mirror of
https://github.com/chanzuckerberg/cellxgene.git
synced 2026-09-15 20:57:56 +08:00
2689d8d2c0
* add function to retrieve latest annotation from db, db updates * read and write tiledb arrays * adding tests
79 lines
2.6 KiB
Python
79 lines
2.6 KiB
Python
from abc import ABCMeta, abstractmethod
|
|
|
|
import fastobo
|
|
import fsspec
|
|
from server.common.errors import OntologyLoadFailure
|
|
|
|
from server.common.utils import series_to_schema
|
|
|
|
|
|
class Annotations(metaclass=ABCMeta):
|
|
""" baseclass for annotations, including ontologies"""
|
|
|
|
""" our default ontology is the PURL for the Cell Ontology.
|
|
See http://www.obofoundry.org/ontology/cl.html """
|
|
DefaultOnotology = "http://purl.obolibrary.org/obo/cl.obo"
|
|
|
|
def __init__(self):
|
|
self.ontology_data = None
|
|
|
|
def load_ontology(self, path):
|
|
"""Load and parse ontologies - currently support OBO files only."""
|
|
if path is None:
|
|
path = self.DefaultOnotology
|
|
|
|
try:
|
|
with fsspec.open(path) as f:
|
|
obo = fastobo.iter(f)
|
|
terms = filter(lambda stanza: type(stanza) is fastobo.term.TermFrame, obo)
|
|
names = [tag.name for term in terms for tag in term if type(tag) is fastobo.term.NameClause]
|
|
self.ontology_data = names
|
|
|
|
except FileNotFoundError as e:
|
|
raise OntologyLoadFailure("Unable to find OBO ontology path") from e
|
|
|
|
except SyntaxError as e:
|
|
raise OntologyLoadFailure("Syntax error loading OBO ontology") from e
|
|
|
|
except Exception as e:
|
|
raise OntologyLoadFailure("Error loading OBO file") from e
|
|
|
|
def get_schema(self, data_adaptor):
|
|
schema = []
|
|
labels = self.read_labels(data_adaptor)
|
|
if labels is not None and not labels.empty:
|
|
for col in labels.columns:
|
|
col_schema = dict(name=col, writable=True)
|
|
col_schema.update(series_to_schema(labels[col]))
|
|
schema.append(col_schema)
|
|
|
|
return schema
|
|
|
|
@abstractmethod
|
|
def set_collection(self, name):
|
|
"""set or create a new annotation collection"""
|
|
pass
|
|
|
|
@abstractmethod
|
|
def read_labels(self, data_adaptor):
|
|
"""Return the labels as a pandas.DataFrame"""
|
|
pass
|
|
|
|
@abstractmethod
|
|
def write_labels(self, df, data_adaptor):
|
|
"""Write the labels (df) to a persistent storage such that it can later be read"""
|
|
pass
|
|
|
|
def update_parameters(self, parameters, data_adaptor):
|
|
"""Update configuration parameters that describe information about the annotations feature"""
|
|
params = {}
|
|
params["annotations"] = True
|
|
|
|
if self.ontology_data:
|
|
params["annotations_cell_ontology_enabled"] = True
|
|
params["annotations_cell_ontology_terms"] = self.ontology_data
|
|
else:
|
|
params["annotations_cell_ontology_enabled"] = False
|
|
|
|
parameters.update(params)
|