def test_gaf_to_gpad2():
line = "PomBase\tSPAC25B8.17\typf1\t\tGO:0000006\tGO_REF:0000024\tISO\tSGD:S000001583\tC\tintramembrane aspartyl protease of the perinuclear ER membrane Ypf1 (predicted)\tppp81\tprotein\ttaxon:999|taxon:888\t20150305\tPomBase\tpart_of(X:1)\tUniProtKB:P12345"
parser = gafparser.GafParser()
out = io.StringIO()
writer = assocwriter.GpadWriter(version=assocwriter.GPAD_2_0, file=out)
assoc = parser.parse_line(line).associations[0]
writer.write_assoc(assoc)
lines = out.getvalue().split("\n")
assert lines[0] == "!gpa-version: 2.0"
assert lines[
1] == "PomBase:SPAC25B8.17\t\tBFO:0000050\tGO:0000006\tGO_REF:0000024\tECO:0000266\tSGD:S000001583\tNCBITaxon:888\t2015-03-05\tPomBase\tBFO:0000050(X:1)\t"
line = "PomBase\tSPAC25B8.17\typf1\tNOT\tGO:0000006\tGO_REF:0000024\tISO\tSGD:S000001583\tC\tintramembrane aspartyl protease of the perinuclear ER membrane Ypf1 (predicted)\tppp81\tprotein\ttaxon:999|taxon:888\t20150305\tPomBase\tpart_of(X:1)\tUniProtKB:P12345"
parser = gafparser.GafParser()
out = io.StringIO()
writer = assocwriter.GpadWriter(version=assocwriter.GPAD_2_0, file=out)
assoc = parser.parse_line(line).associations[0]
writer.write_assoc(assoc)
lines = out.getvalue().split("\n")
assert lines[0] == "!gpa-version: 2.0"
assert lines[
1] == "PomBase:SPAC25B8.17\tNOT\tBFO:0000050\tGO:0000006\tGO_REF:0000024\tECO:0000266\tSGD:S000001583\tNCBITaxon:888\t2015-03-05\tPomBase\tBFO:0000050(X:1)\t"
def test_roundtrip():
"""
Start with a line, parse it, then write it. The beginning line should be the same as what was written.
"""
line = "PomBase\tSPAC25B8.17\typf1\t\tGO:0000006\tGO_REF:0000024\tISO\tSGD:S000001583\tC\tintramembrane aspartyl protease of the perinuclear ER membrane Ypf1 (predicted)\tppp81\tprotein\ttaxon:999|taxon:888\t20150305\tPomBase\tfoo(X:1)\tUniProtKB:P12345"
parser = gafparser.GafParser()
out = io.StringIO()
writer = assocwriter.GafWriter(file=out)
assoc_dict = parser.parse_line(line).associations[0]
writer.write_assoc(assoc_dict)
gaf = [
line for line in out.getvalue().split("\n") if not line.startswith("!")
][0]
assert line == gaf
# Single taxon
line = "PomBase\tSPAC25B8.17\typf1\t\tGO:0000006\tGO_REF:0000024\tISO\tSGD:S000001583\tC\tintramembrane aspartyl protease of the perinuclear ER membrane Ypf1 (predicted)\tppp81\tprotein\ttaxon:1111\t20150305\tPomBase\tfoo(X:1)\tUniProtKB:P12345"
parser = gafparser.GafParser()
out = io.StringIO()
writer = assocwriter.GafWriter(file=out)
assoc_dict = parser.parse_line(line).associations[0]
writer.write_assoc(assoc_dict)
gaf = [
line for line in out.getvalue().split("\n") if not line.startswith("!")
][0]
assert line == gaf
def test_gaf2_2_qualifier_to_gaf2_1():
# Qualifier is `part_of` and should be returned blank instead of removing the whole line
line = "WB\tWBGene00000001\taap-1\tinvolved_in\tGO:0008286\tWB_REF:WBPaper00005614|PMID:12393910\tIMP\t\tP\t\tY110A7A.10\tgene\ttaxon:6239\t20060302\tWB\t\t"
parser = gafparser.GafParser()
parser.version = "2.2"
out = io.StringIO()
writer = assocwriter.GafWriter(file=out,
version="2.1") # Write out to gaf 2.1
assoc = parser.parse_line(line).associations[0]
writer.write_assoc(assoc)
gpad_to_gaf_line = [
line for line in out.getvalue().split("\n") if not line.startswith("!")
][0]
assert gpad_to_gaf_line.split("\t")[3] == ""
# Test with a `NOT`
line = "WB\tWBGene00000001\taap-1\tNOT|involved_in\tGO:0008286\tWB_REF:WBPaper00005614|PMID:12393910\tIMP\t\tP\t\tY110A7A.10\tgene\ttaxon:6239\t20060302\tWB\t\t"
parser = gafparser.GafParser()
parser.version = "2.2"
out = io.StringIO()
writer = assocwriter.GafWriter(file=out,
version="2.1") # Write out to gaf 2.1
assoc = parser.parse_line(line).associations[0]
writer.write_assoc(assoc)
gpad_to_gaf_line = [
line for line in out.getvalue().split("\n") if not line.startswith("!")
][0]
assert gpad_to_gaf_line.split("\t")[3] == "NOT"
def test_no_colon_in_id():
parser = gafparser.GafParser()
valid = parser._validate_id("FOOBAR", "")
assert not valid
assert len(parser.report.messages) == 1
assert parser.report.messages[0]["level"] == assocparser.Report.ERROR
def test_validate_pipe_separated():
parser = gafparser.GafParser()
ids = parser.validate_pipe_separated_ids("PMID:12345", "")
assert set(ids) == set(["PMID:12345"])
ids = parser.validate_pipe_separated_ids("PMID:12345|PMID:11111", "")
assert set(ids) == set(["PMID:12345", "PMID:11111"])
def test_empty_pre_colon():
parser = gafparser.GafParser()
valid = parser._validate_id(":123", "")
assert not valid
assert len(parser.report.messages) == 1
assert parser.report.messages[0]["level"] == assocparser.Report.ERROR
def create_parser_from_header(
line: str,
config: assocparser.AssocParserConfig,
group="unknown",
dataset="unknown",
bio_entities=None) -> Optional[assocparser.AssocParser]:
parser = None
parsed_version = parser_version_regex.findall(line)
if len(parsed_version) == 1:
filetype, version, _ = parsed_version[0]
if filetype in ["gpad", "gpa"]:
parser = gpadparser.GpadParser(config=config,
bio_entities=bio_entities,
group=group,
dataset=dataset)
if version in ["1.2", "2.0"]:
parser.version = version
elif filetype == "gaf":
parser = gafparser.GafParser(config=config,
bio_entities=bio_entities,
group=group,
dataset=dataset)
if version in ["2.1", "2.2"]:
parser.version = version
return parser
def test_pipe_in_id():
parser = gafparser.GafParser()
valid = parser._validate_id("F|OO:123", "")
assert valid
assert len(parser.report.messages) == 1
assert parser.report.messages[0]["level"] == assocparser.Report.WARNING
def test_bad_character_in_id():
parser = gafparser.GafParser()
valid = parser._validate_id("FOO:1&23", "")
assert not valid
assert len(parser.report.messages) == 1
assert parser.report.messages[0]["level"] == assocparser.Report.ERROR
def test_validate_with_allowed_ids():
parser = gafparser.GafParser()
valid = parser._validate_id("FOO:123",
assocparser.SplitLine("", [""] * 17,
"taxon:foo"),
allowed_ids=["FOO"])
assert valid
def test_empty_id():
parser = gafparser.GafParser()
valid = parser._validate_id(
"", assocparser.SplitLine("", [""] * 17, "taxon:foo"))
assert not valid
assert len(parser.report.messages) == 1
assert parser.report.messages[0]["level"] == assocparser.Report.ERROR
def test_pipe_in_id():
parser = gafparser.GafParser()
valid = parser._validate_id(
"F|OO:123", assocparser.SplitLine("", [""] * 17, "taxon:foo"))
assert valid
assert len(parser.report.messages) == 1
