From f157feb1fd587431028f2781f4a7f2cdd6e05a74 Mon Sep 17 00:00:00 2001
From: Kevin Rue-Albrecht <kevinrue67@gmail.com>
Date: Mon, 29 Jul 2024 11:31:42 +0100
Subject: [PATCH] load and preprocess airway data set

---
 DESCRIPTION                           |  5 +++--
 vignettes/workshop_isee_extension.Rmd | 32 ++++++++++++++++++++++++++-
 2 files changed, 34 insertions(+), 3 deletions(-)

diff --git a/DESCRIPTION b/DESCRIPTION
index c438aba..0310586 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -41,10 +41,11 @@ Imports:
     iSEEu
 Suggests:
     airway,
+    BiocStyle,
     knitr,
-    rmarkdown,
+    org.Hs.eg.db,
     pkgdown,
-    BiocStyle,
+    rmarkdown,
     scRNAseq,
     scater
 URL: https://isee.github.io/iSEEDemoEuroBioC2024/
diff --git a/vignettes/workshop_isee_extension.Rmd b/vignettes/workshop_isee_extension.Rmd
index d63b374..054b84d 100644
--- a/vignettes/workshop_isee_extension.Rmd
+++ b/vignettes/workshop_isee_extension.Rmd
@@ -343,12 +343,42 @@ In the next 10 minutes, we will:
 
 The `r BiocStyle::Biocpkg("iSEEpathways")` vignette [Integration with other panels](https://isee.github.io/iSEEpathways/articles/integration.html) can also be accessed locally using the R code `vignette("integration", package = "iSEEpathways")`.
 
-In this part, we load the 
+In this part, we load the `r BiocStyle::Biocexptpkg("airway")` package, providing a `RangedSummarizedExperiment` object for RNA-Seq in airway smooth muscle cells.
 
 ```{r}
 library(airway)
+data(airway)
+airway
 ```
 
+We quickly reorder the levels of the dexamethasone treatment, ensuring that the untreated level is first, and used as reference level during the upcoming differential expression analysis.
+
+```{r}
+airway$dex <- relevel(airway$dex, "untrt")
+```
+
+We also take a minute to convert rownames to more recognisable gene symbols using the annotation package `r BiocStyle::Biocannopkg("org.Hs.eg.db")`.
+
+To avoid losing any information, we store a copy of the original Ensembl gene identifiers and the corresponding gene symbols in the row metadata.
+
+To make sure that rownames are unique, we use the `r BiocStyle::Biocpkg("scater")` function `uniquifyFeatureNames()`.
+The function uses the gene symbol if unique; otherwise it combines it with the Ensembl gene identifier to make it unique.
+
+```{r}
+library("org.Hs.eg.db")
+library("scater")
+rowData(airway)[["ENSEMBL"]] <- rownames(airway)
+rowData(airway)[["SYMBOL"]] <- mapIds(org.Hs.eg.db, rownames(airway), "SYMBOL", "ENSEMBL")
+rowData(airway)[["uniquifyFeatureNames"]] <- uniquifyFeatureNames(
+  ID = rowData(airway)[["ENSEMBL"]],
+  names = rowData(airway)[["SYMBOL"]]
+)
+rownames(airway) <- rowData(airway)[["uniquifyFeatureNames"]]
+```
+
+
+
+
 
 Plan: