def __call__(self, parser, namespace, values, option_string=None):
global snprun
if len(values) == 2:
snprun[values[0]] = int(values[1])
elif len(values) == 1:
rr = int(values)
else:
chrlist = funcs.read_chrstr(values)
def update_chrlist(fixed, linechrs, chrlist):
chrs = funcs.read_chrstr(linechrs) + chrlist
for key, value in Counter(chrs).items():
if value > 1:
if not fixed:
print(
"WARNING: chromosome %d has already been analysed in this run, so it was omitted. "
% key +
"If you want to analyse it anyway, please add '-fixed' attribute"
)
chrlist.remove(key)
if not chrlist:
raise exceptions.WrongValueError(
'chrlist', chrlist,
'There are no chromosomes to analyze!!!')
chrs = list(set(chrs))
chrs.sort()
return funcs.make_chrstr(chrs)
'%d\t%s\t%s\t%s\t%d\n' % (runs[setname], setname, ', '.join([
k for k in dataset.keys() if k != setname
]), funcs.make_chrstr(chrlist), shared_snps))
return shared_snps
dataset = OrderedDict()
chrlist = [i for i in range(1, 24)]
fixed = False
run = None
for q in range(len(sys.argv)):
if sys.argv[q] == '-dataset':
if sys.argv[q + 2][0] in ['.', '~', '/']:
dataset[sys.argv[q + 1]] = sys.argv[q + 2]
else:
raise exceptions.NoParameterError(
'directory',
'After name of data set should appear a directory to folder with it.'
)
if sys.argv[q] == '-chr':
chrlist = funcs.read_chrstr(sys.argv[q + 1])
if sys.argv[q] == '-run':
run = int(sys.argv[q + 1])
if sys.argv[q] == '-fixed':
fixed = True
found = find_shared(dataset, chrlist, fixed, run)
print('%d shared SNPs found!' % found)
def read_boruta_params(chrlist, continuation, dataset, fixed, outdir, pat,
run):
file = '%sboruta_runs.txt' % outdir
funcs.correct_boruta_runs_file(file)
run_file = open(file, 'r')
lines = run_file.readlines()
towrite = ''
occur = False
for line in lines:
if line.startswith(str(run) + '\t'):
line = line.strip().split('\t')
sets_order = line[1].strip().split('+')
if list(dataset.keys()) != sets_order:
if len(dataset.keys()) != len(sets_order):
raise exceptions.WrongValueError(
'dataset', dataset,
'Other data sets were used in the given boruta run')
else:
for s in sets_order:
try:
dataset.move_to_end(s)
except KeyError:
raise exceptions.WrongValueError(
'dataset', dataset,
'Data set named %s was not used in the given boruta run'
% s)
if line[3] == 'None':
patsubset = None
else:
patsubset = line[3].strip()
if line[4] == '-':
patruns = None
else:
patruns = list(map(int, line[4].split('+')))
patruns = OrderedDict([
(name, number)
for name, number in zip(sets_order, patruns)
])
if line[5] == 'None':
snpsubset = None
else:
snpsubset = line[5].strip()
if line[6] == '-':
snpruns = None
else:
snpruns = list(map(int, line[6].split('+')))
snpruns = OrderedDict([
(name, number)
for name, number in zip(sets_order, snpruns)
])
testsize = float(line[7])
perc = list(map(int, line[8].split(',')))
r = int(line[-2])
if continuation:
line = update_chrlist(fixed, line, chrlist)
strin = ''
for el in line:
strin += str(el) + '\t'
strin += '\n'
line = strin
else:
chrlist = funcs.read_chrstr(line[-1])
occur = True
if continuation:
towrite += line
run_file.close()
if not occur:
raise exceptions.WrongValueError(
'-run', str(run),
'Boruta run number %d has not been conducted yet.' % run)
patients = set()
if patsubset is not None:
done = 0
for name in dataset.keys():
with open(
'%s%s/%s_patients_%d.txt' %
(dataset[name], patsubset, patsubset, patruns[name])) as file:
selected = [int(line.strip()) for line in file.readlines()]
patients = patients.union([pp + done for pp in selected])
done += pat[name]
else:
patients = set([i for i in range(sum(pat.values()))])
if testsize != 0:
with open('%stestpat_%d.txt' % (outdir, run), 'r') as ts:
testpat = set([int(el.strip()) for el in ts.readlines()])
trainpat = set([p for p in patients if p not in testpat])
else:
testpat = set()
trainpat = patients
return chrlist, dataset, patruns, perc, r, snpsubset, snpruns, testpat, testsize, towrite, trainpat
def __call__(self, parser, namespace, values, option_string=None):
global chrlist
chrlist = funcs.read_chrstr(values)