R语言中RTCGA包的基本用法

发表于 | 分类于 | | 热度 °C

R语言中的RTCGA包用于下载并分析TCGA上的数据，如要查看RTCGA的示例用法，可以使用如下命令打开”RTCGA package workflow”

1
2
3
4
> browseVignettes("RTCGA")
# 运行之后打开下面这个页面：[RTCGA package workflow](http://127.0.0.1:14929/session/Rvig.2eb41b5b1ec3.html)
# 如果要查看RTCGA.rnaseq的示例，则使用如下命令：
> browseVignettes("RTCGA.rnaseq")

一、查看可用数据集

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
> library(RTCGA)
> x <- infoTCGA() 
> class(x)
[1] "data.frame"
> nrow(x)
[1] 38
> x
                  Cohort  BCR Clinical   CN LowP Methylation mRNA mRNASeq miR miRSeq
ACC-counts           ACC   92       92   90    0          80    0      79   0     80
BLCA-counts         BLCA  412      412  410  112         412    0     408   0    409
BRCA-counts         BRCA 1098     1097 1089   19        1097  526    1093   0   1078
CESC-counts         CESC  307      307  295   50         307    0     304   0    307
CHOL-counts         CHOL   51       45   36    0          36    0      36   0     36
COAD-counts         COAD  460      458  451   69         457  153     457   0    406
COADREAD-counts COADREAD  631      629  616  104         622  222     623   0    549
DLBC-counts         DLBC   58       48   48    0          48    0      48   0     47
ESCA-counts         ESCA  185      185  184   51         185    0     184   0    184
FPPP-counts         FPPP   38       38    0    0           0    0       0   0     23
GBM-counts           GBM  613      595  577    0         420  540     160 565      0
GBMLGG-counts     GBMLGG 1129     1110 1090   52         936  567     676 565    512
HNSC-counts         HNSC  528      528  522  108         528    0     520   0    523
KICH-counts         KICH  113      113   66    0          66    0      66   0     66
KIPAN-counts       KIPAN  973      941  883    0         892   88     889   0    873
KIRC-counts         KIRC  537      537  528    0         535   72     533   0    516
KIRP-counts         KIRP  323      291  289    0         291   16     290   0    291
LAML-counts         LAML  200      200  197    0         194    0     179   0    188
LGG-counts           LGG  516      515  513   52         516   27     516   0    512
LIHC-counts         LIHC  377      377  370    0         377    0     371   0    372
LUAD-counts         LUAD  585      522  516  120         578   32     515   0    513
LUSC-counts         LUSC  504      504  501    0         503  154     501   0    478
MESO-counts         MESO   87       87   87    0          87    0      87   0     87
OV-counts             OV  602      591  586    0         594  574     304 570    453
PAAD-counts         PAAD  185      185  184    0         184    0     178   0    178
PCPG-counts         PCPG  179      179  175    0         179    0     179   0    179
PRAD-counts         PRAD  499      499  492  115         498    0     497   0    494
READ-counts         READ  171      171  165   35         165   69     166   0    143
SARC-counts         SARC  261      261  257    0         261    0     259   0    259
SKCM-counts         SKCM  470      470  469  118         470    0     469   0    448
STAD-counts         STAD  443      443  442  107         443    0     415   0    436
STES-counts         STES  628      628  626  158         628    0     599   0    620
TGCT-counts         TGCT  150      134  150    0         150    0     150   0    150
THCA-counts         THCA  503      503  499   98         503    0     501   0    502
THYM-counts         THYM  124      124  123    0         124    0     120   0    124
UCEC-counts         UCEC  560      548  540  106         547   54     545   0    538
UCS-counts           UCS   57       57   56    0          57    0      57   0     56
UVM-counts           UVM   80       80   80   51          80    0      80   0     80
                RPPA MAF rawMAF
ACC-counts        46  90      0
BLCA-counts      344 130    395
BRCA-counts      887 977      0
CESC-counts      173 194      0
CHOL-counts       30  35      0
COAD-counts      360 154    367
COADREAD-counts  491 223    489
DLBC-counts       33  48      0
ESCA-counts      126 185      0
FPPP-counts        0   0      0
GBM-counts       238 290    290
GBMLGG-counts    668 576    806
HNSC-counts      212 279    510
KICH-counts       63  66     66
KIPAN-counts     756 644    799
KIRC-counts      478 417    451
KIRP-counts      215 161    282
LAML-counts        0 197      0
LGG-counts       430 286    516
LIHC-counts       63 198    373
LUAD-counts      365 230    542
LUSC-counts      328 178      0
MESO-counts       63   0      0
OV-counts        426 316    469
PAAD-counts      123 150    184
PCPG-counts       80 179      0
PRAD-counts      352 332    498
READ-counts      131  69    122
SARC-counts      223 247      0
SKCM-counts      353 343    366
STAD-counts      357 289    395
STES-counts      483 474    395
TGCT-counts      118 149      0
THCA-counts      222 402    496
THYM-counts       90 123      0
UCEC-counts      440 248      0
UCS-counts        48  57      0
UVM-counts        12  80      0

