在r中的for（）循环中转置和重命名数据帧

我有一个具有以下模式的文件列表：sampleid_samplename_counts.csv表示计数矩阵，行中有cellname，列中有genes

我试图从这些文件中生成计数矩阵，加载到Seurat包中，该包需要列中的单元名和行中的基因

我成功地获得了以下矩阵，其中x是所有.csv文件名的向量（我需要为对象创建一个新名称，因为我无法在循环中重新分配“I”）：

但是得到的矩阵没有colname（它被替换为V1、V2、V3…） 每个矩阵的第1行包含单元名

以下是创建正确的列名称：

colnames(file.counts) <- file.counts[1,]
file.counts <- file.counts[-1,]

这就是转置t（）之后的情况

---

也许这有助于

library( data.table )

#build list of csv.gz files (I only kept two files in the dir)
files.to.read <- list.files( "./temp/GSE114725_RAW/", pattern = "\\.csv.gz$", full.names = TRUE )

库（data.table）
#csv.gz文件的构建列表（我在目录中只保留了两个文件）
files.to.阅读一些示例数据/文件会很有帮助…如何传输？我对forumoriginal文件不太熟悉。我使用的原始文件来自这里：（col=基因，rows=细胞计数矩阵）请看一下and.Sebrw，让别人下载83Mb的档案来帮助回答你的问题是不合理的。请参阅Martin提供的链接。注意：是否有简单的方法将NA替换为0？
structure(list(V1 = c(NA, 121270371765165, 121270372580596, 121270373898541, 
121270374395228, 121270374676403, 121270375926581, 121270376000796, 
121270376290589, 121270378289958, 121270378621156, 121347513957787, 
121347516024694, 121347517659934, 121347518125797, 121347519671644, 
121347519760734, 121347519921075, 121347520489203, 121896195804531
), V2 = c("DPM1", "", "", "", "", "", "", "", "", "", "", "", 
"", "", "", "", "", "", "", ""), V3 = c("SCYL3", "", "", "", 
"", "", "", "", "", "", "", "", "", "", "", "", "", "", "", ""
), V4 = c("FGR", "", "", "", "", "", "", "", "", "1.0", "", "", 
"", "", "", "", "", "", "", ""), V5 = c("CFH", "", "", "", "", 
"", "", "", "", "", "", "", "", "", "", "", "", "", "", ""), 
    V6 = c("FUCA2", "", "", "", "", "", "", "", "", "", "", "", 
    "", "", "", "", "", "", "", ""), V7 = c("GCLC", "", "", "", 
    "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", 
    ""), V8 = c("NFYA", "", "", "", "", "", "", "", "", "", "", 
    "", "", "", "", "", "", "", "", ""), V9 = c("NIPAL3", "", 
    "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", 
    "", "", ""), V10 = c("LAS1L", "", "", "", "", "", "", "", 
    "", "", "", "", "", "", "", "", "", "", "", "")), row.names = c(NA, 
20L), class = "data.frame")

structure(c(NA, "DPM1", "SCYL3", "FGR", "CFH", "FUCA2", "GCLC", 
"NFYA", "NIPAL3", "LAS1L", "ENPP4", "ANKIB1", "KRIT1", "RAD52", 
"BAD", "LAP3", "CD99", "MAD1L1", "LASP1", "SNX11", "1.212704e+14", 
"", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", 
"", "", "", "1.212704e+14", "", "", "", "", "", "", "", "", "", 
"", "", "", "", "", "", "1.0", "", "", "", "1.212704e+14", "", 
"", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", 
"", "", "1.212704e+14", "", "", "", "", "", "", "", "", "", "", 
"", "", "", "", "", "", "", "", "", "1.212704e+14", "", "", "", 
"", "", "", "", "", "", "", "", "", "", "", "", "", "", "1.0", 
"", "1.212704e+14", "", "", "", "", "", "", "", "", "", "", "", 
"", "", "", "", "", "", "", "", "1.212704e+14", "", "", "", "", 
"", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "1.212704e+14", 
"", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", 
"", "", "", "1.212704e+14", "", "", "1.0", "", "", "", "", "", 
"", "", "", "", "", "", "", "", "", "", ""), .Dim = c(20L, 10L
), .Dimnames = list(c("V1", "V2", "V3", "V4", "V5", "V6", "V7", 
"V8", "V9", "V10", "V11", "V12", "V13", "V14", "V15", "V16", 
"V17", "V18", "V19", "V20"), NULL))

library( data.table )

#build list of csv.gz files (I only kept two files in the dir)
files.to.read <- list.files( "./temp/GSE114725_RAW/", pattern = "\\.csv.gz$", full.names = TRUE )

#build a list of read data
L <- lapply( files.to.read, data.table::fread )

#transpose each list element
L.transposed <- lapply( L, data.table::transpose, keep.names = "gene", make.names = "V1" )
#set list names based on filenames
names(L.transposed) <- basename( files.to.read )

#write list elements to individual data.tables
for(i in 1:length(L.transposed)) assign(names(L.transposed)[i], L.transposed[[i]])