def test_concat_simple_file_with_header(self):
"""
Test that a single file with no header comes out looking as expected
"""
with TemporaryDirectory() as tmpdir:
# make a dummy file with some lines
input_lines = ["#header", "foo", "bar", "baz"]
input_file = os.path.join(tmpdir, "input.txt")
with open(input_file, "w") as fout:
for line in input_lines:
fout.write(line + '\n')
input_json = {
"input_files": [{
"class": "File",
"path": input_file
}]
}
input_json_file = os.path.join(tmpdir, "input.json")
with open(input_json_file, "w") as input_json_file_data:
json.dump(input_json, input_json_file_data)
output_dir = os.path.join(tmpdir, "output")
tmp_dir = os.path.join(tmpdir, "tmp")
cache_dir = os.path.join(tmpdir, "cache")
command = [
"cwl-runner", *CWL_ARGS, "--outdir", output_dir,
"--tmpdir-prefix", tmp_dir, "--cachedir", cache_dir, cwl_file,
input_json_file
]
returncode, proc_stdout, proc_stderr = run_command(command)
if returncode != 0:
print(proc_stderr)
self.assertEqual(returncode, 0)
output_json = json.loads(proc_stdout)
# check the contents of the concatenated file; should be the same as the input
output_file = output_json['output_file']['path']
with open(output_file) as fin:
output_lines = [line.strip() for line in fin]
self.assertEqual(output_lines, ["foo", "bar", "baz"])
expected_output = {
'output_file': {
'location':
'file://' + os.path.join(output_dir, 'output.txt'),
'basename': 'output.txt',
'class': 'File',
'checksum':
'sha1$0562f08aef399135936d6fb4eb0cc7bc1890d5b4',
'size': 12,
'path': os.path.join(output_dir, 'output.txt')
}
}
self.assertDictEqual(output_json, expected_output)
def test_concat_two_mixed_files(self):
"""
Test that two files, one with a comment and one without, are concatenated correctly
"""
with TemporaryDirectory() as tmpdir:
# make a dummy file with some lines
input_lines1 = ["header1", "foo1", "bar1", "baz1"]
input_file1 = os.path.join(tmpdir, "input1.txt")
with open(input_file1, "w") as fout:
for line in input_lines1:
fout.write(line + '\n')
input_lines2 = ["#comment2", "header2", "foo2", "bar2", "baz2"]
input_file2 = os.path.join(tmpdir, "input2.txt")
with open(input_file2, "w") as fout:
for line in input_lines2:
fout.write(line + '\n')
input_json = {
"input_files": [{
"class": "File",
"path": input_file1
}, {
"class": "File",
"path": input_file2
}]
}
input_json_file = os.path.join(tmpdir, "input.json")
with open(input_json_file, "w") as input_json_file_data:
json.dump(input_json, input_json_file_data)
output_dir = os.path.join(tmpdir, "output")
tmp_dir = os.path.join(tmpdir, "tmp")
cache_dir = os.path.join(tmpdir, "cache")
command = [
"cwl-runner", *CWL_ARGS, "--outdir", output_dir,
"--tmpdir-prefix", tmp_dir, "--cachedir", cache_dir, cwl_file,
input_json_file
]
returncode, proc_stdout, proc_stderr = run_command(command)
if returncode != 0:
print(proc_stderr)
self.assertEqual(returncode, 0)
output_json = json.loads(proc_stdout)
# check the contents of the concatenated file; should be the same as the input
output_file = output_json['output_file']['path']
with open(output_file) as fin:
output_lines = [line.strip() for line in fin]
self.assertEqual(
output_lines,
["header1", "foo1", "bar1", "baz1", "foo2", "bar2", "baz2"])
expected_output = {
'output_file': {
'location':
'file://' + os.path.join(output_dir, 'output.txt'),
'basename': 'output.txt',
'class': 'File',
'checksum':
'sha1$acaa1f09ca0678b8b7c136ce776c04efb6890f6a',
'size': 38,
'path': os.path.join(output_dir, 'output.txt')
}
}
self.assertDictEqual(output_json, expected_output)
def test_concat_three_files_with_comments(self):
"""
Test that a three files with headers are concatenated correctly
Use three this time to clearly show the ordering of the output iteration
"""
with TemporaryDirectory() as tmpdir:
# make a dummy file with some lines
input_lines1 = ["#comment1", "header1", "foo1", "bar1", "baz1"]
input_file1 = os.path.join(tmpdir, "input1.txt")
with open(input_file1, "w") as fout:
for line in input_lines1:
fout.write(line + '\n')
input_lines2 = ["#comment2", "header2", "foo2", "bar2", "baz2"]
input_file2 = os.path.join(tmpdir, "input2.txt")
with open(input_file2, "w") as fout:
for line in input_lines2:
fout.write(line + '\n')
input_lines3 = ["#comment3", "header3", "foo3", "bar3", "baz3"]
input_file3 = os.path.join(tmpdir, "input3.txt")
with open(input_file3, "w") as fout:
for line in input_lines3:
fout.write(line + '\n')
input_json = {
"input_files": [{
"class": "File",
"path": input_file1
}, {
"class": "File",
"path": input_file2
}, {
"class": "File",
"path": input_file3
}]
}
input_json_file = os.path.join(tmpdir, "input.json")
with open(input_json_file, "w") as input_json_file_data:
json.dump(input_json, input_json_file_data)
output_dir = os.path.join(tmpdir, "output")
tmp_dir = os.path.join(tmpdir, "tmp")
cache_dir = os.path.join(tmpdir, "cache")
command = [
"cwl-runner", *CWL_ARGS, "--outdir", output_dir,
"--tmpdir-prefix", tmp_dir, "--cachedir", cache_dir, cwl_file,
input_json_file
]
returncode, proc_stdout, proc_stderr = run_command(command)
if returncode != 0:
print(proc_stderr)
self.assertEqual(returncode, 0)
output_json = json.loads(proc_stdout)
# check the contents of the concatenated file; should be the same as the input
output_file = output_json['output_file']['path']
with open(output_file) as fin:
output_lines = [line.strip() for line in fin]
expected_output_lines = [
"header1", "foo1", "bar1", "baz1", "foo2", "bar2", "baz2",
"foo3", "bar3", "baz3"
]
self.assertEqual(output_lines, expected_output_lines)
# TODO: update this once the above ^^^ passes
expected_output = {
'output_file': {
'location':
'file://' + os.path.join(output_dir, 'output.txt'),
'basename': 'output.txt',
'class': 'File',
'checksum':
'sha1$b115b7b40aa8a2e08e30a55abf60d742e05e62b4',
'size': 53,
'path': os.path.join(output_dir, 'output.txt')
}
}
self.assertDictEqual(output_json, expected_output)
def test_concat1(self):
"""
Test concat when original file has a comment line
"""
with TemporaryDirectory() as tmpdir:
# make a dummy file with some lines
input_lines = ["# comment here", "HEADER", "foo", "bar", "baz"]
input_file = os.path.join(tmpdir, "input.txt")
with open(input_file, "w") as fout:
for line in input_lines:
fout.write(line + '\n')
input_json = {
"input_files": [{
"class": "File",
"path": input_file
}],
"comment_label": "comment_label",
"comment_value": "comment_value"
}
input_json_file = os.path.join(tmpdir, "input.json")
with open(input_json_file, "w") as input_json_file_data:
json.dump(input_json, input_json_file_data)
output_dir = os.path.join(tmpdir, "output")
tmp_dir = os.path.join(tmpdir, "tmp")
cache_dir = os.path.join(tmpdir, "cache")
command = [
"cwl-runner",
*CWL_ARGS,
"--outdir", output_dir,
"--tmpdir-prefix", tmp_dir,
"--cachedir", cache_dir,
cwl_file, input_json_file
]
returncode, proc_stdout, proc_stderr = run_command(command)
if returncode != 0:
print(proc_stderr)
self.assertEqual(returncode, 0)
output_json = json.loads(proc_stdout)
# check the contents of the concatenated file; should be the same as the input
output_file = output_json['output_file']['path']
with open(output_file) as fin:
output_lines = [ line.strip() for line in fin ]
expected_lines = ['# comment here', '#comment_label: comment_value', "HEADER", 'foo', 'bar', 'baz']
self.assertEqual(output_lines, expected_lines)
expected_output = {
'output_file': {
'location': 'file://' + os.path.join(output_dir, 'output.txt'),
'basename': 'output.txt',
'class': 'File',
'checksum': 'sha1$14ee1247f314dba1e3c28aa8aec9ff7b137a1f41',
'size': 64,
'path': os.path.join(output_dir, 'output.txt')
}
}
self.assertDictEqual(output_json, expected_output)
def test_concat_two_files_with_headers(self):
"""
Test that a single file with no header comes out looking as expected
"""
with TemporaryDirectory() as tmpdir:
# make a dummy file with some lines
input_lines1 = ["header", "foo1", "bar1", "baz1"]
input_file1 = os.path.join(tmpdir, "input1.txt")
with open(input_file1, "w") as fout:
for line in input_lines1:
fout.write(line + '\n')
input_lines2 = ["header", "foo2", "bar2", "baz2"]
input_file2 = os.path.join(tmpdir, "input2.txt")
with open(input_file2, "w") as fout:
for line in input_lines2:
fout.write(line + '\n')
input_json = {
"input_files": [{
"class": "File",
"path": input_file1
}, {
"class": "File",
"path": input_file2
}]
}
input_json_file = os.path.join(tmpdir, "input.json")
with open(input_json_file, "w") as input_json_file_data:
json.dump(input_json, input_json_file_data)
output_dir = os.path.join(tmpdir, "output")
tmp_dir = os.path.join(tmpdir, "tmp")
cache_dir = os.path.join(tmpdir, "cache")
command = [
"cwl-runner", *CWL_ARGS, "--outdir", output_dir,
"--tmpdir-prefix", tmp_dir, "--cachedir", cache_dir, cwl_file,
input_json_file
]
returncode, proc_stdout, proc_stderr = run_command(command)
if returncode != 0:
print(proc_stderr)
self.assertEqual(returncode, 0)
output_json = json.loads(proc_stdout)
# check the contents of the concatenated file; should be the same as the input
output_file = output_json['output_file']['path']
with open(output_file) as fin:
output_lines = [line.strip() for line in fin]
self.assertEqual(
output_lines,
["header", "foo1", "bar1", "baz1", "foo2", "bar2", "baz2"])
expected_output = {
'output_file': {
'location':
'file://' + os.path.join(output_dir, 'output.txt'),
'basename': 'output.txt',
'class': 'File',
'checksum':
'sha1$34c3af14e6d21e295f22c77ed5e837b60501bae7',
'size': 37,
'path': os.path.join(output_dir, 'output.txt')
}
}
self.assertDictEqual(output_json, expected_output)
def test_concat2(self):
"""
Test concat when multiple files have comments
"""
with TemporaryDirectory() as tmpdir:
# make a dummy file with some lines
input_lines1 = ["# comment 1 here", "HEADER", "foo1", "bar1"]
input_file1 = os.path.join(tmpdir, "input1.txt")
with open(input_file1, "w") as fout:
for line in input_lines1:
fout.write(line + '\n')
input_lines2 = ["# comment 2 here", "HEADER", "foo2", "bar2"]
input_file2 = os.path.join(tmpdir, "input2.txt")
with open(input_file2, "w") as fout:
for line in input_lines2:
fout.write(line + '\n')
input_json = {
"input_files": [
{
"class": "File",
"path": input_file1
},
{
"class": "File",
"path": input_file2
},
],
"comment_label": "comment_label",
"comment_value": "comment_value"
}
input_json_file = os.path.join(tmpdir, "input.json")
with open(input_json_file, "w") as input_json_file_data:
json.dump(input_json, input_json_file_data)
output_dir = os.path.join(tmpdir, "output")
tmp_dir = os.path.join(tmpdir, "tmp")
cache_dir = os.path.join(tmpdir, "cache")
command = [
"cwl-runner",
*CWL_ARGS,
"--outdir", output_dir,
"--tmpdir-prefix", tmp_dir,
"--cachedir", cache_dir,
cwl_file, input_json_file
]
returncode, proc_stdout, proc_stderr = run_command(command)
if returncode != 0:
print(proc_stderr)
self.assertEqual(returncode, 0)
output_json = json.loads(proc_stdout)
# check the contents of the concatenated file; should be the same as the input
output_file = output_json['output_file']['path']
with open(output_file) as fin:
output_lines = [ line.strip() for line in fin ]
expected_lines = [
'# comment 1 here',
'# comment 2 here',
'#comment_label: comment_value',
"HEADER",
'foo1',
'bar1',
'foo2',
'bar2'
]
self.maxDiff = None
self.assertEqual(output_lines, expected_lines)
expected_output = {
'output_file': {
'location': 'file://' + os.path.join(output_dir, 'output.txt'),
'basename': 'output.txt',
'class': 'File',
'checksum': 'sha1$5dbce16f9bfef135d6b8288b16350351a33998f3',
'size': 91,
'path': os.path.join(output_dir, 'output.txt')
}
}
self.assertDictEqual(output_json, expected_output)
def test_facets_workflow(self):
"""
"""
# the smallest pair of bam files in the test dataset
pair_maf = os.path.join(DATA_SETS['Proj_08390_G']['MAF_DIR'], "Sample24.Sample23.muts.maf")
snp_pileup = os.path.join(DATA_SETS['Proj_08390_G']['SNP_PILEUP_DIR'], "Sample24.Sample23.snp_pileup.gz")
input_json = {
"pairs": [
{
"pair_maf": {
"path": pair_maf,
"class": "File"
},
"snp_pileup": {
"path": snp_pileup,
"class": "File"
},
"pair_id": "Sample24.Sample23",
"normal_id": "Sample23",
"tumor_id": "Sample24"
}
]
}
with TemporaryDirectory() as tmpdir:
input_json_file = os.path.join(tmpdir, "input.json")
with open(input_json_file, "w") as json_out:
json.dump(input_json, json_out)
output_dir = os.path.join(tmpdir, "output")
tmp_dir = os.path.join(tmpdir, "tmp")
cache_dir = os.path.join(tmpdir, "cache")
command = [
"cwl-runner",
*CWL_ARGS,
"--outdir", output_dir,
"--tmpdir-prefix", tmp_dir,
"--cachedir", cache_dir,
cwl_file, input_json_file
]
returncode, proc_stdout, proc_stderr = run_command(command)
if returncode != 0:
print(proc_stderr)
self.assertEqual(returncode, 0)
output_json = json.loads(proc_stdout)
self.maxDiff = None
expected_output = {
'annotated_maf': [{
'location': 'file://' + os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24.Sample23_hisens.ccf.portal.maf'),
'basename': 'Sample24.Sample23_hisens.ccf.portal.maf',
'class': 'File',
'checksum': 'sha1$d91a8e15c66429b09f1b7db41bc38bdfa0b84c64',
'size': 11996607,
'path': os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24.Sample23_hisens.ccf.portal.maf')
}],
'arm_level_txt': [{
'location': 'file://' + os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24.arm_level.txt'),
'basename': 'Sample24.arm_level.txt',
'class': 'File',
'checksum': 'sha1$df37c54ae4969257e436a7a7a595c42ef19ecbb5',
'size': 1824,
'path': os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24.arm_level.txt')
}],
'facets_txt': [{
'location': 'file://' + os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24.txt'),
'basename': 'Sample24.txt',
'class': 'File',
'checksum': 'sha1$a0fb3df832efc18a66a8a54e5609666da5f4d7d7',
'size': 529,
'path': os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24.txt')
}],
'failed_pairs': [],
'gene_level_txt': [{
'location': 'file://' + os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24.gene_level.txt'),
'basename': 'Sample24.gene_level.txt',
'class': 'File',
'checksum': 'sha1$4e916a52458151007486bf536acfff539fdc2ecc',
'size': 148195,
'path': os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24.gene_level.txt')
}],
'hisens_rds': [{
'location': 'file://' + os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24_hisens.rds'),
'basename': 'Sample24_hisens.rds',
'class': 'File',
'checksum': 'sha1$6bfd6c7f29c49ec8ef538dd468a3b4626b05bda2',
'size': 213986,
'path': os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24_hisens.rds')
}],
'output_dir': {
'basename': 'facets',
'class': 'Directory',
'listing': [
{
'basename': 'Sample24.Sample23',
'class': 'Directory',
'listing': [
{
'basename': 'Sample24.Sample23_hisens.ccf.portal.maf',
'checksum': 'sha1$d91a8e15c66429b09f1b7db41bc38bdfa0b84c64',
'class': 'File',
'location': 'file://' + os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24.Sample23_hisens.ccf.portal.maf'),
'path': os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24.Sample23_hisens.ccf.portal.maf'),
'size': 11996607
},
{
'basename': 'Sample24.arm_level.txt',
'checksum': 'sha1$df37c54ae4969257e436a7a7a595c42ef19ecbb5',
'class': 'File',
'location': 'file://' + os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24.arm_level.txt'),
'path': os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24.arm_level.txt'),
'size': 1824
},
{
'basename': 'Sample24.txt',
'checksum': 'sha1$a0fb3df832efc18a66a8a54e5609666da5f4d7d7',
'class': 'File',
'location': 'file://' + os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24.txt'),
'path': os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24.txt'),
'size': 529
},
{
'basename': 'Sample24.gene_level.txt',
'checksum': 'sha1$4e916a52458151007486bf536acfff539fdc2ecc',
'class': 'File',
'location': 'file://' + os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24.gene_level.txt'),
'path': os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24.gene_level.txt'),
'size': 148195
},
{
'basename': 'Sample24_hisens.cncf.txt',
'checksum': 'sha1$db9131a33889a1cac82e3bd6b3f0e5e182c65105',
'class': 'File',
'location': 'file://' + os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24_hisens.cncf.txt'),
'path': os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24_hisens.cncf.txt'),
'size': 5238
},
{
'basename': 'Sample24_hisens.rds',
'checksum': 'sha1$6bfd6c7f29c49ec8ef538dd468a3b4626b05bda2',
'class': 'File',
'location': 'file://' + os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24_hisens.rds'),
'path': os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24_hisens.rds'),
'size': 213986
},
{
'basename': 'Sample24_hisens.seg',
'checksum': 'sha1$652f9c6d0245af49bac6ca67a089af7d4e46801b',
'class': 'File',
'location': 'file://' + os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24_hisens.seg'),
'path': os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24_hisens.seg'),
'size': 1897
},
{
'basename': 'Sample24_purity.rds',
'checksum': 'sha1$dd8b967f84b191ff76214c6110db8d0e65f6514c',
'class': 'File',
'location': 'file://' + os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24_purity.rds'),
'path': os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24_purity.rds'),
'size': 213356
},
{
'basename': 'Sample24_purity.seg',
'checksum': 'sha1$591e6d8b432e1e910fe4fb4b1814508131f960c9',
'class': 'File',
'location': 'file://' + os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24_purity.seg'),
'path': os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24_purity.seg'),
'size': 1285
},
{
'basename': 'Sample24.qc.txt',
'checksum': 'sha1$d4a36726a5fcb7b268aae02d97ce4e382e42d9f6',
'class': 'File',
'location': 'file://' + os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24.qc.txt'),
'path': os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24.qc.txt'),
'size': 1339}
],
'location': 'file://' + os.path.join(output_dir, 'facets/Sample24.Sample23'),
'path': os.path.join(output_dir, 'facets/Sample24.Sample23')
}
],
'location': 'file://' + os.path.join(output_dir, 'facets'),
'path': os.path.join(output_dir, 'facets')
},
'hisens_seg': [{
'location': 'file://' + os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24_hisens.seg'),
'basename': 'Sample24_hisens.seg',
'class': 'File',
'checksum': 'sha1$652f9c6d0245af49bac6ca67a089af7d4e46801b',
'size': 1897,
'path': os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24_hisens.seg')
}],
'purity_rds': [{
'location': 'file://' + os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24_purity.rds'),
'basename': 'Sample24_purity.rds',
'class': 'File',
'checksum': 'sha1$dd8b967f84b191ff76214c6110db8d0e65f6514c',
'size': 213356,
'path': os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24_purity.rds')
}],
'purity_seg': [{
'location': 'file://' + os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24_purity.seg'),
'basename': 'Sample24_purity.seg',
'class': 'File',
'checksum': 'sha1$591e6d8b432e1e910fe4fb4b1814508131f960c9',
'size': 1285,
'path': os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24_purity.seg')
}],
'qc_txt': [{
'location': 'file://' + os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24.qc.txt'),
'basename': 'Sample24.qc.txt',
'class': 'File',
'checksum': 'sha1$d4a36726a5fcb7b268aae02d97ce4e382e42d9f6',
'size': 1339,
'path': os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24.qc.txt')
}],
'hisens_cncf_txt': [{
'basename': 'Sample24_hisens.cncf.txt',
'checksum': 'sha1$db9131a33889a1cac82e3bd6b3f0e5e182c65105',
'class': 'File',
'location': 'file://' + os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24_hisens.cncf.txt'),
'path': os.path.join(output_dir, 'facets/Sample24.Sample23/Sample24_hisens.cncf.txt'),
'size': 5238
}],
}
self.assertDictEqual(output_json, expected_output)
def test_run_facets_wrapper(self):
"""
"""
input_maf = os.path.join(DATA_SETS['Proj_08390_G']['MAF_DIR'],
"Sample1.Sample2.muts.maf")
input_rds = os.path.join(DATA_SETS['Proj_08390_G']['FACETS_SUITE_DIR'],
"Sample1_hisens.rds")
input_json = {
"maf_file": {
"path": input_maf,
"class": "File"
},
"facets_rds": {
"path": input_rds,
"class": "File"
},
"output_filename": "Sample1_hisens.ccf.maf"
}
with TemporaryDirectory() as tmpdir:
input_json_file = os.path.join(tmpdir, "input.json")
with open(input_json_file, "w") as json_out:
json.dump(input_json, json_out)
output_dir = os.path.join(tmpdir, "output")
tmp_dir = os.path.join(tmpdir, "tmp")
cache_dir = os.path.join(tmpdir, "cache")
command = [
"cwl-runner", *CWL_ARGS, "--outdir", output_dir,
"--tmpdir-prefix", tmp_dir, "--cachedir", cache_dir, cwl_file,
input_json_file
]
returncode, proc_stdout, proc_stderr = run_command(command)
if returncode != 0:
print(proc_stderr)
self.assertEqual(returncode, 0)
output_json = json.loads(proc_stdout)
expected_output = {
'failed_txt': None,
'output_file': {
'location':
'file://' +
os.path.join(output_dir, 'Sample1_hisens.ccf.maf'),
'basename':
'Sample1_hisens.ccf.maf',
'class':
'File',
'checksum':
'sha1$7e478a8a44d27735f26e368989c672ed6ef5d52a',
'size':
19217199,
'path':
os.path.join(output_dir, 'Sample1_hisens.ccf.maf')
},
'stderr_txt': {
'basename':
'annotate_maf_stderr.txt',
'checksum':
'sha1$2e672f99c23a2d827c1d33e06377870cdd9c8090',
'class':
'File',
'location':
'file://' +
os.path.join(output_dir, 'annotate_maf_stderr.txt'),
'path':
os.path.join(output_dir, 'annotate_maf_stderr.txt'),
'size':
105
},
'stdout_txt': {
'basename':
'annotate_maf_stdout.txt',
'checksum':
'sha1$da39a3ee5e6b4b0d3255bfef95601890afd80709',
'class':
'File',
'location':
'file://' +
os.path.join(output_dir, 'annotate_maf_stdout.txt'),
'path':
os.path.join(output_dir, 'annotate_maf_stdout.txt'),
'size':
0
}
}
self.maxDiff = None
self.assertDictEqual(output_json, expected_output)
def test_run_copy_number_one_file(self):
"""
Test that Facets geneLevel copy number analysis step runs as expected with a single input file
"""
with TemporaryDirectory() as tmpdir:
output_dir = os.path.join(tmpdir, "output")
input_json = {
"output_cna_filename": "data_CNA.txt",
"targets_list" : {
"class": "File",
"path": DATA_SETS['Proj_08390_G']['targets_list'],
},
"hisens_cncfs": [
{
"class": "File",
"path": os.path.join(DATA_SETS['Proj_08390_G']['FACETS_DIR'], "Sample2.rg.md.abra.printreads__Sample1.rg.md.abra.printreads_hisens.cncf.txt")
}
],
}
input_json_file = os.path.join(tmpdir, "input.json")
with open(input_json_file, "w") as input_json_file_data:
json.dump(input_json, input_json_file_data)
output_dir = os.path.join(tmpdir, "output")
tmp_dir = os.path.join(tmpdir, "tmp")
cache_dir = os.path.join(tmpdir, "cache")
command = [
"cwl-runner",
*CWL_ARGS,
"--outdir", output_dir,
"--tmpdir-prefix", tmp_dir,
"--cachedir", cache_dir,
cwl_file, input_json_file
]
returncode, proc_stdout, proc_stderr = run_command(command)
if returncode != 0:
print(proc_stderr)
self.assertEqual(returncode, 0)
output_json = json.loads(proc_stdout)
expected_output = {
'output_cna_file': {
'location': 'file://' + os.path.join(output_dir, "data_CNA.txt"),
'basename': "data_CNA.txt",
'class': 'File',
'checksum': 'sha1$7cc89d24556de93b9a409812317581e67e5df494',
'size': 87905,
'path': os.path.join(output_dir, "data_CNA.txt")
},
'output_cna_ascna_file': {
'location': 'file://' + os.path.join(output_dir, "data_CNA.ascna.txt"),
'basename': "data_CNA.ascna.txt",
'class': 'File',
'checksum': 'sha1$452d5ddef12a44693d5a98a05f5d300801734cfe',
'size': 6164,
'path': os.path.join(output_dir, "data_CNA.ascna.txt")
},
'output_cna_scna_file': {
'location': 'file://' + os.path.join(output_dir, "data_CNA.scna.txt"),
'basename': "data_CNA.scna.txt",
