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

---
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")) %>%
  dplyr::filter(sample_type == "Tumor",
                composition == "Solid Tissue") 

# Select wanted columns in metadata for merging and assign to a new object
select_metadata <- metadata %>%
  dplyr::select(Kids_First_Participant_ID,
                sample_id,
                Kids_First_Biospecimen_ID,
                short_histology,
                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"))
```

# 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::filter(Hugo_Symbol %in% c("H3F3A", "HIST1H3B") &
                  HGVSp_Short %in% c("p.K28M", "p.G35R",
                                     "p.G35V")) %>%
  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")
  ) %>%
  dplyr::select(
    -HGVSp_Short,
    -Hugo_Symbol
  ) 

# add back in samples with no evidence of these specific mutations
snv_lesions_df <- snv_lesions_df %>%
  dplyr::bind_rows(
    data.frame(
      Tumor_Sample_Barcode = setdiff(unique(snv_df$Tumor_Sample_Barcode),
                                     snv_lesions_df$Tumor_Sample_Barcode)
    )
  ) %>%
  dplyr::mutate_all(function(x) tidyr::replace_na(x, "No"))

# Join the selected variables from the metadata with the snv consensus mutation
# and defining lesions data.frame
snv_lesions_df <- select_metadata %>%
  dplyr::inner_join(snv_lesions_df,
                    by = c("Kids_First_Biospecimen_ID" = "Tumor_Sample_Barcode")) %>%
  dplyr::select(
    dplyr::ends_with("ID"),
    dplyr::starts_with("H"),
    short_histology,
    disease_type_new
  ) %>%
  dplyr::mutate(
    disease_type_reclassified = dplyr::case_when(
      H3F3A.K28M == "Yes" ~ "High-grade glioma, H3 K28 mutant",
        HIST1H3B.K28M == "Yes" ~ "High-grade glioma, H3 K28 mutant",
        H3F3A.G35R == "Yes" ~ "High-grade glioma, H3 G35 mutant",
        H3F3A.G35V == "Yes" ~ "High-grade glioma, H3 G35 mutant",
      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 with the specified mutations that were not classified
# as HGG or DIPG
snv_lesions_df %>%
  dplyr::filter(
    grepl("High-grade glioma", disease_type_reclassified) &
      !(disease_type_new %in% c("High-grade glioma", 
                                "Brainstem glioma- Diffuse intrinsic pontine glioma"))
  )
```

# Session Info

```{r}
# Print the session information
sessionInfo()
```