def main():
option_parser, opts, args = parse_command_line_parameters(**script_info)
if len(opts.taxa_summary_fps) != 2:
option_parser.error("Exactly two taxa summary files are required. You "
"provided %d." % len(opts.taxa_summary_fps))
# Create the output dir if it doesn't already exist.
try:
create_dir(opts.output_dir)
except:
option_parser.error("Could not create or access output directory "
"specified with the -o option.")
sample_id_map = None
if opts.sample_id_map_fp:
sample_id_map = parse_sample_id_map(open(opts.sample_id_map_fp, 'U'))
results = compare_taxa_summaries(
parse_taxa_summary_table(open(opts.taxa_summary_fps[0], 'U')),
parse_taxa_summary_table(open(opts.taxa_summary_fps[1], 'U')),
opts.comparison_mode,
correlation_type=opts.correlation_type,
tail_type=opts.tail_type,
num_permutations=opts.num_permutations,
confidence_level=opts.confidence_level,
perform_detailed_comparisons=opts.perform_detailed_comparisons,
sample_id_map=sample_id_map,
expected_sample_id=opts.expected_sample_id)
# Write out the sorted and filled taxa summaries, basing their
# filenames on the original input filenames. If the filenames are the same,
# append a number to each filename.
same_filenames = False
if basename(opts.taxa_summary_fps[0]) == \
basename(opts.taxa_summary_fps[1]):
same_filenames = True
for orig_ts_fp, filled_ts_lines, file_num in zip(opts.taxa_summary_fps,
results[:2], range(0, 2)):
filename_suffix = '_sorted_and_filled'
if same_filenames:
filename_suffix += '_%d' % file_num
filled_ts_fp = add_filename_suffix(orig_ts_fp, filename_suffix)
filled_ts_f = open(join(opts.output_dir, filled_ts_fp), 'w')
filled_ts_f.write(filled_ts_lines)
filled_ts_f.close()
# Write the overall comparison result.
overall_comp_f = open(join(opts.output_dir, 'overall_comparison.txt'), 'w')
overall_comp_f.write(results[2])
overall_comp_f.close()
# Write the correlation vector containing the pairwise sample comparisons.
if opts.perform_detailed_comparisons:
corr_vec_f = open(join(opts.output_dir, 'detailed_comparisons.txt'),
'w')
corr_vec_f.write(results[3])
corr_vec_f.close()
def main():
option_parser, opts, args = parse_command_line_parameters(**script_info)
if len(opts.taxa_summary_fps) != 2:
option_parser.error("Exactly two taxa summary files are required. You "
"provided %d." % len(opts.taxa_summary_fps))
# Create the output dir if it doesn't already exist.
try:
create_dir(opts.output_dir)
except:
option_parser.error("Could not create or access output directory "
"specified with the -o option.")
sample_id_map = None
if opts.sample_id_map_fp:
sample_id_map = parse_sample_id_map(open(opts.sample_id_map_fp, 'U'))
results = compare_taxa_summaries(
parse_taxa_summary_table(open(opts.taxa_summary_fps[0], 'U')),
parse_taxa_summary_table(open(opts.taxa_summary_fps[1], 'U')),
opts.comparison_mode, correlation_type=opts.correlation_type,
tail_type=opts.tail_type, num_permutations=opts.num_permutations,
confidence_level=opts.confidence_level,
perform_detailed_comparisons=opts.perform_detailed_comparisons,
sample_id_map=sample_id_map,
expected_sample_id=opts.expected_sample_id)
# Write out the sorted and filled taxa summaries, basing their
# filenames on the original input filenames. If the filenames are the same,
# append a number to each filename.
same_filenames = False
if basename(opts.taxa_summary_fps[0]) == \
basename(opts.taxa_summary_fps[1]):
same_filenames = True
for orig_ts_fp, filled_ts_lines, file_num in zip(opts.taxa_summary_fps,
results[:2], range(0, 2)):
filename_suffix = '_sorted_and_filled'
if same_filenames:
filename_suffix += '_%d' % file_num
filled_ts_fp = add_filename_suffix(orig_ts_fp, filename_suffix)
filled_ts_f = open(join(opts.output_dir, filled_ts_fp), 'w')
filled_ts_f.write(filled_ts_lines)
filled_ts_f.close()
