Overview | Setup | Step 1 — Distance matrix | Choosing a distance and normalisation | Step 2 — Unconstrained ordination (PCoA) | Computing PCoA | Scree plot | Feature associations | Plotting PCoA | Basic plot — colour by group | Adding a time factor | Centroids and centroid trajectories | Confidence ellipses | Plotting alternative axes | Step 3 — Constrained ordination (CAP / db-RDA) | Plotting CAP | Step 4 — PERMANOVA | Step 5 — Beta dispersion | Plotting dispersion | Group dispersion | Time dispersion | Step 6 — t-SNE | 2D plot | 3D interactive plot | Putting it all together | Session info

Overview | Setup | Visualising prevalence shift | deltaplot() — static ggplot2 | Adjusting the smooth | Jitter and appearance | deltaplot_interactive() — plotly | Testing global shift: compute_delta() | Unpaired design — group comparison | What's in the output? | Choosing the per-peptide statistic | Aggregation and stratification | Weighting | Paired design — timepoint comparison | Forest plots | forestplot() — static ggplot2 | Diverging colours | Filtering to significant features | forestplot_interactive() — plotly | Putting it all together | Session info

Overview | Setup | Computing prevalence: compute_pop() | Unpaired design — group comparison | What's in the output? | Multiple group columns | Multiple ranks | k-of-n presence threshold | Paired design — timepoint comparison | Scatter plots | scatter_static() — ggplot2 | scatter_interactive() — plotly | Volcano plots | volcano_static() — ggplot2 | Cutoffs | BH correction | volcano_interactive() — plotly | Putting it all together | Session info

Overview | Setup | Computing alpha diversity | Basic usage: peptide-level diversity by group | What's in the output? | Multiple grouping columns | Multiple ranks | Group interactions | Selecting a metric subset | Shannon base | Presence modes | mode = "binary" (default) | mode = "threshold" | mode = "abundance" | Accessing result attributes | Visualising alpha diversity | plot_alpha() — static boxplots | All five metrics | Faceting across multiple ranks | Filtering and ordering groups | Customising appearance | Plotting the interaction table | plot_alpha_interactive() — plotly | Statistical testing | Default: Kruskal-Wallis + Wilcoxon | Global test | Pairwise comparisons | Choosing the test | p-value adjustment | Restricting to a subset of metrics | Multi-rank significance | Visualising significance | Table mode | Heatmap mode | Heatmap across metrics | Significance brackets on boxplots | Putting it all together | Session info

What this covers | Cross-sectional: one sample per subject | Longitudinal: multiple samples per subject | Key points

Overview | 1. Create a bunch of example files | 2. Inspect one file so you know what’s inside | 3. Import all files in one call | 4. Derive run_id and plate_id from sample_id | Summary

Overview | Key concepts (read first) | Cross-sectional workflow (simpler) | Longitudinal workflow (subjects with multiple samples) | Tips and gotchas | Using the built-in example

Practical Example: Optimizing the Matching Process | Step 2: Run the Optimizer | Step 3: Select Optimal Configurations | Step 4: Refit the Optimized Model

Practical Example of the Vector Matching Workflow | Step 1: Data Exploration and Initial Imbalance Assessment | Step 2: Estimation of Generalized Propensity Scores | Step 3: Calculating Common Support Region Borders | Step 4: k-Means Clustering and Matching | Step 5: Post-Matching Quality Assessment | References