def test_get_subclasses_no_xref():
"""This HP has no subclasses and it has no xrefs. So just itself should be returne
as an entry, and xrefs should be an empty list"""
ubergraph = UberGraph()
iri = 'HP:0020154'
subs = ubergraph.get_subclasses_and_xrefs(iri)
assert len(subs) == 1
xrefs = list(subs.values())[0]
assert isinstance(xrefs, list)
assert len(xrefs) == 0
def test_get_subclasses_exact():
"""Check out that we can get subclasses, along with labels and the exact matches for them
Starting with Ciliophora infectious disease which has one subclass"""
ubergraph = UberGraph()
iri = 'MONDO:0005704'
subs = ubergraph.get_subclasses_and_exacts(iri)
assert len(subs) == 2
for k, v in subs.items():
print(k)
print(v)
def test_get_sub_exact_no_exact():
"""If a class doesn't have any exact matches, do we still get it?"""
ubergraph = UberGraph()
#this should have 3 subclasses. One of them (MONDO:0022643) has no exact matches
iri = 'MONDO:0002355'
subs = ubergraph.get_subclasses_and_exacts(iri)
assert len(subs) == 4 #self gets returned too
k = ('MONDO:0022643', 'carcinoma of the vocal tract')
assert k in subs
assert len(subs[k]) == 0
print(subs)
def test_get_subclasses_xref():
"""check that we get both direct and indirect subclasses of a node.
We're using chemoreceptor cell to test, which has 4 direct children,
2 of which have children, for 12 total descendents. The query also
returns the input in the output, so that's 13 total"""
ubergraph = UberGraph()
iri = 'CL:0000206'
subs = ubergraph.get_subclasses_and_xrefs(iri)
assert len(subs) == 13
xrefs = subs[('CL:0000207', 'olfactory receptor cell')]
assert len(xrefs) == 3
def build_pr_uniprot_relationships(outfile, ignore_list=[]):
"""Given an IRI create a list of sets. Each set is a set of equivalent LabeledIDs, and there
is a set for each subclass of the input iri. Write these lists to concord files, indexed by the prefix"""
iri = 'PR:000000001'
uber = UberGraph()
pro_res = uber.get_subclasses_and_xrefs(iri)
with open(outfile, 'w') as concfile:
for k, v in pro_res.items():
for x in v:
if Text.get_curie(x) not in ignore_list:
if k.startswith('PR'):
concfile.write(f'{k}\txref\t{x}\n')
def test_get_subclasses():
"""check that we get both direct and indirect subclasses of a node.
We're using chemoreceptor cell to test, which has 4 direct children,
2 of which have children, for 12 total descendents. The query also
returns the input in the output, so that's 13 total"""
ubergraph = UberGraph()
iri = 'CL:0000206'
subs = ubergraph.get_subclasses_of(iri)
assert len(subs) == 13
for sub in subs:
assert 'descendent' in sub
assert sub['descendent'].startswith('CL')
assert 'descendentLabel' in sub
def pull_uber_labels(expected):
uber = UberGraph()
labels = uber.get_all_labels()
ldict = defaultdict(set)
for unit in labels:
iri = unit['iri']
p = iri.split(':')[0]
ldict[p].add((unit['iri'], unit['label']))
for p in ldict:
if p not in ['http', 'ro'] and not p.startswith('t') and not '#' in p:
fname = make_local_name('labels', subpath=p)
with open(fname, 'w') as outf:
for unit in ldict[p]:
outf.write(f'{unit[0]}\t{unit[1]}\n')
def pull_uber_synonyms(expected):
uber = UberGraph()
labels = uber.get_all_synonyms()
ldict = defaultdict(set)
for unit in labels:
iri = unit[0]
p = iri.split(':')[0]
ldict[p].add(unit)
#There are some of the ontologies that we don't get synonyms for. But this makes snakemake unhappy so
# we are going to make some zero-length files for it
for p in expected:
if p not in ['http', 'ro'] and not p.startswith('t') and not '#' in p:
fname = make_local_name('synonyms', subpath=p)
with open(fname, 'w') as outf:
for unit in ldict[p]:
outf.write(f'{unit[0]}\t{unit[1]}\t{unit[2]}\n')
def write_obo_ids(irisandtypes, outfile, order, exclude=[]):
uber = UberGraph()
iris_to_types = defaultdict(set)
for iri, ntype in irisandtypes:
uberres = uber.get_subclasses_of(iri)
for k in uberres:
iris_to_types[k['descendent']].add(ntype)
excludes = []
for excluded_iri in exclude:
excludes += uber.get_subclasses_of(excluded_iri)
excluded_iris = set([k['descendent'] for k in excludes])
prefix = Text.get_curie(iri)
with open(outfile, 'w') as idfile:
for kd, typeset in iris_to_types.items():
if kd not in excluded_iris and kd.startswith(prefix):
l = list(typeset)
l.sort(key=lambda k: order.index(k))
idfile.write(f'{kd}\t{l[0]}\n')