使用在数据帧中循环的动态查询结果填充R中的列

我有一个数据帧，df:

  Chrom Position Gene.Sym Ref Variant   Lbase   Rbase
1  chr1   888639    NOC2L     T         C  888638  888640
2  chr1   889158    NOC2L     G         C  889157  889159
3  chr1   889159    NOC2L     A         C  889158  889160
4  chr1   982941     AGRN     T         C  982940  982942
5  chr1  1888193 KIAA1751     C         A 1888192 1888194
6  chr1  3319632   PRDM16     G         A 3319631 3319633

我想用readLines的[6]结果填充一个新列df$triplet，该结果应用于一个查询：示例：

> readLines('http://genome.ucsc.edu/cgi-bin/das/hg19/dna?segment=chr20:1888192,1888194')
[1] "<?xml version=\"1.0\" standalone=\"no\"?>"                                  
[2] "<!DOCTYPE DASDNA SYSTEM \"http://www.biodas.org/dtd/dasdna.dtd\">"          
[3] "<DASDNA>"                                                                   
[4] "<SEQUENCE id=\"chr20\" start=\"1888192\" stop=\"1888194\" version=\"1.00\">"
[5] "<DNA length=\"3\">"                                                         
[6] "cct"                                                                        
[7] "</DNA>"                                                                     
[8] "</SEQUENCE>"                                                                
[9] "</DASDNA>"

除了我想循环使用df$Chrom、df$Lbase和df$Rbase中的值，以填充整个列。我知道会是这样的，但我太糊涂了，无法准确地理解：

baseurl = 'http://genome.ucsc.edu/cgi-bin/das/hg19/dna?segment='
myurl = paste(baseurl, trip$Chrom, ":", trip$Lbase, ",", trip$Rbase, sep='')
x = readLines(myurl)

---

您可以使用

sapply

将

readLines

应用于在

myurl

中组装的URL向量，例如，将输出添加回数据帧：

df$dna <- sapply(myurl, function(url) readLines(url)[6])

---

df$dna惯用的方法是解析xml：

f <- function(i) {
  library(XML)
  library(stringr)
  x <- trip[i,]
  segment <- paste0(x$Chrom,":",x$Lbase,",",x$Rbase)
  url     <- paste0("http://genome.ucsc.edu/cgi-bin/das/hg19/dna?segment=",segment)
  doc     <- xmlInternalTreeParse(url)
  return(str_extract(xmlValue(doc["//DNA"][[1]]),"[a-z]+"))
}
trip$triplet=sapply(1:nrow(trip),f)
trip
#   Chrom Position Gene.Sym Ref Variant   Lbase   Rbase triplet
# 1  chr1   888639    NOC2L   T       C  888638  888640     ctt
# 2  chr1   889158    NOC2L   G       C  889157  889159     cga
# 3  chr1   889159    NOC2L   A       C  889158  889160     gaa
# 4  chr1   982941     AGRN   T       C  982940  982942     ctc
# 5  chr1  1888193 KIAA1751   C       A 1888192 1888194     ccg
# 6  chr1  3319632   PRDM16   G       A 3319631 3319633     tgc

f谢谢！这很好用，正是我想要的。
f <- function(i) {
  library(XML)
  library(stringr)
  x <- trip[i,]
  segment <- paste0(x$Chrom,":",x$Lbase,",",x$Rbase)
  url     <- paste0("http://genome.ucsc.edu/cgi-bin/das/hg19/dna?segment=",segment)
  doc     <- xmlInternalTreeParse(url)
  return(str_extract(xmlValue(doc["//DNA"][[1]]),"[a-z]+"))
}
trip$triplet=sapply(1:nrow(trip),f)
trip
#   Chrom Position Gene.Sym Ref Variant   Lbase   Rbase triplet
# 1  chr1   888639    NOC2L   T       C  888638  888640     ctt
# 2  chr1   889158    NOC2L   G       C  889157  889159     cga
# 3  chr1   889159    NOC2L   A       C  889158  889160     gaa
# 4  chr1   982941     AGRN   T       C  982940  982942     ctc
# 5  chr1  1888193 KIAA1751   C       A 1888192 1888194     ccg
# 6  chr1  3319632   PRDM16   G       A 3319631 3319633     tgc