{"id":15906,"date":"2023-10-19T21:54:06","date_gmt":"2023-10-19T13:54:06","guid":{"rendered":"http:\/\/www.biocloudservice.com\/wordpress\/?p=15906"},"modified":"2023-10-19T21:54:07","modified_gmt":"2023-10-19T13:54:07","slug":"%e6%b3%9b%e7%99%8c%e7%ba%af%e7%94%9f%e4%bf%a1%e5%8f%91%e6%96%87%e5%88%a9%e5%99%a8-%e5%8d%95%e5%9f%ba%e5%9b%a0%e6%b3%9b%e7%99%8c%e5%88%86%e8%a3%82%e5%b0%8f%e6%8f%90%e7%90%b4%e5%9b%be","status":"publish","type":"post","link":"http:\/\/www.biocloudservice.com\/wordpress\/?p=15906","title":{"rendered":"\u6cdb\u764c\u7eaf\u751f\u4fe1\u53d1\u6587\u5229\u5668-\u5355\u57fa\u56e0\u6cdb\u764c\u5206\u88c2\u5c0f\u63d0\u7434\u56fe"},"content":{"rendered":"

\u4eca\u5929\u5c0f\u679c\u5e26\u6765\u7684\u5206\u4eab\u975e\u5e38\u5b9e\u7528\uff0c\u5728\u6cdb\u764c\u7eaf\u751f\u4fe1\u6587\u7ae0\u4e2d\u5fc5\u5907\u7684\u5206\u6790\u5185\u5bb9\u4e4b\u4e00\uff0c\u7528\u5206\u88c2\u5c0f\u63d0\u7434\u56fe\u5c55\u793a\u67d0\u4e2a\u57fa\u56e0\u5728TCGA\u80bf\u7624\u548c\u6b63\u5e38\u7ec4\u7ec7\u4e2d\u7684\u8868\u8fbe\u5dee\u5f02\uff0c\u5982\u679c\u60f3\u8981\u5982\u6b64\u9ad8\u989c\u503c\u7684\u56fe\u7247\u51fa\u73b0\u5728\u4f60\u7684\u6587\u7ae0\u4e2d\uff0c\u9a6c\u4e0a\u884c\u52a8\u8d77\u6765\uff0c\u8ddf\u7740\u5c0f\u679c\u5f00\u59cb\u4eca\u5929\u7684\u5b9e\u64cd\u5b66\u4e60\u5427\uff01<\/p>\n

    \n
  1. \u6570\u636e\u4e0b\u8f7d<\/li>\n<\/ol>\n

    \u5728\u8fdb\u884c\u6570\u636e\u5206\u6790\u4e4b\u524d\uff0c\u5c0f\u679c\u5148\u5e26\u7740\u5927\u5bb6\u8fdb\u884c\u6cdb\u764c\u8868\u8fbe\u77e9\u9635\u548c\u6837\u672c\u4fe1\u606f\u76f8\u5173\u6587\u4ef6\u4e0b\u8f7d\uff0c\u901a\u8fc7\u8be5\u7f51\u5740https:\/\/xenabrowser.net\/datapages\/\u4e0b\u8f7d\uff0c\u7f51\u9875\u5982\u4e0b\u56fe\uff1a<\/p>\n

    \"Dingtalk_20230904162129\"<\/p>\n

    2.\u51c6\u5907\u9700\u8981\u7684R\u5305<\/p>\n

    #\u5b89\u88c5\u9700\u8981\u7684R\u5305<\/p>\n

    install.packages(“stringr”)<\/p>\n

    install.packages(“dplyr”)<\/p>\n

    install.packages(“ggplot2”)<\/p>\n

    install.packages(“RColorBrewer”)<\/p>\n

    #\u52a0\u8f7d\u9700\u8981\u7684R\u5305<\/p>\n

    library(stringr)<\/p>\n

    library(dplyr)<\/p>\n

    library(ggplot2)<\/p>\n

    library(RColorBrewer)<\/p>\n

    targetGene <- “TP53” # \u60f3\u8981\u753b\u7684\u76ee\u6807\u57fa\u56e0<\/p>\n

    3.\u8f93\u5165\u6587\u4ef6\u8bfb\u53d6\u548c\u5904\u7406<\/p>\n

    #samplepair.txt\uff0cTCGA\u8ddfGTEx\u7684\u7ec4\u7ec7\u5bf9\u5e94\u5173\u7cfb\u6587\u4ef6<\/p>\n