如上信息也可以在Broad GDAC Firehose的网页中找到。

如果只想查看肿瘤名称，则使用如下语法提取行名，共38种。

1
2
3
4
5
6
7
8
9
10
> cohorts <- infoTCGA() %>% 
+     rownames() %>% 
+     sub('-counts', '', x=.)
> cohorts
 [1] "ACC"      "BLCA"     "BRCA"     "CESC"     "CHOL"     "COAD"     "COADREAD"
 [8] "DLBC"     "ESCA"     "FPPP"     "GBM"      "GBMLGG"   "HNSC"     "KICH"    
[15] "KIPAN"    "KIRC"     "KIRP"     "LAML"     "LGG"      "LIHC"     "LUAD"    
[22] "LUSC"     "MESO"     "OV"       "PAAD"     "PCPG"     "PRAD"     "READ"    
[29] "SARC"     "SKCM"     "STAD"     "STES"     "TGCT"     "THCA"     "THYM"    
[36] "UCEC"     "UCS"      "UVM"

二、数据集发布日期

1
2
3
4
5
6
7
8
9
10
11
12
> checkTCGA('Dates')
 [1] "2011-10-26" "2011-11-15" "2011-11-28" "2011-12-06" "2011-12-30" "2012-01-10"
 [7] "2012-01-24" "2012-02-17" "2012-03-06" "2012-03-21" "2012-04-12" "2012-04-25"
[13] "2012-05-15" "2012-05-25" "2012-06-06" "2012-06-23" "2012-07-07" "2012-07-25"
[19] "2012-08-04" "2012-08-25" "2012-09-13" "2012-10-04" "2012-10-18" "2012-10-20"
[25] "2012-10-24" "2012-11-02" "2012-11-14" "2012-12-06" "2012-12-21" "2013-01-16"
[31] "2013-02-03" "2013-02-22" "2013-03-09" "2013-03-26" "2013-04-06" "2013-04-21"
[37] "2013-05-08" "2013-05-23" "2013-06-06" "2013-06-23" "2013-07-15" "2013-08-09"
[43] "2013-09-23" "2013-10-10" "2013-11-14" "2013-12-10" "2014-01-15" "2014-02-15"
[49] "2014-03-16" "2014-04-16" "2014-05-18" "2014-06-14" "2014-07-15" "2014-09-02"
[55] "2014-10-17" "2014-12-06" "2015-02-02" "2015-02-04" "2015-04-02" "2015-06-01"
[61] "2015-08-21" "2015-11-01" "2016-01-28"

