def test_study_row_reader_minimal_study(minimal_investigation_file,
minimal_study_file):
"""Use ``StudyRowReader`` to read in minimal study file."""
# Create new row reader and check read headers
row_reader = StudyRowReader.from_stream("S1", minimal_study_file)
assert 3 == len(row_reader.header)
# Read all rows in study
rows = list(row_reader.read())
# Check results
assert 1 == len(rows)
first_row = rows[0]
assert 3 == len(first_row)
expected = models.Material("Source Name", "S1-source-0815", "0815", None,
(), (), (), None, [table_headers.SOURCE_NAME])
assert expected == first_row[0]
expected = models.Process(
"sample collection",
"S1-sample collection-2-1",
None,
None,
None,
None,
(),
(),
None,
None,
None,
[table_headers.PROTOCOL_REF],
)
assert expected == first_row[1]
expected = models.Material(
"Sample Name",
"S1-sample-0815-N1",
"0815-N1",
None,
(),
(),
(),
None,
[table_headers.SAMPLE_NAME],
)
assert expected == first_row[2]
def test_assay_reader_minimal_assay(minimal_investigation_file,
minimal_assay_file):
"""Use ``AssayReader`` to read in minimal assay file.
Using the ``AssayReader`` instead of the ``AssayRowReader`` gives us
``Assay`` objects instead of just the row-wise nodes.
"""
# Load investigation (tested elsewhere)
investigation = InvestigationReader.from_stream(
minimal_investigation_file).read()
with pytest.warns(IsaWarning) as record:
InvestigationValidator(investigation).validate()
# Check warnings
assert 1 == len(record)
# Create new row reader and check read headers
reader = AssayReader.from_stream("S1", "A1", minimal_assay_file)
assert 5 == len(reader.header)
# Read and validate assay
assay = reader.read()
AssayValidator(investigation, investigation.studies[0],
investigation.studies[0].assays[0], assay).validate()
# Check results
assert os.path.normpath(str(assay.file)).endswith(
os.path.normpath("data/i_minimal/a_minimal.txt"))
assert 5 == len(assay.header)
assert 3 == len(assay.materials)
assert 1 == len(assay.processes)
assert 3 == len(assay.arcs)
expected = models.Material(
"Sample Name",
"S1-sample-0815-N1",
"0815-N1",
None,
(),
(),
(),
None,
[table_headers.SAMPLE_NAME],
)
assert expected == assay.materials["S1-sample-0815-N1"]
expected = models.Material(
"Raw Data File",
"S1-A1-0815-N1-DNA1-WES1_L???_???_R1.fastq.gz-COL4",
"0815-N1-DNA1-WES1_L???_???_R1.fastq.gz",
None,
(),
(),
(),
None,
[table_headers.RAW_DATA_FILE],
)
assert expected == assay.materials[
"S1-A1-0815-N1-DNA1-WES1_L???_???_R1.fastq.gz-COL4"]
expected = models.Material(
"Raw Data File",
"S1-A1-0815-N1-DNA1-WES1_L???_???_R2.fastq.gz-COL5",
"0815-N1-DNA1-WES1_L???_???_R2.fastq.gz",
None,
(),
(),
(),
None,
[table_headers.RAW_DATA_FILE],
)
assert expected == assay.materials[
"S1-A1-0815-N1-DNA1-WES1_L???_???_R2.fastq.gz-COL5"]
expected = models.Process(
"nucleic acid sequencing",
"S1-A1-0815-N1-DNA1-WES1-3",
"0815-N1-DNA1-WES1",
"Assay Name",
None,
None,
(),
(),
None,
None,
None,
[table_headers.PROTOCOL_REF, table_headers.ASSAY_NAME],
)
assert expected == assay.processes["S1-A1-0815-N1-DNA1-WES1-3"]
expected = (
models.Arc("S1-sample-0815-N1", "S1-A1-0815-N1-DNA1-WES1-3"),
models.Arc("S1-A1-0815-N1-DNA1-WES1-3",
"S1-A1-0815-N1-DNA1-WES1_L???_???_R1.fastq.gz-COL4"),
models.Arc(
"S1-A1-0815-N1-DNA1-WES1_L???_???_R1.fastq.gz-COL4",
"S1-A1-0815-N1-DNA1-WES1_L???_???_R2.fastq.gz-COL5",
),
)
assert expected == assay.arcs
def test_assay_reader_gelelect(gelelect_investigation_file,
gelelect_assay_file):
"""Use ``AssayReader`` to read in small assay file."""