    samplepair <- read.delim(“samplepair.txt”,as.is = T)<\/p>\n

    \"Dingtalk_20230904155715\"<\/p>\n

    gtexpair <- samplepair[,c(1,2,5)]<\/p>\n

    gtexpair<\/p>\n

    #\u4ee5TCGA\u7684\u7f29\u5199\u4e3aGTEx\u7684\u7ec4\u7ec7\u547d\u540d<\/p>\n

    gtexpair$type <- paste0(gtexpair$TCGA,”_normal_GTEx”)<\/p>\n

    gtexpair$type2 <-“normal”<\/p>\n

    gtextcga <- gtexpair[,c(1,3:5)] #\u7b5b\u6389Detail\u5217<\/p>\n

    colnames(gtextcga)[1:2] <- c(“tissue”,”X_primary_site”)<\/p>\n

    head(gtextcga)<\/p>\n

    #\u4e3aGTEx\u7684sample\u6807\u51fa\u7ec4\u7ec7<\/p>\n

    #GTEX_phenotype.gz,GTEX\u6837\u672c\u548c\u7ec4\u7ec7\u5bf9\u5e94\u5173\u7cfb\u6587\u4ef6<\/p>\n

    gtexcase <- read.delim(file=”GTEX_phenotype.gz”,header=T,as.is = T)<\/p>\n

    \"Dingtalk_20230904155950\"<\/p>\n

    colnames(gtexcase)[1] <- “sample”<\/p>\n

    gtexcase2tcga <- merge(gtextcga,gtexcase,by=”X_primary_site”)<\/p>\n

    gtextable <- gtexcase2tcga[,c(5,2:4)]<\/p>\n

    head(gtextable)<\/p>\n

    tissue <- gtexpair$TCGA<\/p>\n

    names(tissue) <- gtexpair$Detail<\/p>\n

    #TCGA_phenotype_denseDataOnlyDownload.tsv.gz,TCGA\u6837\u672c\u4e0e\u7ec4\u7ec7\u5bf9\u5e94\u5173\u7cfb<\/p>\n

    tcgacase <- read.delim(file=”TCGA_phenotype_denseDataOnlyDownload.tsv.gz”,header=T,as.is = T)<\/p>\n

    \"Dingtalk_20230904160150\"<\/p>\n

    tcgacase$tissue <- tissue[tcgacase$X_primary_disease]<\/p>\n

    tcgacase$type<-ifelse(tcgacase$sample_type==’Solid Tissue Normal’,paste(tcgacase$tissue,”normal_TCGA”,sep=”_”),paste(tcgacase$tissue,”tumor_TCGA”,sep=”_”))<\/p>\n

    tcgacase$type2 <- ifelse(tcgacase$sample_type==’Solid Tissue Normal’,”normal”,”tumor”)<\/p>\n

    tcgatable<-tcgacase[,c(1,5:7)]<\/p>\n

    head(tcgatable)<\/p>\n

    #gtex\u6cdb\u764c\u57fa\u56e0\u8868\u8fbe\u77e9\u9635\u6587\u4ef6,\u7b2c\u4e00\u5217\u4e3a\u57fa\u56e0\u540d\uff0c\u5176\u4ed6\u5217\u4e3a\u6837\u672c\u540d<\/p>\n

    headgtex <- read_part(“gtex_RSEM_gene_tpm.gz”, rows = 1)<\/p>\n

    \"Dingtalk_20230904160351\"<\/p>\n

    gtexsample <- headgtex[1,]<\/p>\n

    gtextable2 <- gtextable[gtextable$sample %in% gtexsample,]<\/p>\n

    #TCGA\u6cdb\u764c\u57fa\u56e0\u8868\u8fbe\u77e9\u9635\u6587\u4ef6,\u7b2c\u4e00\u5217\u4e3a\u57fa\u56e0\u540d\uff0c\u5176\u4ed6\u5217\u4e3a\u6837\u672c\u540d<\/p>\n

