def test_build_annotation_inferences():
with open("tests/resources/test.inferences.json") as inferences_file:
gaferences = json.load(inferences_file)
inferences = gaference.build_annotation_inferences(gaferences)
akey = gaference.AnnotationKey(
gaference.RelationTo("http://purl.obolibrary.org/obo/BFO_0000050",
"http://purl.obolibrary.org/obo/GO_0036064"),
"http://purl.obolibrary.org/obo/NCBITaxon_10090",
association.ExtensionConjunctions(
frozenset([
association.ExtensionUnit(
"http://purl.obolibrary.org/obo/BFO_0000050",
"http://purl.obolibrary.org/obo/EMAPA_17168"),
association.ExtensionUnit(
"http://purl.obolibrary.org/obo/BFO_0000050",
"http://purl.obolibrary.org/obo/CL_0010009")
])))
val = inferences[akey]
expected = gaference.InferenceValue(True, False, [
gaference.RelationTo("http://purl.obolibrary.org/obo/BFO_0000050",
"http://purl.obolibrary.org/obo/GO_0097458")
])
assert val == expected
def test_produce_inference_produces_many_inferences():
with open("tests/resources/test.inferences.json") as inference_file:
gaferences = json.load(inference_file)
inferences = gaference.build_annotation_inferences(gaferences)
gaf_line = "MGI\tMGI:1345162\tAdam23\t\tGO:0099056\tMGI:MGI:4431144|PMID:20133599\tIDA\t\tC\ta disintegrin and metallopeptidase domain 23\tMDC3\tprotein\ttaxon:10090\t20180711\tSynGO\tpart_of(GO:0098978),part_of(UBERON:0000061),part_of(EMAPA:35405)|part_of(GO:0098978),part_of(UBERON:0000061),part_of(EMAPA:16894)\t"
gaf = gaf_line.split("\t")
results = gaference.produce_inferences(gaf, inferences)
expected_lines = [
[
"MGI", "MGI:1345162", "Adam23", "", "GO:0098978",
"MGI:MGI:4431144|PMID:20133599", "IDA", "", "C",
"a disintegrin and metallopeptidase domain 23", "MDC3", "protein",
"taxon:10090", "20180711", "SynGO", "", ""
],
[
"MGI", "MGI:1345162", "Adam23", "", "GO:0098978",
"MGI:MGI:4431144|PMID:20133599", "IDA", "", "C",
"a disintegrin and metallopeptidase domain 23", "MDC3", "protein",
"taxon:10090", "20180711", "SynGO", "", ""
],
]
assert len(results) == 2
assert results[0].inferred_gafs[0] == expected_lines[0]
assert results[1].inferred_gafs[0] == expected_lines[1]
def test_pombase_taxon_failure():
with open("tests/resources/test.inferences.json") as inference_file:
gaferences = json.load(inference_file)
inferences = gaference.build_annotation_inferences(gaferences)
gaf_line = "PomBase\tSPBC11B10.09\tcdc2\t\tGO:0007275\tPMID:21873635\tIBA\tPANTHER:PTN000623979|TAIR:locus:2099478\tP\tCyclin-dependent kinase 1\tUniProtKB:P04551|PTN000624043\tprotein\ttaxon:284812\t20170228\tGO_Central"
gaf = gaf_line.split("\t")
results = gaference.produce_inferences(gaf, inferences)
assert len(results) == 1
assert results[0].problem == gaference.ProblemType.TAXON
def test_taxon_check_failure():
with open("tests/resources/test.inferences.json") as inference_file:
gaferences = json.load(inference_file)
inferences = gaference.build_annotation_inferences(gaferences)
