def trio_persons(family_id="trio_family"):
return [
Person(
**{
"family_id": family_id,
"person_id": "mom",
"sex": "F",
"role": "mom",
"status": 1
}),
Person(
**{
"family_id": family_id,
"person_id": "dad",
"sex": "M",
"role": "dad",
"status": 1
}),
Person(
**{
"family_id": family_id,
"person_id": "p1",
"sex": "M",
"role": "prb",
"status": 2
}),
]
def get_persons(self, roles=None, person_ids=None, family_ids=None):
persons = self.rest_client.post_pheno_persons(self.dataset_id, roles,
person_ids, family_ids)
for k, v in persons.items():
persons[k] = Person(**v)
return persons
def member7():
return Person(
person_id="id3",
family_id="fam3",
mom_id="mom3",
dad_id="0",
sex="1",
status="2",
role="prb",
)
def member5():
return Person(
person_id="mom2",
family_id="fam2",
mom_id="0",
dad_id="0",
sex="2",
status="1",
role="mom",
layout="1:50.0,50.0",
generated=False,
)
def member4():
return Person(
person_id="id2",
family_id="fam2",
mom_id="mom2",
dad_id="dad2",
sex="1",
status="2",
role="prb",
layout="2:100.0,75.0",
generated=False,
)
def member3():
return Person(
person_id="dad1",
family_id="fam1",
mom_id="0",
dad_id="0",
sex="1",
status="1",
role="dad",
layout="error",
generated=True,
)
def member2():
return Person(
person_id="mom1",
family_id="fam1",
mom_id="0",
dad_id="0",
sex="2",
status="1",
role="mom",
layout="error",
generated=False,
)
def _build_families(self):
families = dict()
families_details = self.rest_client.get_all_family_details(
self._remote_study_id)
for family in families_details:
family_id = family["family_id"]
person_jsons = family["members"]
family_members = []
for person_json in person_jsons:
family_members.append(Person(**person_json))
families[family_id] = Family.from_persons(family_members)
self._families = FamiliesData.from_families(families)
def multiplex_persons():
persons = trio_persons("multiplex_family")
persons.append(
Person(
**{
"family_id": "multiplex_family",
"person_id": "s1",
"sex": "M",
"role": "sib",
"status": 2
}))
return persons
def multigenerational_persons():
persons = trio_persons("multigenerational_family")
persons.append(
Person(
**{
"family_id": "multigenerational_family",
"person_id": "grandparent",
"sex": "M",
"role": str(Role.maternal_grandfather),
"status": 1
}))
return persons
def quad_persons():
persons = trio_persons("quad_family")
persons.append(
Person(
**{
"family_id": "quad_family",
"person_id": "s1",
"sex": "M",
"role": "sib",
"status": 1
}))
return persons
def member6():
return Person(
person_id="dad2",
family_id="fam2",
mom_id="0",
dad_id="0",
sex="1",
status="1",
role="dad",
layout="1:50.0,100.0",
generated=True,
)
def test_family_type_multigenerational(role):
persons = list(trio_persons("multigenerational"))
persons.append(
Person(
**{
"family_id": "multigenerational",
"person_id": "grandparent",
"sex": "U",
"role": str(role),
"status": 1
}))
family = Family.from_persons(persons)
assert family.family_type is FamilyType.MULTIGENERATIONAL
def simplex_persons_2():
persons = trio_persons("simplex_family")
persons[0]._status = 2
persons[0]._attributes["status"] = 2
persons.append(
Person(
**{
"family_id": "simplex_family",
"person_id": "s1",
"sex": "M",
"role": "sib",
"status": 1
}))
return persons
def get_persons(
self,
roles: Optional[Iterable[Role]] = None,
person_ids: Optional[Iterable[str]] = None,
family_ids: Optional[Iterable[str]] = None) -> Dict[str, Person]:
"""Returns individuals data from phenotype database.
`roles` -- specifies persons of which role should be returned. If not
specified returns all individuals from phenotype database.
`person_ids` -- list of person IDs to filter result. Only data for
individuals with person_id in the list `person_ids` are returned.
`family_ids` -- list of family IDs to filter result. Only data for
individuals that are members of any of the specified `family_ids`
are returned.
Returns a dictionary of (`personId`, `Person()`) where
the `Person` object is the same object used into `VariantDB` families.
