尝试将 Ensembl ID 转换为 R (biomaRt) 中的基因名称

Question

我有一个基因表达数据的大型数据集，我正在尝试使用 RStudio 中的 biomaRt 将基因标识符转换为基因名称，但是由于某种原因，当我在我的数据帧上使用合并 function 时，我的整个数据表合并错误/抹去。 我在这里查看了以前的问题，但无论我尝试什么，我的代码似乎都无法正常工作。 无限感谢！

library(biomaRt)
    
resdata <- merge(as.data.frame(res), as.data.frame(counts(dds, normalized=TRUE)), by="row.names", sort=FALSE)
names(resdata)[1] <- "genes"
head(resdata)

## Write results
resdata <- resdata[complete.cases(resdata), ]

dim(resdata)

问题从这里开始：

#to convert gene accession number to gene name

charg <- resdata$genes
head(charg)

charg2 = sapply(strsplit(charg, '.', fixed=T), function(x) x[1])

ensembl = useMart("ensembl",dataset="hsapiens_gene_ensembl")

theBM = getBM(attributes='hgnc_symbol', 
          filters = 'ensembl_gene_id', 
          values = charg2, 
          mart = ensembl)

resdata <- merge.data.frame(resdata, theBM, by.x="genes",by.y="hgnc_symbol")

# a <- c(resdata[3])
# counts_resdata <-counts[resdata$ensembl_gene_id,]
# row.names(counts_resdata) <- resdata[,"V1"]
# cal_z_score <- function(x){
#   (x - mean(x)) / sd(x)
# }

write.csv(resdata, file="diffexprresultsHEK.csv")
dev.off()

> dput(head(resdata))
structure(list(genes = structure(c("ENSG00000261150.2", "ENSG00000164877.18", 
"ENSG00000120334.15", "ENSG00000100906.10", "ENSG00000182759.3", 
"ENSG00000124145.6"), class = "AsIs"), baseMean = c(4093.85581350533, 
2362.58393155573, 3727.90538524843, 6269.83601940967, 1514.2066991352, 
4802.56186913745), log2FoldChange = c(-7.91660950515258, -5.26346217291626, 
3.32325541003148, 2.95482654632078, -5.67082078657074, 2.79396304109662
), lfcSE = c(0.192088463317979, 0.149333035266368, 0.105355230912976, 
0.097569264524605, 0.194208068005162, 0.0965853229316347), stat = c(-41.2133522670104, 
-35.2464688307429, 31.5433356391815, 30.2843990955331, -29.1997178326289, 
28.9274079776516), pvalue = c(0, 3.88608699685236e-272, 2.21307385030673e-218, 
1.83983881587879e-201, 1.95527687476496e-187, 5.40010609376884e-184
), padj = c(0, 3.9601169541424e-268, 1.50348860477005e-214, 9.3744387266064e-198, 
7.97009959691694e-184, 1.83432603828505e-180), `HEK-FUS1-1.counts` = c(8260.9703617894, 
5075.51515177084, 665.085490083024, 1513.61286043731, 3440.18729968435, 
1262.3583419615), `HEK-FUS1-2.counts` = c(8046.96326903085, 4134.79795973702, 
690.697680591815, 1346.52518701783, 2499.92325557892, 1154.73922910593
), `HEK-H149A-1.counts` = c(34.3284200812733, 113.825813953696, 
6450.12945737609, 10806.2252897945, 60.5264248801398, 8302.96076228903
), `HEK-H149A-2.counts` = c(33.1612031197744, 126.196800761364, 
7105.70891294277, 11412.980740389, 56.1898163973955, 8490.18914319335
)), row.names = c(NA, 6L), class = "data.frame")

这是一些 output （我正在努力）：

> head(charg)
[1] "ENSG00000261150.2"  "ENSG00000164877.18" "ENSG00000120334.15"
[4] "ENSG00000100906.10" "ENSG00000182759.3"  "ENSG00000124145.6" 

> dim(theBM)
[1] 0 1

> head(theBM)
[1] ensembl_gene_id
<0 rows> (or 0-length row.names)

> dim(resdata)
[1] 20381    11
> resdata <- merge.data.frame(resdata, theBM, by.x="genes",by.y="ensembl_gene_id")
> dim(resdata) #after merge
[1]  0 11 #isn't correct -- just row names! where'd my genes go?

编辑：问题解决了！ 原来我引用getBM是错误的。 谢谢你们！

Answer 1

如果您只想用 HGNC ID 覆盖 Ensemble ID，您可以一步完成：

library(biomaRt)
names(resdata)[1] <- "genes"
head(resdata)

## Write results
resdata <- resdata[complete.cases(resdata), ]

dim(resdata)

charg <- resdata$genes
head(charg)

charg2 = sapply(strsplit(charg, '.', fixed=T), function(x) x[1])

ensembl = useMart(biomart = "ensembl", dataset="hsapiens_gene_ensembl")

resdata[1] = getBM(attributes='hgnc_symbol', 
              filters = 'ensembl_gene_id', 
              values = charg2, 
              mart = ensembl)
resdata

（这将 Log2FC 保留为第 3 列，根据管道中的后续步骤，它看起来是正确的，但如果您想要不同的东西，请告诉我，我会更新我的答案以适应）