parser.add_argument(
'--exclude',
help=
"a text file containing strains (one per line) that will be excluded")
args = parser.parse_args()
region = args.region
time_interval = sorted([
numeric_date(x)
for x in determine_time_interval(args.time_interval, args.resolution)
])
# read strains to exclude
excluded_strains = read_strain_list(args.exclude) if args.exclude else []
# read in meta data, parse numeric dates, and exclude outlier strains
metadata = {
k: val
for k, val in parse_metadata(['segment'], [args.metadata]).items()
if k not in excluded_strains
}['segment']
sequences = []
print(time_interval)
for seq in metadata:
if metadata[seq]["num_date"]>=time_interval[0] and \
metadata[seq]["num_date"]<time_interval[1]:
sequences.append(metadata[seq])
age_distribution(sequences, args.output)
return scores
if __name__ == '__main__':
parser = argparse.ArgumentParser(
description="Annotate nodes with scores based on metadata",
formatter_class=argparse.ArgumentDefaultsHelpFormatter
)
parser.add_argument('--metadata', type=str, required=True, help="file with metadata associated with viral sequences, one for each segment")
parser.add_argument('--tree', type=str, required=True, help="file inferred tree")
parser.add_argument('--output', help="name of the file to write selected strains to")
args = parser.parse_args()
# read in meta data and tree
metadata = parse_metadata(['s'], [args.metadata])['s']
T = Phylo.read(args.tree, 'newick')
# dictionary to hold calculated scores for terminal and internal nodes
scores = dict()
for k,v in calculate_average_age(T, metadata, min_clade_size=20).items():
if k not in scores: scores[k] = {}
scores[k]['avg_age'] = v
for k,v in calc_average_vaccination_coverage(T, metadata, min_clade_size=0).items():
if k not in scores: scores[k] = {}
scores[k]['vaccov'] = v
with open(args.output, 'w') as results:
json.dump({"nodes":scores}, results, indent=1, sort_keys = True)