def _get_points_to_estimate(self,
reference_individual_count,
start=1,
stop=None,
num_steps=10):
"""Returns depths/sizes to estimate."""
if stop is None:
# Compute base sample size as stopping point.
min_size, max_size, _, _, _ = compute_counts_per_sample_stats(
self._biom_table)
stop = int(max(2 * min_size, max_size))
if start < 1 or num_steps < 1:
raise ValueError("The minimum individual count and number of "
"steps must both be greater than or equal to 1.")
if start > stop:
raise ValueError("The minimum individual count must be less than "
"or equal to the maximum individual count.")
step_size = max((stop - start) // num_steps, 1)
points = range(start, stop + 1, step_size)
if reference_individual_count not in points:
insort(points, reference_individual_count)
return points
def add_counts_to_mapping(biom_lines, mapping_lines, otu_counts, output_fp):
"""Counts the number of seqs/OTUs per sample and add its to the mapping file
Inputs:
biom_lines:
mapping_lines:
otu_counts:
output_fp:
"""
# Parse biom file
biom = parse_biom_table(biom_lines)
# Parse mapping file
map_data, headers, comments = parse_mapping_file(mapping_lines)
# Compute the counts per sample
min_count, max_count, median_count, mean_count, counts_per_sample =\
compute_counts_per_sample_stats(biom, binary_counts=otu_counts)
# Add the counts to the mapping data
index = len(headers) - 1
headers.insert(index, "NumIndividuals")
for row in map_data:
row.insert(index, str(counts_per_sample[row[0]]))
# # Add the '#' character to the first header
# headers[0] = '#' + headers[0]
# # Add headers to the data
# map_data.insert(0, headers)
# Write the corrected mapping file
write_corrected_mapping(output_fp, headers, comments, map_data)
def add_counts_to_mapping(biom_lines, mapping_lines, otu_counts, output_fp):
"""Counts the number of seqs/OTUs per sample and add its to the mapping file
Inputs:
biom_lines:
mapping_lines:
otu_counts:
output_fp:
"""
# Parse biom file
biom = parse_biom_table(biom_lines)
# Parse mapping file
map_data, headers, comments = parse_mapping_file(mapping_lines)
# Compute the counts per sample
min_count, max_count, median_count, mean_count, counts_per_sample =\
compute_counts_per_sample_stats(biom, binary_counts=otu_counts)
# Add the counts to the mapping data
index = len(headers) - 1
headers.insert(index, "NumIndividuals")
for row in map_data:
row.insert(index, str(counts_per_sample[row[0]]))
# Add the '#' character to the first header
headers[0] = '#' + headers[0]
# Add headers to the data
map_data.insert(0, headers)
# Write the corrected mapping file
write_corrected_file(map_data, comments, output_fp)
def test_compute_counts_per_sample_stats(self):
"""compute_counts_per_sample_stats functions as expected
"""
actual = compute_counts_per_sample_stats(self.biom_otu_table1_w_tax)
self.assertEqual(actual[0],3)
self.assertEqual(actual[1],7)
self.assertEqual(actual[2],4)
self.assertEqual(actual[3],4.5)
self.assertEqual(actual[4],{'Sample1':7,'Sample2':3,'Sample3':4,
'Sample4':6,'Sample5':3,'Sample6':4})
def test_compute_counts_per_sample_stats(self):
"""compute_counts_per_sample_stats functions as expected
"""
actual = compute_counts_per_sample_stats(self.biom_otu_table1_w_tax)
self.assertEqual(actual[0], 3)
self.assertEqual(actual[1], 7)
self.assertEqual(actual[2], 4)
self.assertEqual(actual[3], 4.5)
self.assertEqual(
actual[4], {"Sample1": 7, "Sample2": 3, "Sample3": 4, "Sample4": 6, "Sample5": 3, "Sample6": 4}
)
def test_compute_counts_per_sample_stats_obs_counts(self):
"""compute_counts_per_sample_stats functions as expected
"""
actual = compute_counts_per_sample_stats(self.biom_otu_table1_w_tax,
binary_counts=True)
self.assertEqual(actual[0],1)
self.assertEqual(actual[1],4)
self.assertEqual(actual[2],2.5)
self.assertEqual(actual[3],2.5)
self.assertEqual(actual[4],{'Sample1':2,'Sample2':3,'Sample3':4,
'Sample4':2,'Sample5':1,'Sample6':3})
def test_compute_counts_per_sample_stats_obs_counts(self):
"""compute_counts_per_sample_stats functions as expected
"""
actual = compute_counts_per_sample_stats(self.biom_otu_table1_w_tax, binary_counts=True)
self.assertEqual(actual[0], 1)
self.assertEqual(actual[1], 4)
self.assertEqual(actual[2], 2.5)
self.assertEqual(actual[3], 2.5)
self.assertEqual(
actual[4], {"Sample1": 2, "Sample2": 3, "Sample3": 4, "Sample4": 2, "Sample5": 1, "Sample6": 3}
)
def test_compute_counts_per_sample_stats(self):
"""compute_counts_per_sample_stats functions as expected
This method is ported from QIIME (http://www.qiime.org). QIIME is a GPL
project, but we obtained permission from the authors of this method to
port it to the BIOM Format project (and keep it under BIOM's BSD
license).
