def test_ncbiquery(self):
ncbi = NCBITaxa(dbfile=DATABASE_PATH)
id2name = ncbi.get_taxid_translator(['9606', '7507'])
self.assertEqual(id2name[7507], 'Mantis religiosa')
self.assertEqual(id2name[9606], 'H**o sapiens')
name2id = ncbi.get_name_translator(['Mantis religiosa', 'h**o sapiens'])
self.assertEqual(name2id['Mantis religiosa'], [7507])
self.assertEqual(name2id['h**o sapiens'], [9606])
name2id = ncbi.get_name_translator(['Bacteria'])
self.assertEqual(set(name2id['Bacteria']), set([2, 629395]))
out = ncbi.get_descendant_taxa("9605", intermediate_nodes=True)
#Out[9]: [1425170, 741158, 63221, 9606]
self.assertEqual(set(out), set([1425170, 741158, 63221, 9606]))
out = ncbi.get_descendant_taxa("9605", intermediate_nodes=False)
#Out[10]: [1425170, 741158, 63221]
self.assertEqual(set(out), set([1425170, 741158, 63221]))
out = ncbi.get_descendant_taxa("9605", intermediate_nodes=False, rank_limit="species")
#Out[11]: [9606, 1425170]
self.assertEqual(set(out), set([9606, 1425170]))
def test_ncbiquery(self):
ncbi = NCBITaxa(dbfile=DATABASE_PATH)
id2name = ncbi.get_taxid_translator(["9606", "7507"])
self.assertEqual(id2name[7507], "Mantis religiosa")
self.assertEqual(id2name[9606], "H**o sapiens")
name2id = ncbi.get_name_translator(["Mantis religiosa", "h**o sapiens"])
self.assertEqual(name2id["Mantis religiosa"], 7507)
self.assertEqual(name2id["h**o sapiens"], 9606)
def getNcbiTaxonomy():
ncbi = NCBITaxa()
nameToTaxIdList = ncbi.get_name_translator(ORGANISM_NAMES_LIST)
#print (str(nameToTaxIdList))
with open (OUTPUT_FILE, "w") as outputFile:
for name in ORGANISM_NAMES_LIST:
#for name, taxIds in nameToTaxIdList.items():
taxIds = nameToTaxIdList[name]
for eachId in taxIds:
lineage = ncbi.get_lineage(str(eachId))
names = ncbi.get_taxid_translator(lineage)
outputFile.write("\t".join([names[taxid] for taxid in lineage]) + "\n")
from pandas import DataFrame
from Bio import SeqIO
from pandas import Index
from ete2 import NCBITaxa
data_path = "/home/moritz/people/MoreData/genomes/img_od1s"
img_fasta = "/home/moritz/people/MoreData/raw_imgs/od1s.fasta"
img_xls = "/home/moritz/people/MoreData/raw_imgs/od1s.xls"
name = "parcu_from_img_"
taxDb = NCBITaxa()
contigs = DataFrame.from_csv(img_xls, sep="\t", header=0, index_col=0)
manual_taxo = taxDb.get_name_translator(['Candidatus Parcubacteria'
]).values()[0][0]
metadata = {
name + str(g): {
'IMG_ID': g,
'name': name + str(g),
'species_taxid': manual_taxo,
'long_name': contigs.loc[contigs['Genome ID'] == g]['Genome'].iloc[0]
}
for g in set(contigs['Genome ID'])
}
seq_dict = {k: [] for k in metadata}
with open(img_fasta, "r") as file:
for i, c in enumerate(SeqIO.parse(file, "fasta")):
seq_dict[name + str(contigs.iloc[i]['Genome ID'])] += [c]
def run(args):
# add lineage profiles/stats
import re
from ete2 import PhyloTree, NCBITaxa
if not args.taxonomy and not args.info:
args.taxonomy = True
ncbi = NCBITaxa()
all_taxids = {}
all_names = set()
queries = []
if not args.search:
log.error('Search terms should be provided (i.e. --search) ')
sys.exit(-1)
for n in args.search:
queries.append(n)
try:
all_taxids[int(n)] = None
except ValueError:
all_names.add(n.strip())
# translate names
name2tax = ncbi.get_name_translator(all_names)
all_taxids.update([(v, None) for v in name2tax.values()])