    headtcga <- read_part(“tcga_RSEM_gene_tpm.gz”, rows = 1)<\/p>\n

    \"Dingtalk_20230904160800\"<\/p>\n

    tcgasample <- headtcga[1,]<\/p>\n

    tcgatable2 <- tcgatable[tcgatable$sample %in% tcgasample,]<\/p>\n

    tcga_gtex<-rbind(tcgatable2,gtextable2)<\/p>\n

    statable<-data.frame()<\/p>\n

    for (tissuer in sort(unique(tcga_gtex$tissue))){<\/p>\n

    tcga_gtex_tissuer<-tcga_gtex[tcga_gtex$tissue==tissuer,]<\/p>\n

    tissuer_tumor_TCGA <- paste0(tissuer,”_tumor_TCGA”)<\/p>\n

    tissuer_normal_TCGA <- paste0(tissuer,”_normal_TCGA”)<\/p>\n

    tissuer_normal_GTEx <- paste0(tissuer,”_normal_GTEx”)<\/p>\n

    tissuerdf<-data.frame(TCGA=tissuer,<\/p>\n

    TCGA_new_tumor=sum(tcga_gtex_tissuer$type==tissuer_tumor_TCGA),<\/p>\n

    TCGA_new_normal=sum(tcga_gtex_tissuer$type==tissuer_normal_TCGA),<\/p>\n

    GTEx_new_num=sum(tcga_gtex_tissuer$type==tissuer_normal_GTEx),<\/p>\n

    stringsAsFactors=F)<\/p>\n

    #str(tissuerdf)<\/p>\n

    statable<-rbind(statable,tissuerdf)<\/p>\n

    }<\/p>\n

    cbind(statable, samplepair[,c(1,3:6)])<\/p>\n

    idmap <- read.delim(“gencode.v23.annotation.gene.probemap”,as.is=T)<\/p>\n

    head(idmap)<\/p>\n

    # \u8bfb\u53d6\u7b2c\u4e00\u5217, \u6240\u6709\u884c<\/p>\n

    tpmid2row <- read_part(“gtex_RSEM_gene_tpm.gz”, rows = -1, columns = 1)<\/p>\n

    tpmid2row <- tpmid2row[2:nrow(tpmid2row)]<\/p>\n

    tpmid2row <- data.frame(id = tpmid2row)<\/p>\n

    tpmid2row$rownum <- seq(1,nrow(tpmid2row))<\/p>\n

    head(tpmid2row)<\/p>\n

    gene2id2row <- merge(idmap,tpmid2row,by=”id”)<\/p>\n

    gene2id2row <- gene2id2row[order(gene2id2row$rownum),]<\/p>\n

    head(gene2id2row)<\/p>\n

    generownum <- gene2id2row[gene2id2row$gene==targetGene,]$rownum + 1<\/p>\n

    gtex_colnames <- read_part(“gtex_RSEM_gene_tpm.gz”, rows = 1)<\/p>\n

    gtex_tpm <- read_part(“gtex_RSEM_gene_tpm.gz”, rows = generownum)<\/p>\n

    tcga_colnames <- read_part(“tcga_RSEM_gene_tpm.gz”, rows = 1)<\/p>\n

    tcga_tpm <- read_part(“tcga_RSEM_gene_tpm.gz”, rows = generownum)<\/p>\n

    tpm <- as.numeric(c(gtex_tpm[2:length(gtex_tpm)],<\/p>\n

    tcga_tpm[2:length(tcga_tpm)] ))<\/p>\n

    names(tpm) <- c(gtex_colnames[2:length(gtex_colnames)],<\/p>\n

    tcga_colnames[2:length(tcga_colnames)] )<\/p>\n

    tcga_gtex$tpm <- tpm[tcga_gtex$sample]<\/p>\n

    #\u6309\u7ec4\u7ec7\u6392\u5e8f<\/p>\n

    tcga_gtex <- arrange(tcga_gtex,tissue)<\/p>\n

    write.csv(tcga_gtex[,c(2,4,5)],”easy_input.csv”, quote = F)<\/p>\n

    tcga_gtex <- read.csv(“easy_input.csv”, row.names = 1, header = T, as.is = F)<\/p>\n

