def main():
logging.basicConfig(level=logging.INFO,
format="%(levelname)s: %(message)s")
parser = argparse.ArgumentParser(
description=
"Turn a BIOM file with a taxonomy into a taxtable and seqinfo.")
parser.add_argument('biom',
type=argparse.FileType('r'),
help='input BIOM file')
parser.add_argument('taxtable',
type=argparse.FileType('w'),
help='output taxtable')
parser.add_argument('seqinfo',
type=argparse.FileType('w'),
help='output seqinfo')
args = parser.parse_args()
log.info('loading biom')
with args.biom:
j = json.load(args.biom)
root = TaxNode('root', root_id, name='Root')
root.ranks = rank_order
seqinfo = csv.writer(args.seqinfo)
seqinfo.writerow(('seqname', 'tax_id'))
log.info('determining tax_ids')
for leaf in j['rows']:
leaf_taxonomy = leaf['metadata']['taxonomy']
# Drop nodes containing only rank (e.g. `s__`)
leaf_taxonomy = [i for i in leaf_taxonomy if i[3:]]
leaf_lineages = list(lineages([i for i in leaf_taxonomy if i[3:]]))
seqinfo.writerow((leaf['id'], leaf_lineages[-1][0]))
for tax_id, node, parent in leaf_lineages:
if tax_id in root.index:
continue
root.get_node(parent).add_child(
TaxNode(ranks[node[0]], tax_id, name=node[3:] or node))
log.info('writing taxtable')
with args.taxtable:
root.write_taxtable(args.taxtable)
def setUp(self):
self.taxonomy = TaxNode(rank='root', name='root', tax_id='1')
self.taxonomy.ranks = ['root', 'class', 'genus', 'species']
g1 = TaxNode(rank='genus', name='g1', tax_id='2')
self.g1 = g1
g1.sequence_ids = set(['s1', 's2'])
self.taxonomy.add_child(g1)
g1.add_child(TaxNode(rank='species', name='s1', tax_id='s1'))
g1.add_child(TaxNode(rank='species', name='s2', tax_id='s2'))
g2 = TaxNode(rank='genus', name='g2', tax_id='3')
self.taxonomy.add_child(g2)
s3 = TaxNode(rank='species', name='s3', tax_id='s3')
s3.sequence_ids = set(['s3', 's4'])
g2.add_child(s3)
g2.add_child(TaxNode(rank='species', name='s4', tax_id='s4'))