gaf_line = "MGI\tMGI:1924956\tAbcb5\t\tGO:0048058\tMGI:MGI:5585659|PMID:25030174\tIMP\t\tP\tATP-binding cassette, sub-family B (MDR/TAP), member 5\t9230106F14Rik\tprotein\ttaxon:10090\t20140729\tUniProt\t\t"
gaf = gaf_line.split("\t")
results = gaference.produce_inferences(gaf, inferences)
assert len(results) == 1
assert results[0].problem == gaference.ProblemType.TAXON
def test_extension_check_failure():
with open("tests/resources/test.inferences.json") as inference_file:
gaferences = json.load(inference_file)
inferences = gaference.build_annotation_inferences(gaferences)
gaf_line = "MGI\tMGI:109192\tActn2\t\tGO:0072659\tMGI:MGI:4366185|PMID:19815520\tIMP\t\tP\tactinin alpha 2\t1110008F24Rik\tprotein\ttaxon:10090\t20150506\tUniProt\tpart_of(CL:0002495),has_direct_input(UniProtKB:P58390)\t"
gaf = gaf_line.split("\t")
results = gaference.produce_inferences(gaf, inferences)
assert len(results) == 1
assert results[0].problem == gaference.ProblemType.EXTENSION
def test_produce_inference_produces_inferences():
with open("tests/resources/test.inferences.json") as inference_file:
gaferences = json.load(inference_file)
inferences = gaference.build_annotation_inferences(gaferences)
gaf_line = "MGI\tMGI:2178217\tAkap9\t\tGO:0036064\tMGI:MGI:5303017|PMID:22031837\tIDA\t\tC\tA kinase (PRKA) anchor protein (yotiao) 9\t5730481H23Rik|AKAP450|G1-448-15|mei2-5|repro12\tprotein\ttaxon:10090\t20131226\tMGI\tpart_of(EMAPA:17168),part_of(CL:0010009)\t"
gaf = gaf_line.split("\t")
results = gaference.produce_inferences(gaf, inferences)
expected_line = [
"MGI", "MGI:2178217", "Akap9", "", "GO:0097458",
"MGI:MGI:5303017|PMID:22031837", "IDA", "", "C",
"A kinase (PRKA) anchor protein (yotiao) 9",
"5730481H23Rik|AKAP450|G1-448-15|mei2-5|repro12", "protein",
"taxon:10090", "20131226", "MGI", "", ""
]
assert len(results) == 1
assert len(results[0].inferred_gafs) == 1
assert results[0].inferred_gafs[0] == expected_line
def main():
"""
Wrapper for Assoc Parsing
"""
parser = argparse.ArgumentParser(description='Wrapper for obographs assocmodel library'
"""
By default, ontologies and assocs are cached locally and synced from a remote sparql endpoint
""",
formatter_class=argparse.RawTextHelpFormatter)
parser.add_argument('-r', '--resource', type=str, required=False,
help='Name of ontology')
parser.add_argument('-f', '--file', type=str, required=False,
help='Name of input file for associations - currently GAF is assumed')
parser.add_argument('-F', '--format', type=str, required=False,
help='Format of assoc file. One of GAF, GPAD or HPOA')
parser.add_argument('-o', '--outfile', type=str, required=False,
help='Path to output file')
parser.add_argument("--report-md", type=str, required=False, dest="report_md",
help="Path to report markdown file")
parser.add_argument("--report-json", type=str, required=False, dest="report_json",
help="Path to report JSON file")
parser.add_argument('-t', '--to', type=str, required=False,
help='Output to (tree, dot, ...)')
