Merge pull request #93 from carpentries-incubator/timings

Updates following the EuroBioC workshop
carpentries-incubator · Oct 7, 2023 · 6a72c31 · 6a72c31
2 parents 7078373 + a0b04d1
commit 6a72c31
Show file tree

Hide file tree

Showing 5 changed files with 27 additions and 26 deletions.
diff --git a/episodes/01-intro-to-rnaseq.Rmd b/episodes/01-intro-to-rnaseq.Rmd
@@ -1,8 +1,8 @@
 ---
 source: Rmd
 title: Introduction to RNA-seq
-teaching: 45
-exercises: 30
+teaching: 65
+exercises: 35
 ---
 
 
@@ -172,7 +172,7 @@ If you are mapping your reads to the transcriptome, you will instead need a file
 
 ## Challenge
 
-Download the latest mouse transcriptome fasta file from GENCODE and uncompress it. What do the entries look like? Tip: to read the file into R, consider the `Biostrings` package.
+Download the latest mouse transcriptome fasta file from GENCODE. What do the entries look like? Tip: to read the file into R, consider the `readDNAStringSet()` function from the `Biostrings` package.
 
 ::::::::::::::::::::::::::::::::::::::::::::::::::
 

diff --git a/episodes/02-setup.Rmd b/episodes/02-setup.Rmd
@@ -2,7 +2,7 @@
 source: Rmd
 title: RStudio Project and Experimental Data
 teaching: 20
-exercises: 20
+exercises: 10
 ---
 
 :::::::::::::::::::::::::::::::::::::: questions 

diff --git a/episodes/03-import-annotate.Rmd b/episodes/03-import-annotate.Rmd
@@ -1,11 +1,11 @@
 ---
 title: "Importing and annotating quantified data into R"
 source: Rmd
-teaching: 75
+teaching: 80
 output:
   html_document:
     df_print: paged
-exercises: 30
+exercises: 40
 ---
 
 ```{r setup, echo = FALSE, message = FALSE}

diff --git a/episodes/04-exploratory-qc.Rmd b/episodes/04-exploratory-qc.Rmd
@@ -1,8 +1,8 @@
 ---
 source: Rmd
 title: Exploratory analysis and quality control
-teaching: 60
-exercises: 45
+teaching: 120
+exercises: 60
 editor_options:
   chunk_output_type: console
 ---
@@ -237,10 +237,10 @@ levels(vsd_ex$sample) <- c("sampleA", "sampleB", "sampleC",
                               "sampleD", "sampleE", "sampleF")
 vsd_ex$time <- sample(vsd_ex$time)
 
-pcaData <- DESeq2::plotPCA(vsd_ex, intgroup = c("sample", "time"),
-                           returnData = TRUE)
-percentVar <- round(100 * attr(pcaData, "percentVar"))
-ggplot(pcaData, aes(x = PC1, y = PC2)) +
+pcaDataEx <- DESeq2::plotPCA(vsd_ex, intgroup = c("sample", "time"),
+                             returnData = TRUE)
+percentVar <- round(100 * attr(pcaDataEx, "percentVar"))
+ggplot(pcaDataEx, aes(x = PC1, y = PC2)) +
     geom_point(aes(color = sample, shape = time), size = 5) +
     theme_minimal() +
     xlab(paste0("PC1: ", percentVar[1], "% variance")) +
@@ -279,30 +279,30 @@ Compare before and after variance stabilizing transformation.
 ::::::::::::::::::::::::::::::::::: solution
 
 ```{r pca-lib}
-pcaData <- DESeq2::plotPCA(vsd, intgroup = c("libSize"),
-                           returnData = TRUE)
-percentVar <- round(100 * attr(pcaData, "percentVar"))
-ggplot(pcaData, aes(x = PC1, y = PC2)) +
-    geom_point(aes(color = libSize/ 1e6), size = 5) +
+pcaDataVst <- DESeq2::plotPCA(vsd, intgroup = c("libSize"),
+                              returnData = TRUE)
+percentVar <- round(100 * attr(pcaDataVst, "percentVar"))
+ggplot(pcaDataVst, aes(x = PC1, y = PC2)) +
+    geom_point(aes(color = libSize / 1e6), size = 5) +
     theme_minimal() +
     xlab(paste0("PC1: ", percentVar[1], "% variance")) +
     ylab(paste0("PC2: ", percentVar[2], "% variance")) +
     coord_fixed() + 
-    scale_color_continuous("Total count in millions", type ="viridis")
+    scale_color_continuous("Total count in millions", type = "viridis")
 ```
 
 
 ```{r pca-lib-vst}
-pcaData <- DESeq2::plotPCA(DESeqTransform(se), intgroup = c("libSize"),
-                           returnData = TRUE)
-percentVar <- round(100 * attr(pcaData, "percentVar"))
-ggplot(pcaData, aes(x = PC1, y = PC2)) +
-    geom_point(aes(color = libSize/ 1e6), size = 5) +
+pcaDataCts <- DESeq2::plotPCA(DESeqTransform(se), intgroup = c("libSize"),
+                              returnData = TRUE)
+percentVar <- round(100 * attr(pcaDataCts, "percentVar"))
+ggplot(pcaDataCts, aes(x = PC1, y = PC2)) +
+    geom_point(aes(color = libSize / 1e6), size = 5) +
     theme_minimal() +
     xlab(paste0("PC1: ", percentVar[1], "% variance")) +
     ylab(paste0("PC2: ", percentVar[2], "% variance")) +
     coord_fixed() + 
-    scale_color_continuous("Total count in millions", type ="viridis")
+    scale_color_continuous("Total count in millions", type = "viridis")
 ```
 
 

diff --git a/learners/setup.md b/learners/setup.md
@@ -10,15 +10,16 @@ episode of the [Introduction to data analysis with R and Bioconductor](https://c
 Additionally, you will also need to install the following packages that will be used throughout the lesson. 
 
 ```r
-install.packages("BiocManager")
+install.packages(c("BiocManager", "remotes"))
 BiocManager::install(c("tidyverse", "SummarizedExperiment",
                        "ExploreModelMatrix", "AnnotationDbi", "org.Hs.eg.db", 
                        "org.Mm.eg.db", "csoneson/ConfoundingExplorer",
                        "DESeq2", "vsn", "ComplexHeatmap", "hgu95av2.db",
                        "RColorBrewer", "hexbin", "cowplot", "iSEE",
                        "clusterProfiler", "enrichplot", "kableExtra",
                        "msigdbr", "gplots", "ggplot2", "simplifyEnrichment",
-                       "apeglm", "microbenchmark", "Biostrings"))
+                       "apeglm", "microbenchmark", "Biostrings",
+                       "SingleCellExperiment"))
 
 ```