def main():
"""Invoke when run directly as a program."""
args = parse_arguments()
demux_data = _tsv_to_dict(args.annotation_file)
barcodes = list(demux_data.keys())
adapters_temp = list(set([demux_data[barcode]["3' adapter"] for barcode in barcodes]))
if len(adapters_temp) != 1:
print('{"proc.error":"Only one adapter type is allowed per demultiplexing job."}')
exit(1)
adapter = ''.join([adpr.split('_')[0] for adpr in adapters_temp[0].split(',')])
process = Popen(['iCount', 'demultiplex', args.reads_file, adapter] + barcodes,
stdout=PIPE,
stderr=DEVNULL)
out, err = process.communicate()
demux_files = [f for f in os.listdir('.') if f.startswith('demux')]
for demux_file in demux_files:
print(export(demux_file))
d = {
'process': 'upload-fastq-single',
'input': {
'src': [demux_file]
}
}
print('run {}'.format(json.dumps(d, separators=(',', ':'))))
def main():
"""Invoked when run directly as a program."""
args = parse_arguments()
terms = defaultdict(list)
with gzopen(args.gaf_file) as gaf:
for line in gaf:
if line.startswith('!'):
continue
go_data = line.strip().split('\t')
terms[go_data[4]].append(go_data[1])
for go_term in terms:
outfile = '{}.tab'.format(str(go_term).replace(':', ''))
with open(outfile, "wt") as f:
writer = csv.writer(f, delimiter=str('\t'), lineterminator='\n')
for gene in terms[go_term]:
writer.writerow([gene])
print(export(outfile))
d = {
'process': 'upload-geneset',
'input': {
'src': outfile,
'source': args.source
}
}
print('run {}'.format(json.dumps(d, separators=(',', ':'))))
print('{{"num_genesets":{}}}'.format(len(terms)))
def main():
"""Invoked when run directly as a program."""
args = parse_arguments()
terms = defaultdict(list)
with gzopen(args.gaf_file) as gaf:
for line in gaf:
if line.startswith('!'):
continue
go_data = line.strip().split('\t')
terms[go_data[4]].append(go_data[1])
for go_term in terms:
outfile = '{}.tab'.format(str(go_term).replace(':', ''))
with open(outfile, "wt") as f:
writer = csv.writer(f, delimiter=str('\t'), lineterminator='\n')
for gene in terms[go_term]:
writer.writerow([gene])
print(export(outfile))
d = {
'process': 'upload-geneset',
'input': {
'src': outfile,
'source': args.source
}
}
print('run {}'.format(json.dumps(d, separators=(',', ':'))))
print('{{"num_genesets":{}}}'.format(len(terms)))
nsamples = len(exprs)
progress_step = nsamples / 10.0
progress_milestone = progress_step
rartifact = re.compile("^X[0-9]")
gene_ids = [g[1:] if rartifact.match(g) else g for g in exprs[0]] # pylint: disable=unsubscriptable-object
for i in range(1, nsamples):
sample_id = header[i]
if var_samples is not None and sample_id not in var_samples:
continue
fname = "temp/{}.tab".format(sample_id)
with open(fname, "wb") as tabfile:
tabwriter = csv.writer(tabfile, delimiter="\t", quotechar='"', quoting=csv.QUOTE_MINIMAL)
tabwriter.writerow(["Gene", "Expression"])
tabwriter.writerows(zip(gene_ids, exprs[i])) # pylint: disable=unsubscriptable-object
d = {"process": "upload-expression", "input": {"exp": os.path.basename(fname), "exp_type": "Log2"}}
if var_samples is not None:
d["var_template"] = var_template
d["var"] = var_samples[sample_id]
print(export(fname))
print("run {}".format(json.dumps(d, separators=(",", ":"))))
if i >= progress_milestone:
print('{{"proc.progress": {}}}'.format(args.progress + (1.0 - args.progress) * i / nsamples))
progress_milestone += progress_step
for i in range(1, nsamples):
sample_id = header[i]
if var_samples is not None and sample_id not in var_samples:
continue
fname = 'temp/{}.tab'.format(sample_id)
with open(fname, 'wb') as tabfile:
tabwriter = csv.writer(tabfile, delimiter='\t', quotechar='"', quoting=csv.QUOTE_MINIMAL)
tabwriter.writerow(['Gene', 'Expression'])
tabwriter.writerows(zip(gene_ids, exprs[i])) # pylint: disable=unsubscriptable-object
d = {
'process': 'upload-expression',
'input': {
'exp': os.path.basename(fname),
'exp_type': 'Log2'
}
}
if var_samples is not None:
d['var_template'] = var_template
d['var'] = var_samples[sample_id]
print(export(fname))
print('run {}'.format(json.dumps(d, separators=(',', ':'))))
if i >= progress_milestone:
print('{{"proc.progress": {}}}'.format(args.progress + (1. - args.progress) * i / nsamples))
progress_milestone += progress_step
def test_missing_file(self, isfile_mock):
self.assertEqual(export('foo.txt'),
'{"proc.error": "Referenced file does not exist: \'foo.txt\'."}')
def test_filename(self, isfile_mock):
self.assertEqual(export('foo.txt'), 'export foo.txt')
for f in files:
files[f].close()
return filenames
filenames = read_multiplexed(reads1, reads2, args.barcodes, pool_maps,
args.progress_start)
for name in filenames:
if reads2:
if name.endswith('_mate2.fq.gz'):
continue
name2 = name.replace('_mate1', '_mate2')
print(export(name))
print(export(name2))
d = {
'process': 'upload-fastq-paired',
'input': {
'src1': [name],
'src2': [name2]
}
}
else:
print(export(name))
d = {'process': 'upload-fastq-single', 'input': {'src': [name]}}
print('run {}'.format(json.dumps(d, separators=(',', ':'))))
def test_missing_file(self, isfile_mock):
self.assertEqual(
export('foo.txt'),
'{"proc.error": "Referenced file does not exist: \'foo.txt\'."}')
def test_filename(self, isfile_mock):
self.assertEqual(export('foo.txt'), 'export foo.txt')
for f in files:
files[f].close()
return filenames
filenames = read_multiplexed(reads1, reads2, args.barcodes, pool_maps, args.progress_start)
for name in filenames:
if reads2:
if name.endswith('_mate2.fq.gz'):
continue
name2 = name.replace('_mate1', '_mate2')
print(export(name))
print(export(name2))
d = {
'process': 'upload-fastq-paired',
'input': {
'src1': [name],
'src2': [name2]
}
}
else:
print(export(name))
d = {
'process': 'upload-fastq-single',
'input': {
'src': [name]
}