# Write the overall comparison result.
overall_comp_f = open(join(opts.output_dir, 'overall_comparison.txt'), 'w')
overall_comp_f.write(results[2])
overall_comp_f.close()
# Write the correlation vector containing the pairwise sample comparisons.
if opts.perform_detailed_comparisons:
corr_vec_f = open(join(opts.output_dir,
'detailed_comparisons.txt'), 'w')
corr_vec_f.write(results[3])
corr_vec_f.close()
def _generate_taxa_processing_commands(assigned_taxonomy_dir, input_fasta_fp,
clean_otu_table_fp, run_id):
""" Build command strings for adding and summarizing taxa commands. These
are used with every method. """
taxa_assignments_fp = join(assigned_taxonomy_dir,
splitext(basename(input_fasta_fp))[0] + '_tax_assignments.txt')
otu_table_w_taxa_fp = join(assigned_taxonomy_dir,
add_filename_suffix(clean_otu_table_fp, '_w_taxa'))
add_md_command = [('Adding metadata (%s)' % run_id,
'biom add-metadata -i %s -o %s '
'--observation-metadata-fp %s --sc-separated taxonomy '
'--observation-header OTUID,taxonomy' %
(clean_otu_table_fp, otu_table_w_taxa_fp,
taxa_assignments_fp))]
summarize_taxa_command = [('Summarizing taxa (%s)' % run_id,
'summarize_taxa.py -i %s -o %s' %
(otu_table_w_taxa_fp, assigned_taxonomy_dir))]
return add_md_command, summarize_taxa_command
def _generate_taxa_processing_commands(assigned_taxonomy_dir, input_fasta_fp,
clean_otu_table_fp, run_id):
""" Build command strings for adding and summarizing taxa commands. These
are used with every method. """
taxa_assignments_fp = join(
assigned_taxonomy_dir,
splitext(basename(input_fasta_fp))[0] + '_tax_assignments.txt')
otu_table_w_taxa_fp = join(
assigned_taxonomy_dir,
add_filename_suffix(clean_otu_table_fp, '_w_taxa'))
add_taxa_command = [
('Adding taxa (%s)' % run_id, 'add_taxa.py -i %s -o %s -t %s' %
(clean_otu_table_fp, otu_table_w_taxa_fp, taxa_assignments_fp))
]
summarize_taxa_command = [
('Summarizing taxa (%s)' % run_id, 'summarize_taxa.py -i %s -o %s' %
(otu_table_w_taxa_fp, assigned_taxonomy_dir))
]
return add_taxa_command, summarize_taxa_command
def _build_simulated_data_commands(analysis_type, out_dir, even_otu_table_fp,
map_fp, tree_fp, workflow):
cmds = []
data_type_dir = join(out_dir, 'simulated')
create_dir(data_type_dir)
num_samps = get_num_samples_in_table(even_otu_table_fp)
for category in workflow['categories']:
category_dir = join(data_type_dir, category[0])
create_dir(category_dir)
for trial_num in range(workflow['num_sim_data_trials']):
trial_num_dir = join(category_dir, '%d' % trial_num)
create_dir(trial_num_dir)
for samp_size in workflow['sample_sizes']:
samp_size_dir = join(trial_num_dir, '%d' % samp_size)
create_dir(samp_size_dir)
# Lots of duplicate code between these two blocks...
# need to refactor and test.
if samp_size <= num_samps:
simsam_rep_num = 1
subset_otu_table_fp = join(samp_size_dir, basename(even_otu_table_fp))
subset_map_fp = join(samp_size_dir, basename(map_fp))
if not has_results(samp_size_dir, required_files=[basename(subset_otu_table_fp), basename(subset_map_fp)]):
run_command('choose_data_subset.py -t %s -i %s -m %s -c %s -n %d -o %s' % (analysis_type, even_otu_table_fp, map_fp, category[0], samp_size, samp_size_dir))
assert get_num_samples_in_table(subset_otu_table_fp) == samp_size
assert get_num_samples_in_map(subset_map_fp) == samp_size
for d in workflow['dissim']:
dissim_dir = join(samp_size_dir, repr(d))
create_dir(dissim_dir)
simsam_map_fp = join(dissim_dir, add_filename_suffix(subset_map_fp, '_n%d_d%r' % (simsam_rep_num, d)))
simsam_otu_table_fp = join(dissim_dir, add_filename_suffix(subset_otu_table_fp, '_n%d_d%r' % (simsam_rep_num, d)))
# Check for simulated table/map and various
# distance matrices / coordinates files.
required_simsam_files = [basename(simsam_map_fp), basename(simsam_otu_table_fp)]
has_simsam_files = has_results(dissim_dir, required_files=required_simsam_files)
has_metric_files = True
for metric in workflow['metrics']:
required_metric_files = ['dm.txt', 'map.txt', 'pc.txt']
if analysis_type == 'gradient':
required_metric_files.append('%s_dm.txt' % category[0])
metric_dir = join(dissim_dir, metric[0])
has_metric_files = has_results(metric_dir, required_metric_files)
if not has_metric_files:
break
if not (has_simsam_files and has_metric_files):
cmd = ['simsam.py -i %s -t %s -o %s -d %r -n %d -m %s' % (subset_otu_table_fp, tree_fp, dissim_dir, d, simsam_rep_num, subset_map_fp)]
for metric in workflow['metrics']:
metric_dir = join(dissim_dir, metric[0])
create_dir(metric_dir)
if analysis_type == 'gradient':
cmd.append('distance_matrix_from_mapping.py -i %s -c %s -o %s' % (simsam_map_fp, category[0], join(metric_dir, '%s_dm.txt' % category[0])))
cmd.append('beta_diversity.py -i %s -o %s -m %s -t %s' % (simsam_otu_table_fp, metric_dir, metric[0], tree_fp))
cmd.append('mv %s %s' % (join(metric_dir, '%s_%s.txt' % (metric[0], splitext(basename(simsam_otu_table_fp))[0])), join(metric_dir, 'dm.txt')))
cmd.append('cp %s %s' % (simsam_map_fp, join(metric_dir, 'map.txt')))
cmd.append('principal_coordinates.py -i %s -o %s' % (join(metric_dir, 'dm.txt'), join(metric_dir, 'pc.txt')))
cmds.append(' && '.join(cmd))
else:
# We need to simulate more samples than we originally have.
simsam_rep_num = get_simsam_rep_num(samp_size, num_samps)
for d in workflow['dissim']:
dissim_dir = join(samp_size_dir, repr(d))
create_dir(dissim_dir)
simsam_map_fp = join(dissim_dir, add_filename_suffix(map_fp, '_n%d_d%r' % (simsam_rep_num, d)))
simsam_otu_table_fp = join(dissim_dir, add_filename_suffix(even_otu_table_fp, '_n%d_d%r' % (simsam_rep_num, d)))
required_simsam_files = [basename(simsam_map_fp), basename(simsam_otu_table_fp)]
has_simsam_files = has_results(dissim_dir, required_files=required_simsam_files)
required_subset_files = [basename(simsam_map_fp), basename(simsam_otu_table_fp)]
has_subset_files = has_results(join(dissim_dir, 'subset'), required_files=required_subset_files)
has_metric_files = True
for metric in workflow['metrics']:
required_metric_files = ['dm.txt', 'map.txt', 'pc.txt']
if analysis_type == 'gradient':
required_metric_files.append('%s_dm.txt' % category[0])
metric_dir = join(dissim_dir, metric[0])
has_metric_files = has_results(metric_dir, required_metric_files)
if not has_metric_files:
break
if not (has_simsam_files and has_subset_files and has_metric_files):
cmd = ['simsam.py -i %s -t %s -o %s -d %r -n %d -m %s' % (even_otu_table_fp, tree_fp, dissim_dir, d, simsam_rep_num, map_fp)]
subset_dir = join(dissim_dir, 'subset')
cmd.append('choose_data_subset.py -t %s -i %s -m %s -c %s -n %d -o %s' % (analysis_type, simsam_otu_table_fp, simsam_map_fp, category[0], samp_size, subset_dir))
subset_otu_table_fp = join(subset_dir, basename(simsam_otu_table_fp))
subset_map_fp = join(subset_dir, basename(simsam_map_fp))
for metric in workflow['metrics']:
metric_dir = join(dissim_dir, metric[0])
create_dir(metric_dir)
if analysis_type == 'gradient':
cmd.append('distance_matrix_from_mapping.py -i %s -c %s -o %s' % (subset_map_fp, category[0], join(metric_dir, '%s_dm.txt' % category[0])))
cmd.append('beta_diversity.py -i %s -o %s -m %s -t %s' % (subset_otu_table_fp, metric_dir, metric[0], tree_fp))
cmd.append('mv %s %s' % (join(metric_dir, '%s_%s.txt' % (metric[0], splitext(basename(subset_otu_table_fp))[0])), join(metric_dir, 'dm.txt')))
cmd.append('cp %s %s' % (subset_map_fp, join(metric_dir, 'map.txt')))
cmd.append('principal_coordinates.py -i %s -o %s' % (join(metric_dir, 'dm.txt'), join(metric_dir, 'pc.txt')))
cmds.append(' && '.join(cmd))
return cmds
def create_personal_results(
output_dir,
mapping_fp,
coord_fp,
collated_dir,
otu_table_fp,
prefs_fp,
personal_id_column,
personal_ids=None,
column_title="Self",
individual_titles=None,
category_to_split="BodySite",
time_series_category="WeeksSinceStart",
rarefaction_depth=10000,
alpha=0.05,
rep_set_fp=None,
body_site_rarefied_otu_table_dir=None,
retain_raw_data=False,
suppress_alpha_rarefaction=False,
suppress_beta_diversity=False,
suppress_taxa_summary_plots=False,
suppress_alpha_diversity_boxplots=False,
suppress_otu_category_significance=False,
command_handler=call_commands_serially,
status_update_callback=no_status_updates,
):
# Create our output directory and copy over the resources the personalized
# pages need (e.g. javascript, images, etc.).
create_dir(output_dir)
support_files_dir = join(output_dir, "support_files")
if not exists(support_files_dir):
copytree(join(get_project_dir(), "my_microbes", "support_files"), support_files_dir)
logger = WorkflowLogger(generate_log_fp(output_dir))
mapping_data, header, comments = parse_mapping_file(open(mapping_fp, "U"))
try:
personal_id_index = header.index(personal_id_column)
except ValueError:
raise ValueError("Personal ID field '%s' is not a mapping file column " "header." % personal_id_column)
try:
bodysite_index = header.index(category_to_split)
except ValueError:
raise ValueError("Category to split field '%s' is not a mapping file " "column header." % category_to_split)
header = header[:-1] + [column_title] + [header[-1]]
# column that differentiates between body-sites within a single individual
# used for the creation of the vectors in make_3d_plots.py, this data is
# created by concatenating the two columns when writing the mapping file
site_id_category = "%s&&%s" % (personal_id_column, category_to_split)
header.insert(len(header) - 1, site_id_category)
all_personal_ids = get_personal_ids(mapping_data, personal_id_index)
if personal_ids == None:
personal_ids = all_personal_ids
else:
for pid in personal_ids:
if pid not in all_personal_ids:
raise ValueError(
"'%s' is not a personal ID in the mapping " "file column '%s'." % (pid, personal_id_column)
)
if time_series_category not in header:
raise ValueError("Time series field '%s' is not a mapping file column " "header." % time_series_category)
otu_table_title = splitext(basename(otu_table_fp))
output_directories = []
raw_data_files = []
raw_data_dirs = []
# Rarefy the OTU table and split by body site here (instead of on a
# per-individual basis) as we can use the same rarefied and split tables
# for each individual.
if not suppress_otu_category_significance:
rarefied_otu_table_fp = join(output_dir, add_filename_suffix(otu_table_fp, "_even%d" % rarefaction_depth))
if body_site_rarefied_otu_table_dir is None:
commands = []
cmd_title = "Rarefying OTU table"
cmd = "single_rarefaction.py -i %s -o %s -d %s" % (otu_table_fp, rarefied_otu_table_fp, rarefaction_depth)
commands.append([(cmd_title, cmd)])
raw_data_files.append(rarefied_otu_table_fp)
per_body_site_dir = join(output_dir, "per_body_site_otu_tables")
cmd_title = "Splitting rarefied OTU table by body site"
cmd = "split_otu_table.py -i %s -m %s -f %s -o %s" % (
rarefied_otu_table_fp,
mapping_fp,
category_to_split,
per_body_site_dir,
)
commands.append([(cmd_title, cmd)])
raw_data_dirs.append(per_body_site_dir)
command_handler(commands, status_update_callback, logger, close_logger_on_success=False)
else:
per_body_site_dir = body_site_rarefied_otu_table_dir
for person_of_interest in personal_ids:
