def blast_dico2taxonomy_info(blast_dico):
import sequence_id2scientific_classification
accession2hits_classification = {}
for n, accession in enumerate(blast_dico.keys()):
print n, accession
accession2hits_classification[accession] = {}
all_taxon_ids = []
for n, one_hit_accession in enumerate(blast_dico[accession].keys()):
taxon_ids = blast_dico[accession][one_hit_accession][0]['subject_taxid'].split(";")
all_taxon_ids+=taxon_ids
print "ids:", all_taxon_ids
taxon_id2classification = sequence_id2scientific_classification.taxon_id2scientific_classification(all_taxon_ids)
for n, one_hit_accession in enumerate(blast_dico[accession].keys()):
accession2hits_classification[accession][one_hit_accession] = []
taxon_ids = blast_dico[accession][one_hit_accession][0]['subject_taxid'].split(";")
for taxon in taxon_ids:
try:
accession2hits_classification[accession][one_hit_accession].append(taxon_id2classification[taxon])
except KeyError:
accession2hits_classification[accession][one_hit_accession].append(None)
return accession2hits_classification
def accession2full_taxonomic_path(accession_list, database="nucleotide"):
import sequence_id2scientific_classification
taxon_id_list = accession2taxon_id(accession_list, database).values()
#print 'taxon_id list',
classif = sequence_id2scientific_classification.taxon_id2scientific_classification(
taxon_id_list)
return classif
def accession2taxon_rank(accession, rank='phylum'):
from Bio import Entrez
import sequence_id2scientific_classification
Entrez.email = "*****@*****.**"
handle1 = Entrez.esearch(db="nuccore", term=accession)
record1 = Entrez.read(handle1)
ncbi_id = record1['IdList'][0]
handle2 = Entrez.elink(dbfrom="nuccore", db="taxonomy", id=ncbi_id)
record2 = Entrez.read(handle2)
id = record2[0]['LinkSetDb'][0]['Link'][0]['Id']
taxo_data = sequence_id2scientific_classification.taxon_id2scientific_classification(
[id])
try:
data = taxo_data[id][rank]
except:
print(accession, ncbi_id, taxo_data[id])
return (False)
return data
def insert_taxons_into_sqldb(taxon_id_list,
chunk_size=300,
mysql_host='localhost',
mysql_user='******',
mysql_pwd='wnkonwn',
mysql_db='blastnr'):
import time
import MySQLdb
import sequence_id2scientific_classification
import re
conn = MySQLdb.connect(
host=mysql_host, # your host, usually localhost
user=mysql_user, # your username
passwd=mysql_pwd, # your password
db=mysql_db) # name of the data base
cursor = conn.cursor()
taxid2classification = {}
id_lists = _chunks(taxon_id_list, chunk_size)
for i, one_list in enumerate(id_lists):
print(i, "/", len(id_lists))
if i % 100 == 0 and i != 0:
time.sleep(60)
taxid2classification.update(
sequence_id2scientific_classification.
taxon_id2scientific_classification(one_list))
print('Number of taxon id retrieved:', len(taxid2classification.keys()))
print('Updating blastnr_taxonomy table with %s new taxons' %
str(len(taxon_id_list)))
for taxon_id in taxon_id_list:
if taxon_id == 'N/A':
continue
sql = 'INSERT INTO blastnr_taxonomy(taxon_id) values (%s)' % (taxon_id)
try:
cursor.execute(sql)
conn.commit()
except MySQLdb.IntegrityError:
print('Taxon %s already in database' % str(taxon_id))
continue
try:
for rank in taxid2classification[taxon_id].keys():
sql_id = re.sub(' ', '_', rank)
value = taxid2classification[taxon_id][rank]
sql = 'UPDATE blastnr_taxonomy SET `%s`="%s" where taxon_id=%s' % (
sql_id, value, taxon_id)
#print sql
try:
cursor.execute(sql)
conn.commit()
except:
print('could not insert rank', sql)
except KeyError:
print(
'Could not add the following taxon: %s, trying again to get the data...'
% taxon_id)
temp_dico = sequence_id2scientific_classification.taxon_id2scientific_classification(
[taxon_id])
try:
for rank in temp_dico[taxon_id].keys():
sql_id = re.sub(' ', '_', rank)
value = temp_dico[taxon_id][rank]
sql = 'UPDATE blastnr_taxonomy SET `%s`="%s" where taxon_id=%s' % (
sql_id, value, taxon_id)
cursor.execute(sql)
conn.commit()
print('sucess!')
except KeyError:
print('Could not add %s' % taxon_id)
print("temp_dico", temp_dico)
import argparse
import sequence_id2scientific_classification
parser = argparse.ArgumentParser()
parser.add_argument("-t",
'--taxon_id',
type=str,
help="taxon ncbi id",
nargs='+')
parser.add_argument("-r",
'--rank',
action="store_true",
help="get taxon rank ")
args = parser.parse_args()
classif = sequence_id2scientific_classification.taxon_id2scientific_classification(
args.taxon_id)
#print classif
if not args.rank:
for accession in classif:
data = classif[accession]
try:
superkingdom = data["superkingdom"]
except:
superkingdom = "-"
try:
phylum = data["phylum"]
except:
phylum = "-"
try:
class_ = data["class"]