with pytest.warns(IsaWarning) as record:
# Load investigation
investigation = InvestigationReader.from_stream(
gelelect_investigation_file).read()
InvestigationValidator(investigation).validate()
# Create new row reader and check read headers
reader = AssayReader.from_stream("S1", "A1", gelelect_assay_file)
assert 22 == len(reader.header)
# Read assay
assay = reader.read()
AssayValidator(investigation, investigation.studies[0],
investigation.studies[0].assays[0], assay).validate()
# Check warnings
assert 4 == len(record)
# Check results
assert os.path.normpath(str(assay.file)).endswith(
os.path.normpath(
"data/test_gelelect/a_study01_protein_expression_profiling_gel_electrophoresis.txt"
))
assert 22 == len(assay.header)
assert 9 == len(assay.materials)
assert 10 == len(assay.processes)
assert 18 == len(assay.arcs)
expected = models.Material(
"Image File",
"S1-A1-Image01.jpeg-COL19",
"Image01.jpeg",
None,
(),
(),
(),
None,
[table_headers.IMAGE_FILE],
)
assert expected == assay.materials["S1-A1-Image01.jpeg-COL19"]
expected = models.Process(
"data collection",
"S1-A1-Scan02-18",
"Scan02",
"Scan Name",
None,
None,
(),
(),
None,
None,
None,
[table_headers.PROTOCOL_REF, table_headers.SCAN_NAME],
)
assert expected == assay.processes["S1-A1-Scan02-18"]
header_electrophoresis = [
table_headers.PROTOCOL_REF,
table_headers.GEL_ELECTROPHORESIS_ASSAY_NAME,
table_headers.FIRST_DIMENSION,
table_headers.TERM_SOURCE_REF,
table_headers.TERM_ACCESSION_NUMBER,
table_headers.SECOND_DIMENSION,
table_headers.TERM_SOURCE_REF,
table_headers.TERM_ACCESSION_NUMBER,
]
expected = models.Process(
"electrophoresis",
"S1-A1-Assay01-10",
"Assay01",
"Gel Electrophoresis Assay Name",
None,
None,
(),
(),
None,
models.OntologyTermRef("", "", ""),
models.OntologyTermRef("", "", ""),
header_electrophoresis,
)
assert expected == assay.processes["S1-A1-Assay01-10"]
expected = models.Process(
"electrophoresis",
"S1-A1-electrophoresis-9-2",
"",
"Gel Electrophoresis Assay Name",
None,
None,
(),
(),
None,
models.OntologyTermRef("AssayX", None, None),
models.OntologyTermRef("AssayY", None, None),
header_electrophoresis,
)
assert expected == assay.processes["S1-A1-electrophoresis-9-2"]
def test_assay_reader_small_assay(small_investigation_file, small_assay_file):
"""Use ``AssayReader`` to read in small assay file."""
# Load investigation (tested elsewhere)
investigation = InvestigationReader.from_stream(
small_investigation_file).read()
with pytest.warns(IsaWarning) as record:
InvestigationValidator(investigation).validate()
# Check warnings
assert 1 == len(record)
# Create new row reader and check read headers
reader = AssayReader.from_stream("S1", "A1", small_assay_file)
assert 9 == len(reader.header)
# Read assay
with pytest.warns(IsaWarning) as record:
assay = reader.read()
AssayValidator(investigation, investigation.studies[0],
investigation.studies[0].assays[0], assay).validate()
# Check warnings
assert 1 == len(record)
# Check results
assert os.path.normpath(str(assay.file)).endswith(
os.path.normpath("data/i_small/a_small.txt"))
assert 9 == len(assay.header)
assert 9 == len(assay.materials)
assert 5 == len(assay.processes)
assert 13 == len(assay.arcs)
expected = models.Material(
"Sample Name",
"S1-sample-0815-N1",
"0815-N1",
None,
(),
(),
(),
None,
[table_headers.SAMPLE_NAME],
)
assert expected == assay.materials["S1-sample-0815-N1"]
expected = models.Material(
"Sample Name",
"S1-sample-0815-T1",
"0815-T1",
None,
(),
(),
(),
None,
[table_headers.SAMPLE_NAME],
)
assert expected == assay.materials["S1-sample-0815-T1"]
expected = models.Material(
"Raw Data File",
"S1-A1-0815-N1-DNA1-WES1_L???_???_R1.fastq.gz-COL6",
