02-quality-control.Rmd

```{r, parameters-and-defaults, include = FALSE}
module <- "scRNAseq"
section <- "quality_control"
parameters_and_defaults <- list(
  assay = structure(
    "counts",
    type = "character",
    choices = NA,
    several.ok = FALSE
  ),
  control_feature_yml = structure(
    c(),
    type = "character",
    choices = NA,
    several.ok = FALSE
  ),
  control_samples_yml = structure(
    c(),
    type = "character",
    choices = NA,
    several.ok = FALSE
  ),
  features = structure(
    c("percent_mapped"),
    type = "character",
    choices = NA,
    several.ok = TRUE
  ),
  qc_tsne = structure(
    TRUE,
    type = "logical",
    choices = NA,
    several.ok = FALSE
  ),
  qc_pca = structure(
    c("irlba"),
    type = "character",
    choices = c("none", "irlba", "prcomp"),
    several.ok = FALSE
  ),
  cell_filter_yml = structure(
    "none",
    type = "character",
    choices = NA,
    several.ok = FALSE
  ),
  cell_filter_allow_n_failed = structure(
    1L,
    type = "integer",
    choices = NA,
    several.ok = FALSE
  ),
  tabulate_samples = structure(
    c(),
    type = "character",
    choices = NA,
    several.ok = FALSE
  ),
  gene_filter_yml = structure(
    "none",
    type = "character",
    choices = NA,
    several.ok = FALSE
  ),
  tabulate_features = structure(
    c(),
    type = "character",
    choices = NA,
    several.ok = FALSE
  ),
  summarize_features = structure(
    c(),
    type = "character",
    choices = NA,
    several.ok = TRUE
  ),
  summarize_samples = structure(
    c(),
    type = "character",
    choices = NA,
    several.ok = TRUE
  ),
  plot_saturation = structure(
    TRUE,
    type = "logical",
    choices = NA,
    several.ok = TRUE
  )
)
```

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

## Quality control

* **sequencing depth**: Low quality cells typically have low numbers of reads sequenced.
* **detected features**: Low quality cells typically have low numbers of detected genes.
* **dropout rates**: Low quality cells typically have high dropout-rates.
* **duplicated reads**: Low quality cells typically have high percentage of read duplication.
* **mitochondrial gene expression**: Low quality cells are typically dominated by mitochondrial genes.
* **alignment to genes**: Low number of alignments to genes might be a sign of low quality cells.
* **housekeeping gene expression**: High quality cells express housekeeping genes.

```{r scRNAseq-quality-control-A-params, echo = FALSE, include = FALSE, R.options = params}
theme_qc_pca <- ggplot2::theme(plot.background = ggplot2::element_blank(),
                                 panel.grid.major = ggplot2::element_line(size=.2, colour = "grey"),
                                 panel.grid.minor = ggplot2::element_line(size=.1, colour = "grey"),
                                 panel.border = ggplot2::element_blank(),
                                 panel.background = ggplot2::element_blank(),
                                 axis.line.x = ggplot2::element_line(size=.3),
                                 axis.line.y = ggplot2::element_line(size=.3),
                                 axis.text = ggplot2::element_text(size = 4),
                                 axis.title.y = ggplot2::element_text(size = 5, margin = ggplot2::margin(0, -2, 0, 0)),
                                 axis.title.x = ggplot2::element_text(size = 5, margin = ggplot2::margin(-2, 0, 0, 0)),
                                 legend.text = ggplot2::element_text(size = 5),
                                 legend.title = ggplot2::element_text(size = 5),
                                 plot.title = ggplot2::element_text(face="bold", color="black", size=5),
                                 legend.key.size =  grid::unit(2, "mm"),
                                 legend.margin = ggplot2::margin(b = 2),#grid::unit(-50, "mm"),
                                 legend.position = c(0,1),
                                 legend.justification = c(0,0),
                                 legend.background = ggplot2::element_rect(fill = "white"),
                                 legend.direction = "horizontal")
```

```{r scRNAseq-quality-control-A-setup, echo = FALSE, child = system.file(file.path('content', '02-quality-control-A-setup.Rmd'), package = 'ReporteR.scRNAseq', mustWork = TRUE), R.options = params, eval = TRUE}
```

```{r scRNAseq-quality-control-B-pca, echo = FALSE, child = system.file(file.path('content', '02-quality-control-B-pca.Rmd'), package = 'ReporteR.scRNAseq', mustWork = TRUE), R.options = params, eval = ifelse(exists('local_params'), local_params$qc_pca != "none", FALSE)}
```

```{r scRNAseq-quality-control-C-tsne, echo = FALSE, child = system.file(file.path('content', '02-quality-control-C-tsne.Rmd'), package = 'ReporteR.scRNAseq', mustWork = TRUE), R.options = params, eval = ifelse(exists('local_params'), local_params$qc_tsne, FALSE)}
```

```{r scRNAseq-quality-control-D-cellfiltering, echo = FALSE, child = system.file(file.path('content', '02-quality-control-D-cellfiltering.Rmd'), package = 'ReporteR.scRNAseq', mustWork = TRUE), R.options = params, eval = ifelse(exists('local_params'), local_params$cell_filter_yml != "none", FALSE)}
```

```{r scRNAseq-quality-control-E-genefiltering, echo = FALSE, child = system.file(file.path('content', '02-quality-control-E-genefiltering.Rmd'), package = 'ReporteR.scRNAseq', mustWork = TRUE), R.options = params, eval = ifelse(exists('local_params'), local_params$gene_filter_yml != "none", FALSE)}
```

```{r scRNAseq-quality-control-F-createobject, include=FALSE, echo=FALSE}
# Check presence of control cells and remove them
SummarizedExperiment::colData(object)$qc_status[SummarizedExperiment::colData(object)$is_cell_control] <- "fail"

object[SummarizedExperiment::rowData(object)$qc_status == "pass", SummarizedExperiment::colData(object)$qc_status == "pass"] %>%
  scater::calculateQCMetrics(percent_top = c(50, 100, 500), exprs_values = local_params$assay) %>%
  scater::mutate(percent_dropout = 1 - apply(SummarizedExperiment::assay(., local_params$assay), 2, function(x) mean(x > 0))) -> object_filtered
```

```{r scRNAseq-quality-control-G-saturation, echo = FALSE, child = system.file(file.path('content', '02-quality-control-G-saturation.Rmd'), package = 'ReporteR.scRNAseq', mustWork = TRUE), R.options = params, eval = ifelse(exists('local_params'), local_params$plot_saturation, FALSE)}
```

```{r scRNAseq-quality-control-Y-summary, echo = FALSE, child = system.file(file.path('content', '02-quality-control-Y-summary.Rmd'), package = 'ReporteR.scRNAseq', mustWork = TRUE), R.options = params, eval = TRUE}
```

```{r scRNAseq-quality-control-Z-appendix, echo = FALSE, include = FALSE, R.options=params}
rmd_path <- system.file(file.path('content', '02-quality-control-Z-appendix.Rmd'), package = 'ReporteR.scRNAseq', mustWork = TRUE)
md_path = ReporteR.base::make_md_path(rmd_path)
knitr::knit_child(rmd_path, output = md_path)
```

```{r scRNAseq-quality-control-terminal-cleanup, include = FALSE}
saveRDS(object = object, file = managed_objects$paths$object$path)
saveRDS(object = object_filtered, file = managed_objects$paths$object_filtered$path)

ReporteR.base::purge_nonpersistent()
```