## ----setup, include = FALSE---------------------------------------------------
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.width = 7,
  fig.height = 5
)

## ----load-packages------------------------------------------------------------
library(tidymatrix)
library(dplyr)

## ----create-data--------------------------------------------------------------
set.seed(42)
n_genes <- 100
n_samples <- 20

# Create expression matrix
expression <- matrix(rnorm(n_genes * n_samples), nrow = n_genes, ncol = n_samples)

# Add structure
expression[1:30, 1:10] <- expression[1:30, 1:10] + 2
expression[31:60, 11:20] <- expression[31:60, 11:20] + 2

# Metadata
gene_data <- data.frame(
  gene_id = paste0("Gene_", 1:n_genes),
  category = rep(c("TypeA", "TypeB", "TypeC"), length.out = n_genes)
)

sample_data <- data.frame(
  sample_id = paste0("Sample_", 1:n_samples),
  condition = rep(c("Control", "Treatment"), each = 10),
  batch = rep(c("B1", "B2"), 10)
)

tm <- tidymatrix(expression, gene_data, sample_data)

## ----mds----------------------------------------------------------------------
tm_mds <- tm |>
  activate(columns) |>
  compute_mds(k = 2, name = "sample_mds")

# Check added columns
cat("MDS coordinates added:\n")
print(names(tm_mds$col_data))

# View the results
head(tm_mds$col_data)

## ----mds-object---------------------------------------------------------------
# Get full MDS result
mds_obj <- get_analysis(tm_mds, "sample_mds")
cat("MDS object components:", names(mds_obj), "\n")

## ----tsne, eval=requireNamespace("Rtsne", quietly=TRUE)-----------------------
set.seed(42)
tm_tsne <- tm |>
  activate(columns) |>
  compute_tsne(dims = 2, name = "sample_tsne", perplexity = 5, verbose = FALSE)

# View results
head(tm_tsne$col_data)

## ----tsne-params, eval=requireNamespace("Rtsne", quietly=TRUE)----------------
# Lower perplexity emphasizes local structure
set.seed(42)
tm_tsne_low <- tm |>
  activate(columns) |>
  compute_tsne(dims = 2, name = "tsne_low", perplexity = 3,
               verbose = FALSE, check_duplicates = FALSE)

# Higher perplexity preserves more global structure. Rtsne requires
# 3 * perplexity < n - 1, so with 20 samples the ceiling is 6.
set.seed(42)
tm_tsne_high <- tm |>
  activate(columns) |>
  compute_tsne(dims = 2, name = "tsne_high", perplexity = 6,
               verbose = FALSE, check_duplicates = FALSE)

cat("Different perplexity values create different embeddings\n")

## ----umap, eval=requireNamespace("umap", quietly=TRUE)------------------------
tm_umap <- tm |>
  activate(columns) |>
  compute_umap(n_components = 2, name = "sample_umap",
               n_neighbors = 10, random_state = 42)

# View results
head(tm_umap$col_data)

## ----umap-params, eval=requireNamespace("umap", quietly=TRUE)-----------------
tm_umap_custom <- tm |>
  activate(columns) |>
  compute_umap(n_components = 2, n_neighbors = 5, min_dist = 0.05,
               random_state = 42, name = "umap_tight")

cat("Custom UMAP parameters create tighter clustering\n")

## ----compare-methods----------------------------------------------------------
tm_all <- tm |>
  activate(columns) |>
  compute_mds(k = 2, name = "mds")

# Add t-SNE and UMAP if packages available
if (requireNamespace("Rtsne", quietly = TRUE)) {
  set.seed(42)
  tm_all <- tm_all |>
    compute_tsne(dims = 2, name = "tsne", perplexity = 5,
                 verbose = FALSE, check_duplicates = FALSE)
}

if (requireNamespace("umap", quietly = TRUE)) {
  tm_all <- tm_all |>
    compute_umap(n_components = 2, name = "umap",
                 n_neighbors = 10, random_state = 42)
}

# View all coordinates
head(tm_all$col_data)

## ----gene-level---------------------------------------------------------------
tm_genes <- tm |>
  activate(rows) |>
  compute_mds(k = 2, name = "gene_mds")

# Filter genes by their embedding
interesting_genes <- tm_genes |>
  activate(rows) |>
  filter(gene_mds_1 > median(gene_mds_1))

cat("Genes in right half of MDS space:", nrow(interesting_genes$matrix), "\n")

## ----multi-dim----------------------------------------------------------------
tm_3d <- tm |>
  activate(columns) |>
  compute_mds(k = 3, name = "mds3d")

# Check all three dimensions
cat("MDS columns:", grep("mds3d", names(tm_3d$col_data), value = TRUE), "\n")

## ----flatten-example, eval=FALSE----------------------------------------------
# # After computing dimensionality reduction
# tm |>
#   activate(columns) |>
#   compute_mds(k = 2) |>
#   to_long() |>
#   ggplot(aes(x = column_mds_1, y = column_mds_2, color = condition)) +
#   geom_point()