"""
actual = compute_counts_per_sample_stats(self.biom_otu_table1_w_tax)
self.assertEqual(actual[0], 3)
self.assertEqual(actual[1], 7)
self.assertEqual(actual[2], 4)
self.assertEqual(actual[3], 4.5)
self.assertEqual(actual[4], {'Sample1': 7, 'Sample2': 3, 'Sample3': 4,
'Sample4': 6, 'Sample5': 3, 'Sample6': 4})
def test_compute_counts_per_sample_stats(self):
"""compute_counts_per_sample_stats functions as expected
This method is ported from QIIME (http://www.qiime.org). QIIME is a GPL
project, but we obtained permission from the authors of this method to
port it to the BIOM Format project (and keep it under BIOM's BSD
license).
"""
actual = compute_counts_per_sample_stats(self.biom_otu_table1_w_tax)
self.assertEqual(actual[0], 3)
self.assertEqual(actual[1], 7)
self.assertEqual(actual[2], 4)
self.assertEqual(actual[3], 4.5)
self.assertEqual(actual[4], {'Sample1': 7, 'Sample2': 3, 'Sample3': 4,
'Sample4': 6, 'Sample5': 3, 'Sample6': 4})
def test_compute_counts_per_sample_stats_obs_counts(self):
"""compute_counts_per_sample_stats functions as expected
This method is ported from QIIME (http://www.qiime.org). QIIME is a GPL
project, but we obtained permission from the authors of this method to
port it to the BIOM Format project (and keep it under BIOM's BSD
license).
"""
actual = compute_counts_per_sample_stats(self.biom_otu_table1_w_tax, binary_counts=True)
self.assertEqual(actual[0], 1)
self.assertEqual(actual[1], 4)
self.assertEqual(actual[2], 2.5)
self.assertEqual(actual[3], 2.5)
self.assertEqual(
actual[4], {"Sample1": 2, "Sample2": 3, "Sample3": 4, "Sample4": 2, "Sample5": 1, "Sample6": 3}
)
def _get_points_to_estimate(self, reference_individual_count, start=1,
stop=None, num_steps=10):
"""Returns depths/sizes to estimate."""
if stop is None:
# Compute base sample size as stopping point.
min_size, max_size, _, _, _ = compute_counts_per_sample_stats(
self._biom_table)
stop = int(max(2 * min_size, max_size))
if start < 1 or num_steps < 1:
raise ValueError("The minimum individual count and number of "
"steps must both be greater than or equal to 1.")
if start > stop:
raise ValueError("The minimum individual count must be less than "
"or equal to the maximum individual count.")
step_size = max((stop - start) // num_steps, 1)
points = range(start, stop + 1, step_size)
if reference_individual_count not in points:
insort(points, reference_individual_count)
return points
def run(self, **kwargs):
"""
table: two-element tuple containing the biom table to summarize and
the file(-like) object containing the original table data. The
second element of the tuple (the file(-like) object) may be
None. If this is the case, the MD5 sum will *not* be computed
qualitative: counts are presented as number of unique observation
ids per sample, rather than total observation count per
sample
suppress_md5: if ``True``, the MD5 sum of the table file contents will
not be computed. This parameter is ignored if
``table[1] is None``
"""
result = {}
qualitative = kwargs['qualitative']
table, table_lines = kwargs['table']
min_counts, max_counts, median_counts, mean_counts, counts_per_sample =\
compute_counts_per_sample_stats(table, qualitative)
num_observations = len(table.ObservationIds)
suppress_md5 = (table_lines is None) or kwargs['suppress_md5']
counts_per_sample_values = counts_per_sample.values()
if table.SampleMetadata is None:
sample_md_keys = ["None provided"]
else:
sample_md_keys = table.SampleMetadata[0].keys()
if table.ObservationMetadata is None:
observation_md_keys = ["None provided"]
else:
observation_md_keys = table.ObservationMetadata[0].keys()
lines = []
num_samples = len(counts_per_sample)
lines.append('Num samples: %d' % num_samples)
lines.append('Num observations: %d' % num_observations)
if not qualitative:
total_count = sum(counts_per_sample_values)
lines.append('Total count: %d' % total_count)
lines.append('Table density (fraction of non-zero values): %1.3f' % \
table.getTableDensity())
if not suppress_md5:
lines.append('Table md5 (unzipped): %s' % safe_md5(table_lines))
lines.append('')
if qualitative:
lines.append('Observations/sample summary:')
else:
lines.append('Counts/sample summary:')
lines.append(' Min: %r' % min_counts)
lines.append(' Max: %r' % max_counts)
lines.append(' Median: %1.3f' % median_counts)
lines.append(' Mean: %1.3f' % mean_counts)
lines.append(' Std. dev.: %1.3f' % std(counts_per_sample_values))
lines.append(' Sample Metadata Categories: %s' % '; '.join(sample_md_keys))
lines.append(' Observation Metadata Categories: %s' % '; '.join(observation_md_keys))
lines.append('')
if qualitative:
lines.append('Observations/sample detail:')
else:
lines.append('Counts/sample detail:')
sorted_counts_per_sample = [(v,k) for k,v in counts_per_sample.items()]
sorted_counts_per_sample.sort()
for v,k in sorted_counts_per_sample:
lines.append(' %s: %r' % (k,v))
result['biom-summary'] = lines
return result
def run(self, **kwargs):
result = {}
qualitative = kwargs['qualitative']
by_observations = kwargs['observations']
table, table_lines = kwargs['table']
if by_observations:
table = table.transpose()
min_counts, max_counts, median_counts, mean_counts, counts_per_samp =\
compute_counts_per_sample_stats(table, qualitative)
num_observations = len(table.ids(axis='observation'))
counts_per_sample_values = counts_per_samp.values()
if table.metadata() is None:
sample_md_keys = ["None provided"]
else:
sample_md_keys = table.metadata()[0].keys()
if table.metadata(axis='observation') is None:
observation_md_keys = ["None provided"]
else:
observation_md_keys = table.metadata(axis='observation')[0].keys()
lines = []
num_samples = len(table.ids())
if by_observations:
# as this is a transpose of the original table...
lines.append('Num samples: %d' % num_observations)
lines.append('Num observations: %d' % num_samples)
else:
lines.append('Num samples: %d' % num_samples)
lines.append('Num observations: %d' % num_observations)
if not qualitative:
total_count = sum(counts_per_sample_values)
lines.append('Total count: %d' % total_count)
lines.append('Table density (fraction of non-zero values): %1.3f' %
table.get_table_density())
lines.append('')
if qualitative:
if by_observations:
lines.append('Sample/observations summary:')
else:
lines.append('Observations/sample summary:')
else:
lines.append('Counts/sample summary:')
lines.append(' Min: %r' % min_counts)
lines.append(' Max: %r' % max_counts)
lines.append(' Median: %1.3f' % median_counts)
lines.append(' Mean: %1.3f' % mean_counts)
lines.append(' Std. dev.: %1.3f' % std(counts_per_sample_values))
if by_observations:
# since this is a transpose...
lines.append(' Sample Metadata Categories: %s' %
'; '.join(observation_md_keys))
lines.append(' Observation Metadata Categories: %s' %
'; '.join(sample_md_keys))
lines.append('')
else:
lines.append(' Sample Metadata Categories: %s' %
'; '.join(sample_md_keys))
lines.append(' Observation Metadata Categories: %s' %
'; '.join(observation_md_keys))
lines.append('')
if qualitative:
lines.append('Observations/sample detail:')
else:
lines.append('Counts/sample detail:')
for k, v in sorted(counts_per_samp.items(), key=itemgetter(1)):
lines.append(' %s: %r' % (k, v))
result['biom_summary'] = lines
return result
def _summarize_table(table, qualitative=False, observations=False):
lines = []
locale.setlocale(locale.LC_ALL, '')
if observations:
table = table.transpose()
min_counts, max_counts, median_counts, mean_counts, counts_per_samp =\
compute_counts_per_sample_stats(table, qualitative)
num_observations = len(table.ids(axis='observation'))
counts_per_sample_values = list(counts_per_samp.values())
if table.metadata() is None:
sample_md_keys = ["None provided"]
else:
sample_md_keys = table.metadata()[0].keys()
if table.metadata(axis='observation') is None:
observation_md_keys = ["None provided"]
else:
observation_md_keys = table.metadata(axis='observation')[0].keys()
num_samples = len(table.ids())
if observations:
