROC not available

Examples

data(nadia_dia)
sp <- utils::read.delim(system.file("extdata", "nadia_dia_spikein.tsv.gz",
                                    package = "NADIA"))
ev <- data.frame(Comparison = rep(c("B-A", "D-A"), each = 2),
                 Species = c("ECOLI", "YEAST"),
                 expected_logFC = c(1, -0.58, 2, -3.3))
classified_all <- do.call(rbind, lapply(c("cycloess", "quantile"), function(nm) {
  de <- process_proteomics(nadia_dia, norm_method = nm,
                           verbose = FALSE)$DEPs_results
  de$Species <- sp$PG.OrganismId[match(de$Protein.IDs, sp$PG.ProteinGroups)]
  cl <- benchmarking_proteomics(de, ev, verbose = FALSE)$classified_df
  cl$Assay <- nm
  cl
}))
if (requireNamespace("pROC", quietly = TRUE)) {
  bm_plot_roc(classified_all, comparison = "B-A")
}

Description

Interactive Highcharts Boxplot for Proteomics

Usage

boxplot_highchart_list(
  data,
  assays = NULL,
  color_by = "Condition",
  group_order = NULL,
  palette = NULL,
  title = NULL,
  subtitle = NULL,
  show_outliers = TRUE,
  outlier_jitter = 0.15,
  outlier_size = 3,
  box_width = 20,
  horizontal = TRUE,
  height = NULL
)

Arguments

Value

List of highchart objects (one per assay)

Examples

data(nadia_dia)
res <- process_proteomics(nadia_dia, verbose = FALSE)

# One boxplot per assay; keep only the imputed one
hc_list <- boxplot_highchart_list(
  res$BoxPlot_Input,
  assays      = "Impseqrob_min",
  group_order = c("A", "B", "D"),
  title       = "Boxplot: {assay}"
)
names(hc_list)

Description

Build the clustering matrix aggregated by condition

Usage

build_clustering_matrix(
  intensity_matrix,
  sample_metadata,
  selected_features,
  condition_order = NULL,
  aggregate = c("median", "mean"),
  verbose = TRUE
)

Arguments

Value

Matrix of aggregated intensities (features x conditions)

Description

Creates one row per FeatureID-Cluster combination where membership >= min_membership. This lets a protein appear in several clusters (soft clustering).

Usage

build_long_output(cl, eset_std, conditions, min_membership)

Arguments

Value

DataFrame in long format

Description

Build a PCA scores data frame from data in long format

Usage

build_pca_scores(
  pca_input,
  mode = c("all", "any", "specific"),
  alpha = 0.05,
  comparison = NULL,
  subset_label = NULL,
  center = TRUE,
  scale. = TRUE,
  filter_samples_to_comparison = FALSE,
  cond_col = "Condition"
)

Arguments

Value

Data frame with columns: SampleID, PC1, PC2, PC1_Perc, PC2_Perc, Subset, Condition, Replicate

Examples

data(nadia_dia)
res <- process_proteomics(nadia_dia, verbose = FALSE)

# Scores and the variance explained by the first two components
scores <- build_pca_scores(res$PCA_Input, mode = "all")
head(scores)
unique(scores[c("PC1_Perc", "PC2_Perc")])

Description

Builds a comparative plot with the centroids of all the clusters.

Usage

cluster_centroids_highchart(
  data,
  conditions = NULL,
  clusters = NULL,
  min_membership = NULL,
  centroid_summary = c("mean", "median"),
  palette = NULL,
  line_width = 2.5,
  show_markers = TRUE,
  title = NULL,
  height = NULL
)

Arguments

Value

highchart object

Examples

if (requireNamespace("Mfuzz", quietly = TRUE) &&
    requireNamespace("e1071", quietly = TRUE)) {
  data(nadia_dia)
  res <- process_proteomics(nadia_dia, verbose = FALSE)
  pp <- pattern_profiler_analysis(res$se_proc, res$DEPs_results,
                                  assay_name = "Impseqrob_min",
                                  auto_select_c = FALSE, c = 3,
                                  verbose = FALSE)

  # All the cluster centroids on one chart
  hc <- cluster_centroids_highchart(pp$long_output,
                                    conditions = c("A", "B", "D"),
                                    centroid_summary = "median")
  print(class(hc))
}

Description

Builds an interactive plot showing the expression profiles of the proteins in a given cluster.

