def test_parse(self):
logfile = os.path.join(self.testfiles_dir, "tmalign.log")
TM = tm_parser.TMalignLogParser()
TM.parse(logfile)
self.assertEqual(143, TM.nr_residues_common)
self.assertEqual(0.70502, TM.tm)
self.assertEqual(2.68, TM.rmsd)
self.assertEqual(0.182, TM.seq_id)
def comparison(self, models, structures):
"""
Compare a list of model structures to a second list of reference structures
Parameters
----------
models : list
List containing the paths to the model structure files
structures : list
List containing the paths to the reference structure files
Returns
-------
entries : list
List of TMscore data entries on a per-model basis
"""
if len(models) < 1 or len(structures) < 1:
msg = 'No model structures provided' if len(
models) < 1 else 'No reference structures provided'
logger.critical(msg)
raise RuntimeError(msg)
elif len(structures) == 1:
logger.info(
'Using single structure provided for all model comparisons')
structures = [structures[0] for _ in xrange(len(models))]
elif len(models) != len(structures):
msg = "Unequal number of models and structures!"
logger.critical(msg)
raise RuntimeError(msg)
if self.method == "tmalign":
pt = tm_parser.TMalignLogParser()
elif self.method == "tmscore":
pt = tm_parser.TMscoreLogParser()
else:
msg = "Invalid method selected: %s", self.method
logger.critical(msg)
raise RuntimeError(msg)
logger.info('Using algorithm: {0}'.format(self.method))
logger.info('------- Evaluating decoys -------')
data_entries, job_scripts, log_files = [], [], []
for model_pdb, structure_pdb in zip(models, structures):
model_name = os.path.splitext(os.path.basename(model_pdb))[0]
structure_name = os.path.splitext(
os.path.basename(structure_pdb))[0]
stem = "_".join([model_name, structure_name, self.method])
if os.path.isfile(model_pdb) and os.path.isfile(structure_pdb):
data_entries.append(
[model_name, structure_name, model_pdb, structure_pdb])
script = make_script(
[self.executable, model_pdb, structure_pdb],
prefix="tmscore_",
stem=stem,
directory=self.tmp_dir)
job_scripts.append(script)
log_files.append(os.path.splitext(script)[0] + ".log")
else:
if not os.path.isfile(model_pdb):
logger.warning("Cannot find: %s", model_pdb)
if not os.path.isfile(structure_pdb):
logger.warning("Cannot find: %s", structure_pdb)
continue
logger.info('Executing TManalysis scripts')
j = Job(self._qtype)
j.submit(job_scripts,
nproc=self._nproc,
max_array_jobs=self._max_array_jobs,
queue=self._queue,
name="tmscore")
j.wait(interval=1)
self.entries = []
for entry, log, script in zip(data_entries, log_files, job_scripts):
try:
pt.reset()
pt.parse(log)
except Exception:
logger.critical("Error processing the %s log file: %s",
self.method, log)
log = "None"
model_name, structure_name, model_pdb, structure_pdb = entry
_entry = self._store(model_name, structure_name, model_pdb,
structure_pdb, log, pt)
self.entries.append(_entry)
os.unlink(script)
return self.entries
def comparison(self, models, structures):
"""
Compare a list of model structures to a second list of reference structures
Parameters
----------
models : list
List containing the paths to the model structure files
structures : list
List containing the paths to the reference structure files
Returns
-------
entries : list
List of TMscore data entries on a per-model basis
"""
if len(models) < 1 or len(structures) < 1:
msg = 'No model structures provided' if len(models) < 1 else \
'No reference structures provided'
logger.critical(msg)
raise RuntimeError(msg)
elif len(structures) == 1:
logger.info(
'Using single structure provided for all model comparisons')
structures = [structures[0] for _ in xrange(len(models))]
elif len(models) != len(structures):
msg = "Unequal number of models and structures"
logger.critical(msg)
raise RuntimeError(msg)
# Create a logfile parser
if self.method == "tmalign":
pt = tm_parser.TMalignLogParser()
elif self.method == "tmscore":
pt = tm_parser.TMscoreLogParser()
else:
msg = "Invalid method selected: ", self.method
logger.critical(msg)
raise RuntimeError(msg)
# =======================================================================
# Iterate through the structure files and execute the TMscore comparisons
# =======================================================================
logger.info('Using algorithm: {0}'.format(self.method))
logger.info('------- Evaluating decoys -------')
# Construct the job scripts
data_entries = [] # Store some data
job_scripts = [] # Hold job scripts
log_files = [] # Hold paths to log files
for model_pdb, structure_pdb in zip(models, structures):
# Some file names
model_name = os.path.splitext(os.path.basename(model_pdb))[0]
structure_name = os.path.splitext(
os.path.basename(structure_pdb))[0]
prefix = '{0}_{1}_{2}'.format(model_name, structure_name,
self.method)
if not os.path.isfile(model_pdb):
logger.warning("Cannot find: {0}".format(model_pdb))
continue
elif not os.path.isfile(structure_pdb):
logger.warning("Cannot find: {0}".format(structure_pdb))
continue
# Create the run scripts
script = tempfile.NamedTemporaryFile(prefix=prefix,
suffix=ample_util.SCRIPT_EXT,
delete=False)
script.write(ample_util.SCRIPT_HEADER + os.linesep * 2)
script.write('{exe} {model} {reference} {sep}{sep}'.format(
exe=self.executable,
model=model_pdb,
reference=structure_pdb,
sep=os.linesep,
))
script.close()
os.chmod(script.name, 0o777)
job_scripts.append(script.name)
# Save some more information
data_entries.append(
[model_name, structure_name, model_pdb, structure_pdb])
log_files.append(os.path.splitext(script.name)[0] + ".log")
# Execute the scripts
logger.info('Executing TManalysis scripts')
logger.disabled = True
success = workers_util.run_scripts(
job_scripts=job_scripts,
monitor=None,
check_success=None,
early_terminate=None,
nproc=self._nproc,
job_time=
7200, # Might be too long/short, taken from Rosetta modelling
job_name='tm_analysis',
submit_cluster=self._submit_cluster,
submit_qtype=self._submit_qtype,
submit_queue=self._submit_queue,
submit_array=self._submit_array,
submit_max_array=self._submit_max_array)
logger.disabled = False
if not success:
msg = "Error running TManalysis"
raise RuntimeError(msg)
# Extract the data
entries = []
for entry, log, script in zip(data_entries, log_files, job_scripts):
try:
# Reset the TM log parser to default values
pt.reset()
# Parse the TM method logfile to extract the data
pt.parse(log)
except Exception:
msg = "Error processing the {0} log file: {1}".format(
self.method, log)
logger.critical(msg)
log = "None"
model_name, structure_name, model_pdb, structure_pdb = entry
_entry = self._store(model_name, structure_name, model_pdb,
structure_pdb, log, pt)
entries.append(_entry)
os.unlink(script)
self.entries = entries
return entries