def main():
parser = argparse.ArgumentParser(
description='LOL HI THERE',
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument('--discard-garbage',
dest='discard_garbage',
action='store_true')
parser.add_argument('--handbuilt', dest='handbuilt_fn', required=True)
parser.add_argument('pwgs_ssm_fn')
parser.add_argument('pwgs_params_fn')
parser.add_argument('pairtree_ssm_fn')
parser.add_argument('pairtree_params_fn')
args = parser.parse_args()
tree_type = 'handbuilt.xeno'
hb = load_handbuilt(args.handbuilt_fn, tree_type)
clusters = convert_clusters(hb['clusters'])
garbage = hb['garbage']
# Since we remove the empty first cluster, the indexing on `structure` is now
# a little weird -- cluster `i` is now represented by `i + 1` in `structure`.
# That's okay.
adjl = hb['structure']
parents = convert_adjl_to_parents(adjl)
pwgs_params = inputparser.load_params(args.pwgs_params_fn)
variants = load_phylowgs(args.pwgs_ssm_fn)
if args.discard_garbage:
remove_garbage(variants, garbage)
variants, clusters = make_varids_contiguous(variants, garbage,
clusters)
garbage = []
inputparser.write_ssms(variants, args.pairtree_ssm_fn)
write_pairtree_params(pwgs_params['samples'], garbage, clusters, parents,
args.pairtree_params_fn)
def main():
parser = argparse.ArgumentParser(
description='LOL HI THERE',
formatter_class=argparse.ArgumentDefaultsHelpFormatter
)
parser.add_argument('--counts', required=True)
parser.add_argument('in_ssm_fn')
parser.add_argument('in_params_fn')
parser.add_argument('out_base')
args = parser.parse_args()
random.seed(1337)
counts = [int(C) for C in args.counts.split(',')]
assert len(counts) == len(set(counts))
ssms = inputparser.load_ssms(args.in_ssm_fn)
params = inputparser.load_params(args.in_params_fn)
sampnames = params['samples']
# Always include diagnosis sample, on assumption we're working with
# SJbALL022609 from Steph for the paper congraph figure.
subsets = _select_samp_subsets(sampnames, counts, all_must_include=['D'])
for subset in subsets:
idxs = _find_idxs(sampnames, subset)
new_ssms = _filter_ssms(ssms, idxs)
new_params = dict(params)
new_params['samples'] = subset
out_base = '%s_S%s' % (args.out_base, len(subset))
inputparser.write_ssms(new_ssms, out_base + '.ssm')
with open(out_base + '.params.json', 'w') as F:
json.dump(new_params, F)
def main():
parser = argparse.ArgumentParser(
description='LOL HI THERE',
formatter_class=argparse.ArgumentDefaultsHelpFormatter
)
parser.add_argument('in_ssm_fn')
parser.add_argument('out_ssm_fn')
args = parser.parse_args()
np.set_printoptions(linewidth=400, precision=3, threshold=sys.maxsize, suppress=True)
np.seterr(divide='raise', invalid='raise', over='raise')
ssms = inputparser.load_ssms(args.in_ssm_fn)
fixed_prop = _fix_omegas(ssms, print_bad=False)
print('fixed_omegas=%s' % fixed_prop)
inputparser.write_ssms(ssms, args.out_ssm_fn)
def _process(ssmfn, jsonfn, order):
params = inputparser.load_params(jsonfn)
ssms = inputparser.load_ssms(ssmfn)
order = [int(idx) for idx in order.split(',')]
N = len(params['samples'])
assert set(range(N)) == set(order)
assert len(list(ssms.values())[0]['var_reads']) == N
params['samples'] = [params['samples'][idx] for idx in order]
for vid in ssms.keys():
for K in ('var_reads', 'ref_reads', 'total_reads', 'vaf', 'omega_v'):
ssms[vid][K] = ssms[vid][K][order]
with open(jsonfn, 'w') as F:
json.dump(params, F)
inputparser.write_ssms(ssms, ssmfn)
def _process(ssmfn, jsonfn, to_remove):
params = inputparser.load_params(jsonfn)
ssms = inputparser.load_ssms(ssmfn)
to_remove = set([int(idx) for idx in to_remove.split(',')])
N = len(params['samples'])
all_samps = set(range(N))
assert to_remove.issubset(all_samps)
to_keep = sorted(all_samps - to_remove)
assert len(to_keep) > 0
params['samples'] = [params['samples'][idx] for idx in to_keep]
for vid in ssms.keys():
for K in ('var_reads', 'ref_reads', 'total_reads', 'vaf', 'omega_v'):
ssms[vid][K] = ssms[vid][K][to_keep]
with open(jsonfn, 'w') as F:
json.dump(params, F)
inputparser.write_ssms(ssms, ssmfn)
def main():
parser = argparse.ArgumentParser(
description='LOL HI THERE',
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument('--remove-small-clusters', action='store_true')
parser.add_argument('inssm_fn')
parser.add_argument('outssm_fn')
parser.add_argument('outparams_fn')
args = parser.parse_args()
variants = load_ssms(args.inssm_fn)
clusters = extract_clusters(variants)
clusters = sort_clusters_by_vaf(clusters, variants)
inputparser.write_ssms(variants, args.outssm_fn)
if args.remove_small_clusters:
clusters, garbage = remove_small_clusters(clusters)
else:
garbage = []
sampnames = make_sampnames(variants)
write_params(clusters, garbage, sampnames, args.outparams_fn)
def main():
parser = argparse.ArgumentParser(
description=
'Find variants with likely incorrect var_read_prob by comparing model with provided var_read_prob to haploid (LOH) model using Bayes factors',
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument(
'--logbf-threshold',
type=float,
default=10.,
help=
'Logarithm of Bayes factor threshold at which the haploid model is accepted as more likely model than the model using the provided var_read_prob'
)
parser.add_argument('--verbose',
action='store_true',
help='Print debugging messages')
parser.add_argument(
'--ignore-existing-garbage',
action='store_true',
help=
'Ignore any existing garbage variants listed in in_params_fn and test all variants. If not specified, any existing garbage variants will be kept as garbage and not tested again.'
)
parser.add_argument('--action',
choices=('add_to_garbage', 'modify_var_read_prob'),
default='add_to_garbage')
parser.add_argument('--var-read-prob-alt', type=float, default=1.)
parser.add_argument('in_ssm_fn', help='Input SSM file with mutations')
parser.add_argument(
'in_params_fn',
help=
'Input params file listing sample names and any existing garbage mutations'
)
parser.add_argument(
'out_ssm_fn',
help='Output SSM file with modified list of garbage mutations')
parser.add_argument(
'out_params_fn',
help='Output params file with modified list of garbage mutations')
args = parser.parse_args()
np.set_printoptions(linewidth=400,
precision=3,
threshold=sys.maxsize,
suppress=True)
np.seterr(divide='raise', invalid='raise', over='raise')
if args.ignore_existing_garbage:
variants, params = inputparser.load_ssms_and_params(args.in_ssm_fn,
args.in_params_fn,
remove_garb=False)
params['garbage'] = []
else:
variants, params = inputparser.load_ssms_and_params(
args.in_ssm_fn, args.in_params_fn)
bad_vids, bad_samp_prop = _remove_bad(variants, args.logbf_threshold,
args.var_read_prob_alt, args.verbose)
bad_ssm_prop = len(bad_vids) / len(variants)
if args.action == 'add_to_garbage':
params['garbage'] = common.sort_vids(
set(bad_vids) | set(params['garbage']))
elif args.action == 'modify_var_read_prob':
for vid in bad_vids:
variants[vid]['omega_v'][:] = args.var_read_prob_alt
else:
raise Exception('Unknown action: %s' % args.action)
inputparser.write_ssms(variants, args.out_ssm_fn)
with open(args.out_params_fn, 'w') as F:
json.dump(params, F)
stats = {
'num_bad_ssms': len(bad_vids),
'bad_ssms': common.sort_vids(bad_vids),
'bad_samp_prop': '%.3f' % bad_samp_prop,
'bad_ssm_prop': '%.3f' % bad_ssm_prop,
}
for K, V in stats.items():
print('%s=%s' % (K, V))