def t_gff_annotations(self):
"""Check GFF annotations placed on an entire sequence.
"""
feature_adder = GFFMapReduceFeatureAdder(dict())
feature_adder.add_features(self._test_gff_ann_file)
final_rec = feature_adder.base['I']
assert len(final_rec.annotations.keys()) == 2
assert final_rec.annotations['source'] == ['Expr_profile']
assert final_rec.annotations['expr_profile'] == ['B0019.1']
def t_no_dict_error(self):
"""Ensure an error is raised when no dictionary to map to is present.
"""
feature_adder = GFFMapReduceFeatureAdder(dict(), create_missing=False)
try:
feature_adder.add_features(self._test_gff_file)
# no error -- problem
raise AssertionError('Did not complain with missing dictionary')
except KeyError:
pass
def t_local_map_reduce(self):
"""General map reduce framework without parallelization.
"""
cds_limit_info = dict(
gff_type = ["gene", "mRNA", "CDS"],
gff_id = ['I']
)
feature_adder = GFFMapReduceFeatureAdder(dict(), None)
feature_adder.add_features(self._test_gff_file, cds_limit_info)
final_rec = feature_adder.base['I']
assert len(final_rec.features) == 32
def t_tricky_semicolons(self):
"""Parsing of tricky semi-colon positions in WormBase GFF2.
"""
limit_info = dict(
gff_source_type = [('Genomic_canonical', 'region')]
)
feature_adder = GFFMapReduceFeatureAdder(dict())
feature_adder.add_features(self._wormbase_file, limit_info)
assert len(feature_adder.base['I'].features) == 1
test_feature = feature_adder.base['I'].features[0]
assert test_feature.qualifiers['Note'] == \
['Clone cTel33B; Genbank AC199162', 'Clone cTel33B; Genbank AC199162']
def t_jgi_gff(self):
"""Parsing of JGI formatted GFF2, nested using transcriptId and proteinID
"""
feature_adder = GFFMapReduceFeatureAdder(dict())
feature_adder.add_features(self._jgi_file)
tfeature = feature_adder.base['chr_1'].features[0]
assert tfeature.location.nofuzzy_start == 37060
assert tfeature.location.nofuzzy_end == 38216
assert tfeature.type == 'inferred_parent'
assert len(tfeature.sub_features) == 6
sfeature = tfeature.sub_features[1]
assert sfeature.qualifiers['proteinId'] == ['873']
assert sfeature.qualifiers['phase'] == ['0']
def t_basic_solid_parse(self):
"""Basic parsing of SOLiD GFF results files.
"""
feature_adder = GFFMapReduceFeatureAdder(dict())
feature_adder.add_features(self._test_gff_file)
test_feature = feature_adder.base['3_341_424_F3'].features[0]
assert test_feature.location.nofuzzy_start == 102716
assert test_feature.location.nofuzzy_end == 102736
assert len(test_feature.qualifiers) == 7
assert test_feature.qualifiers['score'] == ['10.6']
assert test_feature.qualifiers['source'] == ['solid']
assert test_feature.strand == -1
assert test_feature.type == 'read'
assert test_feature.qualifiers['g'] == ['T2203031313223113212']
assert len(test_feature.qualifiers['q']) == 20
def t_basic_attributes(self):
"""Parse out basic attributes of GFF2 from Ensembl GTF.
"""
limit_info = dict(
gff_source_type = [('snoRNA', 'exon')]
)
feature_adder = GFFMapReduceFeatureAdder(dict())
feature_adder.add_features(self._ensembl_file, limit_info)
assert len(feature_adder.base['I'].features) == 1
test_feature = feature_adder.base['I'].features[0]
qual_keys = test_feature.qualifiers.keys()
qual_keys.sort()
assert qual_keys == ['Parent', 'exon_number', 'gene_id', 'gene_name',
'source', 'transcript_id', 'transcript_name']
assert test_feature.qualifiers['source'] == ['snoRNA']
assert test_feature.qualifiers['transcript_name'] == ['NR_001477.2']
assert test_feature.qualifiers['exon_number'] == ['1']
def t_disco_map_reduce(self):
"""Map reduce framework parallelized using disco.
"""
# this needs to be more generalized but fails okay with no disco
try:
import disco
import simplejson
except ImportError:
print "Skipping -- disco and json not found"
return
cds_limit_info = dict(
gff_source_type = [('Non_coding_transcript', 'gene'),
('Coding_transcript', 'gene'),
('Coding_transcript', 'mRNA'),
('Coding_transcript', 'CDS')],
gff_id = ['I']
)
feature_adder = GFFMapReduceFeatureAdder(dict(),
disco_host=self._disco_host)
feature_adder.add_features(self._test_gff_file, cds_limit_info)
final_rec = feature_adder.base['I']
# second gene feature is multi-parent
assert len(final_rec.features) == 2 # two gene feature