Usage

cluster_profile_highchart(
  data,
  cluster,
  conditions = NULL,
  min_membership = NULL,
  show_centroid = TRUE,
  centroid_summary = c("mean", "median"),
  cluster_color = NULL,
  line_width = 1,
  line_opacity = 0.4,
  centroid_width = 3,
  title = NULL,
  height = NULL
)

Arguments

Value

highchart object

Examples

if (requireNamespace("Mfuzz", quietly = TRUE) &&
    requireNamespace("e1071", quietly = TRUE)) {
  data(nadia_dia)
  res <- process_proteomics(nadia_dia, verbose = FALSE)
  pp <- pattern_profiler_analysis(res$se_proc, res$DEPs_results,
                                  assay_name = "Impseqrob_min",
                                  auto_select_c = FALSE, c = 3,
                                  verbose = FALSE)

  hc <- cluster_profile_highchart(pp$long_output, cluster = 1,
                                  conditions = c("A", "B", "D"))
  print(class(hc))
}

Description

Builds a list of interactive plots for all the clusters.

Usage

cluster_profile_highchart_list(
  data,
  conditions = NULL,
  clusters = NULL,
  min_membership = NULL,
  show_centroid = TRUE,
  centroid_summary = c("mean", "median"),
  palette = NULL,
  line_width = 1,
  line_opacity = 0.4,
  centroid_width = 3,
  height = NULL
)

Arguments

Value

Named list of highchart objects

Examples

if (requireNamespace("Mfuzz", quietly = TRUE) &&
    requireNamespace("e1071", quietly = TRUE)) {
  data(nadia_dia)
  res <- process_proteomics(nadia_dia, verbose = FALSE)
  pp <- pattern_profiler_analysis(res$se_proc, res$DEPs_results,
                                  assay_name = "Impseqrob_min",
                                  auto_select_c = FALSE, c = 3,
                                  verbose = FALSE)

  hc_profiles <- cluster_profile_highchart_list(pp$long_output,
                                                conditions = c("A", "B", "D"))
  print(names(hc_profiles))
}

Description

Compute benchmark metrics for all comparisons

Usage

compute_benchmark_metrics(
  de_res,
  ev,
  alpha = 0.05,
  lfc_thr = 0,
  p_col = "adj.P.Val",
  comparisons = NULL,
  assay = NULL,
  species_df = NULL
)

Arguments

Value

Data frame with metrics per comparison

Examples

data(nadia_dia)
de <- process_proteomics(nadia_dia, verbose = FALSE)$DEPs_results
sp <- utils::read.delim(system.file("extdata", "nadia_dia_spikein.tsv.gz",
                                    package = "NADIA"))
de$Species <- sp$PG.OrganismId[match(de$Protein.IDs, sp$PG.ProteinGroups)]
ev <- data.frame(Comparison = rep(c("B-A", "D-A"), each = 2),
                 Species = c("ECOLI", "YEAST"),
                 expected_logFC = c(1, -0.58, 2, -3.3))
metrics <- compute_benchmark_metrics(de, ev)
metrics[, c("Comparison", "TP", "FP", "Sensitivity", "Specificity", "F1")]

Description

Computes the coordinates of a confidence ellipse based on the chi-squared distribution, similar to FactoMineR::coord.ellipse and ggplot2::stat_ellipse.

Usage

compute_confidence_ellipse(
  scores_df,
  group_col = "Condition",
  level = 0.95,
  npoints = 100
)

Arguments

Value

List of data frames, each one with columns: group, x, y

Description

Calculates MED, SD, CV, MAD, RCV, IQR, trimmed SD/CV for significant proteins with correct direction.

