Question

我目前有一个脚本，研究不同基因列表之间的基因重叠。因此，代码返回的是一个八乘八的矩阵，其中发现了重叠的不同数量的基因（即这两个列表共有）。我有办法查看这些特定基因并找出它们的基因符号吗？

#-------------------------------------------------------------------------------
# Set the working directory and load the data files
#-------------------------------------------------------------------------------
setwd("~/Desktop/R_Project/Gene_overlap")
getwd()
files <- list.files(pattern="*.txt", full.names = TRUE)
files

data.list <- lapply(files, function(fil) {
  scan(file=fil, what=character())
})

names(data.list) <- basename(files) %>% stringr::str_remove("\\.txt$")

str(data.list)
# List of 8
# $ GSE108363_BCGdown_D:chr [1:350] "IL1B" "IL6" "IL1A" "CCL20" ...
# $ GSE108363_BCGdown_V: chr [1:267] "IL6" "CCL20" "IL1A" "CXCL5" ...
# $ GSE108363_BCGup_D  : chr [1:250] "FABP4" "CMTM2" "FUCA1" "CD36" ...
# $ GSE108363_BCGup_V  : chr [1:429] "FCN1" "FCGR3B" "MNDA" "CPVL" ...
# $ GSE108363_MTBdown_D: chr [1:86] "CCL20" "IL1B" "IL1A" "IL6" ...
# $ GSE108363_MTBdown_V: chr [1:244] "IL1B" "IL1A" "CCL20" "IL6" ...
# $ GSE108363_MTBup_D  : chr [1:128] "FUCA1" "FGL2" "TGFBI" "CPVL" ...
# $ GSE108363_MTBup_V  : chr [1:286] "FABP4" "RNASE1" "MNDA" "CPVL" ...

intersect(data.list$GSE108363_BCGdown_D, data.list$GSE108363_BCGdown_V) %>% length

sapply(data.list, length)



#-------------------------------------------------------------------------------
# Using the intersect function to see the overlaps 
#-------------------------------------------------------------------------------

data.file1 <- "GSE108363_BCGdown_D.txt"
data.file2 <- "GSE108363_BCGdown_V.txt"
data.file3 <- "GSE108363_BCGup_D.txt"
data.file4 <- "GSE108363_BCGup_V.txt"
data.file5 <- "GSE108363_MTBdown_D.txt"
data.file6 <- "GSE108363_MTBdown_V.txt"
data.file7 <- "GSE108363_MTBup_D.txt"
data.file8 <- "GSE108363_MTBup_V.txt"

genevect1 <- scan(data.file1, what=character(), sep="\n")
genevect2 <- scan(data.file2, what=character(), sep="\n")
genevect3 <- scan(data.file3, what=character(), sep="\n")
genevect4 <- scan(data.file4, what=character(), sep="\n")
genevect5 <- scan(data.file5, what=character(), sep="\n")
genevect6 <- scan(data.file6, what=character(), sep="\n")
genevect7 <- scan(data.file7, what=character(), sep="\n")
genevect8 <- scan(data.file8, what=character(), sep="\n")


filelist <- list(data.file1, data.file2, data.file3, data.file4, data.file5, data.file6, data.file7, data.file8)
all(sapply(filelist, file.exists))

#-------------------------------------------------------------------------------
# read files:
#-------------------------------------------------------------------------------

gene.lists <- lapply(filelist, function(f) {
  scan(file=f, what=character())
})


#-------------------------------------------------------------------------------
# set up empty matrix for overlaps
#-------------------------------------------------------------------------------
x <- (length(gene.lists))^2
x
y <- rep(NA, x)
mx <- matrix(y, ncol=length(gene.lists))
mx
row.names(mx) <- sapply(filelist, basename) %>% stringr::str_remove('.txt$')
colnames(mx) <- sapply(filelist, basename) %>% stringr::str_remove('.txt$')
mx

mx.overlap.count <- mx

#-------------------------------------------------------------------------------
# Overlaps
#-------------------------------------------------------------------------------
for (i in seq_along(gene.lists)) {
  g1 <- gene.lists[[i]]
  for (j in seq_along(gene.lists)) {
    g2 <- gene.lists[[j]]
    a <- intersect(g1, g2)
    b <- length(a)
    mx.overlap.count[j,i] <- b
  }
}

mx.overlap.count
round(as.numeric(mx.overlap.count),digits = 1)
View(mx.overlap.count)

此刻，此代码返回数值。但是，我想为要比较的每两个基因列表生成某种类型的列表（或类似的东西），以便我可以准确地看到两个基因共有的基因。

Answer 1

我可以通过遍历对比度矩阵，将相交的长度像矩阵一样存储在矩阵中并将基因名称存储在列表topics中来解决该问题。像这样：

genes.overlap

如何从重叠的基因列表中提取基因名称

1 个答案: