def test_run_pick_closed_reference_otus_sortmerna(self):
"""run_pick_closed_reference_otus generates expected results
using sortmerna
"""
self.params['pick_otus']['otu_picking_method'] = "sortmerna"
run_pick_closed_reference_otus(
self.test_data['seqs'][0],
self.test_data['refseqs'][0],
self.test_out,
self.test_data['refseqs_tax'][0],
call_commands_serially,
self.params,
self.qiime_config,
parallel=False,
status_update_callback=no_status_updates)
input_file_basename = splitext(split(self.test_data['seqs'][0])[1])[0]
otu_map_fp = join(self.test_out, 'sortmerna_picked_otus',
'%s_otus.txt' % input_file_basename)
otu_table_fp = join(self.test_out, 'otu_table.biom')
otu_table = load_table(otu_table_fp)
expected_sample_ids = ['f1', 'f2', 'f3', 'f4', 'p1', 'p2', 't1', 't2']
self.assertItemsEqual(otu_table.ids(), expected_sample_ids)
# Number of OTUs matches manually confirmed result
otu_map_lines = list(open(otu_map_fp))
num_otus = len(otu_map_lines)
otu_map_otu_ids = [o.split()[0] for o in otu_map_lines]
self.assertEqual(num_otus, 3)
# parse the otu table
otu_table = load_table(otu_table_fp)
expected_sample_ids = ['f1', 'f2', 'f3', 'f4', 'p1', 'p2', 't1', 't2']
# sample IDs are as expected
self.assertItemsEqual(otu_table.ids(), expected_sample_ids)
# otu ids are as expected
self.assertItemsEqual(otu_table.ids(axis='observation'),
otu_map_otu_ids)
# expected number of sequences in OTU table
number_seqs_in_otu_table = sum(
[v.sum() for v in otu_table.iter_data()])
self.assertEqual(number_seqs_in_otu_table, 117)
# One tax assignment per otu
self.assertEqual(len(otu_table.metadata(axis='observation')), 3)
# Check that the log file is created and has size > 0
log_fp = glob(join(self.test_out, 'log*.txt'))[0]
self.assertTrue(getsize(log_fp) > 0)
def test_run_pick_closed_reference_otus_sortmerna(self):
"""run_pick_closed_reference_otus generates expected results
using sortmerna
"""
self.params['pick_otus']['otu_picking_method'] = "sortmerna"
run_pick_closed_reference_otus(
self.test_data['seqs'][0],
self.test_data['refseqs'][0],
self.test_out,
self.test_data['refseqs_tax'][0],
call_commands_serially,
self.params,
self.qiime_config,
parallel=False,
status_update_callback=no_status_updates)
input_file_basename = splitext(split(self.test_data['seqs'][0])[1])[0]
otu_map_fp = join(self.test_out, 'sortmerna_picked_otus',
'%s_otus.txt' % input_file_basename)
otu_table_fp = join(self.test_out, 'otu_table.biom')
otu_table = load_table(otu_table_fp)
expected_sample_ids = ['f1', 'f2', 'f3', 'f4', 'p1', 'p2', 't1', 't2']
self.assertItemsEqual(otu_table.ids(), expected_sample_ids)
# Number of OTUs matches manually confirmed result
otu_map_lines = list(open(otu_map_fp))
num_otus = len(otu_map_lines)
otu_map_otu_ids = [o.split()[0] for o in otu_map_lines]
self.assertEqual(num_otus, 3)
# parse the otu table
otu_table = load_table(otu_table_fp)
expected_sample_ids = ['f1', 'f2', 'f3', 'f4', 'p1', 'p2', 't1', 't2']
# sample IDs are as expected
self.assertItemsEqual(otu_table.ids(), expected_sample_ids)
# otu ids are as expected
self.assertItemsEqual(otu_table.ids(axis='observation'),
otu_map_otu_ids)
# expected number of sequences in OTU table
number_seqs_in_otu_table = sum([v.sum()
for v in otu_table.iter_data()])
self.assertEqual(number_seqs_in_otu_table, 117)
# One tax assignment per otu
self.assertEqual(len(otu_table.metadata(axis='observation')), 3)
# Check that the log file is created and has size > 0
log_fp = glob(join(self.test_out, 'log*.txt'))[0]
self.assertTrue(getsize(log_fp) > 0)
def main():
option_parser, opts, args = parse_command_line_parameters(**script_info)
