def test_burst_post_align(self):
database = pkg_resources.resource_filename('shogun.tests', os.path.join('data'))
aligner = BurstAligner(database, threads=1, shell=False)
alignment_file = pkg_resources.resource_filename('shogun.tests', os.path.join('data', 'results', 'burst_results.b6'))
df_capitalist = aligner._post_align(alignment_file)
aligner.post_align = 'taxonomy'
df_non_capitalist = aligner._post_align(alignment_file)
self.assertTrue(df_non_capitalist.any().any())
def test_burst_align(self):
database = pkg_resources.resource_filename('shogun.tests', os.path.join('data'))
aligner = BurstAligner(database, threads=1, shell=False)
infile = pkg_resources.resource_filename('shogun.tests', os.path.join('data', 'combined_seqs.fna'))
outdir = os.path.join(self.temp_dir.name)
self.assertTrue(aligner.align(infile, outdir)[0] == 0)
def assign_taxonomy(ctx, aligner, capitalist, input, database, output):
if not os.path.exists(os.path.dirname(output)):
os.makedirs(os.path.dirname(output))
if not capitalist:
# Set to not run Burst post-align in capitalist mode
ALIGNERS['burst'] = lambda database, shell=ctx.obj[
'shell']: BurstAligner(
database, shell=ctx.obj['shell'], capitalist=False)
# Sniff aligner based on file extension
if aligner == 'auto':
file_ending = input.split(".")[-1]
sniffer_dict = dict(
zip(["b6", "sam", "tsv", "txt"],
["burst", "bowtie2", "utree", "utree"]))
if file_ending in sniffer_dict:
aligner = sniffer_dict[file_ending]
else:
logger.warning("File ending %s not found, assuming burst" %
file_ending)
aligner = "burst"
aligner_cl = ALIGNERS[aligner](database, shell=ctx.obj['shell'])
df = aligner_cl._post_align(input)
df.to_csv(output,
sep='\t',
float_format="%d",
na_rep=0,
index_label="#OTU ID")
def pipeline(ctx, aligner, input, database, output, level, function,
capitalist, taxacut, threads, percent_id, ra):
if not os.path.exists(output):
os.makedirs(output)
if not capitalist:
# Set to not run Burst post-align in capitalist mode
ALIGNERS['burst'] = lambda database, threads=threads, shell=ctx.obj[
'shell']: BurstAligner(database,
shell=ctx.obj['shell'],
threads=threads,
taxacut=taxacute,
capitalist=False,
percent_id=percent_id)
redist_outs = []
redist_levels = []
if aligner == 'all':
for align in ALIGNERS.values():
aligner_cl = align(database,
threads=threads,
shell=ctx.obj['shell'],
percent_id=percent_id,
taxacut=taxacut)
aligner_cl.align(input, output)
if level is not 'off':
redist_out = os.path.join(
output, "taxatable.%s.%s.txt" % (aligner_cl._name, level))
_redist_outs, _redist_levels = _redistribute(
database,
level,
redist_out,
aligner_cl.outfile,
relative_abundance=ra)
redist_outs.extend(_redist_outs)
redist_levels.extend(_redist_levels)
else:
aligner_cl = ALIGNERS[aligner](database,
threads=threads,
shell=ctx.obj['shell'],
percent_id=percent_id,
taxacut=taxacut)
aligner_cl.align(input, output)
logger.debug(level)
if level != 'off':
redist_out = os.path.join(output, "taxatable.%s.txt" % (level))
redist_outs, redist_levels = _redistribute(database,
level,
redist_out,
aligner_cl.outfile,
relative_abundance=ra)
if function and level != 'off':
_function(redist_outs,
database,
output,
redist_levels,
save_median_taxatable=True)
if ra:
_convert_files_to_relative_abundances(redist_outs)
def test_burst_db(self):
self.assertTrue(
BurstAligner.check_database(
pkg_resources.resource_filename('shogun.tests',
os.path.join('data')))[0])