def main():
parser = argparse.ArgumentParser(
description='Write JSON files describing trees',
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
)
parser.add_argument('--include-ssm-names', dest='include_ssm_names', action='store_true',
help='Include SSM names in output (which may be sensitive data)')
parser.add_argument('--min-ssms', dest='min_ssms', type=float, default=0.01,
help='Minimum number or percent of SSMs to retain a subclone')
parser.add_argument('dataset_name',
help='Name identifying dataset')
parser.add_argument('tree_file',
help='File containing sampled trees')
parser.add_argument('tree_summary_output',
help='Output file for JSON-formatted tree summaries')
parser.add_argument('mutlist_output',
help='Output file for JSON-formatted list of mutations')
parser.add_argument('mutass_output',
help='Output file for JSON-formatted list of SSMs and CNVs assigned to each subclone')
args = parser.parse_args()
summaries, mutlist, mutass = ResultGenerator().generate(args.tree_file, args.include_ssm_names)
munger = ResultMunger(summaries, mutlist, mutass, args.min_ssms)
summaries, mutass = munger.munge()
writer = JsonWriter(args.dataset_name)
writer.write_summaries(summaries, args.tree_summary_output)
writer.write_mutlist(mutlist, args.mutlist_output)
writer.write_mutass(mutass, args.mutass_output)
def main():
parser = argparse.ArgumentParser(
description='Write JSON files describing trees',
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
)
parser.add_argument(
'--include-ssm-names',
dest='include_ssm_names',
action='store_true',
help='Include SSM names in output (which may be sensitive data)')
parser.add_argument(
'--min-ssms',
dest='min_ssms',
type=float,
default=0.01,
help='Minimum number or percent of SSMs to retain a subclone')
parser.add_argument('dataset_name', help='Name identifying dataset')
parser.add_argument('tree_file', help='File containing sampled trees')
parser.add_argument('tree_summary_output',
help='Output file for JSON-formatted tree summaries')
parser.add_argument(
'mutlist_output',
help='Output file for JSON-formatted list of mutations')
parser.add_argument(
'mutass_output',
help=
'Output file for JSON-formatted list of SSMs and CNVs assigned to each subclone'
)
args = parser.parse_args()
summaries, mutlist, mutass = ResultGenerator().generate(
args.tree_file, args.include_ssm_names)
munger = ResultMunger(summaries, mutlist, mutass, args.min_ssms)
summaries, mutass = munger.munge()
writer = JsonWriter(args.dataset_name)
writer.write_summaries(summaries, args.tree_summary_output)
writer.write_mutlist(mutlist, args.mutlist_output)
writer.write_mutass(mutass, args.mutass_output)
def main():
parser = argparse.ArgumentParser(
description='Write JSON files describing trees',
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
)
parser.add_argument(
'--include-ssm-names',
dest='include_ssm_names',
action='store_true',
help='Include SSM names in output (which may be sensitive data)')
parser.add_argument(
'--min-ssms',
dest='min_ssms',
type=float,
default=0.01,
help='Minimum number or percent of SSMs to retain a subclone')
parser.add_argument('--include-multiprimary',
dest='include_multiprimary',
action='store_true',
help='Whether to include multiprimary trees in result')
parser.add_argument('--max-multiprimary', dest='max_multiprimary', type=restricted_float, default=0.8,
help='Maximum proportion of trees that may be multiprimary if ' \
'--include=multiprimary=False. In that case, an exception will be thrown if ' \
'the proportion of multiprimary trees exceeds this value.')
parser.add_argument('dataset_name', help='Name identifying dataset')
parser.add_argument('tree_file', help='File containing sampled trees')
parser.add_argument('tree_summary_output',
help='Output file for JSON-formatted tree summaries')
parser.add_argument(
'mutlist_output',
help='Output file for JSON-formatted list of mutations')
parser.add_argument(
'mutass_output',
help=
'Output file for JSON-formatted list of SSMs and CNVs assigned to each subclone'
)
args = parser.parse_args()
summaries, mutlist, mutass, params = ResultGenerator().generate(
args.tree_file, args.include_ssm_names)
munger = ResultMunger(summaries, mutlist, mutass)
summaries, mutass = munger.remove_small_nodes(args.min_ssms)
munger.remove_superclones()
if not args.include_multiprimary:
munger.remove_multiprimary_trees(args.max_multiprimary)
writer = JsonWriter(args.dataset_name)
writer.write_summaries(summaries, params, args.tree_summary_output)
writer.write_mutlist(mutlist, args.mutlist_output)
writer.write_mutass(mutass, args.mutass_output)
def munge(treesummfn, mutlistfn, mutassfn):
loader = ResultLoader(treesummfn, mutlistfn, mutassfn)
dataset_name = loader.dataset_name
treesumm, mutlist, mutass = loader.tree_summary, loader.mutlist, loader.load_all_mut_assignments_into_memory(
)
munger = ResultMunger(treesumm, mutlist, mutass)
munger.remove_superclones()
munger.remove_polyclonal_trees()
writer = JsonWriter(dataset_name)
writer.write_summaries(treesumm, treesummfn)
writer.write_mutlist(mutlist, mutlistfn)
writer.write_mutass(mutass, mutassfn)