def validate_tophat_settings(desc, settings):
try:
t = tophat.tophat_from_settings(settings)
except (TypeError, ValueError), e:
raise (SettingsError("'{}': {}".format(desc, e.message)))
def run(settings_file, reads, outdir, temp_loc=None, extend=False):
if os.path.exists(outdir):
if (check_output and not
query_yes_no("Output path \"{}\" already exists, overwrite?"
.format(outdir))):
print "Cannot continue as output already exists"
sys.exit(1)
shutil.rmtree(outdir)
os.mkdir(outdir)
tempdir = tempfile.mkdtemp(prefix='waistcoat', dir=temp_loc)
#Read and validate settings for waistcoat
if verbose:
print "Reading settings from \'{}\'".format(settings_file)
my_settings = settings.loadf(settings_file)
statistics.setUp(my_settings.barcodes.keys())
#run the preprocessing pipeline
if verbose:
print "\n========== Preprocessing =========="
remove_input = False
if reads.endswith('.gz'):
if verbose:
print "Inflating..."
gzfile = gzip.GzipFile(reads, 'r')
(out, reads) = tempfile.mkstemp(dir=tempdir, prefix='input.',
suffix='.inflated')
out = os.fdopen(out, 'w')
out.writelines(gzfile)
gzfile.close()
out.close()
remove_input = True
files = preprocess.run(reads, my_settings, tempdir, remove_input)
#discard those which map to discard
if verbose:
print "\n========== Discard =========="
for i,(index, dcs) in enumerate(my_settings.discard):
new_files = {}
count = {}
if verbose:
print "Removing reads which map to \'{}\' ({}/{})...".format(index,
i+1, len(my_settings.discard))
for sample,f in files.iteritems():
if verbose:
print "\tScanning \'{}\'".format(sample)
(new_files[sample], count[sample]) = (
tophat.discard_mapped(f, index, tophat_settings = dcs))
files = new_files
statistics.addValues('discard_' + os.path.basename(index), count)
#map to genome
(target, target_settings) = my_settings.target
if verbose:
print "\n========== Map to {} ==========".format(os.path.basename(target))
th = tophat.tophat_from_settings(target_settings)
for i,(sample,f) in enumerate(files.iteritems()):
th.output_dir = os.path.join(outdir, sample)
os.mkdir(th.output_dir)
if verbose: print "Mapping {} ({}/{})...".format(sample, i+1, len(files))
th.run(f, index_base = target)
os.remove(f)
if verbose: print "\n========== Postprocess =========="
count = {}
for i,(sample,f) in enumerate(files.iteritems()):
if verbose: print "{} ({}/{})...".format(sample, i+1, len(files))
out = os.path.join(outdir, '{}.bam'.format(sample))
count[sample] = postprocess.run(outdir, sample, "{}.fa".format(target),
extend=extend)
statistics.collectFinalStats(sample, out)
statistics.addValues('final_seqs', count)
statistics.write(os.path.join(outdir, 'statistics'))
shutil.rmtree(tempdir)
if verbose:
print "\n__________ Pipeline Statistics __________"
print statistics.prettyString()
