def main():
args = parser.parse_args()
datas = []
for i in args.file:
data = fuse.ListWindows()
data.load(i, False, verbose = args.verbose)
datas.append(data)
data1 = datas[0]
data2 = datas[1]
compare(data1, data2, args)
def process_files(args):
outfile = open(args.output, 'w')
used_names = {}
current_file = 0
if len(args.metadata) != len(args.file):
# Not of the same length: ignore metadata
args.metadata = ['' for i in range(len(args.file))]
for vidjil in args.file:
try:
data = fuse.ListWindows()
data.load(vidjil, "")
except Exception:
print "** Warning ** file %s could not be loaded" % vidjil
else:
write_fuse_to_fasta(data, outfile, used_names, vidjil, args, args.metadata[current_file])
current_file += 1
outfile.close()
def main():
print('%%%%', ' '.join(sys.argv))
args = parser.parse_args()
for i in args.file:
data = fuse.ListWindows()
data.load(i, False, verbose=args.verbose)
if data.d['samples'].d['number'] < args.sample + 1:
print("! no sample %d in %s'" % (args.sample, i))
continue
sample = args.sample
m = regex_filename.match(i)
i_short = m.group(1) if m else i
if args.analysis:
# TODO: hardcoded for output of links.py
# should be more flexible
ii = 'data.vidjil/' + 'pat-' + i_short + '.analysis'
data_analysis = analysis.Analysis(data)
data_analysis.load(ii)
data_analysis.cluster_stats()
if str(data_analysis.d['samples']['run_timestamp']) == str(
data.d['samples'].d['run_timestamp']):
print("%% timestamps: OK")
else:
print("%% timestamps: XXX", i,
data.d['samples'].d['run_timestamp'], "instead of",
data_analysis.d['samples']['run_timestamp'])
else:
data_analysis = None
print('%s %% %s' % (i_short, i))
print('%% ', data.d["reads"])
segmented_reads = data.d['reads'].d['segmented'][sample]
out = []
for w in data:
if data_analysis:
tag = data_analysis.tag_of_clone(w)
if not tag:
continue
else:
tag = ''
reads = w.d['reads'][sample]
ratio = float(reads) / segmented_reads
if reads >= args.min and ratio >= args.min_ratio:
out += [(-reads, w, tag)]
for bla, w, tag in sorted(out[:args.top]):
segmented_reads_germline = data.d['reads'].d['germline'][
w.d['germline']][sample]
print(
w.latex(base_germline=segmented_reads_germline,
base=segmented_reads,
tag=tag))
if not out:
print(r'\\')
if data_analysis:
for c in data_analysis.missing_clones(data):
print('%% !! %s' % c)
print(r' \hline')