def test_parse_taxonomy_table(self):
"""
Testing parse_taxonomy_table function.
:return: Returns OK if test goals were achieved, otherwise raises
error.
"""
taxa_data = ut.parse_taxonomy_table("phylotoast/test/test_taxa.txt")
# Testing the validity of the function.
hand_calc = {"018AP132": "k__Bacteria; p__Proteobacteria; c__Betaproteobacteria; o__Neisseriales; f__Neisseriaceae; g__Neisseria; s__HOT.018",
"057BE024": "k__Bacteria; p__Firmicutes; c__Bacilli; o__Lactobacillales; f__Streptococcaceae; g__Streptococcus; s__HOT.057",
"083BS091": "k__Bacteria; p__Firmicutes; c__Clostridia; o__Clostridiales; f__Lachnospiraceae_[XIVa]; g__Lachnoanaerobaculum; s__HOT.083",
"105_3039": "k__Bacteria; p__Firmicutes; c__Clostridia; o__Clostridiales; f__Peptostreptococcaceae_[XI]; g__Eubacterium_[XI][G-1]; s__infirmum",
"122_8622": "k__Bacteria; p__Firmicutes; c__Clostridia; o__Clostridiales; f__Veillonellaceae; g__Megasphaera; s__micronuciformis",
"130Snoxi": "k__Bacteria; p__Firmicutes; c__Clostridia; o__Clostridiales; f__Veillonellaceae; g__Selenomonas; s__noxia",
"139EW076": "k__Bacteria; p__Firmicutes; c__Clostridia; o__Clostridiales; f__Veillonellaceae; g__Selenomonas; s__dianae",
"151_K168": "k__Bacteria; p__Firmicutes; c__Clostridia; o__Clostridiales; f__Veillonellaceae; g__Selenomonas; s__sputigena",
"214DE081": "k__Bacteria; p__Fusobacteria; c__Fusobacteria; o__Fusobacteriales; f__Leptotrichiaceae; g__Leptotrichia; s__shahii",
"220FB074": "k__Bacteria; p__Fusobacteria; c__Fusobacteria; o__Fusobacteriales; f__Leptotrichiaceae; g__Leptotrichiaceae_[G-1]; s__HOT.220",
"222_7816": "k__Bacteria; p__Fusobacteria; c__Fusobacteria; o__Fusobacteriales; f__Leptotrichiaceae; g__Leptotrichia; s__wadei"}
for ids in hand_calc:
self.assertEqual(
taxa_data[ids], hand_calc[ids],
msg="Taxonomy file was not accurately parsed into (OTU, taxonomy) dict."
)
def main():
args = handle_program_options()
try:
with open(args.id_to_taxonomy_fp):
pass
except IOError as ioe:
sys.exit(
'\nError mapping sequences to assigned taxonomy filepath:{}\n'
.format(ioe)
)
# input the ID to Taxonomy table and the rep set
taxids = util.parse_taxonomy_table(args.id_to_taxonomy_fp)
rep_set = SeqIO.to_dict(SeqIO.parse(args.rep_set_fp, 'fasta'))
# write out the assigned taxonomy file
with open(args.assigned_taxonomy_fp, 'w') as outF:
for taxid in rep_set:
line = '{0}\t{1}\t{2}\t{0}\n'.format(taxid, taxids[taxid], 0.0)
outF.write(line)
if args.verbose:
print 'Taxonomy written to: {}'.format(args.assigned_taxonomy_fp)
print '{} OTU records written'.format(len(rep_set))
def main():
args = handle_program_options()
try:
with open(args.otu_id_fp):
pass
except IOError as ioe:
sys.exit("\nError with file containing OTUIDs/BIOM format:{}\n".format(ioe))
with open(args.otu_id_fp, "rU") as otuF:
if args.reverse_lookup:
otu_ids = []
for line in otuF.readlines():
if line:
otu_ids.append(line.strip())
else:
otu_ids = [line.strip().split("\t") for line in otuF.readlines()]
taxa = util.parse_taxonomy_table(args.taxonomy_fp)
with open(args.output_fp, "w") as outF:
for entry in otu_ids:
if isinstance(entry, list):
# check for comments in BIOM files
if not entry[0][0] == "#":
ID = entry[0]
else:
outF.write("{}\n".format("\t".join(entry)))
continue
# instead of a BIOM file, a line-by-line list of OTU IDs
else:
ID = entry
# for looking up OTUIDs
if args.reverse_lookup:
for id, fulltaxa in taxa.iteritems():
otuname = otuc.otu_name(fulltaxa.split("; "))
if otuname == ID:
taxa_id = id
# for looking up OTU name
else:
if ID in taxa:
named_ID = otuc.otu_name(taxa[ID].split("; "))
else:
print "Error: OTU ID {} not found in supplied taxonomy file.".format(ID)
return
# write out to file
out_str = "{}\t{}\n"
if isinstance(entry, list):
outF.write(out_str.format(named_ID, "\t".join(entry[1:])))
else:
if args.reverse_lookup:
outF.write("{}\n".format(taxa_id))
else:
outF.write(out_str.format(ID, named_ID))
def test_parse_taxonomy_table(self):
"""
Testing parse_taxonomy_table function.