'class': 'File',
'checksum': 'sha1$8bec923ab1d622b4cf38ae042ac2416725650aed',
'size': 5463,
'path': os.path.join(output_dir, "data_CNA.scna.txt")
}
}
self.maxDiff = None
self.assertDictEqual(output_json, expected_output)
# load the data_CNA.txt file
path = output_json['output_cna_file']['path']
with open(path) as f:
header = next(f)
header_parts = header.split()
expected_header_parts = ['Tumor_Sample_Barcode', 'Hugo_Symbol', 'tcn', 'lcn', 'cf', 'tcn.em', 'lcn.em', 'cf.em', 'chr', 'seg.start', 'seg.end', 'frac_elev_major_cn', 'Nprobes', 'WGD', 'purity', 'FACETS_CALL', 'ccs_filter', 'review', 'FACETS_CNA']
self.assertEqual(header_parts, expected_header_parts)
path = output_json['output_cna_ascna_file']['path']
with open(path) as f:
header = next(f)
header_parts = header.split()
expected_header_parts = ['Hugo_Symbol', 's_C_VJ7F47_P001_d']
self.assertEqual(header_parts, expected_header_parts)
path = output_json['output_cna_scna_file']['path']
with open(path) as f:
header = next(f)
header_parts = header.split()
expected_header_parts = ['Hugo_Symbol', 's_C_VJ7F47_P001_d']
self.assertEqual(header_parts, expected_header_parts)
def test_run_copy_number_two_files(self):
"""
Test that Facets geneLevel copy number analysis step runs as expected with two input files
"""
with TemporaryDirectory() as tmpdir:
output_dir = os.path.join(tmpdir, "output")
input_json = {
"portal_CNA_file": "data_CNA.txt",
"targets_list" : {
"class": "File",
"path": DATA_SETS['Proj_08390_G']['targets_list'],
},
"hisens_cncfs": [
{
"class": "File",
"path": os.path.join(DATA_SETS['Proj_08390_G']['FACETS_DIR'], "Sample2.rg.md.abra.printreads__Sample1.rg.md.abra.printreads_hisens.cncf.txt")
},
{
"class": "File",
"path": os.path.join(DATA_SETS['Proj_08390_G']['FACETS_DIR'], "Sample9.rg.md.abra.printreads__Sample10.rg.md.abra.printreads_hisens.cncf.txt")
}
],
}
input_json_file = os.path.join(tmpdir, "input.json")
with open(input_json_file, "w") as input_json_file_data:
json.dump(input_json, input_json_file_data)
output_dir = os.path.join(tmpdir, "output")
tmp_dir = os.path.join(tmpdir, "tmp")
cache_dir = os.path.join(tmpdir, "cache")
command = [
"cwl-runner",
*CWL_ARGS,
"--outdir", output_dir,
"--tmpdir-prefix", tmp_dir,
"--cachedir", cache_dir,
cwl_file, input_json_file
]
returncode, proc_stdout, proc_stderr = run_command(command)
if returncode != 0:
print(proc_stderr)
self.assertEqual(returncode, 0)
output_json = json.loads(proc_stdout)
expected_output = {
'output_cna_file': {
'location': 'file://' + os.path.join(output_dir, "data_CNA.txt"),
'basename': "data_CNA.txt",
'class': 'File',
'checksum': 'sha1$6dfa53b8a0fad1156060476bcf445d959f0e6eb2',
'size': 143118,
'path': os.path.join(output_dir, "data_CNA.txt")
},
'output_cna_ascna_file': {
'location': 'file://' + os.path.join(output_dir, "data_CNA.ascna.txt"),
'basename': "data_CNA.ascna.txt",
'class': 'File',
'checksum': 'sha1$3953e55b3db85b69209982211c53b9d8f049dc01',
'size': 8658,
'path': os.path.join(output_dir, "data_CNA.ascna.txt")
},
'output_cna_scna_file': {
'location': 'file://' + os.path.join(output_dir, "data_CNA.scna.txt"),
'basename': "data_CNA.scna.txt",
'class': 'File',
'checksum': 'sha1$9ddcee42cce0d49aec5745303be480b6c4ef0fe8',
'size': 6937,
'path': os.path.join(output_dir, "data_CNA.scna.txt")
}
}
self.maxDiff = None
self.assertDictEqual(output_json, expected_output)