verbose = opts.verbose
input_fp = opts.input_fp
reference_fp = opts.reference_fp
taxonomy_fp = opts.taxonomy_fp
output_dir = opts.output_dir
verbose = opts.verbose
print_only = opts.print_only
parallel = opts.parallel
# No longer checking that jobs_to_start > 2, but
# commenting as we may change our minds about this.
#if parallel: raise_error_on_parallel_unavailable()
if opts.parameter_fp:
try:
parameter_f = open(opts.parameter_fp, 'U')
except IOError:
raise IOError,\
"Can't open parameters file (%s). Does it exist? Do you have read access?"\
% opts.parameter_fp
params = parse_qiime_parameters(parameter_f)
parameter_f.close()
else:
params = parse_qiime_parameters([])
# empty list returns empty defaultdict for now
jobs_to_start = opts.jobs_to_start
default_jobs_to_start = qiime_config['jobs_to_start']
validate_and_set_jobs_to_start(params,
jobs_to_start,
default_jobs_to_start,
parallel,
option_parser)
try:
makedirs(output_dir)
except OSError:
if opts.force:
pass
else:
option_parser.error("Output directory already exists. Please choose"
" a different directory, or force overwrite with -f.")
if print_only:
command_handler = print_commands
else:
command_handler = call_commands_serially
if verbose:
status_update_callback = print_to_stdout
else:
status_update_callback = no_status_updates
run_pick_closed_reference_otus(
input_fp,
reference_fp,
output_dir,
taxonomy_fp,
command_handler=command_handler,
params=params,
qiime_config=qiime_config,
parallel=parallel,
status_update_callback=status_update_callback)
def test_run_pick_closed_reference_otus_rdp_tax_assign(self):
"""run_pick_closed_reference_otus with RDP tax assignment
"""
self.params['assign_taxonomy']['assignment_method'] = 'rdp'
self.params['assign_taxonomy']['id_to_taxonomy_fp'] = \
self.test_data['refseqs_tax'][0]
self.params['assign_taxonomy']['reference_seqs_fp'] = \
self.test_data['refseqs'][0]
run_pick_closed_reference_otus(
self.test_data['seqs'][0],
self.test_data['refseqs'][0],
self.test_out,
self.test_data['refseqs_tax'][0],
call_commands_serially,
self.params,
self.qiime_config,
assign_taxonomy=True,
parallel=False,
status_update_callback=no_status_updates)
input_file_basename = splitext(split(self.test_data['seqs'][0])[1])[0]
otu_map_fp = join(self.test_out, 'uclust_ref_picked_otus',
'%s_otus.txt' % input_file_basename)
assigned_taxonomy_fp = join(
self.test_out, 'rdp_assigned_taxonomy/'
'%s_rep_set_tax_assignments.txt' % input_file_basename)
expected_taxonomies = [
[
'295053',
'k__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Enterobacteriales;f__Enterobacteriaceae;g__;s__',
'1.000'
],
[
'879972',
'k__Bacteria;p__Firmicutes;c__Bacilli;o__Lactobacillales;f__Streptococcaceae;g__Streptococcus;s__',
'1.000'
],
[
'42684',
'k__Bacteria;p__Proteobacteria;c__Betaproteobacteria;o__Neisseriales;f__Neisseriaceae;g__;s__',
'1.000'
]
]
# Assigned taxonomies match expected taxonomies
with open(assigned_taxonomy_fp, 'U') as taxonomy_f:
for line in taxonomy_f:
entry = line.strip().split('\t')
self.assertTrue(entry in expected_taxonomies)
otu_table_fp = join(self.test_out, 'otu_table.biom')
otu_table = load_table(otu_table_fp)
expected_sample_ids = ['f1', 'f2', 'f3', 'f4', 'p1', 'p2', 't1', 't2']
self.assertItemsEqual(otu_table.ids(), expected_sample_ids)
# Number of OTUs matches manually confirmed result
otu_map_lines = list(open(otu_map_fp))
num_otus = len(otu_map_lines)
otu_map_otu_ids = [o.split()[0] for o in otu_map_lines]
self.assertEqual(num_otus, 3)
# parse the otu table
otu_table = load_table(otu_table_fp)
expected_sample_ids = ['f1', 'f2', 'f3', 'f4', 'p1', 'p2', 't1', 't2']
# sample IDs are as expected
self.assertItemsEqual(otu_table.ids(), expected_sample_ids)
# otu ids are as expected
self.assertItemsEqual(otu_table.ids(axis='observation'),
otu_map_otu_ids)
# expected number of sequences in OTU table
number_seqs_in_otu_table = sum(
[v.sum() for v in otu_table.iter_data()])
self.assertEqual(number_seqs_in_otu_table, 117)
# One tax assignment per otu
self.assertEqual(len(otu_table.metadata(axis='observation')), 3)
# Check that the log file is created and has size > 0
log_fp = glob(join(self.test_out, 'log*.txt'))[0]
self.assertTrue(getsize(log_fp) > 0)
def main():
option_parser, opts, args = parse_command_line_parameters(**script_info)
verbose = opts.verbose
input_fp = opts.input_fp
reference_fp = opts.reference_fp
taxonomy_fp = opts.taxonomy_fp
output_dir = opts.output_dir
verbose = opts.verbose
print_only = opts.print_only
assign_taxonomy = opts.assign_taxonomy
parallel = opts.parallel
# No longer checking that jobs_to_start > 2, but
# commenting as we may change our minds about this.
# if parallel: raise_error_on_parallel_unavailable()
if opts.parameter_fp:
try:
parameter_f = open(opts.parameter_fp, 'U')
except IOError:
raise IOError(
"Can't open parameters file (%s). Does it exist? Do you have read access?"
