1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
|
---
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`, `GDCdownload` and `GDCpreprare` to 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 Aggregate GDC MAFs.
For more information please access https://github.com/NCI-GDC/gdc-maf-tool and
[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}
query <- GDCquery(
project = "TCGA-CHOL",
data.category = "Simple Nucleotide Variation",
access = "open",
legacy = FALSE,
data.type = "Masked Somatic Mutation",
workflow.type = "Aliquot Ensemble Somatic Variant Merging and Masking"
)
GDCdownload(query)
maf <- GDCprepare(query)
```
```{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
getResults(query.maf.hg19) %>%
dplyr::select(-contains("sample_type")) %>%
dplyr::select(-contains("cases")) %>%
DT::datatable(
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)
query <- GDCquery(
project = "TCGA-CHOL",
data.category = "Simple Nucleotide Variation",
access = "open",
legacy = FALSE,
data.type = "Masked Somatic Mutation",
workflow.type = "Aliquot Ensemble Somatic Variant Merging and Masking"
)
GDCdownload(query)
maf <- GDCprepare(query)
maf <- maf %>% maftools::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)
```
|