"0815-N1-DNA1-WES1_L???_???_R1.fastq.gz",
None,
(),
(),
(),
None,
[table_headers.RAW_DATA_FILE],
)
assert expected == assay.materials[
"S1-A1-0815-N1-DNA1-WES1_L???_???_R1.fastq.gz-COL6"]
expected = models.Material(
"Raw Data File",
"S1-A1-0815-N1-DNA1-WES1_L???_???_R2.fastq.gz-COL7",
"0815-N1-DNA1-WES1_L???_???_R2.fastq.gz",
None,
(),
(),
(),
None,
[table_headers.RAW_DATA_FILE],
)
assert expected == assay.materials[
"S1-A1-0815-N1-DNA1-WES1_L???_???_R2.fastq.gz-COL7"]
expected = models.Material(
"Raw Data File",
"S1-A1-0815-T1-DNA1-WES1_L???_???_R1.fastq.gz-COL6",
"0815-T1-DNA1-WES1_L???_???_R1.fastq.gz",
None,
(),
(),
(),
None,
[table_headers.RAW_DATA_FILE],
)
assert expected == assay.materials[
"S1-A1-0815-T1-DNA1-WES1_L???_???_R1.fastq.gz-COL6"]
expected = models.Material(
"Raw Data File",
"S1-A1-0815-T1-DNA1-WES1_L???_???_R2.fastq.gz-COL7",
"0815-T1-DNA1-WES1_L???_???_R2.fastq.gz",
None,
(),
(),
(),
None,
[table_headers.RAW_DATA_FILE],
)
assert expected == assay.materials[
"S1-A1-0815-T1-DNA1-WES1_L???_???_R2.fastq.gz-COL7"]
expected = models.Material(
"Derived Data File",
"S1-A1-0815-somatic.vcf.gz-COL9",
"0815-somatic.vcf.gz",
None,
(),
(),
(),
None,
[table_headers.DERIVED_DATA_FILE],
)
assert expected == assay.materials["S1-A1-0815-somatic.vcf.gz-COL9"]
expected = models.Process(
"library preparation",
"S1-A1-library preparation-2-1",
None,
None,
None,
None,
(),
(),
None,
None,
None,
[table_headers.PROTOCOL_REF],
)
assert expected == assay.processes["S1-A1-library preparation-2-1"]
expected = models.Process(
"library preparation",
"S1-A1-library preparation-2-2",
None,
None,
None,
None,
(),
(),
None,
None,
None,
[table_headers.PROTOCOL_REF],
)
assert expected == assay.processes["S1-A1-library preparation-2-2"]
expected = models.Process(
"nucleic acid sequencing",
"S1-A1-0815-N1-DNA1-WES1-5",
"0815-N1-DNA1-WES1",
"Assay Name",
None,
None,
(),
(),
None,
None,
None,
[table_headers.PROTOCOL_REF, table_headers.ASSAY_NAME],
)
assert expected == assay.processes["S1-A1-0815-N1-DNA1-WES1-5"]
expected = models.Process(
"nucleic acid sequencing",
"S1-A1-0815-T1-DNA1-WES1-5",
"0815-T1-DNA1-WES1",
"Assay Name",
None,
None,
(),
(),
None,
None,
None,
[table_headers.PROTOCOL_REF, table_headers.ASSAY_NAME],
)
assert expected == assay.processes["S1-A1-0815-T1-DNA1-WES1-5"]
expected = (
models.Arc("S1-sample-0815-N1", "S1-A1-library preparation-2-1"),
models.Arc("S1-A1-library preparation-2-1", "S1-A1-0815-N1-DNA1-COL3"),
models.Arc("S1-A1-0815-N1-DNA1-COL3", "S1-A1-0815-N1-DNA1-WES1-5"),
models.Arc("S1-A1-0815-N1-DNA1-WES1-5",
"S1-A1-0815-N1-DNA1-WES1_L???_???_R1.fastq.gz-COL6"),
models.Arc(
"S1-A1-0815-N1-DNA1-WES1_L???_???_R1.fastq.gz-COL6",
"S1-A1-0815-N1-DNA1-WES1_L???_???_R2.fastq.gz-COL7",
),
models.Arc("S1-A1-0815-N1-DNA1-WES1_L???_???_R2.fastq.gz-COL7",
"S1-A1-somatic variant calling-1-8"),
models.Arc("S1-A1-somatic variant calling-1-8",
"S1-A1-0815-somatic.vcf.gz-COL9"),
models.Arc("S1-sample-0815-T1", "S1-A1-library preparation-2-2"),
models.Arc("S1-A1-library preparation-2-2", "S1-A1-0815-T1-DNA1-COL3"),
models.Arc("S1-A1-0815-T1-DNA1-COL3", "S1-A1-0815-T1-DNA1-WES1-5"),
models.Arc("S1-A1-0815-T1-DNA1-WES1-5",
"S1-A1-0815-T1-DNA1-WES1_L???_???_R1.fastq.gz-COL6"),
models.Arc(
"S1-A1-0815-T1-DNA1-WES1_L???_???_R1.fastq.gz-COL6",
"S1-A1-0815-T1-DNA1-WES1_L???_???_R2.fastq.gz-COL7",
),
models.Arc("S1-A1-0815-T1-DNA1-WES1_L???_???_R2.fastq.gz-COL7",
"S1-A1-somatic variant calling-1-8"),
)
assert expected == assay.arcs
def test_assay_row_reader_small_assay(small_investigation_file,
small_assay_file):
"""Use ``AssayRowReader`` to read in small assay file."""