    head(tcga_gtex)<\/p>\n

    tumorlist <- unique(tcga_gtex[tcga_gtex$type2==”tumor”,]$tissue)<\/p>\n

    normallist <- unique(tcga_gtex[tcga_gtex$type2==”normal”,]$tissue)<\/p>\n

    withoutNormal <- setdiff(tumorlist, normallist)<\/p>\n

    tcga_gtex$type2 <- factor(tcga_gtex$type2,levels=c(“tumor”,”normal”))<\/p>\n

    tcga_gtex_withNormal <- tcga_gtex[!(tcga_gtex$tissue %in% withoutNormal),]<\/p>\n

    tcga_gtex_MESO <- tcga_gtex[tcga_gtex$tissue==”MESO”,]<\/p>\n

    tcga_gtex_UVM <- tcga_gtex[tcga_gtex$tissue==”UVM”,]<\/p>\n

    source(“GeomSplitViolin.R”) #\u4f4d\u4e8e\u5f53\u524d\u6587\u4ef6\u5939<\/p>\n

    4.\u7ed8\u5236\u5355\u57fa\u56e0\u5206\u88c2\u5c0f\u63d0\u7434\u56fe<\/p>\n

    p <- ggplot(tcga_gtex_withNormal, aes(x = tissue, y = tpm, fill = type2)) + #x\u5bf9\u5e94\u80bf\u7624\u7684\u7c7b\u578b\uff0cy\u5bf9\u5e94\u8868\u8fbe\u91cf\uff0cfill\u586b\u5145\u5bf9\u5e94\u7ec4\u7ec7\u7684\u7c7b\u578b<\/p>\n

    geom_split_violin(draw_quantiles = c(0.25, 0.5, 0.75), #\u753b4\u5206\u4f4d\u7ebf<\/p>\n

    trim = F, #\u662f\u5426\u4fee\u526a\u5c0f\u63d0\u7434\u56fe\u7684\u5bc6\u5ea6\u66f2\u7ebf<\/p>\n

    linetype = “solid”, #\u5468\u56f4\u7ebf\u7684\u8f6e\u5ed3<\/p>\n

    color = “black”, #\u5468\u56f4\u7ebf\u989c\u8272<\/p>\n

    size = 0.2,<\/p>\n

    na.rm = T,<\/p>\n

    position =”identity”)+ #\u5468\u56f4\u7ebf\u7c97\u7ec6<\/p>\n

    ylab(paste0(targetGene, ” expression (TPM)”)) + xlab(“”) +<\/p>\n

    ylim(-4,9) +<\/p>\n

    scale_fill_manual(values = c(“#DF2020”, “#DDDF21”))+<\/p>\n

    theme_set(theme_set(theme_classic(base_size=20)))+<\/p>\n

    theme(axis.text.x = element_text(angle = 45, hjust = .5, vjust = .5)) + #x\u8f74label\u503e\u659c45\u5ea6<\/p>\n

    guides(fill = guide_legend(title = NULL)) +<\/p>\n

    theme(legend.background = element_blank(), #\u79fb\u9664\u6574\u4f53\u8fb9\u6846<\/p>\n

    #\u56fe\u4f8b\u7684\u5de6\u4e0b\u89d2\u7f6e\u4e8e\u7ed8\u56fe\u533a\u57df\u7684\u5de6\u4e0b\u89d2<\/p>\n

    legend.position=c(0,0),legend.justification = c(0,0))<\/p>\n

    p + geom_split_violin(data = tcga_gtex_MESO,<\/p>\n

    mapping = aes(x = tissue, y = tpm, fill = type2),<\/p>\n

    draw_quantiles = c(0.25, 0.5, 0.75), #\u753b4\u5206\u4f4d\u7ebf<\/p>\n

    trim = F, #\u662f\u5426\u4fee\u526a\u5c0f\u63d0\u7434\u56fe\u7684\u5bc6\u5ea6\u66f2\u7ebf<\/p>\n

    linetype = “solid”, #\u5468\u56f4\u7ebf\u7684\u8f6e\u5ed3<\/p>\n

    color = “black”, #\u5468\u56f4\u7ebf\u989c\u8272<\/p>\n

    size = 0.2,<\/p>\n

    na.rm = T,<\/p>\n

    position =”identity”) +<\/p>\n

    geom_split_violin(data = tcga_gtex_UVM,<\/p>\n

    mapping = aes(x = tissue, y = tpm, fill = type2),<\/p>\n

    draw_quantiles = c(0.25, 0.5, 0.75), #\u753b4\u5206\u4f4d\u7ebf<\/p>\n

    trim = F, #\u662f\u5426\u4fee\u526a\u5c0f\u63d0\u7434\u56fe\u7684\u5bc6\u5ea6\u66f2\u7ebf<\/p>\n