Usage

compute_dispersion_metrics(
  de_res,
  ev,
  alpha = 0.05,
  lfc_thr = 0,
  p_col = "adj.P.Val",
  comparisons = NULL,
  assay = NULL,
  trim = 0.1,
  species_df = NULL
)

Arguments

Value

Data frame with dispersion metrics

Examples

data(nadia_dia)
de <- process_proteomics(nadia_dia, verbose = FALSE)$DEPs_results
sp <- utils::read.delim(system.file("extdata", "nadia_dia_spikein.tsv.gz",
                                    package = "NADIA"))
de$Species <- sp$PG.OrganismId[match(de$Protein.IDs, sp$PG.ProteinGroups)]
ev <- data.frame(Comparison = rep(c("B-A", "D-A"), each = 2),
                 Species = c("ECOLI", "YEAST"),
                 expected_logFC = c(1, -0.58, 2, -3.3))
disp <- compute_dispersion_metrics(de, ev)
disp[, c("Comparison", "Species", "expected_logFC", "MED", "MAD", "RCV")]

Description

Compute the convex hull (enclosing polygon) per group

Usage

compute_hulls(scores_df, group_col = "Condition")

Arguments

Value

List of data frames, each one with columns: group, x, y

Description

Calculates additional benchmark metrics based on Peng et al. 2024 (Nature Comms, OpDEA framework):

• pAUC(0.01), pAUC(0.05), pAUC(0.1): Partial AUC with McClish correction

• nMCC: Normalized MCC = (MCC + 1) / 2

• G-mean: sqrt(Sensitivity * Specificity)

Usage

compute_opdea_metrics(
  de_res,
  ev,
  alpha = 0.05,
  lfc_thr = 0,
  p_col = "adj.P.Val",
  comparisons = NULL,
  assay = NULL,
  species_df = NULL
)

Arguments

Value

Data frame with columns: Comparison, nMCC, G_mean, pAUC_001, pAUC_005, pAUC_010

Examples

data(nadia_dia)
de <- process_proteomics(nadia_dia, verbose = FALSE)$DEPs_results
sp <- utils::read.delim(system.file("extdata", "nadia_dia_spikein.tsv.gz",
                                    package = "NADIA"))
de$Species <- sp$PG.OrganismId[match(de$Protein.IDs, sp$PG.ProteinGroups)]
ev <- data.frame(Comparison = rep(c("B-A", "D-A"), each = 2),
                 Species = c("ECOLI", "YEAST"),
                 expected_logFC = c(1, -0.58, 2, -3.3))
compute_opdea_metrics(de, ev)

Description

Configure the colour palette for the clusters

Usage

configure_cluster_palette(n_clusters, palette = NULL)

Arguments

Value

Vector of colours named by cluster

Description

Create an ExpressionSet for Mfuzz

Usage

create_expression_set(mat, feature_info = NULL)

Arguments

Value

ExpressionSet object

Description

Coordinates comparison specification, limma analysis, and result extraction.

Usage

de_analysis_proteomics(
  se,
  assay_name = NULL,
  comparisons = NULL,
  control = NULL,
  logFC_threshold = 0,
  alpha = 0.05,
  p_adj = TRUE,
  eBayes_trend = NULL,
  eBayes_robust = NULL,
  de_method = "limma",
  covariate_column = NULL,
  bio_replicate_column = NULL,
  condition_column = "Condition",
  verbose = TRUE
)

Arguments

Value

List with:

• DEPs_results: Data frame with differential expression results

• comparisons: Comparisons performed

• assay_name: Assay name used

Examples

data(nadia_dia)
norm <- normalize_proteomics(nadia_dia, norm_method = "cycloess",
                             verbose = FALSE)
imp  <- impute_proteomics(norm$se, normalized_assay_name = "cycloess",
                          verbose = FALSE)

# All pairwise comparisons
de <- de_analysis_proteomics(imp$se, assay_name = "Impseqrob_min",
                             verbose = FALSE)
head(de$DEPs_results[, c("Protein.IDs", "Comparison", "logFC", "adj.P.Val")])

# Or every condition against a single control
de2 <- de_analysis_proteomics(imp$se, assay_name = "Impseqrob_min",
                              control = "A", verbose = FALSE)
unique(de2$DEPs_results$Comparison)

Description

Joins the differential-abundance results to the soft clustering, giving the table a functional-enrichment or over-representation analysis needs: the statistics that say which proteins moved, and the cluster that says which pattern they follow.

