Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add more sample name options #10

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from 1 commit
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
37 changes: 33 additions & 4 deletions archaic_match/__main__.py
Original file line number Diff line number Diff line change
Expand Up @@ -62,15 +62,27 @@ def main():
"sample, population, and super-population",
metavar="FILE")
population_group.add_argument("--archaic-populations",
required=True,
required=False,
default=[],
nargs='+',
help="List of archaic populations",
metavar="FILE")
population_group.add_argument("--archaic-samples",
required=False,
default=[],
nargs='+',
help="List of archaic samples")
population_group.add_argument("--modern-populations",
required=True,
required=False,
default=[],
nargs='+',
help="List of modern populations",
metavar="FILE")
population_group.add_argument("--modern-superpopulations",
required=False,
default=[],
nargs='+',
help="List of modern superpopulations")
population_group.add_argument("--chrom-sizes",
required=True,
help="Tab delimited file with seqid\tlength "
Expand Down Expand Up @@ -527,14 +539,31 @@ def match_pct(args):
sample_populations = get_sample_populations(args.populations)
logging.debug("Sample populations: {}".format(sample_populations))

archaic_sample_list = get_samplename_list(args.archaic_populations,
sample_populations)
archaic_sample_list = args.archaic_samples
archaic_sample_list += get_samplename_list(args.archaic_populations,
sample_populations)
# remove duplicates
archaic_sample_list = list(set(archaic_sample_list))

logging.debug("Archaic sample list: {}".format(archaic_sample_list))

modern_sample_list = get_samplename_list(args.modern_populations,
sample_populations)
modern_sample_list += get_samplename_list(args.modern_superpopulations,
sample_populations,
match='superpopulation')
modern_sample_list = list(set(modern_sample_list))

logging.debug("Modern sample list: {}".format(modern_sample_list))

if len(archaic_sample_list) == 0:
raise ValueError("Found no archaic samples, be sure to specify "
"`archaic-populations` or `archaic-samples`")

if len(modern_sample_list) == 0:
raise ValueError("Found no modern samples, be sure to specify "
"`modern-populations` or `modern-superpopulations`")

if args.chrom_sizes.isdigit():
chrom_sizes = defaultdict(lambda: int(args.chrom_sizes))
else:
Expand Down
17 changes: 10 additions & 7 deletions archaic_match/funcmodule.py
Original file line number Diff line number Diff line change
Expand Up @@ -7,13 +7,16 @@
from .classmodule import Window


def get_samplename_list(query_populations, sample_populations):
'''Returns sample names for given population'''
sample_list = list()
for sample in sample_populations.values():
if sample.population in query_populations:
sample_list.append(sample.name)
return sample_list
def get_samplename_list(queries, samples,
match='population'):
'''
Returns sample names for given queries as a list.
Can match to 'population', 'superpopulation' or 'sample'
Default is 'population'
'''
return [sample.name
for sample in samples.values()
if getattr(sample, match) in queries]


def get_chrom_sizes(filename):
Expand Down