assert parser.report.messages[0]["level"] == assocparser.Report.WARNING
def test_normalize_refs_good_and_bad_refs():
parser = gafparser.GafParser()
refs = parser.normalize_refs(["FB:123", "PMID:234"],
assocparser.SplitLine("", [""] * 17,
"taxon:foo"))
assert len(parser.report.messages) == 1
assert parser.report.messages[0][
"type"] == assocparser.Report.INVALID_IDSPACE
def test_validate_pipe_separated_empty_allowed():
parser = gafparser.GafParser()
ids = parser.validate_pipe_separated_ids("",
assocparser.SplitLine(
"", [""] * 17, "taxon:foo"),
empty_allowed=True)
assert ids == []
def test_gaf_2_2_extensions():
line = "WB\tWBGene00000001\taap-1\tinvolved_in\tGO:0008286\tWB_REF:WBPaper00005614|PMID:12393910\tIMP\t\tP\t\tY110A7A.10\tgene\ttaxon:6239\t20060302\tWB\tpart_of(EMAPA:17972),part_of(CL:0000018)\t"
parser = gafparser.GafParser()
parser.version = "2.2"
assoc = parser.parse_line(line).associations[0]
gaf_22_out = assoc.to_gaf_2_2_tsv()
assert gaf_22_out[15] == "part_of(EMAPA:17972),part_of(CL:0000018)"
def test_validate_with_disallowed_id():
parser = gafparser.GafParser()
valid = parser._validate_id("FOO:123",
assocparser.SplitLine("", [""] * 17,
"taxon:foo"),
allowed_ids=["BAR"])
assert len(parser.report.messages) == 1
assert parser.report.messages[0]["level"] == assocparser.Report.WARNING
def test_validate_pipe_separated_with_bad_ids():
parser = gafparser.GafParser()
ids = parser.validate_pipe_separated_ids("PMID:123[2]|PMID:11111", "")
assert ids == None
ids = parser.validate_pipe_separated_ids("PMID:123[2]", "")
assert ids == None
def test_writing_to_gaf_2_2():
line = "WB\tWBGene00000001\taap-1\tinvolved_in\tGO:0008286\tWB_REF:WBPaper00005614|PMID:12393910\tIMP\t\tP\t\tY110A7A.10\tgene\ttaxon:6239\t20060302\tWB\t\t"
parser = gafparser.GafParser()
parser.version = "2.2"
assoc = parser.parse_line(line).associations[0] # type: GoAssociation
gaf_22_out = assoc.to_gaf_2_2_tsv()
assert gaf_22_out[3] == "involved_in"
# With NOT
line = "WB\tWBGene00000001\taap-1\tNOT|involved_in\tGO:0008286\tWB_REF:WBPaper00005614|PMID:12393910\tIMP\t\tP\t\tY110A7A.10\tgene\ttaxon:6239\t20060302\tWB\t\t"
parser = gafparser.GafParser()
parser.version = "2.2"
assoc = parser.parse_line(line).associations[0] # type: GoAssociation
gaf_22_out = assoc.to_gaf_2_2_tsv()
assert gaf_22_out[3] == "NOT|involved_in"
def test_normalize_refs_single_bad_ref():
parser = gafparser.GafParser()
ref = parser.normalize_refs(["FB:123"],
assocparser.SplitLine("", [""] * 17,
"taxon:foo"))
assert ref == ["FB:123"]
assert len(parser.report.messages) == 1
assert parser.report.messages[0][
"type"] == assocparser.Report.INVALID_IDSPACE
def test_validate_pipe_separated():
parser = gafparser.GafParser()
ids = parser.validate_pipe_separated_ids(
"PMID:12345", assocparser.SplitLine("", [""] * 17, "taxon:foo"))
assert set(ids) == set(["PMID:12345"])
ids = parser.validate_pipe_separated_ids(
"PMID:12345|PMID:11111",
assocparser.SplitLine("", [""] * 17, "taxon:foo"))
assert set(ids) == set(["PMID:12345", "PMID:11111"])
def create_base_parser(format: FormatType) -> Optional[assocparser.AssocParser]:
"""
Make an unconfigured parser based on the format. Only GAF is supported currently.
"""
parser = None
if format == FormatType.GAF:
parser = gafparser.GafParser(config=assocparser.AssocParserConfig())
else:
parser = None
return parser
def test_validate_pipe_separated_with_bad_ids():
parser = gafparser.GafParser()
ids = parser.validate_pipe_separated_ids(
"PMID:123[2]|PMID:11111",
assocparser.SplitLine("", [""] * 17, "taxon:foo"))
assert ids == None
ids = parser.validate_pipe_separated_ids(
"PMID:123[2]", assocparser.SplitLine("", [""] * 17, "taxon:foo"))
assert ids == None
def test_validate_pipe_with_additional_delims():
parser = gafparser.GafParser()
ids = parser.validate_pipe_separated_ids("F:123,B:234|B:111",
"",
extra_delims=",")
assert set(ids) == set(["F:123", "B:234", "B:111"])
result = parser.parse_line(
"PomBase\tSPAC25B8.17\typf1\t\tGO:1990578\tGO_REF:0000024\tISO\tUniProtKB:Q9CXD9|ensembl:ENSMUSP00000038569,PMID:11111\tC\tintramembrane aspartyl protease of the perinuclear ER membrane Ypf1 (predicted)\tppp81\tprotein\ttaxon:4896\t20150305\tPomBase\t\t"
)
assert set(result.associations[0]["evidence"]["with_support_from"]) == set(
["UniProtKB:Q9CXD9", "ensembl:ENSMUSP00000038569", "PMID:11111"])
def test_full_gaf_2_2_write():
line = "WB\tWBGene00000001\taap-1\tinvolved_in\tGO:0008286\tWB_REF:WBPaper00005614|PMID:12393910\tIMP\t\tP\t\tY110A7A.10\tgene\ttaxon:6239\t20060302\tWB\t\t"
parser = gafparser.GafParser()
parser.version = "2.2"
out = io.StringIO()
writer = assocwriter.GafWriter(file=out, version="2.2")
assoc = parser.parse_line(line).associations[0]
writer.write_assoc(assoc)
out_line = [
line for line in out.getvalue().split("\n") if not line.startswith("!")
][0]
assert out_line.split("\t") == line.split("\t")
def test_gpad_iba_writing():
out = io.StringIO()
parser = gafparser.GafParser()
parser.config = assocparser.AssocParserConfig(paint=True)
writer = assocwriter.GpadWriter(file=out)
for assoc in parser.association_generator(
skipheader=True, file=open("tests/resources/wb_single_iba.gaf")):
writer.write_assoc(assoc)
outlines = out.getvalue().split("\n")
expected_lines = [
"!gpa-version: 1.1",
"WB\tWBGene00022144\tpart_of\tGO:0005886\tPMID:21873635\tECO:0000318\tPANTHER:PTN000073732|RGD:3252\t\t20180308\tGO_Central\t\t",
""
]
assert expected_lines == outlines
def test_negated_qualifers():
gaf = [
"PomBase", "SPBC11B10.09", "cdc2", "NOT", "GO:0007275",
"PMID:21873635", "ISO", "PANTHER:PTN000623979|TAIR:locus:2099478", "P",
"Cyclin-dependent kinase 1", "UniProtKB:P04551|PTN000624043",
"protein", "taxon:284812", "20170228", "GO_Central", "", ""
]
parser = gafparser.GafParser()
result = parser.parse_line("\t".join(gaf))
writer = assocwriter.GafWriter()
parsed = writer.as_tsv(result.associations[0])
print(parsed)
assert parsed[3] == "NOT"
writer = assocwriter.GpadWriter()
parsed = writer.as_tsv(result.associations[0])
print(parsed)
assert parsed[2] == "NOT|involved_in"
def test_validate_pipe_with_additional_delims():
parser = gafparser.GafParser()
ids = parser.validate_pipe_separated_ids("F:123,B:234|B:111",
assocparser.SplitLine(
"", [""] * 17, "taxon:foo"),
extra_delims=",")
assert set(ids) == set(["F:123", "B:234", "B:111"])
result = parser.parse_line(
"PomBase\tSPAC25B8.17\typf1\t\tGO:1990578\tGO_REF:0000024\tISO\tUniProtKB:Q9CXD9|ensembl:ENSMUSP00000038569,PMID:11111\tC\tintramembrane aspartyl protease of the perinuclear ER membrane Ypf1 (predicted)\tppp81\tprotein\ttaxon:4896\t20150305\tPomBase\t\t"
)
expected = [
association.ConjunctiveSet(
elements=[association.Curie.from_str("UniProtKB:Q9CXD9")]),
association.ConjunctiveSet(elements=[
association.Curie.from_str("ensembl:ENSMUSP00000038569"),
association.Curie.from_str("PMID:11111")
])
]
assert result.associations[0].evidence.with_support_from == expected
def test_normalize_refs_good():
parser = gafparser.GafParser()
refs = parser.normalize_refs(["PMID:123"],
assocparser.SplitLine("", [""] * 17,
"taxon:foo"))
assert refs == ["PMID:123"]
def _association_parser(association_type, config):
if association_type == "gaf":
return gafparser.GafParser(config=config)
def test_doi_id():
parser = gafparser.GafParser()
valid = parser._validate_id(
"DOI:10.1007/BF00127499",
assocparser.SplitLine("", [""] * 17, "taxon:foo"))
assert valid