def findName(accession):
s = EUtils()
theID = None
geneOrProtein = "gene"
# Check gene database
res = s.ESearch("gene", accession)
if len(res["idlist"]) > 0:
# Get the ID in the "gene" database
theID = res["idlist"][0]
# If that fails, check the protein database
if theID == None:
res = s.ESearch("protein", accession)
if len(res["idlist"]) > 0:
theID = res["idlist"][0]
geneOrProtein = "protein"
# Couldn't find in either database
if not theID:
print("ERROR: couldn't find link for %s" % accession)
# Get link to the corresponding ID in the Taxonomy database
link = s.ELink(db="taxonomy",
dbfrom=geneOrProtein,
id=theID,
retmode="json")
taxID = json.loads(link)["linksets"][0]["linksetdbs"][0]["links"][0]
# Download taxonomy record
tax = s.EFetch(db="taxonomy", id=taxID)
#print(tax)
tree = ElementTree.fromstring(tax)
xmlP = parseString(tax)
#print(xmlP.toprettyxml())
taxonTag = tree.find("Taxon")
sciName = taxonTag.find("ScientificName")
return sciName.text
def to_genbank(self, retmax=10000):
"""Draft: from a TaxID, uses EUtils to retrieve
the GenBank identifiers
:Inspiration: https://gist.github.com/fjossinet/5673672
"""
from bioservices import EUtils
e = EUtils()
idlist = e.ESearch(db='nucleotide',
term='txid%s[Organism:exp]' % self.taxid,
restart=0,
retmax=retmax)['idlist']
results = e.ESummary(db='nucleotide', id=idlist, retmax=retmax)
return results
def get_entrez_summary(gene_id):
e = EUtils()
ret = e.ESearch('gene', gene_id)
ret = e.EFetch('gene', ret['idlist'])
return ret.decode("utf-8")