# Create new row reader and check read headers
row_reader = AssayRowReader.from_stream("S1", "A1", small_assay_file)
assert 9 == len(row_reader.header)
# Read all rows in assay
rows = list(row_reader.read())
# Check results
assert 2 == len(rows)
first_row = rows[0]
second_row = rows[1]
assert 8 == len(first_row)
expected = models.Material(
"Sample Name",
"S1-sample-0815-N1",
"0815-N1",
None,
(),
(),
(),
None,
[table_headers.SAMPLE_NAME],
)
assert expected == first_row[0]
expected = models.Process(
"library preparation",
"S1-A1-library preparation-2-1",
None,
None,
None,
None,
(),
(),
None,
None,
None,
[table_headers.PROTOCOL_REF],
)
assert expected == first_row[1]
expected = models.Material(
"Library Name",
"S1-A1-0815-N1-DNA1-COL3",
"0815-N1-DNA1",
None,
(),
(),
(),
None,
[table_headers.LIBRARY_NAME],
)
assert expected == first_row[2]
expected = models.Process(
"nucleic acid sequencing",
"S1-A1-0815-N1-DNA1-WES1-5",
"0815-N1-DNA1-WES1",
"Assay Name",
None,
None,
(),
(),
None,
None,
None,
[table_headers.PROTOCOL_REF, table_headers.ASSAY_NAME],
)
assert expected == first_row[3]
expected = models.Material(
"Raw Data File",
"S1-A1-0815-N1-DNA1-WES1_L???_???_R1.fastq.gz-COL6",
"0815-N1-DNA1-WES1_L???_???_R1.fastq.gz",
None,
(),
(),
(),
None,
[table_headers.RAW_DATA_FILE],
)
assert expected == first_row[4]
expected = models.Material(
"Raw Data File",
"S1-A1-0815-N1-DNA1-WES1_L???_???_R2.fastq.gz-COL7",
"0815-N1-DNA1-WES1_L???_???_R2.fastq.gz",
None,
(),
(),
(),
None,
[table_headers.RAW_DATA_FILE],
)
assert expected == first_row[5]
expected = models.Process(
"Unknown",
"S1-A1-somatic variant calling-1-8",
"somatic variant calling-1",
"Data Transformation Name",
None,
None,
(),
(),
None,
None,
None,
[table_headers.DATA_TRANSFORMATION_NAME],
)
assert expected == first_row[6]
expected = models.Material(
"Derived Data File",
"S1-A1-0815-somatic.vcf.gz-COL9",
"0815-somatic.vcf.gz",
None,
(),
(),
(),
None,
[table_headers.DERIVED_DATA_FILE],
)
assert expected == first_row[7]
assert 8 == len(second_row)
expected = models.Material(
"Sample Name",
"S1-sample-0815-T1",
"0815-T1",
None,
(),
(),
(),
None,
[table_headers.SAMPLE_NAME],
)
assert expected == second_row[0]
expected = models.Process(
"library preparation",
"S1-A1-library preparation-2-2",
None,
None,
None,
None,
(),
(),
None,
None,
None,
[table_headers.PROTOCOL_REF],
)
assert expected == second_row[1]
expected = models.Material(
"Library Name",
"S1-A1-0815-T1-DNA1-COL3",
"0815-T1-DNA1",
None,
(),
(),
(),
None,
[table_headers.LIBRARY_NAME],
)
assert expected == second_row[2]
expected = models.Process(
"nucleic acid sequencing",
"S1-A1-0815-T1-DNA1-WES1-5",
"0815-T1-DNA1-WES1",
"Assay Name",
None,
None,
(),
(),
None,
None,
None,
[table_headers.PROTOCOL_REF, table_headers.ASSAY_NAME],
)
assert expected == second_row[3]
expected = models.Material(
"Raw Data File",
"S1-A1-0815-T1-DNA1-WES1_L???_???_R1.fastq.gz-COL6",
"0815-T1-DNA1-WES1_L???_???_R1.fastq.gz",
None,
(),
(),
(),
None,
[table_headers.RAW_DATA_FILE],
)
assert expected == second_row[4]
expected = models.Material(
"Raw Data File",
"S1-A1-0815-T1-DNA1-WES1_L???_???_R2.fastq.gz-COL7",
"0815-T1-DNA1-WES1_L???_???_R2.fastq.gz",
None,
(),
(),
(),
None,
[table_headers.RAW_DATA_FILE],
)
assert expected == second_row[5]
expected = models.Process(
"Unknown",
"S1-A1-somatic variant calling-1-8",
"somatic variant calling-1",
"Data Transformation Name",
None,
None,
(),
(),
None,
None,
None,
[table_headers.DATA_TRANSFORMATION_NAME],
)
assert expected == second_row[6]
expected = models.Material(
"Derived Data File",
"S1-A1-0815-somatic.vcf.gz-COL9",
"0815-somatic.vcf.gz",
None,
(),
(),
(),
None,
[table_headers.DERIVED_DATA_FILE],
)
assert expected == second_row[7]
def test_assay_row_reader_minimal_assay(minimal_investigation_file,
minimal_assay_file):
"""Use ``AssayRowReader`` to read in minimal assay file."""
# Create new row reader and check read headers
row_reader = AssayRowReader.from_stream("S1", "A1", minimal_assay_file)
assert 5 == len(row_reader.header)
# Read all rows in assay
rows = list(row_reader.read())
# Check results
assert 1 == len(rows)
first_row = rows[0]
assert 4 == len(first_row)
expected = models.Material(
"Sample Name",
"S1-sample-0815-N1",
"0815-N1",
None,
(),
(),
(),
None,
[table_headers.SAMPLE_NAME],
)
assert expected == first_row[0]
expected = models.Process(
"nucleic acid sequencing",
"S1-A1-0815-N1-DNA1-WES1-3",
"0815-N1-DNA1-WES1",
"Assay Name",
None,
None,
(),
(),
None,
None,
None,
[table_headers.PROTOCOL_REF, table_headers.ASSAY_NAME],
)
assert expected == first_row[1]
expected = models.Material(
"Raw Data File",
"S1-A1-0815-N1-DNA1-WES1_L???_???_R1.fastq.gz-COL4",
"0815-N1-DNA1-WES1_L???_???_R1.fastq.gz",
None,
(),
(),
(),
None,
[table_headers.RAW_DATA_FILE],
)
assert expected == first_row[2]
expected = models.Material(
"Raw Data File",
"S1-A1-0815-N1-DNA1-WES1_L???_???_R2.fastq.gz-COL5",
"0815-N1-DNA1-WES1_L???_???_R2.fastq.gz",
None,
(),
(),
(),
None,
[table_headers.RAW_DATA_FILE],
)
assert expected == first_row[3]
def test_study_reader_minimal_study(minimal_investigation_file,
minimal_study_file):
"""Use ``StudyReader`` to read in minimal study file.
