03-normalization-A-sumfactors.Rmd

```{r parameters-and-defaults, include = FALSE}
module <- "scRNAseq"
section <- "normalization"
```

```{r parameter-merge, include = FALSE}
local_params <- module %>%
  options() %>%
  magrittr::extract2(module) %>%
  magrittr::extract2(section) %>%
  ReporteR.base::validate_params(parameters_and_defaults)
```

```{r scRNAseq-normalization-A-sumfactors-checks, include = FALSE, echo = FALSE}
num_figure_rows <- 3
assertive.sets::assert_is_subset(local_params$features, colnames(SummarizedExperiment::colData(object_filtered)))
if (assertive.properties::is_empty(local_params$features)) {
  local_params$features <- c(NULL)
  num_figure_rows <- 2
}


if (assertive.properties::is_non_empty(local_params$batch)) {
  assertive.sets::assert_is_subset(local_params$batch, colnames(SummarizedExperiment::colData(object_filtered)))
  batch = droplevels(as.factor(SummarizedExperiment::colData(object_filtered)[, local_params$batch]))
  cellcount <- table(batch)
} else {
  batch = NULL
  cellcount <- dim(object_filtered)[2]
}

assertive.numbers::assert_all_are_greater_than(min(cellcount), 15)
```

### Sumfactor normalization

```{r scRNAseq-normalization-A-sumfactors-processing, include = FALSE, echo = FALSE}
# Calculate senseful sizes for normalization
max_size <- max(ceiling( 2 * sqrt(min(cellcount))), 150)
step <- floor( 1/2 * sqrt(min(cellcount)))

if (min(cellcount) < 50) {
  sizes <- 5:max_size * step
} else {
  sizes <- 4:max_size * step
}

object_filtered <- scran::computeSumFactors(object_filtered, clusters = batch, sizes = sizes)

assertive.numbers::assert_all_are_non_negative(SingleCellExperiment::sizeFactors(object_filtered))  

object_filtered <- scater::normalize(object_filtered)
SummarizedExperiment::assay(object_filtered, "norm_sumfactor") <- SummarizedExperiment::assay(object_filtered, "logcounts")

# Reset logcounts
SummarizedExperiment::assay(object_filtered, "logcounts") <- log2(SummarizedExperiment::assay(object_filtered, "counts") + 1)
```

Here, we apply a novel approach [@lun_pooling_2016] where normalization is performed on pooled counts for multiple cells, where the incidence of problematic zeroes is reduced by summing across cells. Expression values are summed across pools of cells of different sizes, and the summed values are used for normalization. The pool-based size factors are then deconvolved to infer the size factors for the individual cells without the need of spike-ins. The deconvolution approach was shown to outperform existing methods for accurate normalization of cell-specific biases in simulated data. Similar behavior is observed in real data, where deconvolution improves the relevance of results of downstream analyses [@lun_pooling_2016]. Figure \@ref(fig:scRNAseq-normalization-A-sumfactors-figure) depicts effects of the normalization strategy. 

```{r scRNAseq-normalization-A-sumfactors-figure-params, include = FALSE, echo = FALSE}
fig_height <- ReporteR.base::estimate_figure_height(
  height_in_panels = num_figure_rows,
  panel_height_in_in = params$formatting_defaults$figures$panel_height_in,
  axis_space_in_in = params$formatting_defaults$figures$axis_space_in,
  mpf_row_space = as.numeric(grid::convertUnit(grid::unit(5, 'mm'), 'in')),
  max_height_in_in = params$formatting_defaults$figures$max_height_in)
```

```{r scRNAseq-normalization-A-sumfactors-figure, echo = FALSE, message=FALSE, warning=FALSE, fig.height = fig_height$global, fig.cap = paste("Results of sumfactor normalization.", caption_norm_pca, ifelse(num_figure_rows == 3, caption_norm_pca_extra, ""))}
figure_normalization_sumfactors <- multipanelfigure::multi_panel_figure(height = fig_height$sub, columns = 3, rows = num_figure_rows, unit = "in")

# Based on raw counts
figure_normalization_sumfactors <- multipanelfigure::fill_panel(figure_normalization_sumfactors,
                                                                scater::plotPCASCE(object_filtered, ntop = 10, exprs_values = "logcounts", colour_by = local_params$features[1], add_ticks = FALSE) +
                                                                  theme_norm_pca)
figure_normalization_sumfactors <- multipanelfigure::fill_panel(figure_normalization_sumfactors,
                                                                scater::plotExplanatoryVariables(object_filtered, exprs_values = "logcounts", variables = local_params$features) +
                                                                  theme_norm_pca,
                                                                column = 2:3)

# Based on normalized values
figure_normalization_sumfactors <- multipanelfigure::fill_panel(figure_normalization_sumfactors,
                                                                scater::plotPCASCE(object_filtered, ntop = 10, exprs_values = "norm_sumfactor", colour_by = local_params$features[1], add_ticks = FALSE) +
                                                                  ggplot2::guides(colour = FALSE) +
                                                                  theme_norm_pca)
figure_normalization_sumfactors <- multipanelfigure::fill_panel(figure_normalization_sumfactors,
                                                                scater::plotExplanatoryVariables(object_filtered, exprs_values = "norm_sumfactor", variables = local_params$features) +
                                                                  theme_norm_pca,
                                                                column = 2:3)

# Additional panels for first three variables
if(num_figure_rows == 3) {
  for(i in 1:min(3, length(local_params$features))) {
    figure_normalization_sumfactors <- multipanelfigure::fill_panel(figure_normalization_sumfactors,
                                                                    scater::plotPCASCE(object_filtered, ntop = 10, exprs_values = "norm_sumfactor", colour_by = local_params$features[i], add_ticks = FALSE) + 
                                                                      ggplot2::guides(colour = FALSE) +
                                                                      theme_norm_pca)
  }
}

figure_normalization_sumfactors

```