芯片数据的下载与清洗

最后发布时间:2021-04-29 09:08:48 浏览量:

芯片数据下载与读取

GEOquery

AnnotGPL=T 使用GPLXXX.annot.gz文件
AnnotGPL=F 使用GPLXXX.soft文件

gpl_1 <- getGEO("GPL16699",AnnotGPL=T,destdir = "data")

getGPL =F只下载表达矩阵
GSEMatrix =TRUE 不从soft文件解析表达矩阵

gset_1_1 <- getGEO("GSE165004", GSEMatrix =TRUE, getGPL =F,destdir = "data")

下载GSEXXXX_RAW.tar原始文件

getGEOSuppFiles("GSE165004",baseDir = "data")

提取表达矩阵

图片alt

exprs from GEOquery

gset_expr <- exprs(gset[[1]])

from GSEXXXXX_series_matrix.txt.gz
从原始数据提取表达矩阵

提取注释信息

图片alt

annotation from GEOquery

gpl_1 <- getGEO("GPL16699",AnnotGPL=T,destdir = "data")
gpl_1 <- Table(gpl_1)

annotation from GPL soft file
annotation form microarry manufacture website
annotation from Bioconductor

提取GEO的样本及临床信息

图片alt

gset_1_pd <- pData(gset_1) %>% 
  dplyr::select(sample_id=geo_accession,sample_name=title,tissue_type=source_name_ch1)%>%
  mutate(group= case_when(tissue_type == "Endometrial_Tissue_Fertile_Control" ~"control",
                          tissue_type=="Endometrial_Tissue_Fertile_RPL"~"RPL",
                          tissue_type=="Endometrial_Tissue_Fertile_UIF"~"UIF"))