## ----setup, include=FALSE-----------------------------------------------------
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  message = FALSE,
  warning = FALSE
)

## ----session-info, eval=FALSE-------------------------------------------------
# if (!requireNamespace("BiocManager", quietly = TRUE))
#   install.packages("BiocManager")
# BiocManager::install("RFGeneRank")

## ----package-overview---------------------------------------------------------
suppressPackageStartupMessages({
  library(RFGeneRank)
  library(SummarizedExperiment)
  library(S4Vectors)
})

set.seed(42)

n_genes <- 300
n_samples <- 60

genes   <- paste0("Gene", seq_len(n_genes))
samples <- paste0("Sample", seq_len(n_samples))

# Sample metadata (rows must match sample names)
meta_df <- data.frame(
  state = factor(rep(c("CTRL","CASE"), each = n_samples/2), levels = c("CTRL","CASE")),
  batch = factor(rep(c("B1","B2"), length.out = n_samples)),
  sex   = factor(rep(c("M","F"), length.out = n_samples)),
  age   = round(stats::runif(n_samples, 25, 65)),
  stringsAsFactors = FALSE,
  check.names = TRUE
)

# Transcriptomics-like expression: strictly positive values (log-normal)
expr <- matrix(
  exp(rnorm(n_genes * n_samples, mean = 2.5, sd = 0.6)),
  nrow = n_genes, ncol = n_samples,
  dimnames = list(genes, samples)
)

# Inject signal in CASE for a subset of genes
signal_genes <- genes[1:25]
case_cols <- meta_df$state == "CASE"
expr[signal_genes, case_cols] <- expr[signal_genes, case_cols] * 1.8

# Critical alignment: metadata rownames must match expression colnames
rownames(meta_df) <- colnames(expr)
stopifnot(identical(colnames(expr), rownames(meta_df)))

# Build SummarizedExperiment
se <- SummarizedExperiment(
  assays  = list(expr = expr),
  colData = DataFrame(meta_df)
)

se

## ----simulate-expression------------------------------------------------------
# Detect whether the matrix is count-like (integer); our simulated data are continuous.
is_integerish <- function(x) all(abs(x - round(x)) < 1e-8, na.rm = TRUE)
counts_flag <- is_integerish(expr)

se_prep <- prepare_data(
  mats   = list(SummarizedExperiment::assay(se, "expr")),
  metas  = list(meta_df),   # use data.frame for robustness in vignettes
  label_col  = "state",
  batch_col  = "batch",
  log1p      = counts_flag,
  batch_method = "combat",
  batch_correction_scope = "global"
)

se_prep

## ----build-se-----------------------------------------------------------------
cw <- c(CTRL = 1, CASE = 2)

fit <- rank_genes(
  se_prep,
  label_col = "state",
  cv = "kfold", k = 3,
  n_top = 100,
  trees = 300,
  fold_batch_correction = FALSE,
  batch_col = "batch",
  class_weights = cw,
  auto_confounds = FALSE,
  seed = 42
)

fit

## ----run-rank-genes-----------------------------------------------------------
top_genes(fit, n = 10)

## ----inspect-fit--------------------------------------------------------------
tab_signed <- sign_importance(
  fit, se_prep,
  y = SummarizedExperiment::colData(se_prep)[["state"]],
  method = "mean"
)

head(tab_signed, 10)

## ----plotting-example---------------------------------------------------------
plot_importance(
  fit,
  top = 20,
  map_to_symbol = FALSE
)

plot_roc(fit)

plot_sign_importance(
  fit,
  tab = tab_signed,
  top = 20
)

## ----session------------------------------------------------------------------
sessionInfo()