edits

Author: mblue9

vignettes/solutions.Rmd

@@ -14,46 +14,42 @@ library(plotly)
 library(dplyr)
 library(colorspace)
 library(dittoSeq)
+library(tidySingleCellExperiment)
+
+sce_obj <- bioc2022tidytranscriptomics::sce_obj
 ```
 
 ## Question 1
 
-What is the proportion of gamma-delta T cells, among all cells? Use signature_score > 0.8 to identify gamma-delta T cells.
-
-```{r, eval=FALSE}
+What proportion of all cells are gamma-delta T cells? Use signature_score > 0.7 to identify gamma-delta T cells.
 
-seurat_obj |>
-  
+```{r}
+sce_obj |>
   
   join_features(
     features = c("CD3D", "TRDC", "TRGC1", "TRGC2", "CD8A", "CD8B"),
-    shape = "wide",
-    assay = "SCT"
-    
+    shape = "wide"
   ) |>
   
   mutate(signature_score =
-           scales::rescale(CD3D + TRDC + TRGC1+ TRGC2, to=c(0,1)) -
+           scales::rescale(CD3D + TRDC + TRGC1 + TRGC2, to=c(0,1)) -
            scales::rescale(CD8A + CD8B, to=c(0,1))
   ) |>
 
-  mutate(is_gamma-delta = signature_score > 0.8) |>
+  mutate(gamma_delta = signature_score > 0.7) |>
   
-  count(is_gamma-delta) %>% 
+  count(gamma_delta) |> 
   summarise(proportion = n/sum(n))
-
 ```
 
 ## Question 2
 
-There is a cluster of cells characterised by a low RNA output (nCount_RNA < 100). Identify the cell composition (curated_cell_type) of that cluster.
-
+There is a cluster of cells characterised by a low RNA output (nCount_RNA < 100). Identify the cell composition (cell_type) of that cluster.
 
-```{r, eval=FALSE}
 
-seurat_obj |>
+```{r}
+sce_obj |>
     filter(nCount_RNA < 100) %>% 
-    count(curated_cell_type)
-
+    count(cell_type)
 ```
 

vignettes/supplementary.Rmd

@@ -13,23 +13,27 @@ knitr::opts_chunk$set(echo = TRUE)
 
 
 ```{r message = FALSE}
+library(batchelor)
+library(igraph)
+library(scran)
+library(magrittr)
 library(ggplot2)
 library(plotly)
 library(dplyr)
 library(colorspace)
 library(dittoSeq)
 library(tidySingleCellExperiment)
 library(tidygate)
-```
 
+sce_obj <- bioc2022tidytranscriptomics::sce_obj
+```
 
-The gamma delta T cells (the blue cluster on the left with high signature score) could be interactively selected from the plot using the tidygate package.
 
-```{r eval=FALSE}
+Instead of filtering using a specified threshold, the gamma delta T cells could be interactively selected from the plot using the tidygate package.
 
+```{r eval = FALSE}
 sce_obj |>
 
-
   join_features(
     features = c("CD3D", "TRDC", "TRGC1", "TRGC2", "CD8A", "CD8B" ), shape = "wide"
   ) |>
@@ -47,10 +51,9 @@ sce_obj |>
 
 ```
 
-After the selection we can reload from file the gate drawn for reproducibility.
-
-```{r eval=FALSE}
+After the selection we could reload from a file the gate that was drawn, for reproducibility.
 
+```{r}
 sce_obj |>
 
   join_features(
@@ -72,12 +75,12 @@ sce_obj |>
 
 ```
 
-And the dataset could be filtered for just these cells using tidyverse `filter`.
-
-```{r eval=FALSE}
-
-sce_obj |>
+The dataset can be filtered for just these cells using tidyverse `filter`.
 
+```{r}
+sce_obj_gamma_delta <-
+    
+  sce_obj |>
 
   join_features(
     features = c("CD3D", "TRDC", "TRGC1", "TRGC2", "CD8A", "CD8B" ), shape = "wide"
@@ -94,68 +97,24 @@ sce_obj |>
   filter(gate == 1)
 ```
 
-It was then possible to perform analyses on these gamma delta T cells by simply chaining further commands, such as below.
+For comparison, we show the alternative using base R and SingleCellExperiment.
 
-```{r eval = FALSE}
-
-sce_obj |>
-
-
-  join_features(
-    features = c("CD3D", "TRDC", "TRGC1", "TRGC2", "CD8A", "CD8B"),   shape = "wide"
-
-  ) |>
-
-  mutate(signature_score =
-           scales::rescale(CD3D + TRDC + TRGC1+ TRGC2, to=c(0,1)) -
-           scales::rescale(CD8A + CD8B, to=c(0,1))
-  ) |>
-
-  mutate( gate = gate_int(UMAP_1, UMAP_2, gate_list = bioc2022tidytranscriptomics::gate_sce_obj) ) |>
-
-  filter(gate == 1) |>
-
-  # Reanalyse
-  NormalizeData(assay="RNA") |>
-  FindVariableFeatures( nfeatures = 100, assay="RNA") |>
-  SplitObject(split.by = "file") |>
-  RunFastMNN(assay="RNA") |>
-  RunUMAP(reduction = "mnn", dims = 1:20) |>
-  FindNeighbors( dims = 1:20, reduction = "mnn") |>
-  FindClusters( resolution = 0.3)
-```
-
-For comparison, we show the alternative using base R and SingleCellExperiment
-
-```{r eval = FALSE}
-
-counts_positive =
-  GetAssayData(sce_obj, assay="SCT")[c("CD3D", "TRDC", "TRGC1", "TRGC2"),] |>
+```{r}
+counts_positive <-
+  assay(sce_obj)[c("CD3D", "TRDC", "TRGC1", "TRGC2"),] |>
   colSums() |>
   scales::rescale(to=c(0,1))
 
-counts_negative =
-  GetAssayData(sce_obj, assay="SCT")[c("CD8A", "CD8B"),] |>
+counts_negative <-
+  assay(sce_obj)[c("CD8A", "CD8B"),] |>
   colSums()  |>
   scales::rescale(to=c(0,1))
 
-sce_obj$signature_score = counts_positive - counts_negative
-
-p = FeaturePlot(sce_obj, features = "signature_score")
+sce_obj$signature_score <- counts_positive - counts_negative
 
 # This is not reproducible (in contrast to tidygate)
-sce_obj$within_gate = colnames(sce_obj) %in% CellSelector(plot = p)
+sce_obj$within_gate <- colnames(sce_obj) %in% CellSelector(plot = p)
 
-sce_obj |>
-  subset(within_gate == TRUE) |>
-
-  # Reanalyse
-  NormalizeData(assay="RNA") |>
-  FindVariableFeatures( nfeatures = 100, assay="RNA") |>
-  SplitObject(split.by = "file") |>
-  RunFastMNN(assay="RNA") |>
-  RunUMAP(reduction = "mnn", dims = 1:20) |>
-  FindNeighbors( dims = 1:20, reduction = "mnn") |>
-  FindClusters( resolution = 0.3)
+sce_obj_gamma_delta <- sce_obj[, sce_obj$within_gate == TRUE]
 ```