Created
September 27, 2016 14:46
-
-
Save fbreitwieser/8127619d193d19804f7a68f74eb34623 to your computer and use it in GitHub Desktop.
Get taxID for NCBI AC, as well as tax path
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
library(rentrez) | |
library(taxize) | |
library(XML) | |
get_docsum_val <- function(top, val) { | |
sapply(getNodeSet(top,sprintf("/eSummaryResult/DocSum/Item[@Name='%s']", val)), xmlValue) | |
} | |
list_docsum_items <- function(top) { | |
sapply(getNodeSet(top,"/eSummaryResult/DocSum/Item"), xmlGetAttr, name = "Name") | |
} | |
fetch_docsum_xml_root <- function(ac) { | |
docsum <- entrez_fetch("nucleotide", ac, rettype = "docsum", retmode = "xml") | |
doc <- xmlTreeParse(docsum) | |
xmlRoot(doc) | |
} | |
get_taxid_for_ac <- function(ac) { | |
top <- fetch_docsum_xml_root(ac) | |
get_docsum_val(top, "TaxId") | |
} | |
top <- fetch_docsum_xml_root("NC_000883") | |
taxid <- get_docsum_val(top, "TaxId") | |
list_docsum_items(top) | |
tax_path <- taxize::classification(taxid, db='ncbi') | |
Species_name <- sapply(tax_path, function(x) x$name[x$rank == "species"] ) | |
Species_taxid <- sapply(tax_path, function(x) x$id[x$rank == "species"] ) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment