多个基因集相关性热图
- 2020 年 3 月 30 日
- 筆記
第四单元第三讲：多个基因集相关性热图
课程链接在：http://jm.grazy.cn/index/mulitcourse/detail.html?cid=53 基于前面的两节，这一节变得更容易理解
文章正文还是以乳腺癌为例，绘制了6个数据集和两个亚型基因集之间的相关性
这次还是要对基因集进行操作，因此也是需要进行上一次的colMeans()操作，只不过上次总共得到4个，这次是7个（因为下文将troma1和stroma2合并为一个stroma）
获取各个基因集的基因
一共5篇参考文献，需要将其中各个基因集拿出来：
library(stringr) # vCAF基因集 vCAF='Esam, Gng11, Higd1b, Cox4i2, Cygb, Gja4, Eng' vCAF=unlist(str_split(vCAF,', ')) # mCAF基因集 mCAF='Dcn, Col12a1, Mmp2, Lum, Mrc2, Bicc1, Lrrc15, Mfap5, Col3A1, Mmp14, Spon1, Pdgfrl, Serpinf1, Lrp1, Gfpt2, Ctsk, Cdh11, Itgbl1, Col6a2, Postn, Ccdc80, Lox, Vcan, Col1a1, Fbn1, Col1a2, Pdpn, Col6a1, Fstl1, Col5a2, Aebp1' mCAF=unlist(str_split(mCAF,', ')) # ECM基因集 ECM=c('COL1A1', 'COL1A2','COL3A1') # Endothelial基因集 endothelial=c('CDH5', 'DIPK2B','TIE1') # for 参考文献ref32：proliferation 基因集 proliferation <- c("BAG1","ESR1","FOXA1","GPR160","NAT1","NAT1","MAPT","MLPH","PGR") # for ref31: stroma-related 基因集 stroma <- c('DCN', 'CSPG2', 'CDH11', 'COL3A1', 'FAP', 'PEDF', 'FBN1', 'PDGFRL', 'CTSK', 'HTRA1', 'ASPN', 'SPARC', 'COL5A2', 'LOXL1', 'MMP2', 'SPON1', 'SFRP4', 'ITGBL1', 'CALD1', 'COPZ2', 'MFAP2', 'ANGPTL2', 'PLAU', 'COL1A2', 'LRRC17', 'C1QTNF3', 'SNAI2', 'PCOLCE', 'POSTN', 'ECM2', 'FBLN1', 'ADAM12', 'MMP11', 'AEBP1', 'PDGFRB', 'GAS1', 'COL6A3', 'RARRES2', 'COL6A1', 'TGFB3', 'NDN', 'C1R', 'LRP1', 'COL10A1', 'DPYSL3', 'OLFML2B', 'MMP14', 'DACT1', 'MGC3047', 'THBS2') # for ref29: endothelial/microvasculature 基因集 microvasculature <- c('ARAP3','ADCY4','ESAM','ERG','SLC43A3','SOX7','PTPRB','PTPRM','AFAP1L1','MMRN2','TENC1','STARD9','COL4A3','LRRK1','PALD1','NPR3','ROBO4','NOTCH4','TIE1','RASIP1','ACVRL1','RAMP2','FAM110D','EGFL7','SMAD6','FGD5','ENG','CASKIN2','ACKR2','SLC9A3R2','CALCRL','HSPA12B','EPAS1','EHD4','LATS2','ICAM1','HBEGF','PLTP','C1orf54','CTTNBP2NL','MYO1B','SLCO2A1','KIFC1','EPHB4','SOX13','DRAM1','PECAM1','ENTPD1','ICAM2','CLDN5','SDPR','CDH5','GPR116','ELTD1','KDR','HILPDA','NPNT')
然后得到7个基因集的表达量
# 读入数据TCGA-BRCA.htseq_counts.tsv.gz library(data.table) filepath <- file.choose() a=fread(filepath ,data.table=F) # Ensembl ID切割 library(stringr) esid=str_split(a$Ensembl_ID, '[.]',simplify = T)[,1] # ID转换 e2s=select(org.Hs.eg.db,keys = esid,columns = c( "ENSEMBL" , "SYMBOL" ),keytype = 'ENSEMBL') vCAF=toupper(vCAF);vCAF=vCAF[vCAF %in% e2s$SYMBOL,] mCAF=toupper(mCAF);mCAF=mCAF[mCAF %in% e2s$SYMBOL,] # 获得表达量 rownames(a)=esid a=a[,-1] # vCAF ng=e2s[match(vCAF,e2s$SYMBOL),1] vCAF_value=colMeans(a[ng,]) # mCAF ng=e2s[match(mCAF,e2s$SYMBOL),1] mCAF_value=colMeans(a[ng,]) # ECM ng=e2s[match(ECM,e2s$SYMBOL),1] ECM_value=colMeans(a[ng,]) # Endothelial ng=e2s[match(endothelial,e2s$SYMBOL),1] endothelial_value=colMeans(a[ng,]) # proliferation(注意这里加上了检测基因名是否存在的代码) ng=e2s[match(proliferation,e2s$SYMBOL),1];ng=ng[!is.na(ng)];ng proliferation_value=colMeans(a[ng,]) # stroma ng=e2s[match(stroma,e2s$SYMBOL),1];ng=ng[!is.na(ng)];ng stroma_value=colMeans(a[ng,]) # microvasculature ng=e2s[match(microvasculature,e2s$SYMBOL),1];ng=ng[!is.na(ng)];ng microvasculature_value=colMeans(a[ng,]) dat=data.frame(vCAF=vCAF_value, mCAF=mCAF_value, ECM=ECM_value, endothelial=endothelial_value, microvasculature=microvasculature_value, stroma=stroma_value, proliferation=proliferation_value) > dat[1:4,1:4] vCAF mCAF ECM endothelial TCGA-A1-A0SP-01A 8.794181 13.07456 17.13670 9.990037 TCGA-BH-A201-01A 9.549604 14.86951 19.40557 10.895579 TCGA-E2-A14T-01A 9.600401 13.33230 17.61368 10.475556 TCGA-AC-A8OS-01A 9.998759 14.07297 19.24798 11.932741
最后做相关性热图
M=cor(dat) pheatmap::pheatmap(M)
从图中得知（同样也是作者想要证明的），vCAF和mCAF能够分开，并且它们各有特性。比如可以看到mCAF与ECM、stroma更像；而vCAF与microvasculature更像；另外vCAF和mCAF都与proliferation都不相关
总而言之，做这些就是想说明这几个分群的生物学意义的