Usage

deps_with_clusters(
  DEPs_results,
  pattern_profiler,
  assignment = c("primary", "all"),
  min_membership = NULL,
  comparison = NULL,
  significant_only = FALSE
)

Arguments

Details

The join is a left join from the results, so every protein that was tested survives it, with or without a cluster. That matters more than it looks: the complete set of tested proteins is the background an enrichment is computed against, and a protein with no cluster – one that was never selected for the clustering, or that the clustering dropped – belongs in that background rather than in the bin.

Clustering is fuzzy, so a protein can belong to several clusters at once. assignment decides what to do about it. "primary" keeps only the dominant pattern of each protein and returns exactly one row per protein and comparison, which is what most enrichment tools expect. "all" keeps every association above the threshold, which is the honest representation of a soft clustering and the one to use when the analysis downstream can weight by membership.

Value

A data frame with the columns of DEPs_results followed by Cluster, Membership and ClusterRank (1 is the protein's dominant cluster).

See Also

nadia_deps_with_clusters() for the same table read from a .nadia file, and pattern_profiler_analysis() for the clustering.

Examples

data(nadia_dia)
res <- process_proteomics(nadia_dia, verbose = FALSE)

# Without a clustering the shape is the same and the clusters are NA.
fi <- deps_with_clusters(res$DEPs_results, NULL)
head(fi)

if (requireNamespace("Mfuzz", quietly = TRUE) &&
    requireNamespace("Biobase", quietly = TRUE) &&
    requireNamespace("e1071", quietly = TRUE)) {
    pp <- pattern_profiler_analysis(res$se_proc, res$DEPs_results,
                                    assay_name = "Impseqrob_min",
                                    verbose = FALSE)

    primary <- deps_with_clusters(res$DEPs_results, pp)
    nrow(primary) == nrow(res$DEPs_results)   # the background is intact

    soft <- deps_with_clusters(res$DEPs_results, pp, assignment = "all")
    table(soft$ClusterRank)
}

Description

Detect the condition columns (z-scores)

Usage

detect_condition_columns(data)

Arguments

Value

Vector with the names of the condition columns

Description

Evaluate a range of cluster numbers

Usage

evaluate_cluster_range(
  eset_std,
  c_range = 2:10,
  m = NULL,
  seeds = c(42, 123, 456),
  verbose = TRUE
)

Arguments

Value

DataFrame with the metrics per number of clusters

Description

Retrieves the intensity matrix, the feature IDs and the sample metadata from a SummarizedExperiment object.

Usage

extract_se_data(se_proc, assay_name = NULL, verbose = TRUE)

Arguments

Value

List with:

• intensity_matrix: features x samples matrix

• feature_ids: vector of protein IDs

• sample_metadata: DataFrame with SampleID, Condition, etc.

Description

Filter features by significance

Usage

filter_significant_features(
  feature_info,
  filter_mode = c("any", "all", "specific"),
  comparison = NULL,
  alpha = 0.05,
  verbose = TRUE
)

Arguments

Value

Vector of the selected FeatureIDs

Description

Build the Colour Palette for Categorical Annotations

Usage

get_annotation_palette(levels, palette = NULL)

Arguments

Value

Named vector of colours

Description

Build the Colour Palette for the Heatmap Values

Usage

get_heatmap_palette(palette = NULL, n = 11, reverse = FALSE)

Arguments

Value

Vector of colours, or a colorRamp2 function

Description

Extracts complete-case rows from the assay, introduces artificial NAs, re-imputes with each method, and computes four quality metrics plus a combined ranking.

