## ----setup, include = FALSE---------------------------------------------------
knitr::opts_chunk$set(echo = TRUE, message = FALSE, warning = FALSE)

## ----simulate-----------------------------------------------------------------
library(prolfqua)
library(ggplot2)
sim <- sim_lfq_data_protein_config(Nprot = 100, weight_missing = 0.5, seed = 1234)
lfq <- LFQData$new(sim$data, sim$config)

wide <- lfq$data_wide(as.matrix = TRUE)$data
empty_group <- lfq$data_long() |>
  dplyr::group_by(protein_Id, group_) |>
  dplyr::summarise(empty = all(is.na(abundance)), .groups = "drop") |>
  dplyr::filter(empty)
c(
  proteins = nrow(wide),
  complete = sum(stats::complete.cases(wide)),
  with_empty_group = dplyr::n_distinct(empty_group$protein_Id)
)

## ----emptyGroups--------------------------------------------------------------
lfq$data_long() |>
  dplyr::filter(protein_Id %in% empty_group$protein_Id) |>
  dplyr::select(protein_Id, sampleName, abundance) |>
  tidyr::pivot_wider(names_from = sampleName, values_from = abundance) |>
  knitr::kable(digits = 1)

## ----fill---------------------------------------------------------------------
contrasts <- c(AvsC = "group_A - group_Ctrl", BvsC = "group_B - group_Ctrl")
fa <- build_contrast_analysis(lfq, "~ group_", contrasts, method = "lm_impute")
filled <- impute_from_model(fa$model, lfq)
table(filled$summary$route)

## ----lod----------------------------------------------------------------------
MissingHelpers$new(lfq$data_long(), lfq$get_config())$get_lod()

## ----filledCells--------------------------------------------------------------
filled$lfqdata$data_long() |>
  dplyr::filter(protein_Id %in% empty_group$protein_Id) |>
  dplyr::select(protein_Id, sampleName, abundance) |>
  tidyr::pivot_wider(names_from = sampleName, values_from = abundance) |>
  knitr::kable(digits = 1)

## ----heatmapOrder-------------------------------------------------------------
before <- lfq$data_wide(as.matrix = TRUE)
after <- filled$lfqdata$data_wide(as.matrix = TRUE)
row_order <- rownames(after$data)[hclust(dist(t(scale(t(after$data)))))$order]

## ----heatmapBefore, fig.cap = "Before imputation: missing cells are grey."----
ht_before <- plot_heatmap(
  before$data, before$annotation, lfq$factor_keys(), lfq$sample_name(),
  na_fraction = 1, row_order = row_order
)
ht_before

## ----heatmapAfter, fig.cap = "After imputation: every cell holds a value."----
ht_after <- plot_heatmap(
  after$data, after$annotation, lfq$factor_keys(), lfq$sample_name(),
  na_fraction = 1, row_order = row_order
)
ht_after

## ----pca, fig.cap = "PCA before (top) and after (bottom) imputation.", fig.height = 8----
n_complete <- sum(filled$summary$route == "complete")
gridExtra::grid.arrange(
  lfq$get_Plotter()$pca() +
    ggtitle(paste0("Before imputation: ", n_complete, " complete proteins")),
  filled$lfqdata$get_Plotter()$pca() +
    ggtitle(paste0("After imputation: ", nrow(filled$summary), " proteins")),
  ncol = 1
)

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