def convert_tree_taxon_id2accession(biodb_name,
input_tree,
output_tree,
sqlite=False):
server, db = manipulate_biosqldb.load_db(biodb_name, sqlite=sqlite)
taxon_id2accession = manipulate_biosqldb.taxon_id2accession_chromosome(
server, biodb_name)
for i in taxon_id2accession:
taxon_id2accession[str(i)] = taxon_id2accession[i]
print "taxon_id2accession", taxon_id2accession
new_tree = parse_newick_tree.convert_terminal_node_names(
input_tree, taxon_id2accession)
Phylo.write(new_tree, output_tree, 'newick')
def convert_tree_accession2taxon_id(biodb_name,
input_tree,
output_tree,
sqlite=False):
server, db = manipulate_biosqldb.load_db(biodb_name, sqlite=sqlite)
accession2taxon_id = manipulate_biosqldb.accession2taxon_id(
server, biodb_name)
for i in accession2taxon_id:
accession2taxon_id[i] = str(accession2taxon_id[i])
print "accession2taxon_id", accession2taxon_id
new_tree = parse_newick_tree.convert_terminal_node_names(
input_tree, accession2taxon_id)
Phylo.write(new_tree, output_tree, 'newick')
def convert_tree_taxon2genome(biodb_name,
input_tree,
output_tree,
sqlite=False):
server, db = manipulate_biosqldb.load_db(biodb_name, sqlite=sqlite)
print biodb_name
taxon_id2genome_description = manipulate_biosqldb.taxon_id2genome_description(
server, biodb_name)
print taxon_id2genome_description
#locus2genome = manipulate_biosqldb.locus_tag2genome_name(server, biodb_name)
import re
for i in taxon_id2genome_description.keys():
print i
taxon_id2genome_description[i] = re.sub(" subsp\. aureus", "",
taxon_id2genome_description[i])
taxon_id2genome_description[i] = re.sub(", complete genome\.", "",
taxon_id2genome_description[i])
taxon_id2genome_description[i] = re.sub(", complete sequence\.", "",
taxon_id2genome_description[i])
taxon_id2genome_description[i] = re.sub("strain ", "",
taxon_id2genome_description[i])
taxon_id2genome_description[i] = re.sub("str\. ", "",
taxon_id2genome_description[i])
taxon_id2genome_description[i] = re.sub(" complete genome sequence\.",
"",
taxon_id2genome_description[i])
taxon_id2genome_description[i] = re.sub(" complete genome\.", "",
taxon_id2genome_description[i])
taxon_id2genome_description[i] = re.sub(" chromosome", "",
taxon_id2genome_description[i])
taxon_id2genome_description[i] = re.sub("Staphylococcus", "S.",
taxon_id2genome_description[i])
taxon_id2genome_description[i] = re.sub(" DNA", "S.",
taxon_id2genome_description[i])
#print taxon_id2genome_description[i]
print taxon_id2genome_description
new_tree = parse_newick_tree.convert_terminal_node_names(
input_tree, taxon_id2genome_description)
#print new_tree[0]
print "writing converted tree..."
print output_tree
Phylo.write(new_tree, output_tree, 'newick')
def convert_leaf_labels_from_genbank(input_tree,
input_gbk_list,
show_rank=False,
use_gbk_file_names=False,
use_source_organism=False):
import gbk2accessiontodefinition
import parse_newick_tree
if not use_source_organism:
id2description = gbk2accessiontodefinition.get_coressp(
input_gbk_list, use_gbk_file_names=use_gbk_file_names)
else:
id2description = gbk2accessiontodefinition.get_corresp_organism(
input_gbk_list)
if show_rank:
for id in id2description:
print('searching rank for %s...' % id)
try:
id2description[id] = id2description[
id] + ' (%s)' % accession2taxon_rank(id, 'phylum')
except:
print('no phylum for %s' % id)
try:
id2description[id] = id2description[
id] + ' (order: %s)' % accession2taxon_rank(
id, 'order')
except:
print('no order for %s' % id)
id2description[id] = id2description[id] + ' (?)'
new_tree = parse_newick_tree.convert_terminal_node_names(
input_tree, id2description, 1)
return new_tree
return name2description
if __name__ == '__main__':
import argparse
from Bio import SeqIO
import re
import parse_newick_tree
from Bio import Phylo
parser = argparse.ArgumentParser()
parser.add_argument("-g",
'--input_gbk',
type=str,
help="input gbk files",
nargs='+')
parser.add_argument("-m",
'--molis_table',
type=str,
help="input molis number table")
parser.add_argument("-t", '--tree', type=str, help="input tree")
args = parser.parse_args()
id2description = get_coressp(args.input_gbk, args.molis_table)
new_tree = parse_newick_tree.convert_terminal_node_names(
args.tree, id2description)
print "writing converted tree..."
with open("parsnp_renames.nwk", 'w') as output_tree:
Phylo.write(new_tree, output_tree, 'newick')