def run_warnings_caught(args):
# Read investigation
investigation = InvestigationReader.from_stream(args.input_investigation_file).read()
args.input_investigation_file.close()
# Validate investigation
InvestigationValidator(investigation).validate()
# Read studies and assays
path_in = os.path.normpath(os.path.dirname(args.input_investigation_file.name))
studies = {}
assays = {}
for s, study_info in enumerate(investigation.studies):
if study_info.info.path:
with open(os.path.join(path_in, study_info.info.path), "rt") as inputf:
studies[s] = StudyReader.from_stream("S{}".format(s + 1), inputf).read()
if study_info.assays:
assays[s] = {}
for a, assay_info in enumerate(study_info.assays):
if assay_info.path:
with open(os.path.join(path_in, assay_info.path), "rt") as inputf:
assays[s][a] = AssayReader.from_stream(
"S{}".format(s + 1), "A{}".format(a + 1), inputf
).read()
# Validate studies and assays
for s, study_info in enumerate(investigation.studies):
if study_info.info.path:
StudyValidator(investigation, study_info, studies[s]).validate()
for a, assay_info in enumerate(study_info.assays):
if assay_info.path:
AssayValidator(investigation, study_info, assay_info, assays[s][a]).validate()
def test_assay_reader_minimal_assay_iostring2(minimal_investigation_file,
minimal_assay_file):
# Load investigation (tested elsewhere)
stringio = io.StringIO(minimal_investigation_file.read())
investigation = InvestigationReader.from_stream(stringio).read()
with pytest.warns(IsaWarning) as record:
InvestigationValidator(investigation).validate()
# Check warnings
assert 2 == len(record)
# Create new assay reader and read from StringIO with no filename indicated
stringio = io.StringIO(minimal_assay_file.read())
reader = AssayReader.from_stream("S1", "A1", stringio)
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 str(assay.file) == os.path.normpath("<no file>")
assert 5 == len(assay.header)
assert 3 == len(assay.materials)
assert 1 == len(assay.processes)
assert 3 == len(assay.arcs)
def _parse_write_assert_assay(investigation_file,
tmp_path,
quote=None,
normalize=False,
skip=None):
# Load investigation
investigation = InvestigationReader.from_stream(investigation_file).read()
InvestigationValidator(investigation).validate()
directory = os.path.normpath(os.path.dirname(investigation_file.name))
# Iterate assays
for s, study_info in enumerate(investigation.studies):
for a, assay_info in enumerate(study_info.assays):
if skip and str(assay_info.path) in skip:
continue
# Load assay
path_in = os.path.join(directory, assay_info.path)
with open(path_in, "rt") as inputf:
assay = AssayReader.from_stream("S{}".format(s + 1),
"A{}".format(a + 1),
inputf).read()
AssayValidator(investigation, study_info, assay_info,
assay).validate()
# Write assay to temporary file
path_out = tmp_path / assay_info.path
with open(path_out, "wt", newline="") as file:
AssayWriter.from_stream(assay, file, quote=quote).write()
if normalize:
# Read and write assay again
path_in = path_out
with open(path_out, "rt") as inputf:
assay = AssayReader.from_stream("S{}".format(s + 1),
"A{}".format(a + 1),
inputf).read()
AssayValidator(investigation, study_info, assay_info,
assay).validate()
path_out = tmp_path / (assay_info.path.name + "_b")
with open(path_out, "wt", newline="") as file:
AssayWriter.from_stream(assay, file, quote=quote).write()
# Sort and compare input and output
path_in_s = tmp_path / (assay_info.path.name + ".in.sorted")
path_out_s = tmp_path / (assay_info.path.name + ".out.sorted")
assert filecmp.cmp(sort_file(path_in, path_in_s),
sort_file(path_out, path_out_s),
shallow=False)
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_small2_assay(small2_investigation_file,
small2_assay_file):
"""Use ``AssayReader`` to read in small assay file."""
