def replicate_fasta():
if not paths.exists(scr_fasta):
utilities.debug("Replicating fasta file")
utilities.copy(fasta_file, scr_fasta)
paths.existsOrFail(scr_fasta)
def gather():
util.debug("Gathering result")
job_results = results
paths.ensure(job_results)
#aazj00103_05.075_v1_3.bz2 zj001.fasta zj001.psipred_ss2
#aazj00109_05.075_v1_3.bz2 zj001.psipred
aa_pattern = "aa" + name + "(03|09)\_05\.075\_v1\_3$"
patterns = [aa_pattern]
for suf in [".fasta", ".psipred", ".psipred_ss2"]:
patterns.append(name + suf)
try:
for pattern in patterns:
print "Pattern ", pattern
match = paths.find(pattern, scr_job)
if not match:
raise "Missing file"
for path in match:
if pattern == aa_pattern:
print "Filtering Columns %s" % path
for line in fileinput.input(path, inplace=1):
print " " + line[:47].strip()
fileinput.close()
print "Path ", path
file = paths.getFile(path)
dest = paths.join(job_results, file)
util.copy(path, job_results)
if pattern == aa_pattern:
util.system("bzip2 %s" % dest)
except:
paths.removerf(job_results)
raise
def gather():
util.debug("Gathering result")
job_results = results
paths.ensure(job_results)
#aazj00103_05.075_v1_3.bz2 zj001.fasta zj001.psipred_ss2
#aazj00109_05.075_v1_3.bz2 zj001.psipred
aa_pattern = "aa"+name+"(03|09)\_05\.075\_v1\_3$"
patterns = [aa_pattern]
for suf in [".fasta", ".psipred", ".psipred_ss2"]:
patterns.append(name+suf)
try:
for pattern in patterns:
print "Pattern ",pattern
match = paths.find(pattern, scr_job)
if not match:
raise "Missing file"
for path in match:
if pattern == aa_pattern:
print "Filtering Columns %s" % path
for line in fileinput.input(path, inplace=1):
print " "+line[:47].strip()
fileinput.close()
print "Path ", path
file = paths.getFile(path)
dest = paths.join(job_results, file)
util.copy(path, job_results)
if pattern == aa_pattern:
util.system("bzip2 %s" % dest)
except:
paths.removerf(job_results)
raise
def replicate_fasta():
if not paths.exists(scr_fasta):
utilities.debug("Replicating fasta file")
utilities.copy(fasta_file, scr_fasta)
paths.existsOrFail(scr_fasta)
def replicate_fasta():
global scr_fasta
file = paths.getFile(fasta_file)
scr_fasta = paths.join(scr_job, file)
if not paths.exists(scr_fasta):
util.debug("Replicating fasta file")
util.copy(fasta_file, scr_fasta)
paths.existsOrFail(scr_fasta)
def replicate_fasta():
global scr_fasta
file = paths.getFile(fasta_file)
scr_fasta = paths.join(scr_job, file)
if not paths.exists(scr_fasta):
util.debug("Replicating fasta file")
util.copy(fasta_file, scr_fasta)
paths.existsOrFail(scr_fasta)
def gather():
global code, task_id
utilities.debug("Gathering result")
paths.ensure(results_dir)
# Contents of results directory (3' library, 9' library, fasta, psipred, and psipred_ss2 files). EG:
#aazj00103_05.075_v1_3.bz2 zj001.fasta zj001.psipred_ss2
#aazj00109_05.075_v1_3.bz2 zj001.psipred
# Set "patterns" for results files.
aa_pattern = "aa"+code+task_id+"(03|09)\_05\.075\_v1\_3$"
patterns = [aa_pattern]
for suf in [".fasta", ".psipred", ".psipred_ss2"]:
patterns.append(code+task_id+suf)
try:
for pattern in patterns:
print "Pattern ",pattern
# Find the results file in scr_job_dir
match = paths.find(pattern, scr_job_dir)
# If a results file matching pattern is not found in the scr_jobs_dir, raise exception.
if not match:
raise "Missing file"
# Copy all results files in scr_job_dir to results_dir.
for path in match:
# If the results file is a frag library, format the frag library file.
if pattern == aa_pattern:
print "Filtering Columns of file %s" % path
# fileinput.input opens a file for iteration. Defining inplace=1 allows to given file to be
# altered "in place": file is backed up, and stdout is then directed to the file.
# Filters the file: writes " " + first 47 chars of the line. (Specific formatting).
for line in fileinput.input(path, inplace=1):
print " "+line[:47].strip()
fileinput.close()
print "Path ", path
# Copy the result file to results_dir.
utilities.copy(path, results_dir)
# If the results file is a frag library, bzip it in the results_dir.
if pattern == aa_pattern:
dest = paths.join(results_dir, paths.getFile(path))
utilities.system("bzip2 %s" % dest)
# If gathering the results files fails, delete the results_dir and exit.
except:
paths.removerf(results_dir)
raise
def gather():
global code, task_id
utilities.debug("Gathering result")
paths.ensure(results_dir)
# Contents of results directory (3' library, 9' library, fasta, psipred, and psipred_ss2 files). EG:
#aazj00103_05.075_v1_3.bz2 zj001.fasta zj001.psipred_ss2
#aazj00109_05.075_v1_3.bz2 zj001.psipred
# Set "patterns" for results files.
aa_pattern = "aa" + code + task_id + "(03|09)\_05\.075\_v1\_3$"
patterns = [aa_pattern]
for suf in [".fasta", ".psipred", ".psipred_ss2"]:
patterns.append(code + task_id + suf)
try:
for pattern in patterns:
print "Pattern ", pattern
# Find the results file in scr_job_dir
match = paths.find(pattern, scr_job_dir)
# If a results file matching pattern is not found in the scr_jobs_dir, raise exception.
if not match:
raise "Missing file"
# Copy all results files in scr_job_dir to results_dir.
for path in match:
# If the results file is a frag library, format the frag library file.
if pattern == aa_pattern:
print "Filtering Columns of file %s" % path
# fileinput.input opens a file for iteration. Defining inplace=1 allows to given file to be
# altered "in place": file is backed up, and stdout is then directed to the file.
# Filters the file: writes " " + first 47 chars of the line. (Specific formatting).
for line in fileinput.input(path, inplace=1):
print " " + line[:47].strip()
fileinput.close()
print "Path ", path
# Copy the result file to results_dir.
utilities.copy(path, results_dir)
# If the results file is a frag library, bzip it in the results_dir.
if pattern == aa_pattern:
dest = paths.join(results_dir, paths.getFile(path))
utilities.system("bzip2 %s" % dest)
# If gathering the results files fails, delete the results_dir and exit.
except:
paths.removerf(results_dir)
raise
def _gather_results(self):
# Move all results files to results directory and update instance variable values to reflect
# new location.
for res in self.results_files:
copy(res, self.results_dir)
self.frag3_lib = os.path.join(self.results_dir, os.path.basename(self.frag3_lib))
self.frag9_lib = os.path.join(self.results_dir, os.path.basename(self.frag9_lib))
self.frag_psipred = os.path.join(self.results_dir, os.path.basename(self.frag_psipred))
self.frag_psipred2 = os.path.join(self.results_dir, os.path.basename(self.frag_psipred2))
self.frag_fasta = os.path.join(self.results_dir, os.path.basename(self.frag_fasta))
self.results_files = [self.frag3_lib, self.frag9_lib, self.frag_psipred, self.frag_psipred2, self.frag_fasta]
def run(self, nohoms=False, cleanup=True):
try:
# Populate environment with tool & DB locations (req'ed by make_fragments.local.pl).
print "Fragmentor - run: set environment"
self._set_env()
# Create working and results directory structures, and move into working directory.
print "Fragmentor - run:set directories"
self._dir_setup()
# Copy fasta file to working directory, set as working_fasta_file.
print "Fragmentor - run: copy fasta files to working dir"
copy(self.fasta_file, self.working_dir)
working_fasta_file = os.path.join(self.working_dir, os.path.basename(self.fasta_file))
# Run make_fragments script (treat as a black box).
print "Fragmentor - run: run frag script"
self._run_frag(nohoms, working_fasta_file)
# Check for results files and set results instance variables.
print "Fragmentor - run: set results variables and structure"
self._set_results()
# Filter 3' and 9' fragment library results (cut column size, bzip files).
print "Fragmentor - run: filter fragment libs"
self._filter_fraglibs()
# Gather results (move all files to results directory).
print "Fragmentor - run: gather results"
self._gather_results()
except:
print "\nFragment picking failed. Exiting.\n"
raise
finally:
if cleanup:
# Clean up work files and finish.
self.cleanup()
print "\nFragment picking completed successfully\n"
