---
title: "TCGAbiolinks: Searching, downloading and visualizing mutation files"
date: "`r BiocStyle::doc_date()`"
vignette: >
  %\VignetteIndexEntry{"5. Mutation data"}
  %\VignetteEngine{knitr::rmarkdown}
  %\VignetteEncoding{UTF-8}
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
knitr::opts_knit$set(progress = FALSE)
```

```{r message=FALSE, warning=FALSE, include=FALSE}
library(TCGAbiolinks)
library(SummarizedExperiment)
library(dplyr)
library(DT)
```


# Search and Download

**TCGAbiolinks** has provided a few functions to download mutation data from GDC.
There are two options to download the data:

1. Use `GDCquery_Maf` which will download MAF aligned against hg38
2. Use `GDCquery`, `GDCdownload` and `GDCpreprare` to download MAF aligned against hg19
3. Use `getMC3MAF()`, to download MC3 MAF from  https://gdc.cancer.gov/about-data/publications/mc3-2017

## Mutation data (hg38)

This example will download MAF (mutation annotation files) for variant calling pipeline muse.
Pipelines options are: `muse`, `varscan2`, `somaticsniper`, `mutect`. For more information please access
[GDC docs](https://docs.gdc.cancer.gov/Data/Bioinformatics_Pipelines/DNA_Seq_Variant_Calling_Pipeline/).

```{r results = 'hide', echo=TRUE, message=FALSE, warning=FALSE,eval=F}
maf <- GDCquery_Maf("CHOL", pipelines = "muse")
```
```{r results = 'hide', echo=TRUE, message=FALSE, warning=FALSE,eval=T,include=F}
maf <- chol_maf@data
```

```{r  echo = TRUE, message = FALSE, warning = FALSE}
# Only first 50 to make render faster
datatable(maf[1:20,],
          filter = 'top',
          options = list(scrollX = TRUE, keys = TRUE, pageLength = 5), 
          rownames = FALSE)
```

## Mutation data (hg19)

This example will download MAF (mutation annotation files) aligned against hg19 (Old TCGA maf files)


```{r results = 'hide', echo=TRUE, message=FALSE, warning=FALSE}
query.maf.hg19 <- GDCquery(project = "TCGA-CHOL", 
                           data.category = "Simple nucleotide variation", 
                           data.type = "Simple somatic mutation",
                           access = "open", 
                           legacy = TRUE)
```
```{r  echo = TRUE, message = FALSE, warning = FALSE}
# Check maf availables
datatable(dplyr::select(getResults(query.maf.hg19),-contains("cases")),
          filter = 'top',
          options = list(scrollX = TRUE, keys = TRUE, pageLength = 10), 
          rownames = FALSE)
```
```{r results = 'hide', echo=TRUE, message=FALSE, warning=FALSE,eval=FALSE}
query.maf.hg19 <- GDCquery(project = "TCGA-CHOL", 
                           data.category = "Simple nucleotide variation", 
                           data.type = "Simple somatic mutation",
                           access = "open", 
                           file.type = "bcgsc.ca_CHOL.IlluminaHiSeq_DNASeq.1.somatic.maf",
                           legacy = TRUE)
GDCdownload(query.maf.hg19)
maf <- GDCprepare(query.maf.hg19)
```

```{r message=FALSE, warning=FALSE, include=FALSE}
data <- bcgsc.ca_CHOL.IlluminaHiSeq_DNASeq.1.somatic.maf
```
```{r  echo = TRUE, message = FALSE, warning = FALSE}
# Only first 50 to make render faster
datatable(maf[1:20,],
          filter = 'top',
          options = list(scrollX = TRUE, keys = TRUE, pageLength = 5), 
          rownames = FALSE)
```


## Mutation data MC3 file

This will download the MC3 MAF file from https://gdc.cancer.gov/about-data/publications/mc3-2017,
and add project each sample belongs.

```{r results = 'hide', echo=TRUE, message=FALSE, warning=FALSE,eval=FALSE}
maf <- getMC3MAF()
```


# Visualize the data
To visualize the data you can use the Bioconductor package [maftools](https://bioconductor.org/packages/release/bioc/html/maftools.html). For more information, please check its [vignette](https://bioconductor.org/packages/release/bioc/vignettes/maftools/inst/doc/maftools.html#rainfall-plots).


```{r  results = "hide",echo = TRUE, message = FALSE, warning = FALSE, eval=FALSE}
library(maftools)
library(dplyr)
maf <- GDCquery_Maf("CHOL", pipelines = "muse") %>% read.maf
```

```{r message=FALSE, warning=FALSE, include=FALSE}
library(maftools)
library(dplyr)
maf <- chol_maf
```

```{r  results = "hide",echo = TRUE, message = FALSE, warning = FALSE}
datatable(getSampleSummary(maf),
          filter = 'top',
          options = list(scrollX = TRUE, keys = TRUE, pageLength = 5), 
          rownames = FALSE)
plotmafSummary(maf = maf, rmOutlier = TRUE, addStat = 'median', dashboard = TRUE)
```
```{r  echo = TRUE, message = FALSE,eval = FALSE, warning = FALSE}
oncoplot(maf = maf, top = 10, removeNonMutated = TRUE)
titv = titv(maf = maf, plot = FALSE, useSyn = TRUE)
#plot titv summary
plotTiTv(res = titv)
```