Using the ``StudyReader`` instead of the ``StudyRowReader`` gives us
``Study`` objects instead of just the row-wise nodes.
"""
# Load investigation (tested elsewhere)
investigation = InvestigationReader.from_stream(
minimal_investigation_file).read()
with pytest.warns(IsaWarning) as record:
InvestigationValidator(investigation).validate()
# Check warnings
assert 2 == len(record)
# Create new row reader and check read headers
reader = StudyReader.from_stream("S1", minimal_study_file)
assert 3 == len(reader.header)
# Read study
study = reader.read()
StudyValidator(investigation, investigation.studies[0], study).validate()
# Check results
assert os.path.normpath(str(study.file)).endswith(
os.path.normpath("data/i_minimal/s_minimal.txt"))
assert 3 == len(study.header)
assert 2 == len(study.materials)
assert 1 == len(study.processes)
assert 2 == len(study.arcs)
expected = models.Material("Source Name", "S1-source-0815", "0815", None,
(), (), (), None, [table_headers.SOURCE_NAME])
assert expected == study.materials["S1-source-0815"]
expected = models.Material(
"Sample Name",
"S1-sample-0815-N1",
"0815-N1",
None,
(),
(),
(),
None,
[table_headers.SAMPLE_NAME],
)
assert expected == study.materials["S1-sample-0815-N1"]
expected = models.Process(
"sample collection",
"S1-sample collection-2-1",
None,
None,
None,
None,
(),
(),
None,
None,
None,
[table_headers.PROTOCOL_REF],
)
assert expected == study.processes["S1-sample collection-2-1"]
expected = (
models.Arc("S1-source-0815", "S1-sample collection-2-1"),
models.Arc("S1-sample collection-2-1", "S1-sample-0815-N1"),
)
assert expected == study.arcs
def test_study_reader_small_study(small_investigation_file, small_study_file):
"""Use ``StudyReader`` to read in small study file."""
# Load investigation (tested elsewhere)
with pytest.warns(IsaWarning) as record:
investigation = InvestigationReader.from_stream(
small_investigation_file).read()
InvestigationValidator(investigation).validate()
# Check warnings
assert 2 == len(record)
# Create new row reader and check read headers
reader = StudyReader.from_stream("S1", small_study_file)
assert 13 == len(reader.header)
# Read study
study = reader.read()
StudyValidator(investigation, investigation.studies[0], study).validate()
# Check results
assert os.path.normpath(str(study.file)).endswith(
os.path.normpath("data/i_small/s_small.txt"))
assert 13 == len(study.header)
assert 9 == len(study.materials)
assert 5 == len(study.processes)
assert 10 == len(study.arcs)
headers_source = [
table_headers.SOURCE_NAME,
table_headers.CHARACTERISTICS + "[organism]",
table_headers.TERM_SOURCE_REF,
table_headers.TERM_ACCESSION_NUMBER,
table_headers.CHARACTERISTICS + "[age]",
table_headers.UNIT,
table_headers.TERM_SOURCE_REF,
table_headers.TERM_ACCESSION_NUMBER,
]
headers_collection = [
table_headers.PROTOCOL_REF,
table_headers.PARAMETER_VALUE + "[instrument]",
table_headers.PERFORMER,
table_headers.DATE,
]
headers_sample = [
table_headers.SAMPLE_NAME,
table_headers.CHARACTERISTICS + "[status]",
table_headers.FACTOR_VALUE + "[treatment]",
]
unit = models.OntologyTermRef(
name="day",
accession="http://purl.obolibrary.org/obo/UO_0000033",
ontology_name="UO")
characteristics1 = (
models.Characteristics(
name="organism",
value=[
models.OntologyTermRef(
name="Mus musculus",
accession="http://purl.bioontology.org/ontology/"
"NCBITAXON/10090",
ontology_name="NCBITAXON",
)
],
unit=None,
),
models.Characteristics(name="age", value=["90"], unit=unit),
)
characteristics2 = (
models.Characteristics(
name="organism",
value=[models.OntologyTermRef("Mus musculus", "", "")],
unit=None),
models.Characteristics(name="age", value=[""], unit=unit),
)
characteristics3 = (
models.Characteristics(
name="organism",
value=[models.OntologyTermRef(None, None, None)],
unit=None),
models.Characteristics(name="age", value=["150"], unit=unit),
)
expected = models.Material(
"Source Name",
"S1-source-0815",
"0815",
None,
characteristics1,
(),
(),
None,
headers_source,
)
assert expected == study.materials["S1-source-0815"]
expected = models.Material(
"Source Name",
"S1-source-0816",
"0816",
None,
characteristics2,
(),
(),
None,
headers_source,
)
assert expected == study.materials["S1-source-0816"]
expected = models.Material(
"Source Name",
"S1-source-0817",
"0817",
None,
characteristics3,
(),
(),
None,
headers_source,
)
assert expected == study.materials["S1-source-0817"]
expected = models.Material(