parser.add_argument("--filter-out", nargs="+", required=False, default=[], metavar="EVIDENCE",
help="List of any evidence codes to filter out of the GAF. E.G. --filter-out IEA IMP")
parser.add_argument("--filtered-file", required=False, default=None, metavar="FILTERED_FILE",
help="File to write the filtered out evidence GAF to")
parser.add_argument('-T', '--taxon', nargs='*', required=False,
help='valid taxon (NCBITaxon ID) - validate against this')
parser.add_argument('--subject_prefix', nargs='*', required=False,
help='E.g PomBase - validate against this')
parser.add_argument('--object_prefix', nargs='*', required=False,
help='E.g GO - validate against this')
parser.add_argument("-I", "--gaferencer-file", type=argparse.FileType('r'), required=False,
help="Output from Gaferencer run on a set of GAF annotations")
parser.add_argument('-v', '--verbosity', default=0, action='count',
help='Increase output verbosity')
parser.add_argument("--allow_paint", required=False, action="store_const", const=True,
help="Allow IBAs in parser")
parser.add_argument("-g", "--gpi", type=str, required=False, default=None,
help="GPI file")
parser.add_argument("-l", "--rule", action="append", required=None, default=[], dest="rule_set",
help="Set of rules to be run. Default is no rules to be run, with the exception \
of gorule-0000027 and gorule-0000020. See command line documentation in the \
ontobio project or readthedocs for more information")
subparsers = parser.add_subparsers(dest='subcommand', help='sub-command help')
parser_n = subparsers.add_parser('validate', help='Validate associations')
parser_n.set_defaults(function=validate_assocs)
parser_n = subparsers.add_parser('filter', help='Filter associations')
parser_n.set_defaults(function=filter_assocs)
parser_n = subparsers.add_parser('convert', help='Convert associations')
parser_n.set_defaults(function=convert_assocs)
parser_n.add_argument('-t', '--to', type=str, required=True, choices=["GAF", "GPAD", "gaf", "gpad"],
help='Format to convert to')
parser_n.add_argument("-n", "--format-version", dest="version", type=str, required=False, default=None,
help="Version for the file format. GAF default is 2.1, GPAD default is 1.2")
parser_n = subparsers.add_parser('map2slim', help='Map to a subset/slim')
parser_n.set_defaults(function=map2slim)
parser_n.add_argument('-p', '--properties', nargs='*', type=str, default=['subClassOf', 'BFO:0000050'],
help='Properties')
parser_n.add_argument('-s', '--subset', type=str, required=True,
help='subset (e.g. map2slim)')
args = parser.parse_args()
if args.verbosity >= 2:
logging.basicConfig(level=logging.DEBUG)
elif args.verbosity == 1:
logging.basicConfig(level=logging.INFO)
else:
logging.basicConfig(level=logging.WARNING)
logging.info("Welcome!")
# Ontology Factory
ont = None
if args.resource is not None:
ofactory = OntologyFactory()
logging.info("Creating ont object from: {} {}".format(args.resource, ofactory))
ont = ofactory.create(args.resource)
logging.info("ont: {}".format(ont))
func = args.function
# Upper case all evidence codes
args.filter_out = [code.upper() for code in args.filter_out]
gaferences = None
if args.gaferencer_file:
gaferences = gaference.build_annotation_inferences(json.load(args.gaferencer_file))
rule_set = args.rule_set
if rule_set == ["all"]:
rule_set = assocparser.RuleSet.ALL
# set configuration
filtered_evidence_file = open(args.filtered_file, "w") if args.filtered_file else None
config = assocparser.AssocParserConfig(
valid_taxa=args.taxon,
ontology=ont,
class_idspaces=args.object_prefix,
entity_idspaces=args.subject_prefix,
filter_out_evidence=args.filter_out,
filtered_evidence_file=filtered_evidence_file,
annotation_inferences=gaferences,
paint=args.allow_paint,
gpi_authority_path=args.gpi,
rule_set=rule_set
)
p = None
fmt = None
if args.format is None:
fmt = 'gaf'
else:
fmt = args.format.lower()
# TODO: use a factory
if fmt == 'gaf':
p = GafParser(config=config, dataset=args.file)
elif fmt == 'gpad':
p = GpadParser(config=config)
elif fmt == 'hpoa':
p = HpoaParser(config=config)
elif fmt == "gpi":
p = entityparser.GpiParser()
func = validate_entity
outfh = None
if args.outfile is not None:
two_mb = 2097152
outfh = open(args.outfile, "w", buffering=two_mb)
func(ont, args.file, outfh, p, args)
if filtered_evidence_file:
filtered_evidence_file.close()
if outfh is not None:
outfh.close()
if args.report_md is not None:
report_md = open(args.report_md, "w")
report_md.write(p.report.to_markdown())
report_md.close()
if args.report_json is not None:
report_json = open(args.report_json, "w")
report_json.write(json.dumps(p.report.to_report_json(), indent=4))
report_json.close()
if not (args.report_md or args.report_json):
print(p.report.to_markdown())