Usage

im_compute_metrics(
  se,
  assay_name = NULL,
  methods = .IM_BENCH_METHODS,
  combo_methods = list(),
  condition_col = "Condition",
  na_prop = 0.2,
  seed = 42L,
  pattern = "random",
  method_args = list(),
  with_value = NA_real_,
  verbose = TRUE
)

Arguments

Value

data.frame with columns: Method, NRMSE, SOR, PSS, ACC_OI, NRMSE_Rank, SOR_Rank, PSS_Rank, ACC_OI_Rank, Rank_Mean. Ordered by Rank_Mean (best first).

Examples

data(nadia_dia)
se <- im_prepare_se(nadia_dia, norm_method = "cycloess", verbose = FALSE)

# Ground-truth simulation: complete rows are masked and re-imputed, so the
# error of each method can be measured against the values it did not see
metrics <- im_compute_metrics(se, methods = c("min", "zero", "knn"),
                              verbose = FALSE)
metrics[, c("Method", "NRMSE", "SOR", "Rank_Mean")]

Description

Bar chart of Average Correlation Coefficient (ACC_OI), ordered descending (higher is better).

Usage

im_plot_acc_oi(metrics_df, ...)

Arguments

Value

ggplot object.

Examples

data(nadia_dia)
se <- im_prepare_se(nadia_dia, norm_method = "cycloess", verbose = FALSE)
metrics <- im_compute_metrics(se, methods = c("min", "zero", "knn"),
                              verbose = FALSE)
im_plot_acc_oi(metrics)

Description

Similar to nm_plot_metrics(): one facet per metric with free y-scales, labeled values on bars.

Usage

im_plot_metrics(metrics_df, ...)

Arguments

Value

ggplot object.

Examples

data(nadia_dia)
se <- im_prepare_se(nadia_dia, norm_method = "cycloess", verbose = FALSE)
metrics <- im_compute_metrics(se, methods = c("min", "zero", "knn"),
                              verbose = FALSE)
im_plot_metrics(metrics)

Description

Bar chart of NRMSE values, ordered ascending (lower is better).

Usage

im_plot_nrmse(metrics_df, ...)

Arguments

Value

ggplot object.

Examples

data(nadia_dia)
se <- im_prepare_se(nadia_dia, norm_method = "cycloess", verbose = FALSE)
metrics <- im_compute_metrics(se, methods = c("min", "zero", "knn"),
                              verbose = FALSE)
im_plot_nrmse(metrics)

Description

Bar chart of Procrustes Statistical Shape (PSS), ordered ascending (lower is better). Requires vegan; NA values shown as 0-height bars.

Usage

im_plot_pss(metrics_df, ...)

Arguments

Value

ggplot object.

Examples

data(nadia_dia)
se <- im_prepare_se(nadia_dia, norm_method = "cycloess", verbose = FALSE)
metrics <- im_compute_metrics(se, methods = c("min", "zero", "knn"),
                              verbose = FALSE)
im_plot_pss(metrics)

Description

Heatmap (geom_tile + geom_text) showing per-metric ranks and the combined Rank_Mean. Rows = methods (ordered by Rank_Mean), columns = metrics.

Usage

im_plot_ranking(metrics_df, ...)

Arguments

Value

ggplot object.

Examples

data(nadia_dia)
se <- im_prepare_se(nadia_dia, norm_method = "cycloess", verbose = FALSE)
metrics <- im_compute_metrics(se, methods = c("min", "zero", "knn"),
                              verbose = FALSE)
im_plot_ranking(metrics)

Description

Bar chart of Sum of Ranks (SOR), ordered ascending (lower is better).

Usage

im_plot_sor(metrics_df, ...)

Arguments

Value

ggplot object.

Examples

data(nadia_dia)
se <- im_prepare_se(nadia_dia, norm_method = "cycloess", verbose = FALSE)
metrics <- im_compute_metrics(se, methods = c("min", "zero", "knn"),
                              verbose = FALSE)
im_plot_sor(metrics)

Description

Convenience function that creates a SE from a proteomics_data object and applies the winning normalization method (from normalization benchmarking). The result is ready for imputation_metrics().