not_found_names = all_names - set(name2tax.keys())
if args.fuzzy and not_found_names:
log.warn("%s unknown names", len(not_found_names))
for name in not_found_names:
# enable extension loading
tax, realname, sim = ncbi.get_fuzzy_name_translation(
name, args.fuzzy)
if tax:
all_taxids[tax] = None
name2tax[name] = tax
name2realname[name] = realname
name2score[name] = "Fuzzy:%0.2f" % sim
if args.taxonomy:
log.info("Dumping NCBI taxonomy of %d taxa..." % (len(all_taxids)))
t = ncbi.get_topology(all_taxids.keys(),
intermediate_nodes=args.full_lineage,
rank_limit=args.rank_limit,
collapse_subspecies=args.collapse_subspecies)
id2name = ncbi.get_taxid_translator([n.name for n in t.traverse()])
for n in t.traverse():
n.add_features(taxid=n.name)
n.add_features(sci_name=str(id2name.get(int(n.name), "?")))
n.name = "%s - %s" % (id2name.get(int(n.name), n.name), n.name)
lineage = ncbi.get_lineage(n.taxid)
n.add_features(
named_lineage='|'.join(ncbi.translate_to_names(lineage)))
dump(t,
features=[
"taxid", "name", "rank", "bgcolor", "sci_name",
"collapse_subspecies", "named_lineage"
])
elif args.info:
print '# ' + '\t'.join(
["Taxid", "Sci.Name", "Rank", "Named Lineage", "Taxid Lineage"])
translator = ncbi.get_taxid_translator(all_taxids)
ranks = ncbi.get_rank(all_taxids)
for taxid, name in translator.iteritems():
lineage = ncbi.get_lineage(taxid)
named_lineage = ','.join(ncbi.translate_to_names(lineage))
lineage_string = ','.join(map(str, lineage))
print '\t'.join([
str(taxid), name,
ranks.get(taxid, ''), named_lineage, lineage_string
])
def run(args):
# add lineage profiles/stats
import re
from ete2 import PhyloTree, NCBITaxa
# dump tree by default
if not args.tree and not args.info and not args.descendants:
args.tree = True
ncbi = NCBITaxa()
all_taxids = {}
all_names = set()
queries = []
if not args.search:
log.error('Search terms should be provided (i.e. --search) ')
sys.exit(-1)
for n in args.search:
queries.append(n)
try:
all_taxids[int(n)] = None
except ValueError:
all_names.add(n.strip())
# translate names
name2tax = ncbi.get_name_translator(all_names)
all_taxids.update([(v, None) for v in name2tax.values()])
not_found_names = all_names - set(name2tax.keys())
if args.fuzzy and not_found_names:
log.warn("%s unknown names", len(not_found_names))
for name in not_found_names:
# enable extension loading
tax, realname, sim = ncbi.get_fuzzy_name_translation(name, args.fuzzy)
if tax:
all_taxids[tax] = None
name2tax[name] = tax
name2realname[name] = realname
name2score[name] = "Fuzzy:%0.2f" %sim
if not_found_names:
log.warn("[%s] could not be translated into taxids!" %','.join(not_found_names))
if args.tree:
if len(all_taxids) == 1:
target_taxid = all_taxids.keys()[0]
log.info("Dumping NCBI descendants tree for %s" %(target_taxid))
t = ncbi.get_descendant_taxa(target_taxid, collapse_subspecies=args.collapse_subspecies, rank_limit=args.rank_limit, return_tree=True)
else:
log.info("Dumping NCBI taxonomy of %d taxa..." %(len(all_taxids)))
t = ncbi.get_topology(all_taxids.keys(),
intermediate_nodes=args.full_lineage,
rank_limit=args.rank_limit,
collapse_subspecies=args.collapse_subspecies)
id2name = ncbi.get_taxid_translator([n.name for n in t.traverse()])
for n in t.traverse():
n.add_features(taxid=n.name)
n.add_features(sci_name=str(id2name.get(int(n.name), "?")))