"Sample Name",
"S1-sample-0815-N1",
"0815-N1",
None,
(models.Characteristics("status", ["0"], None), ),
(),
(models.FactorValue("treatment", "yes", None), ),
None,
headers_sample,
)
assert expected == study.materials["S1-sample-0815-N1"]
expected = models.Material(
"Sample Name",
"S1-sample-0815-T1",
"0815-T1",
None,
(models.Characteristics("status", ["2"], None), ),
(),
(models.FactorValue("treatment", "", None), ),
None,
headers_sample,
)
assert expected == study.materials["S1-sample-0815-T1"]
expected = models.Material(
"Sample Name",
"S1-sample-0816-T1",
"0816-T1",
None,
(models.Characteristics("status", ["1"], None), ),
(),
(models.FactorValue("treatment", "yes", None), ),
None,
headers_sample,
)
assert expected == study.materials["S1-sample-0816-T1"]
expected = models.Material(
"Sample Name",
"S1-Empty Sample Name-13-5",
"",
None,
(models.Characteristics("status", [""], None), ),
(),
(models.FactorValue("treatment", "", None), ),
None,
headers_sample,
)
assert expected == study.materials["S1-Empty Sample Name-13-5"]
expected = models.Process(
"sample collection",
"S1-sample collection-9-2",
None,
None,
date(2018, 2, 2),
"John Doe",
(models.ParameterValue("instrument", ["scalpel"], None), ),
(),
None,
None,
None,
headers_collection,
)
assert expected == study.processes["S1-sample collection-9-2"]
expected = models.Process(
"sample collection",
"S1-sample collection-9-3",
None,
None,
date(2018, 2, 2),
"John Doe",
(models.ParameterValue("instrument",
["scalpel type A", "scalpel type B"], None), ),
(),
None,
None,
None,
headers_collection,
)
assert expected == study.processes["S1-sample collection-9-3"]
expected = models.Process(
"sample collection",
"S1-sample collection-9-4",
None,
None,
date(2018, 2, 2),
"John Doe",
(models.ParameterValue("instrument", ["scalpel"], None), ),
(),
None,
None,
None,
headers_collection,
)
assert expected == study.processes["S1-sample collection-9-4"]
expected = (
models.Arc("S1-source-0814", "S1-sample collection-9-1"),
models.Arc("S1-sample collection-9-1", "S1-sample-0814-N1"),
models.Arc("S1-source-0815", "S1-sample collection-9-2"),
models.Arc("S1-sample collection-9-2", "S1-sample-0815-N1"),
models.Arc("S1-source-0815", "S1-sample collection-9-3"),
models.Arc("S1-sample collection-9-3", "S1-sample-0815-T1"),
models.Arc("S1-source-0816", "S1-sample collection-9-4"),
models.Arc("S1-sample collection-9-4", "S1-sample-0816-T1"),
models.Arc("S1-source-0817", "S1-sample collection-9-5"),
models.Arc("S1-sample collection-9-5", "S1-Empty Sample Name-13-5"),
)
assert expected == study.arcs
def test_study_row_reader_small_study(small_investigation_file,
small_study_file):
"""Use ``StudyRowReader`` to read in small study file."""
# Create new row reader and check read headers (+ string representation)
row_reader = StudyRowReader.from_stream("S1", small_study_file)
assert 13 == len(row_reader.header)
rep0 = "ColumnHeader(column_type='Source Name', col_no=0, span=1)"
rep1 = "LabeledColumnHeader(column_type='Characteristics', col_no=1, span=1, label='organism')"
assert rep0 == repr(row_reader.header[0])
assert rep1 == repr(row_reader.header[1])
# Read all rows in study
rows = list(row_reader.read())
# Check results
assert 5 == len(rows)
first_row = rows[0]
second_row = rows[1]
third_row = rows[2]
assert 3 == len(second_row)
headers_source = [
table_headers.SOURCE_NAME,
table_headers.CHARACTERISTICS + "[organism]",
table_headers.TERM_SOURCE_REF,
table_headers.TERM_ACCESSION_NUMBER,
table_headers.CHARACTERISTICS + "[age]",
table_headers.UNIT,
table_headers.TERM_SOURCE_REF,
table_headers.TERM_ACCESSION_NUMBER,
]
headers_collection = [
table_headers.PROTOCOL_REF,
table_headers.PARAMETER_VALUE + "[instrument]",
table_headers.PERFORMER,
table_headers.DATE,
]
headers_sample = [
table_headers.SAMPLE_NAME,
table_headers.CHARACTERISTICS + "[status]",
table_headers.FACTOR_VALUE + "[treatment]",
]
unit = models.OntologyTermRef(
name="day",
accession="http://purl.obolibrary.org/obo/UO_0000033",
ontology_name="UO")
characteristics1 = (
models.Characteristics(
name="organism",
value=[
models.OntologyTermRef(
name="Mus musculus",
accession=
"http://purl.bioontology.org/ontology/NCBITAXON/10090",
ontology_name="NCBITAXON",
),
models.OntologyTermRef(
name="H**o sapiens",
accession=
"http://purl.bioontology.org/ontology/NCBITAXON/9606",
ontology_name="NCBITAXON",
),
],
unit=None,
),
models.Characteristics(name="age", value=["90"], unit=unit),
