def test_api_summary(db: Session, client: TestClient):
# TODO: This would be better queried against the real data
for _ in range(10):
fakes.BiosampleFactory()
fakes.MetagenomeAnnotationFactory()
fakes.MetagenomeAssemblyFactory()
fakes.MetaproteomicAnalysisFactory()
fakes.DataObjectFactory()
db.commit()
assert_status(client.get("/api/summary"))
assert_status(client.get("/api/stats"))
def test_query_gene_function_mga_metap(db: Session):
sample1 = fakes.BiosampleFactory(id="sample1")
fakes.BiosampleFactory(id="sample2")
gene_functions = [
fakes.MGAGeneFunction(function__id=f"function{i}") for i in range(10)
]
fakes.MetagenomeAnnotationFactory(id="mga1",
gene_functions=gene_functions,
omics_processing__biosample=sample1)
metap = fakes.MetaproteomicAnalysisFactory(id="metap1")
peptide = fakes.MetaproteomicPeptideFactory(
metaproteomic_analysis=metap, best_protein_object=gene_functions[2])
fakes.PeptideMGAGeneFunctionFactory(mga_gene_function=gene_functions[1],
metaproteomic_peptide=peptide)
db.commit()
models.MGAGeneFunctionAggregation.populate(db)
models.MetaPGeneFunctionAggregation.populate(db)
db.commit()
q = query.MetagenomeAnnotationQuerySchema(conditions=[{
"table": "gene_function",
"field": "id",
"value": "function1",
}], )
assert {r.id for r in q.execute(db)} == {"mga1"}
q = query.MetagenomeAnnotationQuerySchema(conditions=[{
"table": "gene_function",
"field": "id",
"value": "invalid",
}], )
assert {r.id for r in q.execute(db)} == set()
q1 = query.MetaproteomicAnalysisQuerySchema(conditions=[{
"table":
"gene_function",
"field":
"id",
"value":
"function1",
}], )
assert {r.id for r in q1.execute(db)} == {"metap1"}
q1 = query.MetaproteomicAnalysisQuerySchema(conditions=[{
"table": "gene_function",
"field": "id",
"value": "invalid",
}], )
assert {r.id for r in q1.execute(db)} == set()
def test_list_data_objects(db: Session, client: TestClient, endpoint: str):
data_object = fakes.DataObjectFactory(id="do")
omics_processing = fakes.OmicsProcessingFactory(id="1")
reads_qc = fakes.ReadsQCFactory(id="1")
assembly = fakes.MetagenomeAssemblyFactory(id="1")
annotation = fakes.MetagenomeAnnotationFactory(id="1")
analysis = fakes.MetaproteomicAnalysisFactory(id="1")
omics_processing.outputs = [data_object]
reads_qc.outputs = [data_object]
assembly.outputs = [data_object]
annotation.outputs = [data_object]
analysis.outputs = [data_object]
db.commit()
resp = client.get(f"/api/{endpoint}/1/outputs")
assert_status(resp)
assert ["do"] == [r["id"] for r in resp.json()]
def test_basic_query(db: Session, table):
tests: Dict[str, Tuple[fakes.AnnotatedFactory, query.BaseQuerySchema]] = {
"study": (fakes.StudyFactory(), query.StudyQuerySchema()),
"omics_processing":
(fakes.OmicsProcessingFactory(), query.OmicsProcessingQuerySchema()),
"biosample": (fakes.BiosampleFactory(), query.BiosampleQuerySchema()),
"reads_qc": (fakes.ReadsQCFactory(), query.ReadsQCQuerySchema()),
"metagenome_assembly": (
fakes.MetagenomeAssemblyFactory(),
query.MetagenomeAssemblyQuerySchema(),
),
"metagenome_annotation": (
fakes.MetagenomeAnnotationFactory(),
query.MetagenomeAnnotationQuerySchema(),
),
"metaproteomic_analysis": (
fakes.MetaproteomicAnalysisFactory(),
query.MetaproteomicAnalysisQuerySchema(),
),
}
db.commit()
q = tests[table][1].execute(db)
assert tests[table][0].id in {r.id for r in q.all()}