# Load investigation (tested elsewhere)
investigation = InvestigationReader.from_stream(
small2_investigation_file).read()
InvestigationValidator(investigation).validate()
# Create new row reader and check read headers
reader = AssayReader.from_stream("S1", "A1", small2_assay_file)
assert 14 == len(reader.header)
# Read 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_small2/a_small2.txt"))
assert 14 == len(assay.header)
assert 25 == len(assay.materials)
assert 41 == len(assay.processes)
assert 74 == len(assay.arcs)
# Comments
expected = models.Comment(name="Replicate", value="B")
assert assay.materials["S1-A1-0815-T1-Pro1-B-115-COL5"].comments[
0] == expected
# Expected arcs
expected = (
models.Arc("S1-sample-0815-N1", "S1-A1-extraction-2-1"),
models.Arc("S1-sample-0815-T1", "S1-A1-extraction-2-2"),
models.Arc("S1-A1-extraction-2-1", "S1-A1-0815-N1-Pro1-COL3"),
models.Arc("S1-A1-extraction-2-2", "S1-A1-0815-T1-Pro1-COL3"),
models.Arc("S1-A1-0815-N1-Pro1-COL3", "S1-A1-labeling-4-1"),
models.Arc("S1-A1-0815-T1-Pro1-COL3", "S1-A1-labeling-4-2"),
models.Arc("S1-A1-0815-N1-Pro1-COL3", "S1-A1-labeling-4-3"),
models.Arc("S1-A1-0815-T1-Pro1-COL3", "S1-A1-labeling-4-4"),
models.Arc("S1-A1-0815-N1-Pro1-COL3", "S1-A1-labeling-4-5"),
models.Arc("S1-A1-0815-T1-Pro1-COL3", "S1-A1-labeling-4-6"),
models.Arc("S1-A1-0815-N1-Pro1-COL3", "S1-A1-labeling-4-7"),
models.Arc("S1-A1-0815-T1-Pro1-COL3", "S1-A1-labeling-4-8"),
models.Arc("S1-A1-0815-N1-Pro1-COL3", "S1-A1-labeling-4-9"),
models.Arc("S1-A1-0815-T1-Pro1-COL3", "S1-A1-labeling-4-10"),
models.Arc("S1-A1-0815-N1-Pro1-COL3", "S1-A1-labeling-4-11"),
models.Arc("S1-A1-0815-T1-Pro1-COL3", "S1-A1-labeling-4-12"),
models.Arc("S1-A1-labeling-4-1", "S1-A1-0815-N1-Pro1-A-114-COL5"),
models.Arc("S1-A1-labeling-4-2", "S1-A1-0815-T1-Pro1-A-115-COL5"),
models.Arc("S1-A1-labeling-4-3", "S1-A1-0815-N1-Pro1-B-114-COL5"),
models.Arc("S1-A1-labeling-4-4", "S1-A1-0815-T1-Pro1-B-115-COL5"),
models.Arc("S1-A1-labeling-4-5", "S1-A1-0815-N1-Pro1-C-114-COL5"),
models.Arc("S1-A1-labeling-4-6", "S1-A1-0815-T1-Pro1-C-115-COL5"),
models.Arc("S1-A1-labeling-4-7", "S1-A1-0815-N1-Pro1-D-114-COL5"),
models.Arc("S1-A1-labeling-4-8", "S1-A1-0815-T1-Pro1-D-115-COL5"),
models.Arc("S1-A1-labeling-4-9", "S1-A1-0815-N1-Pro1-E-114-COL5"),
models.Arc("S1-A1-labeling-4-10", "S1-A1-0815-T1-Pro1-E-115-COL5"),
models.Arc("S1-A1-labeling-4-11", "S1-A1-0815-N1-Pro1-F-114-COL5"),
models.Arc("S1-A1-labeling-4-12", "S1-A1-0815-T1-Pro1-F-115-COL5"),
models.Arc("S1-A1-0815-N1-Pro1-A-114-COL5",
"S1-A1-chromatography-8-1"),
models.Arc("S1-A1-0815-T1-Pro1-A-115-COL5",
"S1-A1-chromatography-8-2"),
models.Arc("S1-A1-0815-N1-Pro1-B-114-COL5",
"S1-A1-chromatography-8-3"),
models.Arc("S1-A1-0815-T1-Pro1-B-115-COL5",
"S1-A1-chromatography-8-4"),
models.Arc("S1-A1-0815-N1-Pro1-C-114-COL5",
"S1-A1-chromatography-8-5"),
models.Arc("S1-A1-0815-T1-Pro1-C-115-COL5",
"S1-A1-chromatography-8-6"),
models.Arc("S1-A1-0815-N1-Pro1-D-114-COL5",