)
expected = models.Material(
"Source Name",
"S1-source-0814",
"0814",
None,
characteristics1,
(),
(),
None,
headers_source,
)
assert expected == first_row[0]
characteristics2 = (
models.Characteristics(
name="organism",
value=[
models.OntologyTermRef(
name="Mus musculus",
accession=
"http://purl.bioontology.org/ontology/NCBITAXON/10090",
ontology_name="NCBITAXON",
)
],
unit=None,
),
models.Characteristics(name="age", value=["90"], unit=unit),
)
expected = models.Material(
"Source Name",
"S1-source-0815",
"0815",
None,
characteristics2,
(),
(),
None,
headers_source,
)
assert expected == second_row[0]
expected = models.Process(
"sample collection",
"S1-sample collection-9-2",
None,
None,
date(2018, 2, 2),
"John Doe",
(models.ParameterValue("instrument", ["scalpel"], None), ),
(),
None,
None,
None,
headers_collection,
)
assert expected == second_row[1]
expected = models.Material(
"Sample Name",
"S1-sample-0815-N1",
"0815-N1",
None,
(models.Characteristics("status", ["0"], None), ),
(),
(models.FactorValue("treatment", "yes", None), ),
None,
headers_sample,
)
assert expected == second_row[2]
assert 3 == len(third_row)
expected = models.Material(
"Source Name",
"S1-source-0815",
"0815",
None,
characteristics2,
(),
(),
None,
headers_source,
)
assert expected == third_row[0]
expected = models.Process(
"sample collection",
"S1-sample collection-9-3",
None,
None,
date(2018, 2, 2),
"John Doe",
(models.ParameterValue("instrument",
["scalpel type A", "scalpel type B"], None), ),
(),
None,
None,
None,
headers_collection,
)
assert expected == third_row[1]
expected = models.Material(
"Sample Name",
"S1-sample-0815-T1",
"0815-T1",
None,
(models.Characteristics("status", ["2"], None), ),
(),
(models.FactorValue("treatment", "", None), ),
None,
headers_sample,
)
assert expected == third_row[2]
def create_and_write(out_path):
"""Create an investigation with a study and assay and write to ``output_path``."""
# Prepare one or more study sections
# Prepare basic study information
study_info = models.BasicInfo(
path="s_minimal.txt",
identifier="s_minimal",
title="Germline Study",
description=None,
submission_date=None,
public_release_date=None,
comments=(
models.Comment(name="Study Grant Number", value=None),
models.Comment(name="Study Funding Agency", value=None),
),
headers=[],
)
# Create one or more assays
assay_01 = models.AssayInfo(
measurement_type=models.OntologyTermRef(
name="exome sequencing assay",
accession="http://purl.obolibrary.org/obo/OBI_0002118",
ontology_name="OBI",
),
technology_type=models.OntologyTermRef(
name="nucleotide sequencing",
accession="http://purl.obolibrary.org/obo/OBI_0000626",
ontology_name="OBI",
),
platform=None,
path="a_minimal.txt",
comments=(),
headers=[],
)
# Prepare one or more protocols
protocol_01 = models.ProtocolInfo(
name="sample collection",
type=models.OntologyTermRef(name="sample collection"),
description=None,
uri=None,
version=None,
parameters={},
components={},
comments=(),
headers=[],
)
protocol_02 = models.ProtocolInfo(
name="nucleic acid sequencing",
type=models.OntologyTermRef(name="nucleic acid sequencing"),
description=None,
uri=None,
version=None,
parameters={},
components={},
comments=(),
headers=[],
)
# Create study object
study_01 = models.StudyInfo(
info=study_info,
designs=(),
publications=(),
factors={},
assays=(assay_01, ),
protocols={
protocol_01.name: protocol_01,
protocol_02.name: protocol_02
},
contacts=(),
)
# Prepare other investigation section
# Prepare one or more ontology term source references
onto_ref_01 = models.OntologyRef(
name="OBI",
file="http://data.bioontology.org/ontologies/OBI",
version="31",
description="Ontology for Biomedical Investigations",
comments=(),
headers=[],
)
# Prepare basic investigation information
invest_info = models.BasicInfo(
path="i_minimal.txt",
identifier="i_minimal",
title="Minimal Investigation",
description=None,
submission_date=None,
public_release_date=None,
comments=(),
headers=[],
)
# Create investigation object
investigation = models.InvestigationInfo(
ontology_source_refs={onto_ref_01.name: onto_ref_01},
info=invest_info,
publications=(),
contacts=(),
studies=(study_01, ),
)
# Validate investigation
InvestigationValidator(investigation).validate()
# Write the investigation as ISA-Tab txt file
with open(join(out_path, investigation.info.path), "wt",
newline="") as outputf:
InvestigationWriter.from_stream(investigation=investigation,
