跟着jmzeng学习GEO数据分析-GEO42872_1--题外

##这个可以跑
if(T){
  gset <- getGEO("GSE42872",destdir = ".",AnnotGPL = F,getGPL = F)
  save(gset,file  ="GSE42872_eSet.Rdata")
}
##也就说if(!file.exists(f))等同于if(T)。!file.exists(f)返回的逻辑值是T，才执行后面{}中的内容。file.exist(f)返回FALSE，前面加上!表示否定，即为真

##这个跑了没动静，语法错误。。。哈哈
if(F){
  gset <- getGEO("GSE42872",destdir = ".",AnnotGPL = F,getGPL = F)
  save(gset,file  ="GSE42872_eSet.Rdata")
}

> dir()
[1] "GSE42872_eSet.Rdata"           "GSE42872_series_matrix.txt.gz"
> f = "a.txt"
> file.exists(f)
[1] FALSE
> dir()
[1] "a.txt"                         "GSE42872_eSet.Rdata"          
[3] "GSE42872_series_matrix.txt.gz"
> file.exists(f)
[1] TRUE

 

 

##从GEO数据库导入GSE文件得到的一个list，其第一个元素才是ExpressionSet对象，元素名就是该GSE号对应的压缩文件名
> gset <- getGEO("GSE42872",destdir = ".",AnnotGPL = F,getGPL = F) ##注释文件和平台文件都不要
Found 1 file(s)
GSE42872_series_matrix.txt.gz
试开URL’https://ftp.ncbi.nlm.nih.gov/geo/series/GSE42nnn/GSE42872/matrix/GSE42872_series_matrix.txt.gz'
Content type 'application/x-gzip' length 768865 bytes (750 KB)
downloaded 750 KB

Parsed with column specification:
cols(
  ID_REF = col_double(),
  GSM1052615 = col_double(),
  GSM1052616 = col_double(),
  GSM1052617 = col_double(),
  GSM1052618 = col_double(),
  GSM1052619 = col_double(),
  GSM1052620 = col_double()
)
> class(gset)
[1] "list"
> length(gset)
[1] 1
> class(gset[[1]])
[1] "ExpressionSet"
attr(,"package")
[1] "Biobase"
> gset
$GSE42872_series_matrix.txt.gz
ExpressionSet (storageMode: lockedEnvironment)
assayData: 33297 features, 6 samples 
  element names: exprs 
protocolData: none
phenoData
  sampleNames: GSM1052615 GSM1052616 ... GSM1052620 (6 total)
  varLabels: title geo_accession ... cell type:ch1 (34 total)
  varMetadata: labelDescription
featureData: none
experimentData: use 'experimentData(object)'
  pubMedIds: 24469106 
Annotation: GPL6244

 

##如果是已经下好了GSE号对应的原始压缩文件(这个好像不是最原来的raw.data吧)，getGEO()可以直接读取之，得到直接就是上述的gset[[1]]，就是那个ExpressionSet对象。
> a  =  getGEO(file = "GSE42872_series_matrix.txt.gz",AnnotGPL = F,getGPL = F)
Parsed with column specification:
cols(
  ID_REF = col_double(),
  GSM1052615 = col_double(),
  GSM1052616 = col_double(),
  GSM1052617 = col_double(),
  GSM1052618 = col_double(),
  GSM1052619 = col_double(),
  GSM1052620 = col_double()
)
|=====================================================================================| 100%    1 MB  ##1M？好像就是解压缩了一样。。。
> class(a)
[1] "ExpressionSet"
attr(,"package")
[1] "Biobase"
> length(a)
[1] 1
> a
ExpressionSet (storageMode: lockedEnvironment)
assayData: 33297 features, 6 samples 
  element names: exprs 
protocolData: none
phenoData
  sampleNames: GSM1052615 GSM1052616 ... GSM1052620 (6 total)
  varLabels: title geo_accession ... cell type:ch1 (34 total)
  varMetadata: labelDescription
featureData: none
experimentData: use 'experimentData(object)'
  pubMedIds: 24469106 
Annotation: GPL6244

 

> b  =  getGEO(file = "GSE42872_series_matrix.txt.gz") ##如果不加参数Annotation及getGPL，好像会额外下载文件GPL6244.soft这个文件？不知道是啥？注释文件嘛？
Parsed with column specification:
cols(
  ID_REF = col_double(),
  GSM1052615 = col_double(),
  GSM1052616 = col_double(),
  GSM1052617 = col_double(),
  GSM1052618 = col_double(),
  GSM1052619 = col_double(),
  GSM1052620 = col_double()
)
File stored at: 
C:\Users\HWC\AppData\Local\Temp\RtmpGqMiOr/GPL6244.soft
|=====================================================================================| 100%   96 MB

##下不下GPL6244.soft这个文件是AnnotGPL这个参数定的，默认为T，下载
> c  =  getGEO(file = "GSE42872_series_matrix.txt.gz",getGPL = F)
Parsed with column specification:
cols(
  ID_REF = col_double(),
  GSM1052615 = col_double(),
  GSM1052616 = col_double(),
  GSM1052617 = col_double(),
  GSM1052618 = col_double(),
  GSM1052619 = col_double(),
  GSM1052620 = col_double()
)
> class(c)
[1] "ExpressionSet"
attr(,"package")
[1] "Biobase"
> d  =  getGEO(file = "GSE42872_series_matrix.txt.gz",AnnotGPL = F)
Parsed with column specification:
cols(
  ID_REF = col_double(),
  GSM1052615 = col_double(),
  GSM1052616 = col_double(),
  GSM1052617 = col_double(),
  GSM1052618 = col_double(),
  GSM1052619 = col_double(),
  GSM1052620 = col_double()
)
Using locally cached version of GPL6244 found here:
C:\Users\HWC\AppData\Local\Temp\RtmpGqMiOr/GPL6244.soft 
|=====================================================================================| 100%   96 MB

 

---

 

 

> ls()
[1] "a"    "b"    "c"    "d"    "gset"
> rm(c(b,c))
Error in rm(c(b, c)) : ...要么含名字，要么是字符串 ##c()里边如果是字符串，要有引号。。。
> rm(b,c) ##还以为要用c(),删除多个，直接逗号隔开列出即可
> ls()
[1] "a"    "d"    "gset"
> history(20) ##history()查看历史命令