% opts.parameter_fp)
params = parse_qiime_parameters(parameter_f)
parameter_f.close()
else:
params = parse_qiime_parameters([])
# empty list returns empty defaultdict for now
jobs_to_start = opts.jobs_to_start
default_jobs_to_start = qiime_config['jobs_to_start']
validate_and_set_jobs_to_start(params, jobs_to_start,
default_jobs_to_start, parallel,
option_parser)
if print_only:
command_handler = print_commands
else:
command_handler = call_commands_serially
try:
makedirs(output_dir)
except OSError:
if opts.force:
pass
else:
option_parser.error(
"Output directory already exists. Please choose"
" a different directory, or force overwrite with -f.")
if verbose:
status_update_callback = print_to_stdout
else:
status_update_callback = no_status_updates
run_pick_closed_reference_otus(
input_fp,
reference_fp,
output_dir,
taxonomy_fp,
assign_taxonomy=assign_taxonomy,
command_handler=command_handler,
params=params,
qiime_config=qiime_config,
parallel=parallel,
status_update_callback=status_update_callback)
def test_run_pick_closed_reference_otus_rdp_tax_assign(self):
"""run_pick_closed_reference_otus with RDP tax assignment
"""
self.params['assign_taxonomy']['assignment_method'] = 'rdp'
self.params['assign_taxonomy']['id_to_taxonomy_fp'] = \
self.test_data['refseqs_tax'][0]
self.params['assign_taxonomy']['reference_seqs_fp'] = \
self.test_data['refseqs'][0]
run_pick_closed_reference_otus(
self.test_data['seqs'][0],
self.test_data['refseqs'][0],
self.test_out,
self.test_data['refseqs_tax'][0],
call_commands_serially,
self.params,
self.qiime_config,
assign_taxonomy=True,
parallel=False,
status_update_callback=no_status_updates)
input_file_basename = splitext(split(self.test_data['seqs'][0])[1])[0]
otu_map_fp = join(self.test_out, 'uclust_ref_picked_otus',
'%s_otus.txt' % input_file_basename)
assigned_taxonomy_fp = join(self.test_out, 'rdp_assigned_taxonomy/'
'%s_rep_set_tax_assignments.txt' %
input_file_basename)
expected_taxonomies = [['295053', 'k__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Enterobacteriales;f__Enterobacteriaceae;g__;s__', '1.000'],
['879972', 'k__Bacteria;p__Firmicutes;c__Bacilli;o__Lactobacillales;f__Streptococcaceae;g__Streptococcus;s__', '1.000'],
['42684', 'k__Bacteria;p__Proteobacteria;c__Betaproteobacteria;o__Neisseriales;f__Neisseriaceae;g__;s__', '1.000']]
# Assigned taxonomies match expected taxonomies
with open(assigned_taxonomy_fp, 'U') as taxonomy_f:
for line in taxonomy_f:
entry = line.strip().split('\t')
self.assertTrue(entry in expected_taxonomies)
otu_table_fp = join(self.test_out, 'otu_table.biom')
otu_table = load_table(otu_table_fp)
expected_sample_ids = ['f1', 'f2', 'f3', 'f4', 'p1', 'p2', 't1', 't2']
self.assertItemsEqual(otu_table.ids(), expected_sample_ids)
# Number of OTUs matches manually confirmed result
otu_map_lines = list(open(otu_map_fp))
num_otus = len(otu_map_lines)
otu_map_otu_ids = [o.split()[0] for o in otu_map_lines]
self.assertEqual(num_otus, 3)
# parse the otu table
otu_table = load_table(otu_table_fp)
expected_sample_ids = ['f1', 'f2', 'f3', 'f4', 'p1', 'p2', 't1', 't2']
# sample IDs are as expected
self.assertItemsEqual(otu_table.ids(), expected_sample_ids)
# otu ids are as expected
self.assertItemsEqual(otu_table.ids(axis='observation'),
otu_map_otu_ids)
# expected number of sequences in OTU table
number_seqs_in_otu_table = sum([v.sum()
for v in otu_table.iter_data()])
self.assertEqual(number_seqs_in_otu_table, 117)
# One tax assignment per otu
self.assertEqual(len(otu_table.metadata(axis='observation')), 3)
# Check that the log file is created and has size > 0
log_fp = glob(join(self.test_out, 'log*.txt'))[0]
self.assertTrue(getsize(log_fp) > 0)