output_file=outputf).write()
# Create a corresponding Study graph
# Create at least on source, one sample and one collection process
# Unique names are required for unambiguous node identification
source_01 = models.Material(
type="Source Name",
unique_name="S1-source-0815",
name="0815",
extract_label=None,
characteristics=(),
comments=(),
factor_values=(),
material_type=None,
headers=[table_headers.SOURCE_NAME],
)
sample_01 = models.Material(
type="Sample Name",
unique_name="S1-sample-0815-N1",
name="0815-N1",
extract_label=None,
characteristics=(),
comments=(),
factor_values=(),
material_type=None,
headers=[table_headers.SAMPLE_NAME],
)
process_01 = models.Process(
protocol_ref="sample collection",
unique_name="S1-sample collection-2-1",
name=None,
name_type=None,
date=None,
performer=None,
parameter_values=(),
comments=(),
array_design_ref=None,
first_dimension=None,
second_dimension=None,
headers=[table_headers.PROTOCOL_REF],
)
# Create the arcs to connect the material and process nodes, referenced by the unique name
arc_01 = models.Arc(tail="S1-source-0815", head="S1-sample collection-2-1")
arc_02 = models.Arc(tail="S1-sample collection-2-1",
head="S1-sample-0815-N1")
# Create the study graph object
study_graph_01 = models.Study(
file=investigation.studies[0].info.path,
header=None,
materials={
source_01.unique_name: source_01,
sample_01.unique_name: sample_01
},
processes={process_01.unique_name: process_01},
arcs=(arc_01, arc_02),
)
# Validate study graph
StudyValidator(investigation=investigation,
study_info=investigation.studies[0],
study=study_graph_01).validate()
# Write the study as ISA-Tab txt file
with open(join(out_path, investigation.studies[0].info.path),
"wt",
newline="") as outputf:
StudyWriter.from_stream(study_or_assay=study_graph_01,
output_file=outputf).write()
# Create a corresponding Assay graph
# Create at least on samples, one output material and one collection process
# Unique names are required for unambiguous node identification
# Explicit header definition per node is currently required to enable export to ISA-Tab
sample_01 = models.Material(
type="Sample Name",
unique_name="S1-sample-0815-N1",
name="0815-N1",
extract_label=None,
characteristics=(),
comments=(),
factor_values=(),
material_type=None,
headers=[table_headers.SAMPLE_NAME],
)
data_file_01 = models.Material(
type="Raw Data File",
unique_name="S1-A1-0815-N1-DNA1-WES1_L???_???_R1.fastq.gz-COL4",
name="0815-N1-DNA1-WES1_L???_???_R1.fastq.gz",
extract_label=None,
characteristics=(),
comments=(),
factor_values=(),
material_type=None,
headers=[table_headers.RAW_DATA_FILE],
)
data_file_02 = models.Material(
type="Raw Data File",
unique_name="S1-A1-0815-N1-DNA1-WES1_L???_???_R2.fastq.gz-COL5",
name="0815-N1-DNA1-WES1_L???_???_R2.fastq.gz",
extract_label=None,
characteristics=(),
comments=(),
factor_values=(),
material_type=None,
headers=[table_headers.RAW_DATA_FILE],
)
process_01 = models.Process(
protocol_ref="nucleic acid sequencing",
unique_name="S1-A1-0815-N1-DNA1-WES1-3",
name="0815-N1-DNA1-WES1",
name_type="Assay Name",
date=None,
performer=None,
parameter_values=(),
comments=(),
array_design_ref=None,
first_dimension=None,
second_dimension=None,
headers=[table_headers.PROTOCOL_REF, table_headers.ASSAY_NAME],
)
# Create the arcs to connect the material and process nodes, referenced by the unique name
arcs = (
models.Arc(tail="S1-sample-0815-N1", head="S1-A1-0815-N1-DNA1-WES1-3"),
models.Arc(
tail="S1-A1-0815-N1-DNA1-WES1-3",
head="S1-A1-0815-N1-DNA1-WES1_L???_???_R1.fastq.gz-COL4",
),
models.Arc(
tail="S1-A1-0815-N1-DNA1-WES1_L???_???_R1.fastq.gz-COL4",
head="S1-A1-0815-N1-DNA1-WES1_L???_???_R2.fastq.gz-COL5",
),
)
# Create the assay graph object
assay_graph_01 = models.Assay(
file=investigation.studies[0].assays[0].path,
header=None,
materials={
sample_01.unique_name: sample_01,
data_file_01.unique_name: data_file_01,
data_file_02.unique_name: data_file_02,
},
processes={process_01.unique_name: process_01},
arcs=arcs,
)
# Validate assay graph
AssayValidator(
investigation=investigation,
study_info=investigation.studies[0],
assay_info=investigation.studies[0].assays[0],
assay=assay_graph_01,
).validate()
# Write the assay as ISA-Tab txt file
with open(join(out_path, investigation.studies[0].assays[0].path),
"wt",
newline="") as outputf:
AssayWriter.from_stream(study_or_assay=assay_graph_01,
output_file=outputf).write()