三、查看特定肿瘤类型的数据集名称和大小

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
> checkTCGA('DataSets',
+           cancerType = 'BRCA',
+           date = '2016-01-28') %>% dim
[1] 43  2
> checkTCGA('DataSets',
+           cancerType = 'BRCA',
+           date = '2016-01-28')
   Size
1   37M
2   50K
3  723K
4  135K
5  135K
6   77K
7   78K
8  1.5M
9   57K
10 1.2K
11 160K
12 3.4M
13  86K
14  83M
15 3.2G
16 1.1M
17  15M
18 2.9M
19  44M
20 1.3M
21 2.6G
22 277M
23 195M
24 298M
25  93M
26 869M
27 249M
28 2.8G
29 243M
30  18M
31  18M
32 5.3M
33 4.6M
34  37M
35 399M
36  10M
37 1.1G
38  81M
39 1.9M
40  37M
41 1.5G
42 6.6M
43 7.4M
                                                                                                                                            Name
1  BRCA-FFPE.Merge_methylation__humanmethylation450__jhu_usc_edu__Level_3__within_bioassay_data_set_function__data.Level_3.2016012800.0.0.tar.gz
2                   BRCA-FFPE.Merge_mirnaseq__illuminahiseq_mirnaseq__bcgsc_ca__Level_3__miR_gene_expression__data.Level_3.2016012800.0.0.tar.gz
3                BRCA-FFPE.Merge_mirnaseq__illuminahiseq_mirnaseq__bcgsc_ca__Level_3__miR_isoform_expression__data.Level_3.2016012800.0.0.tar.gz
4                         BRCA-FFPE.Merge_snp__genome_wide_snp_6__broad_mit_edu__Level_3__segmented_scna_hg18__seg.Level_3.2016012800.0.0.tar.gz
5                         BRCA-FFPE.Merge_snp__genome_wide_snp_6__broad_mit_edu__Level_3__segmented_scna_hg19__seg.Level_3.2016012800.0.0.tar.gz
6      BRCA-FFPE.Merge_snp__genome_wide_snp_6__broad_mit_edu__Level_3__segmented_scna_minus_germline_cnv_hg18__seg.Level_3.2016012800.0.0.tar.gz
7      BRCA-FFPE.Merge_snp__genome_wide_snp_6__broad_mit_edu__Level_3__segmented_scna_minus_germline_cnv_hg19__seg.Level_3.2016012800.0.0.tar.gz
8                                                                                 BRCA-FFPE.Methylation_Preprocess.Level_3.2016012800.0.0.tar.gz
9                                                                               BRCA-FFPE.miRseq_Mature_Preprocess.Level_3.2016012800.0.0.tar.gz
10                                                                                     BRCA-FFPE.miRseq_Preprocess.Level_3.2016012800.0.0.tar.gz
11                                                                                        BRCA.Clinical_Pick_Tier1.Level_4.2016012800.0.0.tar.gz
12                                                                                             BRCA.Merge_Clinical.Level_1.2016012800.0.0.tar.gz
13                              BRCA.Merge_cna__illuminahiseq_dnaseqc__hms_harvard_edu__Level_3__segmentation__seg.Level_3.2016012800.0.0.tar.gz
14       BRCA.Merge_methylation__humanmethylation27__jhu_usc_edu__Level_3__within_bioassay_data_set_function__data.Level_3.2016012800.0.0.tar.gz
15      BRCA.Merge_methylation__humanmethylation450__jhu_usc_edu__Level_3__within_bioassay_data_set_function__data.Level_3.2016012800.0.0.tar.gz
16                          BRCA.Merge_mirnaseq__illuminaga_mirnaseq__bcgsc_ca__Level_3__miR_gene_expression__data.Level_3.2016012800.0.0.tar.gz
17                       BRCA.Merge_mirnaseq__illuminaga_mirnaseq__bcgsc_ca__Level_3__miR_isoform_expression__data.Level_3.2016012800.0.0.tar.gz
18                       BRCA.Merge_mirnaseq__illuminahiseq_mirnaseq__bcgsc_ca__Level_3__miR_gene_expression__data.Level_3.2016012800.0.0.tar.gz
19                    BRCA.Merge_mirnaseq__illuminahiseq_mirnaseq__bcgsc_ca__Level_3__miR_isoform_expression__data.Level_3.2016012800.0.0.tar.gz
20                     BRCA.Merge_protein_exp__mda_rppa_core__mdanderson_org__Level_3__protein_normalization__data.Level_3.2016012800.0.0.tar.gz
21                                BRCA.Merge_rnaseq__illuminahiseq_rnaseq__unc_edu__Level_3__exon_expression__data.Level_3.2016012800.0.0.tar.gz
