2_pancreas_get_SpatialExperiment.Rmd

---
title: "ABACBS EMCR Hackathon - 2. Summarise MoleculeExperiments and predict cell types"
author: "Shila Ghazanfar"
date: "`r format(Sys.time(), '%d %B, %Y')`"
output:
       html_document:
                     toc: true
                     toc_float:
                           collapsed: false
                           smooth_scroll: false
                     code_folding: hide
                     fig_width: 10 
                     fig_height: 8
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE,
                      warning = FALSE,
                      message = FALSE,
                      cache = FALSE,
                      cache.lazy = FALSE)

set.seed(2024)
```

# Load packages and data
Load scripts and packages. Load the processed data we generated earlier.

```{r}
library(MoleculeExperiment) # for data structure
library(SpatialExperiment) # for data structure
library(randomForest) # for predictive model
library(scater) # for plotting
library(patchwork) # for plotting
```

```{r}
pancreas_colours = readRDS("../analysisOutput/pancreas_colours.Rds")
fit = readRDS("../analysisOutput/sc_cell_type_RF_fit.Rds")
feats = rownames(fit$importance)
me = readRDS("../processedData/xenium_pancreas_me.Rds")
me
```

In this document we take the MoleculeExperiment object, summarise to 
SpatialExperiment and perform cell type prediction on both assays.

# Count molecules over boundaries

We use the `countMolecules` function to count the molecules over the bounaries
for either cells or tiles. This generates SpatialExperiment objects with 
different numbers of cells/tiles.

We also perform filtering and logcount normalisation.

```{r}
spe_cells = countMolecules(me, boundariesAssay = "cell")[feats,]
spe_tiles = countMolecules(me, boundariesAssay = "tiles")[feats,]

spe_cells = addPerCellQCMetrics(spe_cells)
spe_tiles = addPerCellQCMetrics(spe_tiles)

spe_cells = logNormCounts(spe_cells[, spe_cells$total >= 5])
spe_tiles = logNormCounts(spe_tiles[, spe_tiles$total >= 5])

spe_cells
spe_tiles
```

# Predict cell types

```{r}
pred_cells = predict(fit, newdata = as.matrix(t(assay(spe_cells, "logcounts"))))
spe_cells$cell_type_pred <- pred_cells

pred_tiles = predict(fit, newdata = as.matrix(t(assay(spe_tiles, "logcounts"))))
spe_tiles$cell_type_pred <- pred_tiles
```

# Plots

Generate plots of cells/tiles in space coloured by predicted cell type

```{r, fig.width = 15, fig.height = 20}
g = plotReducedDim(spe_cells, "spatial",
                   colour_by = "cell_type_pred", point_size = 0.5) + 
  ggtitle("cells") +
  scale_colour_manual(values = pancreas_colours) +
  coord_fixed() +
  plotReducedDim(spe_tiles, "spatial",
                 colour_by = "cell_type_pred", point_size = 0.5) + 
  ggtitle("tiles") + 
  scale_colour_manual(values = pancreas_colours) + 
  coord_fixed() +
  plot_layout(nrow = 2) +
  NULL
g
```

# Save the objects

We save the two SpatialExperiment objects in the `../ProcessedData/` folder.

```{r}
saveRDS(spe_cells, file = "../processedData/xenium_pancreas_spe_cells.Rds")
saveRDS(spe_tiles, file = "../processedData/xenium_pancreas_spe_tiles.Rds")
```

# Finish

```{r}
sessionInfo()
```