:return: Returns OK if test goals were achieved, otherwise raises
error.
"""
taxa_data = ut.parse_taxonomy_table("phylotoast/test/test_taxa.txt")
# Testing the validity of the function.
hand_calc = {
"018AP132":
"k__Bacteria; p__Proteobacteria; c__Betaproteobacteria; o__Neisseriales; f__Neisseriaceae; g__Neisseria; s__HOT.018",
"057BE024":
"k__Bacteria; p__Firmicutes; c__Bacilli; o__Lactobacillales; f__Streptococcaceae; g__Streptococcus; s__HOT.057",
"083BS091":
"k__Bacteria; p__Firmicutes; c__Clostridia; o__Clostridiales; f__Lachnospiraceae_[XIVa]; g__Lachnoanaerobaculum; s__HOT.083",
"105_3039":
"k__Bacteria; p__Firmicutes; c__Clostridia; o__Clostridiales; f__Peptostreptococcaceae_[XI]; g__Eubacterium_[XI][G-1]; s__infirmum",
"122_8622":
"k__Bacteria; p__Firmicutes; c__Clostridia; o__Clostridiales; f__Veillonellaceae; g__Megasphaera; s__micronuciformis",
"130Snoxi":
"k__Bacteria; p__Firmicutes; c__Clostridia; o__Clostridiales; f__Veillonellaceae; g__Selenomonas; s__noxia",
"139EW076":
"k__Bacteria; p__Firmicutes; c__Clostridia; o__Clostridiales; f__Veillonellaceae; g__Selenomonas; s__dianae",
"151_K168":
"k__Bacteria; p__Firmicutes; c__Clostridia; o__Clostridiales; f__Veillonellaceae; g__Selenomonas; s__sputigena",
"214DE081":
"k__Bacteria; p__Fusobacteria; c__Fusobacteria; o__Fusobacteriales; f__Leptotrichiaceae; g__Leptotrichia; s__shahii",
"220FB074":
"k__Bacteria; p__Fusobacteria; c__Fusobacteria; o__Fusobacteriales; f__Leptotrichiaceae; g__Leptotrichiaceae_[G-1]; s__HOT.220",
"222_7816":
"k__Bacteria; p__Fusobacteria; c__Fusobacteria; o__Fusobacteriales; f__Leptotrichiaceae; g__Leptotrichia; s__wadei"
}
for ids in hand_calc:
self.assertEqual(
taxa_data[ids],
hand_calc[ids],
msg=
"Taxonomy file was not accurately parsed into (OTU, taxonomy) dict."
)
def main():
args = handle_program_options()
try:
with open(args.otu_id_fp):
pass
except IOError as ioe:
sys.exit('\nError with file containing OTUIDs/BIOM format:{}\n'.format(ioe))
with open(args.otu_id_fp, 'rU') as otuF:
otu_ids = [line.strip().split('\t') for line in otuF.readlines()]
taxa = util.parse_taxonomy_table(args.taxonomy_fp)
with open(args.output_fp, 'w') as outF:
for entry in otu_ids:
if isinstance(entry, list):
# check for comments in BIOM files
if not entry[0][0] == '#':
ID = entry[0]
else:
outF.write('{}\n'.format('\t'.join(entry)))
continue
# instead of a BIOM file, a line-by-line list of OTU IDs
else:
ID = entry
if ID in taxa:
named_ID = otuc.otu_name(taxa[ID].split('; '))
else:
print 'Error: OTU ID {} not found in supplied taxonomy file; stopping...'.format(ID)
return
# write out to file
out_str = '{}\t{}\n'
if isinstance(entry, list):
outF.write(out_str.format(named_ID, '\t'.join(entry[1:])))
else:
outF.write(out_str.format(ID, named_ID))