n.name = "%s - %s" %(id2name.get(int(n.name), n.name), n.name)
lineage = ncbi.get_lineage(n.taxid)
n.add_features(named_lineage = '|'.join(ncbi.translate_to_names(lineage)))
dump(t, features=["taxid", "name", "rank", "bgcolor", "sci_name",
"collapse_subspecies", "named_lineage"])
elif args.descendants:
log.info("Dumping NCBI taxonomy of %d taxa..." %(len(all_taxids)))
print '# ' + '\t'.join(["Taxid", "Sci.Name", "Rank", "descendant_taxids", "descendant_names"])
translator = ncbi.get_taxid_translator(all_taxids)
ranks = ncbi.get_rank(all_taxids)
for taxid in all_taxids:
descendants = ncbi.get_descendant_taxa(taxid, collapse_subspecies=args.collapse_subspecies, rank_limit=args.rank_limit)
print '\t'.join([str(taxid), translator.get(taxid, taxid), ranks.get(taxid, ''),
'|'.join(map(str, descendants)),
'|'.join(map(str, ncbi.translate_to_names(descendants)))])
elif args.info:
print '# ' + '\t'.join(["Taxid", "Sci.Name", "Rank", "Named Lineage", "Taxid Lineage"])
translator = ncbi.get_taxid_translator(all_taxids)
ranks = ncbi.get_rank(all_taxids)
for taxid, name in translator.iteritems():
lineage = ncbi.get_lineage(taxid)
named_lineage = ','.join(ncbi.translate_to_names(lineage))
lineage_string = ','.join(map(str, lineage))
print '\t'.join([str(taxid), name, ranks.get(taxid, ''), named_lineage, lineage_string])
from ete2 import NCBITaxa
from ete2 import Tree, TreeStyle, AttrFace
ncbi = NCBITaxa()
input = [l.rstrip("\n") for l in open("db/example_input", "r")]
taxid = ncbi.get_name_translator(input)
tree = ncbi.get_topology(taxid.values())
#print tree.get_ascii(attributes=["sci_name", "rank", "taxid"])
# custom layout: adds "rank" on top of branches, and sci_name as tip names
def my_layout(node):
if getattr(node, "rank", None):
rank_face = AttrFace("rank", fsize=7, fgcolor="indianred")
node.add_face(rank_face, column=0, position="branch-top")
if node.is_leaf():
sciname_face = AttrFace("sci_name", fsize=9, fgcolor="steelblue")
node.add_face(sciname_face, column=0, position="branch-right")
ts = TreeStyle()
ts.layout_fn = my_layout
ts.show_leaf_name = False
tree.render("tree.pdf", tree_style=ts)
from ete2 import NCBITaxa
from ete2 import Tree, TreeStyle, AttrFace
ncbi = NCBITaxa()
input = [l.rstrip("\n") for l in open("db/example_input", "r")]
taxid = ncbi.get_name_translator(input)
tree = ncbi.get_topology(taxid.values())
#print tree.get_ascii(attributes=["sci_name", "rank", "taxid"])
# custom layout: adds "rank" on top of branches, and sci_name as tip names
def my_layout(node):
if getattr(node, "rank", None):
rank_face = AttrFace("rank", fsize=7, fgcolor="indianred")
node.add_face(rank_face, column=0, position="branch-top")
if node.is_leaf():
sciname_face = AttrFace("sci_name", fsize=9, fgcolor="steelblue")
node.add_face(sciname_face, column=0, position="branch-right")
ts = TreeStyle()
ts.layout_fn = my_layout
ts.show_leaf_name = False
tree.render("tree.pdf", tree_style=ts)
