def read(self):
"""
Returns gene annotation list and ontology graph read from nexo file.
"""
content_handler = NexoContentHandler(self.get_all_attrs,
self.annotation_source)
xml.sax.parse(self.handle, content_handler)
annotations = []
for obj, assocs in content_handler.annotations.items():
annotations.append(
GeneAnnotation(
obj, associations=[TermAssociation(x) for x in assocs]))
graph = OntologyGraph()
for _, node in content_handler.nodes.items():
graph.add_node(node.id, node)
edge_types = set()
for edge in content_handler.edges:
source = content_handler.nodes[edge[0]].id
target = content_handler.nodes[edge[1]].id
graph.add_edge(target, source,
edge[2]) # in our representation it is inverted
edge_types.add(edge[2])
for edge_type in edge_types:
graph.typedefs[edge_type] = {"id": edge_type}
return (annotations, graph)
def test_resolve(self): #TODO
assocs = [GeneAnnotation('FBgn0004364', attrs = {'Synonym':
['18wheeler', 'CG8896', 'CT25100']}),
GeneAnnotation('FBgn0043467'),
GeneAnnotation('FBgn0004907', attrs = {'Synonym':
['14-3-3', '14-3-3 zeta', 'x']}),
GeneAnnotation('FBgn0010339', attrs = {'Synonym':
['CG8340', 'GTP-bp', 'X71866', 'x']})
]
resolver = FirstOneResolver(assocs)
resolved = [resolver.resolve(x) for x in ['FBgn0043467', 'CT25100',
'x', 'FBgn0010340']]
print "dupa", resolved
expected = ['FBgn0043467', 'FBgn0004364', 'FBgn0004907', 'FBgn0010340']
self.assertEqual(expected, resolved)
def _to_goa(obj_rows, version):
row = obj_rows[0]
obj_id = row[1]
obj_attrs = {GAF20FIELDS[0] : row[0],
GAF20FIELDS[2] : row[2],
GAF20FIELDS[9] : row[9],
GAF20FIELDS[10] : _split_multi(row[10]),
GAF20FIELDS[11] : row[11],
GAF20FIELDS[12]: _split_multi(row[12])}
if version == "1.0":
row_len = 15
else:
row_len = 17
obj_attrs[GAF20FIELDS[15]] = _split_multi(row[15])
obj_attrs[GAF20FIELDS[16]] = row[16]
assocs = []
for row in obj_rows:
if len(row) == row_len:
assocs.append(TermAssociation(row[4],
{GAF20FIELDS[3] : _split_multi(row[3]),
GAF20FIELDS[5] : _split_multi(row[5]),
GAF20FIELDS[6] : row[6],
GAF20FIELDS[7] :_split_multi(row[7]),
GAF20FIELDS[8] : row[8],
GAF20FIELDS[13] : row[13],
GAF20FIELDS[14] : row[14]}
))
else:
raise ValueError("Invalid gaf file: Incorrect row length.")
return GeneAnnotation(obj_id, assocs, obj_attrs)
def test_read_file(self):
to = {
'FBgn0026615':
GeneAnnotation(
'FBgn0026615', [
TermAssociation(
'GO:0005737', {
GAF20FIELDS[3]: [],
GAF20FIELDS[5]: ['FB:FBrf0106275'],
GAF20FIELDS[6]: 'IDA',
GAF20FIELDS[7]: [],
GAF20FIELDS[8]: 'C',
GAF20FIELDS[13]: '20060803',
GAF20FIELDS[14]: 'FlyBase'
}),
TermAssociation(
'GO:0045177', {
GAF20FIELDS[3]: [],
GAF20FIELDS[5]: ['FB:FBrf0106275'],
GAF20FIELDS[6]: 'IDA',
GAF20FIELDS[7]: [],
GAF20FIELDS[8]: 'C',
GAF20FIELDS[13]: '20060803',
GAF20FIELDS[14]: 'FlyBase'
})
], {
GAF20FIELDS[0]: 'FB',
GAF20FIELDS[2]: '10-4',
GAF20FIELDS[9]: '10-4',
GAF20FIELDS[10]: [],
GAF20FIELDS[11]: 'gene_product',
GAF20FIELDS[12]: ['taxon:7227'],
GAF20FIELDS[15]: [],
GAF20FIELDS[16]: ''
}),
'FBgn0043467':
GeneAnnotation(
'FBgn0043467', [
TermAssociation(
'GO:0048149', {
GAF20FIELDS[3]: [],
GAF20FIELDS[5]:
['FB:FBrf0131396', 'PMID:11086999'],
GAF20FIELDS[6]: 'IMP',
GAF20FIELDS[7]: [],
GAF20FIELDS[8]: 'P',
GAF20FIELDS[13]: '20060803',
GAF20FIELDS[14]: 'FlyBase'
})
], {
GAF20FIELDS[0]: 'FB',
GAF20FIELDS[2]: '064Ya',
GAF20FIELDS[9]: '064Ya',
GAF20FIELDS[10]: [],
GAF20FIELDS[11]: 'gene_product',
GAF20FIELDS[12]: ['taxon:7227'],
GAF20FIELDS[15]: [],
GAF20FIELDS[16]: ''
})
}
with open('Ontology/GoaIO/correct20.fb', 'r') as f:
objs = GafReader(f).read()
self.assertEqual(to, objs)