22                                BRCA.Merge_rnaseq__illuminahiseq_rnaseq__unc_edu__Level_3__gene_expression__data.Level_3.2016012800.0.0.tar.gz
23                     BRCA.Merge_rnaseq__illuminahiseq_rnaseq__unc_edu__Level_3__splice_junction_expression__data.Level_3.2016012800.0.0.tar.gz
24                                 BRCA.Merge_rnaseqv2__illuminahiseq_rnaseqv2__unc_edu__Level_3__RSEM_genes__data.Level_3.2016012800.0.0.tar.gz
25                      BRCA.Merge_rnaseqv2__illuminahiseq_rnaseqv2__unc_edu__Level_3__RSEM_genes_normalized__data.Level_3.2016012800.0.0.tar.gz
26                              BRCA.Merge_rnaseqv2__illuminahiseq_rnaseqv2__unc_edu__Level_3__RSEM_isoforms__data.Level_3.2016012800.0.0.tar.gz
27                   BRCA.Merge_rnaseqv2__illuminahiseq_rnaseqv2__unc_edu__Level_3__RSEM_isoforms_normalized__data.Level_3.2016012800.0.0.tar.gz
28                        BRCA.Merge_rnaseqv2__illuminahiseq_rnaseqv2__unc_edu__Level_3__exon_quantification__data.Level_3.2016012800.0.0.tar.gz
29                    BRCA.Merge_rnaseqv2__illuminahiseq_rnaseqv2__unc_edu__Level_3__junction_quantification__data.Level_3.2016012800.0.0.tar.gz
30                             BRCA.Merge_snp__genome_wide_snp_6__broad_mit_edu__Level_3__segmented_scna_hg18__seg.Level_3.2016012800.0.0.tar.gz
31                             BRCA.Merge_snp__genome_wide_snp_6__broad_mit_edu__Level_3__segmented_scna_hg19__seg.Level_3.2016012800.0.0.tar.gz
32          BRCA.Merge_snp__genome_wide_snp_6__broad_mit_edu__Level_3__segmented_scna_minus_germline_cnv_hg18__seg.Level_3.2016012800.0.0.tar.gz
33          BRCA.Merge_snp__genome_wide_snp_6__broad_mit_edu__Level_3__segmented_scna_minus_germline_cnv_hg19__seg.Level_3.2016012800.0.0.tar.gz
34       BRCA.Merge_transcriptome__agilentg4502a_07_3__unc_edu__Level_3__unc_lowess_normalization_gene_level__data.Level_3.2016012800.0.0.tar.gz
35                                                                                     BRCA.Methylation_Preprocess.Level_3.2016012800.0.0.tar.gz
36                                                                                    BRCA.Mutation_Packager_Calls.Level_3.2016012800.0.0.tar.gz
37                                                                                 BRCA.Mutation_Packager_Coverage.Level_3.2016012800.0.0.tar.gz
38                                                                          BRCA.Mutation_Packager_Oncotated_Calls.Level_3.2016012800.0.0.tar.gz
39                                                                                      BRCA.RPPA_AnnotateWithGene.Level_3.2016012800.0.0.tar.gz
40                                                                                     BRCA.mRNA_Preprocess_Median.Level_3.2016012800.0.0.tar.gz
41                                                                                         BRCA.mRNAseq_Preprocess.Level_3.2016012800.0.0.tar.gz
42                                                                                   BRCA.miRseq_Mature_Preprocess.Level_3.2016012800.0.0.tar.gz
43                                                                                          BRCA.miRseq_Preprocess.Level_3.2016012800.0.0.tar.gz

四、数据下载

1
2
3
4
5
6
7
8
9
> downloadTCGA(
+   cancerTypes = "BRCA",
+   dataSet = "Merge_Clinical.Level_1",
+   destDir = "./"
+ )
trying URL 'http://gdac.broadinstitute.org/runs/stddata__2016_01_28/data/BRCA/20160128/gdac.broadinstitute.org_BRCA.Merge_Clinical.Level_1.2016012800.0.0.tar.gz'
Content type 'application/x-gzip' length 3615793 bytes (3.4 MB)
downloaded 3.4 MB
# 这里是下载到了当前工作目录下，也可选择其他文件夹，当然，首先得新建目的目录，使用dir.create("download_folder")

五、读取数据 

1
readTCGA(path, dataType, ...)
  • 本文作者：括囊无誉
  • 本文链接： TCGA/RTCGAbasic/
  • 版权声明： 本博客所有文章均为原创作品，转载请注明出处！
------ 本文结束 ------
坚持原创文章分享，您的支持将鼓励我继续创作！