def get_runObj(run):
""" Tries to read runParameters.xml to parse the type of sequencer
and then return the respective Run object (MiSeq, HiSeq..)
:param run: run name identifier
:type run: string
:rtype: Object
:returns: returns the sequencer type object,
None if the sequencer type is unknown of there was an error
"""
if os.path.exists(os.path.join(run, 'runParameters.xml')):
run_parameters_file = "runParameters.xml"
elif os.path.exists(os.path.join(run, 'RunParameters.xml')):
run_parameters_file = "RunParameters.xml"
else:
logger.error("Cannot find RunParameters.xml or runParameters.xml in the run folder for run {}".format(run))
return
rppath = os.path.join(run, run_parameters_file)
try:
rp = RunParametersParser(os.path.join(run, run_parameters_file))
except OSError:
logger.warn("Problems parsing the runParameters.xml file at {}. "
"This is quite unexpected. please archive the run {} manually".format(rppath, run))
else:
#do a case by case test becasue there are so many version of RunParameters that there is no real other way
runtype = rp.data['RunParameters'].get("Application", "")
if "Setup" in rp.data['RunParameters']:
#this is the HiSeq2500, MiSeq, and HiSeqX case
try:
# Works for recent control software
runtype = rp.data['RunParameters']["Setup"]["Flowcell"]
except KeyError:
# Use this as second resource but print a warning in the logs
logger.warn("Parsing runParameters to fecth instrument type, "
"not found Flowcell information in it. Using ApplicationName")
# here makes sense to use get with default value "" ->
# so that it doesn't raise an exception in the next lines
# (in case ApplicationName is not found, get returns None)
runtype = rp.data['RunParameters']["Setup"].get("ApplicationName", "")
if "HiSeq X" in runtype in runtype:
return HiSeqX_Run(run, CONFIG["analysis"]["HiSeqX"])
elif "HiSeq" in runtype or "TruSeq" in runtype:
return HiSeq_Run(run, CONFIG["analysis"]["HiSeq"])
elif "MiSeq" in runtype:
return MiSeq_Run(run, CONFIG["analysis"]["MiSeq"])
elif "NextSeq" in runtype:
return NextSeq_Run(run, CONFIG["analysis"]["NextSeq"])
elif "NovaSeq" in runtype:
return NovaSeq_Run(run, CONFIG["analysis"]["NovaSeq"])
else:
logger.warn("Unrecognized run type {}, cannot archive the run {}. "
"Someone as likely bought a new sequencer without telling "
"it to the bioinfo team".format(runtype, run))
# Not necessary as the function will return None at this point but
# just for being explicit
return None
def setUpClass(self):
""" Creates the following directory tree for testing purposes:
tmp/
|__ 141124_ST-COMPLETED_01_AFCIDXX
| |__ RunInfo.xml
| |__ Demultiplexing
| | |__ Stats
| | |__ DemultiplexingStats.xml
| |__ RTAComplete.txt
|__ 141124_ST-INPROGRESS_02_AFCIDXX
| |__ RunInfo.xml
| |__ Demultiplexing
| |__ RTAComplete.txt
|__ 141124_ST-RUNNING_03_AFCIDXX
| |__ RunInfo.xml
|__ 141124_ST-TOSTART_04_FCIDXXX
|__ RunInfo.xml
|__ RTAComplete.txt
"""
self.tmp_dir = os.path.join(tempfile.mkdtemp(), 'tmp')
self.transfer_file = os.path.join(self.tmp_dir, 'transfer.tsv')
running = os.path.join(self.tmp_dir, '141124_ST-RUNNING1_03_AFCIDXX')
to_start = os.path.join(self.tmp_dir, '141124_ST-TOSTART1_04_FCIDXXX')
in_progress = os.path.join(self.tmp_dir, '141124_ST-INPROGRESS1_02_AFCIDXX')
completed = os.path.join(self.tmp_dir, '141124_ST-COMPLETED1_01_AFCIDXX')
finished_runs = [to_start, in_progress, completed]
# Create runs directory structure
os.makedirs(self.tmp_dir)
os.makedirs(running)
os.makedirs(to_start)
os.makedirs(os.path.join(in_progress, 'Demultiplexing'))
os.makedirs(os.path.join(completed, 'Demultiplexing', 'Stats'))
# Create files indicating that the run is finished
for run in finished_runs:
open(os.path.join(run, 'RTAComplete.txt'), 'w').close()
# Create files indicating that the preprocessing is done
open(os.path.join(completed, 'Demultiplexing', 'Stats', 'DemultiplexingStats.xml'), 'w').close()
# Create transfer file and add the completed run
with open(self.transfer_file, 'w') as f:
tsv_writer = csv.writer(f, delimiter='\t')
tsv_writer.writerow([os.path.basename(completed), str(datetime.now())])
# Move sample RunInfo.xml file to every run directory
for run in [running, to_start, in_progress, completed]:
shutil.copy('data/RunInfo.xml', run)
shutil.copy('data/runParameters.xml', run)
# Create run objects
# Jose : add tests for other sequencers
self.running = HiSeqX_Run(os.path.join(self.tmp_dir,
'141124_ST-RUNNING1_03_AFCIDXX'),
CONFIG["analysis"]["HiSeqX"])
self.to_start = Run(os.path.join(self.tmp_dir,
'141124_ST-TOSTART1_04_FCIDXXX'),
CONFIG["analysis"]["HiSeqX"])
self.in_progress = Run(os.path.join(self.tmp_dir,
'141124_ST-INPROGRESS1_02_AFCIDXX'),
CONFIG["analysis"]["HiSeqX"])
self.completed = Run(os.path.join(self.tmp_dir,
'141124_ST-COMPLETED1_01_AFCIDXX'),
CONFIG["analysis"]["HiSeqX"])
self.finished_runs = [self.to_start, self.in_progress, self.completed]
self.transfer_file = os.path.join(self.tmp_dir, 'transfer.tsv')
class TestTracker(unittest.TestCase):
""" analysis.py script tests
"""
@classmethod
def setUpClass(self):
""" Creates the following directory tree for testing purposes:
tmp/
|__ 141124_ST-COMPLETED_01_AFCIDXX
| |__ RunInfo.xml
| |__ Demultiplexing
| | |__ Stats
| | |__ DemultiplexingStats.xml
| |__ RTAComplete.txt
|__ 141124_ST-INPROGRESS_02_AFCIDXX
| |__ RunInfo.xml
| |__ Demultiplexing
| |__ RTAComplete.txt
|__ 141124_ST-RUNNING_03_AFCIDXX
| |__ RunInfo.xml
|__ 141124_ST-TOSTART_04_FCIDXXX
|__ RunInfo.xml
|__ RTAComplete.txt
"""
self.tmp_dir = os.path.join(tempfile.mkdtemp(), 'tmp')
self.transfer_file = os.path.join(self.tmp_dir, 'transfer.tsv')
running = os.path.join(self.tmp_dir, '141124_ST-RUNNING1_03_AFCIDXX')
to_start = os.path.join(self.tmp_dir, '141124_ST-TOSTART1_04_FCIDXXX')
in_progress = os.path.join(self.tmp_dir, '141124_ST-INPROGRESS1_02_AFCIDXX')
completed = os.path.join(self.tmp_dir, '141124_ST-COMPLETED1_01_AFCIDXX')
finished_runs = [to_start, in_progress, completed]
# Create runs directory structure
os.makedirs(self.tmp_dir)
os.makedirs(running)
os.makedirs(to_start)
os.makedirs(os.path.join(in_progress, 'Demultiplexing'))
os.makedirs(os.path.join(completed, 'Demultiplexing', 'Stats'))
# Create files indicating that the run is finished
for run in finished_runs:
open(os.path.join(run, 'RTAComplete.txt'), 'w').close()
# Create files indicating that the preprocessing is done
open(os.path.join(completed, 'Demultiplexing', 'Stats', 'DemultiplexingStats.xml'), 'w').close()
# Create transfer file and add the completed run
with open(self.transfer_file, 'w') as f:
tsv_writer = csv.writer(f, delimiter='\t')
tsv_writer.writerow([os.path.basename(completed), str(datetime.now())])
# Move sample RunInfo.xml file to every run directory
for run in [running, to_start, in_progress, completed]:
shutil.copy('data/RunInfo.xml', run)
shutil.copy('data/runParameters.xml', run)
# Create run objects
# Jose : add tests for other sequencers
self.running = HiSeqX_Run(os.path.join(self.tmp_dir,
'141124_ST-RUNNING1_03_AFCIDXX'),
CONFIG["analysis"]["HiSeqX"])
self.to_start = Run(os.path.join(self.tmp_dir,
'141124_ST-TOSTART1_04_FCIDXXX'),
CONFIG["analysis"]["HiSeqX"])
self.in_progress = Run(os.path.join(self.tmp_dir,
'141124_ST-INPROGRESS1_02_AFCIDXX'),
CONFIG["analysis"]["HiSeqX"])
self.completed = Run(os.path.join(self.tmp_dir,
'141124_ST-COMPLETED1_01_AFCIDXX'),
CONFIG["analysis"]["HiSeqX"])
self.finished_runs = [self.to_start, self.in_progress, self.completed]
self.transfer_file = os.path.join(self.tmp_dir, 'transfer.tsv')
@classmethod
def tearDownClass(self):
shutil.rmtree(self.tmp_dir)
def test_1_is_finished(self):
""" Is finished should be True only if "RTAComplete.txt" file is present...
"""
self.assertFalse(self.running._is_sequencing_done())
self.assertTrue(all(map(lambda run: run._is_sequencing_done, self.finished_runs)))
def test_2_processing_status(self):
""" Status of the processing depends on the generated files
"""
self.assertEqual('SEQUENCING', self.running.get_run_status())
self.assertEqual('TO_START', self.to_start.get_run_status())
self.assertEqual('IN_PROGRESS', self.in_progress.get_run_status())
self.assertEqual('COMPLETED', self.completed.get_run_status())
def test_3_is_transferred(self):
""" is_transferred should rely on the info in transfer.tsv
"""
self.assertTrue(self.completed.is_transferred(self.transfer_file))
self.assertFalse(self.running.is_transferred(self.transfer_file))
self.assertFalse(self.to_start.is_transferred(self.transfer_file))
self.assertFalse(self.in_progress.is_transferred( self.transfer_file))
def get_runObj(run):
"""Tries to read runParameters.xml to parse the type of sequencer
and then return the respective Run object (MiSeq, HiSeq..)
:param run: run name identifier
:type run: string
:rtype: Object
:returns: returns the sequencer type object,
None if the sequencer type is unknown of there was an error
"""
if os.path.exists(os.path.join(run, 'runParameters.xml')):
run_parameters_file = 'runParameters.xml'
elif os.path.exists(os.path.join(run, 'RunParameters.xml')):
run_parameters_file = 'RunParameters.xml'
else:
logger.error(
'Cannot find RunParameters.xml or runParameters.xml in the run folder for run {}'
.format(run))
return
rppath = os.path.join(run, run_parameters_file)
try:
rp = RunParametersParser(os.path.join(run, run_parameters_file))
except OSError:
logger.warn(
'Problems parsing the runParameters.xml file at {}. '
'This is quite unexpected. please archive the run {} manually'.
format(rppath, run))
else:
# Do a case by case test becasue there are so many version of RunParameters that there is no real other way
runtype = rp.data['RunParameters'].get(
'Application', rp.data['RunParameters'].get('ApplicationName', ''))
if 'Setup' in rp.data['RunParameters']:
# This is the HiSeq2500, MiSeq, and HiSeqX case
try:
# Works for recent control software
runtype = rp.data['RunParameters']['Setup']['Flowcell']
except KeyError:
# Use this as second resource but print a warning in the logs
logger.warn(
'Parsing runParameters to fecth instrument type, '
'not found Flowcell information in it. Using ApplicationName'
)
# Here makes sense to use get with default value '' ->
# so that it doesn't raise an exception in the next lines
# (in case ApplicationName is not found, get returns None)
runtype = rp.data['RunParameters']['Setup'].get(
'ApplicationName', '')
if 'HiSeq X' in runtype:
return HiSeqX_Run(run, CONFIG['analysis']['HiSeqX'])
elif 'HiSeq' in runtype or 'TruSeq' in runtype:
return HiSeq_Run(run, CONFIG['analysis']['HiSeq'])
elif 'MiSeq' in runtype:
return MiSeq_Run(run, CONFIG['analysis']['MiSeq'])
elif 'NextSeq' in runtype:
return NextSeq_Run(run, CONFIG['analysis']['NextSeq'])
elif 'NovaSeq' in runtype:
return NovaSeq_Run(run, CONFIG['analysis']['NovaSeq'])
else:
logger.warn(
'Unrecognized run type {}, cannot archive the run {}. '
'Someone as likely bought a new sequencer without telling '
'it to the bioinfo team'.format(runtype, run))
return None
