def test_to_gff(self, test_data_dir, tmp_path):
"""Parse GFF, write to disk, parse, compare"""
gff = test_data_dir / "INSC1006_chrI.gff3"
parsed = list(parse_standard_gff3(gff))
a = [x.to_annotation_collection() for x in parsed]
tmp_gff = tmp_path / "tmp.gff"
with open(tmp_gff, "w") as fh:
collection_to_gff3(a, fh)
gff2 = list(parse_standard_gff3(tmp_gff))
a2 = [x.to_annotation_collection() for x in gff2]
for c1, c2 in zip(a, a2):
assert c1.to_dict() == c2.to_dict()
def test_parse_insc1006(self, test_data_dir):
"""INSC1006_chrI is a 4-gene manually built file from INSC1006. It uses the default naive parser."""
gff = test_data_dir / "INSC1006_chrI.gff3"
recs = list(parse_standard_gff3(gff))
c = recs[0].annotation
with open(test_data_dir / "INSC1006_chrI.json") as fh:
assert AnnotationCollectionModel.Schema().load(json.load(fh)) == c
def test_parse_peg10(self, test_data_dir):
"""
PEG10 is a gene with a -1 frameshift in one isoform, that is parsed using the RefSeq parser.
"""
gff = test_data_dir / "PEG10_minus1frameshift.gff3"
rec = list(parse_standard_gff3(gff))[0]
with open(test_data_dir / "PEG10_minus1frameshift.json") as fh:
assert AnnotationCollectionModel.Schema().load(json.load(fh)) == rec.annotation
def test_parse_non_gene_locus_tag(self, test_data_dir):
"""Ran into bug in which non-gene feature with locus tag led to error, ensure handled correctly. Using cases
from S288C gff3 that surfaced the issue."""
gff = test_data_dir / "feature_test_non_gene_locus_tag.gff"
recs = list(parse_standard_gff3(gff))
features = list(recs[0].annotation.to_annotation_collection())
assert features[0].to_dict()["locus_tag"] is None
assert features[1].to_dict()["locus_tag"] == "YFL007W"
def test_transitive(self, test_data_dir):
"""Test transitive loops"""
for gff in ["SGCE.gff3", "FRG2B.gff3", "PEG10_minus1frameshift.gff3", "INSC1006_chrI.gff3"]:
gff = test_data_dir / gff
recs = list(parse_standard_gff3(gff))
c = recs[0].to_annotation_collection()
assert (
AnnotationCollectionModel.Schema().load(c.to_dict()).to_annotation_collection().to_dict() == c.to_dict()
)
def test_transcript_inference(self, test_data_dir):
recs = list(parse_standard_gff3(test_data_dir / "feature_test_1.gff"))
c = recs[0].annotation.to_annotation_collection()
# 4 total genes
assert len(c.genes) == 4
# two different types of pseudogene transcripts were inferred, one without exons and one with exons
# one gene with an invalid biotype who was set to None
assert len([x for x in c.genes if x.gene_type == Biotype.pseudogene]) == 2
assert len([x for x in c.genes if x.gene_type == Biotype.lncRNA]) == 1
invalid_biotype = [x for x in c.genes if not x.gene_type]
assert len(invalid_biotype) == 1
assert list(invalid_biotype[0].qualifiers["provided_biotype"])[0] == "invalid"
def test_gff3_strand_error(self, tmp_path):
tmp_gff3 = tmp_path / "tmp.gff3"
annot = self.annot.to_annotation_collection().to_dict()
annot["feature_collections"][0]["feature_intervals"][0][
"strand"] = "MINUS"
annot = AnnotationCollectionModel.Schema().load(
annot).to_annotation_collection()
with open(tmp_gff3, "w") as fh:
collection_to_gff3([annot], fh)
with pytest.raises(GFF3ChildParentMismatchError):
_ = list(parse_standard_gff3(tmp_gff3))
def test_parse_sgce(self, test_data_dir):
"""
SGCE is an example of a protein coding gene with multiple isoforms, that is parsed using the RefSeq parser.
"""
gff = test_data_dir / "SGCE.gff3"
recs = list(parse_standard_gff3(gff))
assert len(recs) == 1
rec = recs[0]
genes = rec.annotation.genes
assert len(genes) == 1
gene = genes[0]
txs = gene.transcripts
assert len(txs) == 22
with open(test_data_dir / "SGCE.json") as fh:
assert AnnotationCollectionModel.Schema().load(json.load(fh)) == rec.annotation
def test_parse_frg2b(self, test_data_dir):
"""
FRG2B is an example of a standard coding gene.
"""
gff = test_data_dir / "FRG2B.gff3"
recs = list(parse_standard_gff3(gff))
assert len(recs) == 1
rec = recs[0]
genes = rec.annotation.genes
assert len(genes) == 1
assert rec.annotation.feature_collections is None
gene = genes[0]
txs = gene.transcripts
assert len(txs) == 1
tx = txs[0]
assert tx.__dict__ == {
"exon_starts": [133623894, 133625921, 133626228, 133626564],
"exon_ends": [133625604, 133625999, 133626303, 133626795],
"strand": Strand.MINUS,
"cds_starts": [133625098, 133625921, 133626228, 133626564],
"cds_ends": [133625604, 133625999, 133626303, 133626742],
"cds_frames": [CDSFrame.ONE, CDSFrame.ONE, CDSFrame.ONE, CDSFrame.ZERO],
"qualifiers": {
"Dbxref": ["Ensembl:ENST00000425520.2", "Genbank:NM_001080998.2", "GeneID:441581", "HGNC:HGNC:33518"],
"gbkey": ["mRNA"],
"gene": ["FRG2B"],
"tag": ["MANE Select"],
},
"is_primary_tx": False,
"transcript_id": "NM_001080998.2",
"protein_id": "NP_001074467.1",
"product": "protein FRG2-like-1",
"transcript_symbol": None,
"transcript_type": Biotype.protein_coding,
"sequence_name": "NC_000010.11",
"sequence_guid": None,
"transcript_interval_guid": None,
"transcript_guid": None,
}
def test_gff3_locus_tag_error(self, test_data_dir):
with pytest.raises(GFF3LocusTagError):
_ = list(
parse_standard_gff3(test_data_dir /
"feature_test_locus_tag_error.gff"))
def test_direct_cds_exon(self, test_data_dir):
recs = list(parse_standard_gff3(test_data_dir / "gene_cds_direct_child.gff3"))
c = recs[0].annotation
with open(test_data_dir / "gene_cds_direct_child.json") as fh:
assert AnnotationCollectionModel.Schema().load(json.load(fh)) == c
def test_parse_feature_tests(self, test_data_dir, gff3, json_file):
recs = list(parse_standard_gff3(test_data_dir / gff3))
c = recs[0].annotation
with open(test_data_dir / json_file) as fh:
assert AnnotationCollectionModel.Schema().load(json.load(fh)) == c