    linetype = “solid”, #\u5468\u56f4\u7ebf\u7684\u8f6e\u5ed3<\/p>\n

    color = “black”, #\u5468\u56f4\u7ebf\u989c\u8272<\/p>\n

    size = 0.2,<\/p>\n

    na.rm = T,<\/p>\n

    position =”identity”) +<\/p>\n

    scale_x_discrete(limits = levels(tcga_gtex$tissue))<\/p>\n

    ggsave(paste0(targetGene, “expression.pdf”),width = 20, height = 6)<\/p>\n

      \n
    1. \u7ed3\u679c\u6587\u4ef6<\/li>\n<\/ol>\n

      TP53_expression.pdf<\/p>\n

      \"Dingtalk_20230904161026\"<\/p>\n

      \u6700\u7ec8\u5c0f\u679c\u5b8c\u6210\u4e86\u5355\u57fa\u56e0\u6cdb\u764c\u5206\u88c2\u5c0f\u63d0\u7434\u56fe\uff0c\u770b\u8d77\u6765\u56fe\u7247\u8fd8\u4e0d\u9519\u54df\uff01\u6cdb\u764c\u5176\u4ed6\u5206\u6790\u5185\u5bb9\u53ef\u4ee5\u6b22\u8fce\u5c1d\u8bd5\u4f7f\u7528\u672c\u516c\u53f8\u65b0\u5f00\u53d1\u7684\u4e91\u5e73\u53f0\u751f\u7269\u4fe1\u606f\u5206\u6790\u5c0f\u5de5\u5177\uff0c\u96f6\u4ee3\u7801\u5b8c\u6210\u5206\u6790\uff0c\u4e91\u5e73\u53f0\u7f51\u5740\uff1ahttp:\/\/www.biocloudservice.com\/home.html\uff1b\u4e3b\u8981\u5305\u62ec\u6cdb\u764c\u4e2d\u4f53\u7ec6\u80de\u62f7\u8d1d\u6570\u53d8\u5f02\u5206\u6790(http:\/\/www.biocloudservice.com\/704\/704.php),\u6cdb\u764c\u4e2d\u70ed\u56fe\u548c\u7bb1\u7ebf\u56fe(http:\/\/www.biocloudservice.com\/773\/773.php),\u57fa\u56e0\u5728\u80bf\u7624\u4e0e\u6b63\u5e38\u7ec4\u7ec7\u4e2d\u5dee\u5f02\u5206\u6790(http:\/\/www.biocloudservice.com\/710\/710.php)\u7b49\u76f8\u5173\u6cdb\u764c\u5206\u6790\u5c0f\u5de5\u5177\uff0c\u5c0f\u679c\u4eca\u5929\u7684\u5206\u4eab\u5c31\u5230\u8fd9\u91cc\uff0c\u6b22\u8fce\u5927\u5bb6\u548c\u5c0f\u679c\u4e00\u8d77\u8ba8\u8bba\u5b66\u4e60\u5965\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"

      \u4eca\u5929\u5c0f\u679c\u5e26\u6765\u7684\u5206\u4eab\u975e\u5e38\u5b9e\u7528\uff0c\u5728\u6cdb\u764c\u7eaf\u751f\u4fe1\u6587\u7ae0\u4e2d\u5fc5\u5907\u7684\u5206\u6790\u5185\u5bb9\u4e4b\u4e00\uff0c\u7528\u5206\u88c2\u5c0f\u63d0\u7434\u56fe\u5c55\u793a\u67d0\u4e2a\u57fa\u56e0\u5728TCGA\u80bf\u7624\u548c\u6b63 […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"jetpack_post_was_ever_published":false,"_jetpack_newsletter_access":""},"categories":[1],"tags":[],"jetpack_featured_media_url":"","_links":{"self":[{"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/15906"}],"collection":[{"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=15906"}],"version-history":[{"count":1,"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/15906\/revisions"}],"predecessor-version":[{"id":15914,"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/15906\/revisions\/15914"}],"wp:attachment":[{"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=15906"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=15906"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=15906"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}