"""
persons = {}
df = self.get_persons_df(
roles=roles, person_ids=person_ids, family_ids=family_ids)
for row in df.to_dict("records"):
person_id = row["person_id"]
p = Person(**row)
# p.person_id = person_id
# p.family_id = family_id
assert row["role"] in Role, "{} not a valid role".format(
row["role"]
)
assert row["sex"] in Sex, "{} not a valid sex".format(row["sex"])
assert row["status"] in Status, "{} not a valid status".format(
row["status"]
)
persons[person_id] = p
return persons
def add_missing_members(family):
new_members = []
id_to_individual = defaultdict(Individual)
for member in family.full_members:
individual = id_to_individual[member.person_id]
individual.member = member
missing_father_mothers = {}
missing_mother_fathers = {}
for member in family.full_members:
if member.mom_id == member.dad_id:
continue
if member.mom_id is None:
assert member.dad_id is not None
if member.dad_id not in missing_mother_fathers:
missing_mother_fathers[member.dad_id] = Person(
person_id=member.dad_id + ".mother",
family_id=family.family_id,
mom_id="0",
dad_id="0",
sex="2",
status="-",
role=Role.unknown,
generated=True,
)
new_members.append(missing_mother_fathers[member.dad_id])
member.mom_id = member.dad_id + ".mother"
elif member.dad_id is None:
assert member.mom_id is not None
if member.mom_id not in missing_father_mothers:
missing_father_mothers[member.mom_id] = Person(
person_id=member.mom_id + ".father",
family_id=family.family_id,
mom_id="0",
dad_id="0",
sex="1",
status="-",
role=Role.unknown,
generated=True,
)
new_members.append(missing_father_mothers[member.mom_id])
member.dad_id = member.mom_id + ".father"
mother = id_to_individual[member.mom_id]
father = id_to_individual[member.dad_id]
if mother.member is None and mother not in new_members:
mother.member = Person(
person_id=member.mom_id,
family_id=family.family_id,
mom_id="0",
dad_id="0",
sex=Sex.F,
status=Status.unspecified,
role=Role.unknown,
generated=True,
)
new_members.append(mother.member)
if father.member is None and father not in new_members:
father.member = Person(
person_id=member.dad_id,
family_id=family.family_id,
mom_id="0",
dad_id="0",
sex="1",
status="-",
role=Role.unknown,
generated=True,
)
new_members.append(father.member)
unique_new_members_ids = set([])
unique_new_members = []
for person in new_members:
if person.person_id in unique_new_members_ids:
continue
unique_new_members.append(person)
unique_new_members_ids.add(person.person_id)
family.add_members(unique_new_members)
def load_simple_families_file(infile, ped_sep="\t"):
fam_df = pd.read_csv(
infile,
sep=ped_sep,
index_col=False,
skipinitialspace=True,
converters={
"role": lambda r: Role.from_name(r),
"gender": lambda s: Sex.from_name(s),
"sex": lambda s: Sex.from_name(s),
},
dtype={
"familyId": str,
"personId": str
},
comment="#",
)
fam_df = fam_df.rename(columns={
"gender": "sex",
"personId": "person_id",
"familyId": "family_id",
"momId": "mom_id",
"dadId": "dad_id",
"sampleId": "sample_id",
}, )
fam_df["status"] = pd.Series(index=fam_df.index, data=1)
fam_df.loc[fam_df.role == Role.prb, "status"] = 2
fam_df["status"] = fam_df.status.apply(lambda s: Status.from_value(s))
fam_df["mom_id"] = pd.Series(index=fam_df.index, data="0")
fam_df["dad_id"] = pd.Series(index=fam_df.index, data="0")
if "sample_id" not in fam_df.columns:
sample_ids = pd.Series(data=fam_df["person_id"].values)
fam_df["sample_id"] = sample_ids
families = defaultdict(list)
for rec in fam_df.to_dict(orient="records"):
families[rec["family_id"]].append(rec)
result = defaultdict(list)
for fam_id, members in families.items():
mom_id = None
dad_id = None
children = []
for member in members:
role = member["role"]
if role == Role.mom:
mom_id = member["person_id"]
elif role == Role.dad:
dad_id = member["person_id"]
else:
assert role in set([Role.prb, Role.sib])
children.append(member)
for child in children:
child["mom_id"] = mom_id
child["dad_id"] = dad_id
result[fam_id] = [Person(**member) for member in members]
return FamiliesData.from_family_persons(result)