# as this is a transpose of the original table...
lines.append('Num samples: ' + locale.format('%d', num_observations,
grouping=True))
lines.append('Num observations: ' + locale.format('%d', num_samples,
grouping=True))
else:
lines.append('Num samples: ' + locale.format('%d', num_samples,
grouping=True))
lines.append('Num observations: ' + locale.format('%d',
num_observations, grouping=True))
if not qualitative:
total_count = sum(counts_per_sample_values)
lines.append('Total count: ' + locale.format('%d', total_count,
grouping=True))
lines.append('Table density (fraction of non-zero values): %1.3f' %
table.get_table_density())
lines.append('')
if qualitative:
if observations:
lines.append('Sample/observations summary:')
else:
lines.append('Observations/sample summary:')
else:
lines.append('Counts/sample summary:')
lines.append(' Min: ' + locale.format('%1.3f', min_counts, grouping=True))
lines.append(' Max: ' + locale.format('%1.3f', max_counts, grouping=True))
lines.append(' Median: ' + locale.format('%1.3f', median_counts,
grouping=True))
lines.append(' Mean: ' + locale.format('%1.3f', mean_counts,
grouping=True))
lines.append(' Std. dev.: ' + locale.format('%1.3f',
std(counts_per_sample_values), grouping=True))
if observations:
# since this is a transpose...
lines.append(
' Sample Metadata Categories: %s' %
'; '.join(observation_md_keys))
lines.append(
' Observation Metadata Categories: %s' %
'; '.join(sample_md_keys))
lines.append('')
else:
lines.append(
' Sample Metadata Categories: %s' %
'; '.join(sample_md_keys))
lines.append(
' Observation Metadata Categories: %s' %
'; '.join(observation_md_keys))
lines.append('')
if qualitative:
lines.append('Observations/sample detail:')
else:
lines.append('Counts/sample detail:')
for k, v in sorted(counts_per_samp.items(), key=itemgetter(1)):
lines.append('%s: ' % k + locale.format('%1.3f', v, grouping=True))
return "\n".join(lines)
def run(self, **kwargs):
result = {}
qualitative = kwargs['qualitative']
by_observations = kwargs['observations']
table, table_lines = kwargs['table']
if by_observations:
table = table.transpose()
min_counts, max_counts, median_counts, mean_counts, counts_per_samp =\
compute_counts_per_sample_stats(table, qualitative)
num_observations = len(table.ids(axis='observation'))
counts_per_sample_values = counts_per_samp.values()
if table.metadata() is None:
sample_md_keys = ["None provided"]
else:
sample_md_keys = table.metadata()[0].keys()
if table.metadata(axis='observation') is None:
observation_md_keys = ["None provided"]
else:
observation_md_keys = table.metadata(axis='observation')[0].keys()
lines = []
num_samples = len(table.ids())
if by_observations:
# as this is a transpose of the original table...
lines.append('Num samples: %d' % num_observations)
lines.append('Num observations: %d' % num_samples)
else:
lines.append('Num samples: %d' % num_samples)
lines.append('Num observations: %d' % num_observations)
if not qualitative:
total_count = sum(counts_per_sample_values)
lines.append('Total count: %d' % total_count)
lines.append('Table density (fraction of non-zero values): %1.3f' %
table.get_table_density())
lines.append('')
if qualitative:
if by_observations:
lines.append('Sample/observations summary:')
else:
lines.append('Observations/sample summary:')
else:
lines.append('Counts/sample summary:')
lines.append(' Min: %r' % min_counts)
lines.append(' Max: %r' % max_counts)
lines.append(' Median: %1.3f' % median_counts)
lines.append(' Mean: %1.3f' % mean_counts)
lines.append(' Std. dev.: %1.3f' % std(counts_per_sample_values))
if by_observations:
# since this is a transpose...
lines.append(
' Sample Metadata Categories: %s' %
'; '.join(observation_md_keys))
lines.append(
' Observation Metadata Categories: %s' %
'; '.join(sample_md_keys))
lines.append('')
else:
lines.append(
' Sample Metadata Categories: %s' %
'; '.join(sample_md_keys))
lines.append(
' Observation Metadata Categories: %s' %
'; '.join(observation_md_keys))
lines.append('')
if qualitative:
lines.append('Observations/sample detail:')
else:
lines.append('Counts/sample detail:')
for k, v in sorted(counts_per_samp.items(), key=itemgetter(1)):
lines.append(' %s: %r' % (k, v))
result['biom_summary'] = lines
return result
def test_compute_counts_per_sample_stats_empty(self):
t = Table({}, [] ,[])
res = compute_counts_per_sample_stats(t)
self.assertEqual(res, (0, 0, 0, 0, {}))
def test_compute_counts_per_sample_stats_empty(self):
t = Table({}, [] ,[])
res = compute_counts_per_sample_stats(t)
self.assertEqual(res, (0, 0, 0, 0, {}))
def run(self, **kwargs):
result = {}
qualitative = kwargs['qualitative']
table, table_lines = kwargs['table']
min_counts, max_counts, median_counts, mean_counts, counts_per_sample =\
compute_counts_per_sample_stats(table, qualitative)
num_observations = len(table.observation_ids)
suppress_md5 = (table_lines is None) or kwargs['suppress_md5']
counts_per_sample_values = counts_per_sample.values()
if table.sample_metadata is None:
sample_md_keys = ["None provided"]
else:
sample_md_keys = table.sample_metadata[0].keys()
if table.observation_metadata is None:
observation_md_keys = ["None provided"]
else:
observation_md_keys = table.observation_metadata[0].keys()
lines = []
num_samples = len(table.sample_ids)
lines.append('Num samples: %d' % num_samples)
lines.append('Num observations: %d' % num_observations)
if not qualitative:
total_count = sum(counts_per_sample_values)
lines.append('Total count: %d' % total_count)
lines.append('Table density (fraction of non-zero values): %1.3f' %
table.get_table_density())
if not suppress_md5:
lines.append('Table md5 (unzipped): %s' % safe_md5(table_lines))
lines.append('')
if qualitative:
lines.append('Observations/sample summary:')
else:
lines.append('Counts/sample summary:')
lines.append(' Min: %r' % min_counts)
lines.append(' Max: %r' % max_counts)
lines.append(' Median: %1.3f' % median_counts)
lines.append(' Mean: %1.3f' % mean_counts)
lines.append(' Std. dev.: %1.3f' % std(counts_per_sample_values))
lines.append(
' Sample Metadata Categories: %s' %
'; '.join(sample_md_keys))
lines.append(
' Observation Metadata Categories: %s' %
'; '.join(observation_md_keys))
lines.append('')
if qualitative:
lines.append('Observations/sample detail:')
else:
lines.append('Counts/sample detail:')
for k, v in sorted(counts_per_sample.items(), key=itemgetter(1)):
lines.append(' %s: %r' % (k, v))
result['biom_summary'] = lines
return result
def run_alpha_rarefaction(otu_table_fp,
mapping_fp,
output_dir,
command_handler,
params,
qiime_config,
tree_fp=None,
num_steps=10,
parallel=False,
logger=None,
min_rare_depth=10,
max_rare_depth=None,
suppress_md5=False,
status_update_callback=print_to_stdout,
plot_stderr_and_stddev=False,
retain_intermediate_files=True):
""" Run the data preparation steps of Qiime
The steps performed by this function are:
1) Generate rarefied OTU tables;
2) Compute alpha diversity metrics for each rarefied OTU table;
3) Collate alpha diversity results;
4) Generate alpha rarefaction plots.
"""
# Prepare some variables for the later steps
otu_table_dir, otu_table_filename = split(otu_table_fp)
otu_table_basename, otu_table_ext = splitext(otu_table_filename)
create_dir(output_dir)
commands = []
if logger is None:
logger = WorkflowLogger(generate_log_fp(output_dir),
params=params,
qiime_config=qiime_config)
close_logger_on_success = True
else:
close_logger_on_success = False
if not suppress_md5:
log_input_md5s(logger, [otu_table_fp, mapping_fp, tree_fp])
if max_rare_depth is None:
min_count, max_count, median_count, mean_count, counts_per_sample =\
compute_counts_per_sample_stats(
load_table(otu_table_fp))
max_rare_depth = median_count
step = int((max_rare_depth - min_rare_depth) / num_steps) or 1
max_rare_depth = int(max_rare_depth)
rarefaction_dir = '%s/rarefaction/' % output_dir
create_dir(rarefaction_dir)
try:
params_str = get_params_str(params['multiple_rarefactions'])
except KeyError:
params_str = ''
if parallel:
params_str += ' %s' % get_params_str(params['parallel'])
# Build the rarefaction command
rarefaction_cmd = \
'parallel_multiple_rarefactions.py -T -i %s -m %s -x %s -s %s -o %s %s' %\
(otu_table_fp, min_rare_depth, max_rare_depth, step,
rarefaction_dir, params_str)
else:
# Build the rarefaction command
rarefaction_cmd = \
'multiple_rarefactions.py -i %s -m %s -x %s -s %s -o %s %s' %\
(otu_table_fp, min_rare_depth, max_rare_depth, step,
rarefaction_dir, params_str)
commands.append([('Alpha rarefaction', rarefaction_cmd)])
# Prep the alpha diversity command
alpha_diversity_dir = '%s/alpha_div/' % output_dir
create_dir(alpha_diversity_dir)
try:
params_str = get_params_str(params['alpha_diversity'])
except KeyError:
params_str = ''
if tree_fp:
params_str += ' -t %s' % tree_fp
if parallel:
params_str += ' %s' % get_params_str(params['parallel'])
# Build the alpha diversity command
alpha_diversity_cmd = \
"parallel_alpha_diversity.py -T -i %s -o %s %s" %\
(rarefaction_dir, alpha_diversity_dir, params_str)
else:
# Build the alpha diversity command
alpha_diversity_cmd = \
"alpha_diversity.py -i %s -o %s %s" %\
(rarefaction_dir, alpha_diversity_dir, params_str)
commands.append([('Alpha diversity on rarefied OTU tables',
alpha_diversity_cmd)])
# Prep the alpha diversity collation command
alpha_collated_dir = '%s/alpha_div_collated/' % output_dir
create_dir(alpha_collated_dir)
try:
params_str = get_params_str(params['collate_alpha'])
except KeyError:
params_str = ''
# Build the alpha diversity collation command
alpha_collated_cmd = 'collate_alpha.py -i %s -o %s %s' %\
(alpha_diversity_dir, alpha_collated_dir, params_str)
commands.append([('Collate alpha', alpha_collated_cmd)])
if not retain_intermediate_files:
commands.append([
('Removing intermediate files',
'rm -r %s %s' % (rarefaction_dir, alpha_diversity_dir))
])
else:
commands.append([('Skipping removal of intermediate files.', '')])
# Prep the make rarefaction plot command(s)
try:
params_str = get_params_str(params['make_rarefaction_plots'])
except KeyError:
params_str = ''
if 'std_type' in params[
'make_rarefaction_plots'] or not plot_stderr_and_stddev:
rarefaction_plot_dir = '%s/alpha_rarefaction_plots/' % output_dir
create_dir(rarefaction_plot_dir)
# Build the make rarefaction plot command(s)
# for metric in alpha_diversity_metrics:
make_rarefaction_plot_cmd =\
'make_rarefaction_plots.py -i %s -m %s -o %s %s' %\
(alpha_collated_dir, mapping_fp, rarefaction_plot_dir, params_str)
commands.append([('Rarefaction plot: %s' % 'All metrics',
make_rarefaction_plot_cmd)])
else:
rarefaction_plot_dir_stddev = '%s/alpha_rarefaction_plots_stddev/' % output_dir
rarefaction_plot_dir_stderr = '%s/alpha_rarefaction_plots_stderr/' % output_dir
create_dir(rarefaction_plot_dir_stddev)
create_dir(rarefaction_plot_dir_stderr)
# Build the make rarefaction plot command(s)
# for metric in alpha_diversity_metrics:
make_rarefaction_plot_cmd =\
'make_rarefaction_plots.py -i %s -m %s -o %s %s --std_type stddev' %\
(alpha_collated_dir, mapping_fp, rarefaction_plot_dir_stddev,
params_str)
commands.append([('Rarefaction plot: %s' % 'All metrics',
make_rarefaction_plot_cmd)])
make_rarefaction_plot_cmd =\
'make_rarefaction_plots.py -i %s -m %s -o %s %s --std_type stderr' %\
(alpha_collated_dir, mapping_fp, rarefaction_plot_dir_stderr,
params_str)
commands.append([('Rarefaction plot: %s' % 'All metrics',
make_rarefaction_plot_cmd)])
# Call the command handler on the list of commands
command_handler(commands,
status_update_callback,
logger=logger,
close_logger_on_success=close_logger_on_success)
def run_alpha_rarefaction(otu_table_fp,
mapping_fp,
output_dir,
command_handler,
params,
qiime_config,
tree_fp=None,
num_steps=10,
parallel=False,
logger=None,
min_rare_depth=10,
max_rare_depth=None,
suppress_md5=False,
status_update_callback=print_to_stdout,
plot_stderr_and_stddev=False,
retain_intermediate_files=True):
""" Run the data preparation steps of Qiime
The steps performed by this function are:
1) Generate rarefied OTU tables;
2) Compute alpha diversity metrics for each rarefied OTU table;
3) Collate alpha diversity results;
4) Generate alpha rarefaction plots.
"""
# Prepare some variables for the later steps
otu_table_dir, otu_table_filename = split(otu_table_fp)
otu_table_basename, otu_table_ext = splitext(otu_table_filename)
create_dir(output_dir)
commands = []
python_exe_fp = qiime_config['python_exe_fp']
script_dir = get_qiime_scripts_dir()
if logger == None:
logger = WorkflowLogger(generate_log_fp(output_dir),
params=params,
qiime_config=qiime_config)
close_logger_on_success = True
else:
close_logger_on_success = False
if not suppress_md5:
log_input_md5s(logger,[otu_table_fp,mapping_fp,tree_fp])
if max_rare_depth == None:
min_count, max_count, median_count, mean_count, counts_per_sample =\
compute_counts_per_sample_stats(parse_biom_table(open(otu_table_fp,'U')))
max_rare_depth = median_count
step = int((max_rare_depth - min_rare_depth) / num_steps) or 1
max_rare_depth = int(max_rare_depth)
rarefaction_dir = '%s/rarefaction/' % output_dir
create_dir(rarefaction_dir)
try:
params_str = get_params_str(params['multiple_rarefactions'])
except KeyError:
params_str = ''
if parallel:
params_str += ' %s' % get_params_str(params['parallel'])
# Build the rarefaction command
rarefaction_cmd = \
'%s %s/parallel_multiple_rarefactions.py -T -i %s -m %s -x %s -s %s -o %s %s' %\
(python_exe_fp, script_dir, otu_table_fp, min_rare_depth, max_rare_depth,
step, rarefaction_dir, params_str)
else:
# Build the rarefaction command
rarefaction_cmd = \
'%s %s/multiple_rarefactions.py -i %s -m %s -x %s -s %s -o %s %s' %\
(python_exe_fp, script_dir, otu_table_fp, min_rare_depth, max_rare_depth,
step, rarefaction_dir, params_str)
commands.append([('Alpha rarefaction', rarefaction_cmd)])
# Prep the alpha diversity command
alpha_diversity_dir = '%s/alpha_div/' % output_dir
create_dir(alpha_diversity_dir)
try:
params_str = get_params_str(params['alpha_diversity'])
except KeyError:
params_str = ''
if tree_fp:
params_str += ' -t %s' % tree_fp
if parallel:
params_str += ' %s' % get_params_str(params['parallel'])
# Build the alpha diversity command
alpha_diversity_cmd = \
"%s %s/parallel_alpha_diversity.py -T -i %s -o %s %s" %\
(python_exe_fp, script_dir, rarefaction_dir, alpha_diversity_dir,
params_str)
else:
# Build the alpha diversity command
alpha_diversity_cmd = \
"%s %s/alpha_diversity.py -i %s -o %s %s" %\
(python_exe_fp, script_dir, rarefaction_dir, alpha_diversity_dir,
params_str)
commands.append(\
[('Alpha diversity on rarefied OTU tables',alpha_diversity_cmd)])
# Prep the alpha diversity collation command
alpha_collated_dir = '%s/alpha_div_collated/' % output_dir
create_dir(alpha_collated_dir)
try:
params_str = get_params_str(params['collate_alpha'])
except KeyError:
params_str = ''
# Build the alpha diversity collation command
alpha_collated_cmd = '%s %s/collate_alpha.py -i %s -o %s %s' %\
(python_exe_fp, script_dir, alpha_diversity_dir, \
alpha_collated_dir, params_str)
commands.append([('Collate alpha',alpha_collated_cmd)])
if not retain_intermediate_files:
commands.append([('Removing intermediate files',
'rm -r %s %s' % (rarefaction_dir,alpha_diversity_dir))])
else:
commands.append([('Skipping removal of intermediate files.','')])
# Prep the make rarefaction plot command(s)
try:
params_str = get_params_str(params['make_rarefaction_plots'])
except KeyError:
params_str = ''
if 'std_type' in params['make_rarefaction_plots'] or not plot_stderr_and_stddev:
rarefaction_plot_dir = '%s/alpha_rarefaction_plots/' % output_dir
create_dir(rarefaction_plot_dir)
# Build the make rarefaction plot command(s)
#for metric in alpha_diversity_metrics:
make_rarefaction_plot_cmd =\
'%s %s/make_rarefaction_plots.py -i %s -m %s -o %s %s' %\
(python_exe_fp, script_dir, alpha_collated_dir, mapping_fp,
rarefaction_plot_dir, params_str)
commands.append(\
[('Rarefaction plot: %s' % 'All metrics',make_rarefaction_plot_cmd)])
else:
rarefaction_plot_dir_stddev = '%s/alpha_rarefaction_plots_stddev/' % output_dir
rarefaction_plot_dir_stderr = '%s/alpha_rarefaction_plots_stderr/' % output_dir
create_dir(rarefaction_plot_dir_stddev)
create_dir(rarefaction_plot_dir_stderr)
# Build the make rarefaction plot command(s)
# for metric in alpha_diversity_metrics:
make_rarefaction_plot_cmd =\
'%s %s/make_rarefaction_plots.py -i %s -m %s -o %s %s --std_type stddev' %\
(python_exe_fp, script_dir, alpha_collated_dir, mapping_fp,
rarefaction_plot_dir_stddev, params_str)
commands.append(\
[('Rarefaction plot: %s' % 'All metrics',make_rarefaction_plot_cmd)])
make_rarefaction_plot_cmd =\
'%s %s/make_rarefaction_plots.py -i %s -m %s -o %s %s --std_type stderr' %\
(python_exe_fp, script_dir, alpha_collated_dir, mapping_fp,
rarefaction_plot_dir_stderr, params_str)
commands.append(\
[('Rarefaction plot: %s' % 'All metrics',make_rarefaction_plot_cmd)])
# Call the command handler on the list of commands
command_handler(commands,
status_update_callback,
logger=logger,
close_logger_on_success=close_logger_on_success)
def main():
opts,args = parser.parse_args()
if opts.input_fp is None:
parser.print_help()
parser.error('Must specify an input file!')
input_fp = opts.input_fp
output_fp = opts.output_fp
table = parse_biom_table(biom_open(input_fp,'U'))
min_counts, max_counts, median_counts, mean_counts, counts_per_sample =\
compute_counts_per_sample_stats(table, opts.num_observations)
num_observations = len(table.ObservationIds)
suppress_md5 = opts.suppress_md5
counts_per_sample_values = counts_per_sample.values()
try:
sample_md_keys = table.SampleMetadata[0].keys()
except TypeError:
sample_md_keys = ["None provided"]
try:
observation_md_keys = table.ObservationMetadata[0].keys()
except TypeError:
observation_md_keys = ["None provided"]
lines = []
num_samples = len(counts_per_sample)
lines.append('Num samples: %s' % str(num_samples))
lines.append('Num observations: %s' % str(num_observations))
if not opts.num_observations:
total_count = sum(counts_per_sample_values)
lines.append('Total count: %s' % str(total_count))
lines.append('Table density (fraction of non-zero values): %1.4f' % \
table.getTableDensity())
if not suppress_md5:
lines.append('Table md5 (unzipped): %s' % safe_md5(biom_open(input_fp,'U')))
lines.append('')
if opts.num_observations:
lines.append('Observations/sample summary:')
else:
lines.append('Counts/sample summary:')
lines.append(' Min: %s' % str(min_counts))
lines.append(' Max: %s' % str(max_counts))
lines.append(' Median: %s' % str(median_counts))
lines.append(' Mean: %s' % str(mean_counts))
lines.append(' Std. dev.: %s' % (str(std(counts_per_sample_values))))
lines.append(' Sample Metadata Categories: %s' % '; '.join(sample_md_keys))
lines.append(' Observation Metadata Categories: %s' % '; '.join(observation_md_keys))
lines.append('')
if opts.num_observations:
lines.append('Observations/sample detail:')
else:
lines.append('Counts/sample detail:')
sorted_counts_per_sample = [(v,k) for k,v in counts_per_sample.items()]
sorted_counts_per_sample.sort()
for v,k in sorted_counts_per_sample:
lines.append(' %s: %s' % (k,str(v)))
if output_fp != None:
open(output_fp,'w').write('\n'.join(lines))
else:
print '\n'.join(lines)