"S1-A1-chromatography-8-7"),
models.Arc("S1-A1-0815-T1-Pro1-D-115-COL5",
"S1-A1-chromatography-8-8"),
models.Arc("S1-A1-0815-N1-Pro1-E-114-COL5",
"S1-A1-chromatography-8-9"),
models.Arc("S1-A1-0815-T1-Pro1-E-115-COL5",
"S1-A1-chromatography-8-10"),
models.Arc("S1-A1-0815-N1-Pro1-F-114-COL5",
"S1-A1-chromatography-8-11"),
models.Arc("S1-A1-0815-T1-Pro1-F-115-COL5",
"S1-A1-chromatography-8-12"),
models.Arc("S1-A1-chromatography-8-1", "S1-A1-poolA-10"),
models.Arc("S1-A1-chromatography-8-2", "S1-A1-poolA-10"),
models.Arc("S1-A1-chromatography-8-3", "S1-A1-mass spectrometry-9-3"),
models.Arc("S1-A1-chromatography-8-4", "S1-A1-mass spectrometry-9-4"),
models.Arc("S1-A1-chromatography-8-5", "S1-A1-poolC-10"),
models.Arc("S1-A1-chromatography-8-6", "S1-A1-poolC-10"),
models.Arc("S1-A1-chromatography-8-7", "S1-A1-mass spectrometry-9-7"),
models.Arc("S1-A1-chromatography-8-8", "S1-A1-mass spectrometry-9-8"),
models.Arc("S1-A1-chromatography-8-9", "S1-A1-poolE-10"),
models.Arc("S1-A1-chromatography-8-10", "S1-A1-poolE-10"),
models.Arc("S1-A1-chromatography-8-11", "S1-A1-poolF-10"),
models.Arc("S1-A1-chromatography-8-12", "S1-A1-poolF-10"),
models.Arc("S1-A1-poolA-10", "S1-A1-poolA.raw-COL11"),
models.Arc("S1-A1-mass spectrometry-9-3", "S1-A1-poolB.raw-COL11"),
models.Arc("S1-A1-mass spectrometry-9-4", "S1-A1-poolB.raw-COL11"),
models.Arc("S1-A1-poolC-10",
"S1-A1-Empty Raw Spectral Data File-11-5"),
models.Arc("S1-A1-mass spectrometry-9-7",
"S1-A1-Empty Raw Spectral Data File-11-7"),
models.Arc("S1-A1-mass spectrometry-9-8",
"S1-A1-Empty Raw Spectral Data File-11-8"),
models.Arc("S1-A1-poolE-10", "S1-A1-poolE.raw-COL11"),
models.Arc("S1-A1-poolF-10",
"S1-A1-Empty Raw Spectral Data File-11-11"),
models.Arc("S1-A1-poolA.raw-COL11", "S1-A1-data transformation-12-1"),
models.Arc("S1-A1-poolB.raw-COL11", "S1-A1-data transformation-12-3"),
models.Arc("S1-A1-Empty Raw Spectral Data File-11-5",
"S1-A1-data transformation-12-5"),
models.Arc("S1-A1-Empty Raw Spectral Data File-11-7",
"S1-A1-data transformation-12-7"),
models.Arc("S1-A1-Empty Raw Spectral Data File-11-8",
"S1-A1-data transformation-12-8"),
models.Arc("S1-A1-poolE.raw-COL11", "S1-A1-data transformation-12-9"),
models.Arc("S1-A1-Empty Raw Spectral Data File-11-11",
"S1-A1-data analysis-13"),
models.Arc("S1-A1-data transformation-12-1",
"S1-A1-results.csv-COL14"),
models.Arc("S1-A1-data transformation-12-3",
"S1-A1-results.csv-COL14"),
models.Arc("S1-A1-data transformation-12-5",
"S1-A1-results.csv-COL14"),
models.Arc("S1-A1-data transformation-12-7",
"S1-A1-results.csv-COL14"),
models.Arc("S1-A1-data transformation-12-8",
"S1-A1-results.csv-COL14"),
models.Arc("S1-A1-data transformation-12-9",
"S1-A1-Empty Derived Data File-14-9"),
models.Arc("S1-A1-data analysis-13", "S1-A1-results.csv-COL14"),
)
assert sorted(expected) == sorted(assay.arcs)
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 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()