def test_pipeline_query(db: Session, table):
omics_processing1 = fakes.OmicsProcessingFactory(name="omics_processing1")
omics_processing2 = fakes.OmicsProcessingFactory(name="omics_processing2")
fakes.ReadsQCFactory(omics_processing=omics_processing1, name="reads_qc1")
fakes.ReadsQCFactory(omics_processing=omics_processing1, name="reads_qc2")
fakes.ReadsQCFactory(omics_processing=omics_processing2, name="reads_qc3")
fakes.MetagenomeAssemblyFactory(omics_processing=omics_processing1,
name="assembly1")
fakes.MetagenomeAssemblyFactory(omics_processing=omics_processing1,
name="assembly2")
fakes.MetagenomeAssemblyFactory(omics_processing=omics_processing2,
name="assembly3")
fakes.MetagenomeAnnotationFactory(omics_processing=omics_processing1,
name="annotation1")
fakes.MetagenomeAnnotationFactory(omics_processing=omics_processing1,
name="annotation2")
fakes.MetagenomeAnnotationFactory(omics_processing=omics_processing2,
name="annotation3")
fakes.MetaproteomicAnalysisFactory(omics_processing=omics_processing1,
name="analysis1")
fakes.MetaproteomicAnalysisFactory(omics_processing=omics_processing1,
name="analysis2")
fakes.MetaproteomicAnalysisFactory(omics_processing=omics_processing2,
name="analysis3")
fakes.MAGsAnalysisFactory(omics_processing=omics_processing1, name="mags1")
fakes.MAGsAnalysisFactory(omics_processing=omics_processing1, name="mags2")
fakes.MAGsAnalysisFactory(omics_processing=omics_processing2, name="mags3")
fakes.ReadBasedAnalysisFactory(omics_processing=omics_processing1,
name="reads1")
fakes.ReadBasedAnalysisFactory(omics_processing=omics_processing1,
name="reads2")
fakes.ReadBasedAnalysisFactory(omics_processing=omics_processing2,
name="reads3")
fakes.NOMAnalysisFactory(omics_processing=omics_processing1, name="nom1")
fakes.NOMAnalysisFactory(omics_processing=omics_processing1, name="nom2")
fakes.NOMAnalysisFactory(omics_processing=omics_processing2, name="nom3")
fakes.MetabolomicsAnalysisFactory(omics_processing=omics_processing1,
name="metab1")
fakes.MetabolomicsAnalysisFactory(omics_processing=omics_processing1,
name="metab2")
fakes.MetabolomicsAnalysisFactory(omics_processing=omics_processing2,
name="metab3")
db.commit()
# test omics_processing not associated with biosamples
omics_processing1.biosample_id = None
db.add(omics_processing1)
# test omics_processing not associated with studies
omics_processing2.study_id = None
db.add(omics_processing2)
db.commit()
query_schema = {
"reads_qc": query.ReadsQCQuerySchema,
"assembly": query.MetagenomeAssemblyQuerySchema,
"annotation": query.MetagenomeAnnotationQuerySchema,
"analysis": query.MetaproteomicAnalysisQuerySchema,
"mags": query.MAGsAnalysisQuerySchema,
"reads": query.ReadBasedAnalysisQuerySchema,
"nom": query.NOMAnalysisQuerySchema,
"metab": query.MetabolomicsAnalysisQuerySchema,
}[table]
q = query_schema()
assert {f"{table}{i}"
for i in [1, 2, 3]} == {r.name
for r in q.execute(db).all()}
q = query_schema(conditions=[{
"table": "omics_processing",
"field": "name",
"value": "omics_processing1",
}])
assert {f"{table}{i}"
for i in [1, 2]} == {r.name
for r in q.execute(db).all()}
q = query.OmicsProcessingQuerySchema(conditions=[{
"table": q.table.value,
"field": "name",
"value": f"{table}1"
}])
assert ["omics_processing1"] == [r.name for r in q.execute(db).all()]