Question

我以这种方式获得了一个txt文件：

-- SMART RESULTS TEXTFORMAT --
USER_PROTEIN_ID = SAUSA300_RS14200
SMART_PROTEIN_ID = uniprot|Q5HCS9|Q5HCS9_STAAC
NUMBER_OF_FEATURES_FOUND=1
DOMAIN=transmembrane_domain
START=7
END=29
EVALUE=0
TYPE=INTRINSIC
STATUS=visible|OK
-- FINISHED --
-- SMART RESULTS TEXTFORMAT --
USER_PROTEIN_ID = SAUSA300_RS11975
SMART_PROTEIN_ID = uniprot|A6QJ58|A6QJ58_STAAE
NUMBER_OF_FEATURES_FOUND=0
-- FINISHED --
-- SMART RESULTS TEXTFORMAT --
USER_PROTEIN_ID = SAUSA300_RS14395
SMART_PROTEIN_ID = uniprot|Q2FDK5|SRAP_STAA3
NUMBER_OF_FEATURES_FOUND=1
DOMAIN=Pfam:Gram_pos_anchor
START=2221
END=2258
EVALUE=6e-08
TYPE=PFAM
STATUS=visible|OK
-- FINISHED --

我想要获得的是“ SMART RESULTS TEXTFORMAT”和“ FINISHED”之间的信息，并将不同USER_PROTEIN_ID的各个部分导出到表的每一行中。

有人可以提供一些代码吗？我一个人有一些复杂的东西。它最终出现在一个数据框中，但不知道如何继续导出到excel中的每一行。

start="-- SMART RESULTS TEXTFORMAT --"
end="-- FINISHED --"
n=nrow(myfile)
index=c(1:n)
myfile=cbind(index,myfile)
starline=as.data.frame(grep(start,myfile[,2]))
endline=as.data.frame(grep(end,myfile[,2]))
indexlist=cbind(starline,endline)
newlist=character(length = n)
for (i in 1:n) {
 index1=indexlist[i,1]+1
 index2=indexlist[i,2]-1
newlist[i]=as.data.frame(as.data.frame(myfile[index1:index2,2]))
}

Answer 1

您编写的代码看起来不错。

对于excel导出，请查看xlsx package

Answer 2

我认为这对您应该很好：

library("magrittr")
data <- split(txt, cumsum(grepl("-- SMART RESULTS TEXTFORMAT --", txt))) %>% 
  lapply(function(i) i[!grepl("-- SMART RESULTS TEXTFORMAT --|-- FINISHED --", i)]) %>% 
  lapply(function(i) {
    read.table(text = i, sep = "=", header = FALSE) %>% 
      t(.) %>% 
      tibble::as_tibble() %>% 
      magrittr::set_colnames(trimws(.[1, ])) %>% 
      slice(-1)
  }) %>% 
  plyr::rbind.fill()

对于出口，我强烈推荐rio：

rio::export(data, "data.xlsx")

这是我获取数据的方式（我将文本写出来并读回以模拟该部分）：

txt <- "-- SMART RESULTS TEXTFORMAT --
USER_PROTEIN_ID = SAUSA300_RS14200
SMART_PROTEIN_ID = uniprot|Q5HCS9|Q5HCS9_STAAC
NUMBER_OF_FEATURES_FOUND=1
DOMAIN=transmembrane_domain
START=7
END=29
EVALUE=0
TYPE=INTRINSIC
STATUS=visible|OK
-- FINISHED --
-- SMART RESULTS TEXTFORMAT --
USER_PROTEIN_ID = SAUSA300_RS11975
SMART_PROTEIN_ID = uniprot|A6QJ58|A6QJ58_STAAE
NUMBER_OF_FEATURES_FOUND=0
-- FINISHED --
-- SMART RESULTS TEXTFORMAT --
USER_PROTEIN_ID = SAUSA300_RS14395
SMART_PROTEIN_ID = uniprot|Q2FDK5|SRAP_STAA3
NUMBER_OF_FEATURES_FOUND=1
DOMAIN=Pfam:Gram_pos_anchor
START=2221
END=2258
EVALUE=6e-08
TYPE=PFAM
STATUS=visible|OK
-- FINISHED --"
writeLines(txt, "test.txt")
txt <- readLines("test.txt")

R：如何从两个关键词之间的文本中提取信息并导出到表格？

2 个答案: