Created
January 29, 2011 18:53
-
-
Save brantfaircloth/802094 to your computer and use it in GitHub Desktop.
Lookup NCBI taxonomy for species by name
This file contains hidden or 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
import sys | |
from Bio import Entrez | |
def get_taxid(species): | |
"""to get data from ncbi taxomomy, we need to have the taxid. we can | |
get that by passing the species name to esearch, which will return | |
the tax id""" | |
species = species.replace(" ", "+").strip() | |
search = Entrez.esearch(term = species, db = "taxonomy", retmode = "xml") | |
record = Entrez.read(search) | |
return record['IdList'][0] | |
def get_tax_data(taxid): | |
"""once we have the taxid, we can fetch the record""" | |
search = Entrez.efetch(id = taxid, db = "taxonomy", retmode = "xml") | |
return Entrez.read(search) | |
Entrez.email = "" | |
if not Entrez.email: | |
print "you must add your email address" | |
sys.exit(2) | |
taxid = get_tax_id("Erodium carvifolium") | |
data = get_tax_data(taxid) | |
lineage = {d['Rank']:d['ScientificName'] for d in | |
data[0]['LineageEx'] if d['Rank'] in ['family', 'order']} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment