PR 1 of n: Molecular Subtyping - HGG (Defining Lesions)

.circleci/config.yml

@@ -99,6 +99,10 @@ jobs:
       - run:
           name: Process SV file
           command: ./scripts/run_in_ci.sh Rscript analyses/sv-analysis/01-process-sv-file.R
+
+      - run:
+          name: Molecular Subtyping - HGG
+          command: ./scripts/run_in_ci.sh Rscript -e "rmarkdown::render('analyses/molecular-subtyping-HGG/01-HGG-molecular-subtyping-defining-lesions.Rmd', clean = TRUE)"
 
       - run:
           name: Oncoprint plotting

analyses/molecular-subtyping-HGG/01-HGG-molecular-subtyping-defining-lesions.Rmd

@@ -0,0 +1,169 @@
+---
+title: "High-Grade Glioma Molecular Subtyping - Defining Lesions"
+output: 
+  html_notebook:
+    toc: TRUE
+    toc_float: TRUE
+author: Chante Bethell for ALSF CCDL
+date: 2019
+---
+
+This notebook looks at the defining lesions for all samples for the issue of 
+molecular subtyping high-grade glioma samples in the OpenPBTA dataset. 
+
+# Usage
+
+This notebook is intended to be run via the command line from the top directory
+of the repository as follows:
+
+`Rscript -e "rmarkdown::render('analyses/molecular-subtyping-HGG/01-HGG-molecular-subtyping-defining-lesions.Rmd', clean = TRUE)"`
+
+# Set Up
+
+```{r}
+# Get `magrittr` pipe
+`%>%` <- dplyr::`%>%`
+```
+
+## Directories and Files
+
+```{r}
+# Detect the ".git" folder -- this will in the project root directory.
+# Use this as the root directory to ensure proper sourcing of functions no
+# matter where this is called from
+root_dir <- rprojroot::find_root(rprojroot::has_dir(".git"))
+
+# File path to results directory
+results_dir <-
+  file.path(root_dir, "analyses", "molecular-subtyping-HGG", "results")
+
+if (!dir.exists(results_dir)) {
+  dir.create(results_dir)
+}
+
+# Read in metadata
+metadata <-
+  readr::read_tsv(file.path(root_dir, "data", "pbta-histologies.tsv"))
+
+# Select wanted columns in metadata for merging and assign to a new object
+select_metadata <- metadata %>%
+  dplyr::select(sample_id,
+                Kids_First_Participant_ID,
+                Kids_First_Biospecimen_ID,
+                disease_type_new)
+
+# Read in snv consensus mutation data
+snv_df <-
+  data.table::fread(file.path(root_dir,
+                              "data",
+                              "pbta-snv-consensus-mutation.maf.tsv.gz"))
+```
+
+## Custom Function
+
+```{r}
+# Custom datatable function
+# Function code adapted from: https://github.com/AlexsLemonade/OpenPBTA-analysis/blob/49acc98f5ffd86853fc70f220623311e13e3ca9f/analyses/collapse-rnaseq/02-analyze-drops.Rmd#L23
+viewDataTable <- function(data) {
+  DT::datatable(
+    data,
+    rownames = FALSE,
+    filter = "bottom",
+    class = "cell-border stripe",
+    options = list(
+      pageLength = 5,
+      searchHighlight = TRUE,
+      scrollX = TRUE,
+      dom = "tpi",
+      initComplete = htmlwidgets::JS(
+        "function(settings, json) {",
+        "$(this.api().table().header()).css({'background-color':
+                                            '#004467', 'color': '#fff'});",
+        "}"
+      )
+    )
+  )
+}
+```
+
+# Prepare Data 
+
+## SNV consensus mutation data - defining lesions
+
+```{r}
+# Filter the snv consensus mutatation data for the target lesions
+snv_lesions_df <- snv_df %>%
+  dplyr::select(Tumor_Sample_Barcode, Hugo_Symbol, HGVSp_Short) %>%
+  dplyr::mutate(
+    H3F3A.K28M = dplyr::case_when(Hugo_Symbol == "H3F3A" &
+                                    HGVSp_Short == "p.K28M" ~ "Yes",
+                                  TRUE ~ "No"),
+    HIST1H3B.K28M = dplyr::case_when(
+      Hugo_Symbol == "HIST1H3B" & HGVSp_Short == "p.K28M" ~ "Yes",
+      TRUE ~ "No"
+    ),
+    H3F3A.G35R = dplyr::case_when(Hugo_Symbol == "H3F3A" &
+                                    HGVSp_Short == "p.G35R" ~ "Yes",
+                                  TRUE ~ "No"),
+    H3F3A.G35V = dplyr::case_when(Hugo_Symbol == "H3F3A" &
+                                    HGVSp_Short == "p.G35V" ~ "Yes",
+                                  TRUE ~ "No")
+  )
+
+# Join the selected variables from the metadata with the snv consensus mutation
+# and defining lesions data.frame
+snv_lesions_df <- snv_lesions_df %>%
+  dplyr::left_join(select_metadata,
+                   by = c("Tumor_Sample_Barcode" = "Kids_First_Biospecimen_ID")) %>%
+  dplyr::select(
+    Kids_First_Participant_ID,
+    sample_id,
+    Kids_First_Biospecimen_ID = Tumor_Sample_Barcode,
+    dplyr::everything(),
+    -HGVSp_Short,
+    -Hugo_Symbol
+  ) %>%
+  dplyr::distinct() %>%
+  dplyr::mutate(
+    disease_type_reclassified = dplyr::case_when(
+      H3F3A.K28M == "Yes" |
+        HIST1H3B.K28M == "Yes" |
+        H3F3A.G35R == "Yes" |
+        H3F3A.G35V == "Yes" ~ "High-grade glioma",
+      TRUE ~ as.character(disease_type_new)
+    )
+  )
+
+# Display `snv_lesions_df`
+snv_lesions_df 
+```
+
+## Save final table of results
+
+```{r}
+# Save final data.frame to file
+readr::write_tsv(snv_lesions_df,
+                 file.path(results_dir, "HGG_defining_lesions.tsv"))
+```
+
+## Inconsistencies in disease classification
+
+```{r}
+# Isolate the samples that should be reclassified as HGG
+hgg_samples <- snv_lesions_df %>%
+  dplyr::filter(
+    disease_type_reclassified == "High-grade glioma" &
+      disease_type_new != "High-grade glioma;astrocytoma (WHO grade III/IV)"
+  )
+
+# Display the reclassified samples
+viewDataTable(hgg_samples)
+```
+
+# Session Info
+
+```{r}
+# Print the session information
+sessionInfo()
+```
+