Usage

im_prepare_se(
  preprocessing,
  norm_method = NULL,
  pc1_rank = NULL,
  min_reps = NULL,
  min_groups = 1,
  covariate_df = NULL,
  norm_method_args = list(),
  include_log2 = TRUE,
  verbose = TRUE
)

Arguments

Details

Internally calls nm_prepare_se() to build the baseline SE with assay "log2", then applies the chosen normalization via .nm_dispatch_normalization().

Value

SummarizedExperiment with assays "log2" (optional) + winner method.

Examples

data(nadia_dia)

# Option A: name the normalization to benchmark imputation on
se <- im_prepare_se(nadia_dia, norm_method = "cycloess", verbose = FALSE)
SummarizedExperiment::assayNames(se)

# Option B: let the winner of normalization_metrics() decide. That function
# takes a SummarizedExperiment, so the baseline is built first.
se_base <- nm_prepare_se(nadia_dia, verbose = FALSE)
nm <- normalization_metrics(se_base,
                            methods = c("cycloess", "quantile", "MAD"),
                            plots = "pc1_ranking", verbose = FALSE)
nm$pc1_rank
se2 <- im_prepare_se(nadia_dia, pc1_rank = nm$pc1_rank, verbose = FALSE)
SummarizedExperiment::assayNames(se2)

Description

Reads benchmark_metrics.tsv files from subdirectories, adding an Assay column derived from the folder name.

Usage

import_benchmark_metrics(
  results_dir,
  pattern = "benchmark_metrics\\.tsv$",
  method_names = NULL,
  recursive = TRUE
)

Arguments

Value

data.frame with columns: Assay, Comparison, TP, FP, TN, FN, Sensitivity, Specificity, Precision, NPV, Accuracy, F1, MCC, AUC, Performance

Examples

data(nadia_dia)
sp <- utils::read.delim(system.file("extdata", "nadia_dia_spikein.tsv.gz",
                                    package = "NADIA"))
ev <- data.frame(Comparison = rep(c("B-A", "D-A"), each = 2),
                 Species = c("ECOLI", "YEAST"),
                 expected_logFC = c(1, -0.58, 2, -3.3))
root <- file.path(tempdir(), "nadia_bench")
for (nm in c("cycloess", "quantile")) {
  de <- process_proteomics(nadia_dia, norm_method = nm,
                           verbose = FALSE)$DEPs_results
  de$Species <- sp$PG.OrganismId[match(de$Protein.IDs, sp$PG.ProteinGroups)]
  benchmarking_proteomics(de, ev, output_dir = file.path(root, nm),
                          verbose = FALSE)
}
bench_all <- import_benchmark_metrics(root)
bench_all[, c("Assay", "Comparison", "Sensitivity", "Specificity", "F1")]

Description

Reads benchmark_classified.tsv files from subdirectories, adding an Assay column derived from the folder name.

Usage

import_classified_results(
  results_dir,
  pattern = "benchmark_classified\\.tsv$",
  method_names = NULL,
  recursive = TRUE
)

Arguments

Value

data.frame with columns from classified_df plus Assay

Examples

data(nadia_dia)
sp <- utils::read.delim(system.file("extdata", "nadia_dia_spikein.tsv.gz",
                                    package = "NADIA"))
ev <- data.frame(Comparison = rep(c("B-A", "D-A"), each = 2),
                 Species = c("ECOLI", "YEAST"),
                 expected_logFC = c(1, -0.58, 2, -3.3))
root <- file.path(tempdir(), "nadia_bench")
for (nm in c("cycloess", "quantile")) {
  de <- process_proteomics(nadia_dia, norm_method = nm,
                           verbose = FALSE)$DEPs_results
  de$Species <- sp$PG.OrganismId[match(de$Protein.IDs, sp$PG.ProteinGroups)]
  benchmarking_proteomics(de, ev, output_dir = file.path(root, nm),
                          verbose = FALSE)
}
classified_all <- import_classified_results(root)
table(classified_all$Assay, classified_all$classification)

Description

Reads benchmark_confusion_overall.tsv files from subdirectories, adding an Assay column derived from the folder name.

Usage

import_confusion_results(
  results_dir,
  pattern = "benchmark_confusion_overall\\.tsv$",
  method_names = NULL,
  recursive = TRUE
)

Arguments

Value

data.frame with columns: Assay, Comparison, N, TP, FP, TN, FN, plus percentage columns

Examples

data(nadia_dia)
sp <- utils::read.delim(system.file("extdata", "nadia_dia_spikein.tsv.gz",
                                    package = "NADIA"))
ev <- data.frame(Comparison = rep(c("B-A", "D-A"), each = 2),
                 Species = c("ECOLI", "YEAST"),
                 expected_logFC = c(1, -0.58, 2, -3.3))
root <- file.path(tempdir(), "nadia_bench")
for (nm in c("cycloess", "quantile")) {
  de <- process_proteomics(nadia_dia, norm_method = nm,
                           verbose = FALSE)$DEPs_results
  de$Species <- sp$PG.OrganismId[match(de$Protein.IDs, sp$PG.ProteinGroups)]
  benchmarking_proteomics(de, ev, output_dir = file.path(root, nm),
                          verbose = FALSE)
}
confusion_all <- import_confusion_results(root)
confusion_all[, c("Assay", "Comparison", "TP", "FP", "TN", "FN")]

Description

Reads all TSV files matching a pattern from a directory, one assay per file. Each TSV must have column 1 as protein identifier and remaining columns as sample names matching the sample_col in the metadata file.

Usage

import_imp_matrices(
  tsv_dir,
  metadata_path,
  pattern = "matrix_log2_.*\\.tsv$",
  method_names = NULL,
  condition_col = "Condition",
  sample_col = "Column"
)

Arguments

Value

A SummarizedExperiment with one assay per TSV, colData from metadata, and rowData containing Protein.IDs.

Examples

# Round trip: write the imputed matrices out, then read them back in
data(nadia_dia)
res <- process_proteomics(nadia_dia, export_dir = tempdir(),
                          export_format = "tsv", verbose = FALSE)

meta <- file.path(tempdir(), "metadata.tsv")
utils::write.table(
  data.frame(Column = res$se_proc$Column, Condition = res$se_proc$Condition,
             Replicate = res$se_proc$Replicate),
  meta, sep = "\t", row.names = FALSE, quote = FALSE)

se <- import_imp_matrices(tsv_dir = tempdir(), metadata_path = meta)
SummarizedExperiment::assayNames(se)

Description

Reads all TSV files matching a pattern from a directory, one assay per file. Each TSV must have column 1 named ProteinGroups and remaining columns as sample names matching the sample_col in the metadata file.

Usage

import_norm_matrices(
  tsv_dir,
  metadata_path,
  pattern = "matrix_log2_.*\\.tsv$",
  method_names = NULL,
  condition_col = "Condition",
  sample_col = "Column"
)

Arguments

Value

A SummarizedExperiment with one assay per TSV, colData from metadata, and rowData containing Protein.IDs.

Examples

data(nadia_dia)
se <- nm_prepare_se(nadia_dia, verbose = FALSE)
se <- nm_run_normalizations(se, methods = c("cycloess", "MAD"), verbose = FALSE)

# Write the normalized assays as TSVs, then read them back into a new SE
tsv_dir <- file.path(tempdir(), "nm_matrices")
dir.create(tsv_dir, showWarnings = FALSE)
for (a in c("cycloess", "MAD")) {
  m <- SummarizedExperiment::assay(se, a)
  utils::write.table(
    data.frame(ProteinGroups = rownames(m), m, check.names = FALSE),
    file.path(tsv_dir, paste0("matrix_log2_", a, ".tsv")),
    sep = "\t", row.names = FALSE, quote = FALSE)
}
meta_path <- file.path(tsv_dir, "metadata.tsv")
utils::write.table(as.data.frame(SummarizedExperiment::colData(se)), meta_path,
                   sep = "\t", row.names = FALSE, quote = FALSE)

se_nm <- import_norm_matrices(tsv_dir, meta_path)
SummarizedExperiment::assayNames(se_nm)