第1题
根据R包org.Hs.eg.db找到下面ensembl 基因ID 对应的基因名(symbol)
> library(org.Hs.eg.db)
> g2s=toTable(org.Hs.egSYMBOL)
> g2e=toTable(org.Hs.egENSEMBL)
> match.id <- merge(g2s, g2e)
> head(match.id)
gene_id symbol ensembl_id
1 1 A1BG ENSG00000121410
2 10 NAT2 ENSG00000156006
3 100 ADA ENSG00000196839
4 1000 CDH2 ENSG00000170558
5 10000 AKT3 ENSG00000117020
6 10000 AKT3 ENSG00000275199
# 说明：
> ls("package:org.Hs.eg.db")
[1] "org.Hs.eg" "org.Hs.eg.db"
[3] "org.Hs.eg_dbconn" "org.Hs.eg_dbfile"
[5] "org.Hs.eg_dbInfo" "org.Hs.eg_dbschema"
[7] "org.Hs.egACCNUM" "org.Hs.egACCNUM2EG"
[9] "org.Hs.egALIAS2EG" "org.Hs.egCHR"
[11] "org.Hs.egCHRLENGTHS" "org.Hs.egCHRLOC"
[13] "org.Hs.egCHRLOCEND" "org.Hs.egENSEMBL"
[15] "org.Hs.egENSEMBL2EG" "org.Hs.egENSEMBLPROT"
[17] "org.Hs.egENSEMBLPROT2EG" "org.Hs.egENSEMBLTRANS"
[19] "org.Hs.egENSEMBLTRANS2EG" "org.Hs.egENZYME"
[21] "org.Hs.egENZYME2EG" "org.Hs.egGENENAME"
[23] "org.Hs.egGO" "org.Hs.egGO2ALLEGS"
[25] "org.Hs.egGO2EG" "org.Hs.egMAP"
[27] "org.Hs.egMAP2EG" "org.Hs.egMAPCOUNTS"
[29] "org.Hs.egOMIM" "org.Hs.egOMIM2EG"
[31] "org.Hs.egORGANISM" "org.Hs.egPATH"
[33] "org.Hs.egPATH2EG" "org.Hs.egPFAM"
[35] "org.Hs.egPMID" "org.Hs.egPMID2EG"
[37] "org.Hs.egPROSITE" "org.Hs.egREFSEQ"
[39] "org.Hs.egREFSEQ2EG" "org.Hs.egSYMBOL"
……
> org.Hs.egSYMBOL
SYMBOL map for Human (object of class "AnnDbBimap")
##class一下对象，就知道具体名字##
> methods(class='AnnDbBimap') #操作函数
[1] $ [ [[ as.character
[5] as.data.frame as.list colmetanames colnames
[9] contents count.links count.mappedkeys count.mappedLkeys
[13] count.mappedRkeys dbconn dbfile dbInfo
[17] dbmeta dbschema dim direction
[21] direction<- eapply exists get
[25] getBimapFilters isNA keyname keys
[29] keys<- length links Lkeyname
[33] Lkeys Lkeys<- Llength ls
[37] mappedkeys mappedLkeys mappedRkeys mget
[41] ncol nhit nrow Rattribnames
[45] Rattribnames<- revmap Rkeyname Rkeys
[49] Rkeys<- Rlength sample show
[53] subset summary tagname toTable
第2题
根据R包hgu133a.db找到下面探针对应的基因名(symbol)
library(hgu133a.db)
ids=toTable(hgu133aSYMBOL)
head(ids)
# 出现如下提示：
> library(hgu133a.db)
Error in library(hgu133a.db) : 不存在叫‘hgu133a.db’这个名字的程辑包
> library(hgu133a.db)
# 根据提示解决问题。找到JM写的代码，修改一下下
rm(list = ls())
options()$repos ## 我不知道这些代码啥意思，有空再查
options()$BioC_mirror
options(BioC_mirror="https://mirrors.ustc.edu.cn/bioc/")
options("repos" = c(CRAN="https://mirrors.tuna.tsinghua.edu.cn/CRAN/")) # 修改了镜像
options()$repos
options()$BioC_mirror
if (!requireNamespace("hgu133a.db", quietly = TRUE))
install.packages("hgu133a.db")
BiocManager::install("hgu133a.db",ask = F,update = F)
# 在运行之前的代码
> ids=toTable(hgu133aSYMBOL)
> head(ids)
probe_id symbol
1 1053_at RFC2
2 117_at HSPA6
3 121_at PAX8
4 1255_g_at GUCA1A
5 1316_at THRA
6 1320_at PTPN21
第3题
找到R包CLL内置的数据集的表达矩阵里面的TP53基因的表达量，并且绘制在 progres.-stable分组的boxplot图。并思考如何通过 ggpubr 进行美化。
> rm(list = ls())
> suppressPackageStartupMessages(library(CLL))
> data(sCLLex)
> sCLLex
ExpressionSet (storageMode: lockedEnvironment)
assayData: 12625 features, 22 samples
element names: exprs
protocolData: none
phenoData
sampleNames: CLL11.CEL CLL12.CEL ... CLL9.CEL (22 total)
varLabels: SampleID Disease
varMetadata: labelDescription
featureData: none
experimentData: use 'experimentData(object)'
Annotation: hgu95av2
> exprSet=exprs(sCLLex)
> library(hgu95av2.db)