# Files to clean up on a per-individual basis.
personal_raw_data_files = []
personal_raw_data_dirs = []
create_dir(join(output_dir, person_of_interest))
personal_mapping_file_fp = join(output_dir, person_of_interest, "mapping_file.txt")
html_fp = join(output_dir, person_of_interest, "index.html")
personal_mapping_data = create_personal_mapping_file(
mapping_data, person_of_interest, personal_id_index, bodysite_index, individual_titles
)
personal_mapping_f = open(personal_mapping_file_fp, "w")
personal_mapping_f.write(format_mapping_file(header, personal_mapping_data, comments))
personal_mapping_f.close()
personal_raw_data_files.append(personal_mapping_file_fp)
column_title_index = header.index(column_title)
column_title_values = set([e[column_title_index] for e in personal_mapping_data])
cat_index = header.index(category_to_split)
cat_values = set([e[cat_index] for e in personal_mapping_data])
# Generate alpha diversity boxplots, split by body site, one per
# metric. We run this one first because it completes relatively
# quickly and it does not call any QIIME scripts.
alpha_diversity_boxplots_html = ""
if not suppress_alpha_diversity_boxplots:
adiv_boxplots_dir = join(output_dir, person_of_interest, "adiv_boxplots")
create_dir(adiv_boxplots_dir)
output_directories.append(adiv_boxplots_dir)
logger.write("\nGenerating alpha diversity boxplots (%s)\n\n" % person_of_interest)
plot_filenames = _generate_alpha_diversity_boxplots(
collated_dir,
personal_mapping_file_fp,
category_to_split,
column_title,
rarefaction_depth,
adiv_boxplots_dir,
)
# Create relative paths for use with the index page.
rel_boxplot_dir = basename(normpath(adiv_boxplots_dir))
plot_fps = [join(rel_boxplot_dir, plot_filename) for plot_filename in plot_filenames]
alpha_diversity_boxplots_html = create_alpha_diversity_boxplots_html(plot_fps)
## Alpha rarefaction steps
if not suppress_alpha_rarefaction:
rarefaction_dir = join(output_dir, person_of_interest, "alpha_rarefaction")
output_directories.append(rarefaction_dir)
commands = []
cmd_title = "Creating rarefaction plots (%s)" % person_of_interest
cmd = "make_rarefaction_plots.py -i %s -m %s -p %s -o %s" % (
collated_dir,
personal_mapping_file_fp,
prefs_fp,
rarefaction_dir,
)
commands.append([(cmd_title, cmd)])
personal_raw_data_dirs.append(join(rarefaction_dir, "average_plots"))
personal_raw_data_dirs.append(join(rarefaction_dir, "average_tables"))
command_handler(commands, status_update_callback, logger, close_logger_on_success=False)
## Beta diversity steps
if not suppress_beta_diversity:
pcoa_dir = join(output_dir, person_of_interest, "beta_diversity")
pcoa_time_series_dir = join(output_dir, person_of_interest, "beta_diversity_time_series")
output_directories.append(pcoa_dir)
output_directories.append(pcoa_time_series_dir)
commands = []
cmd_title = "Creating beta diversity time series plots (%s)" % person_of_interest
cmd = "make_3d_plots.py -m %s -p %s -i %s -o %s --custom_axes=" % (
personal_mapping_file_fp,
prefs_fp,
coord_fp,
pcoa_time_series_dir,
) + "'%s' --add_vectors='%s,%s'" % (time_series_category, site_id_category, time_series_category)
commands.append([(cmd_title, cmd)])
cmd_title = "Creating beta diversity plots (%s)" % person_of_interest
cmd = "make_3d_plots.py -m %s -p %s -i %s -o %s" % (personal_mapping_file_fp, prefs_fp, coord_fp, pcoa_dir)
commands.append([(cmd_title, cmd)])
command_handler(commands, status_update_callback, logger, close_logger_on_success=False)
## Time series taxa summary plots steps
taxa_summary_plots_html = ""
if not suppress_taxa_summary_plots:
area_plots_dir = join(output_dir, person_of_interest, "time_series")
create_dir(area_plots_dir)
output_directories.append(area_plots_dir)
files_to_remove, dirs_to_remove = _generate_taxa_summary_plots(
otu_table_fp,
personal_mapping_file_fp,
person_of_interest,
column_title,
column_title_values,
category_to_split,
cat_values,
time_series_category,
area_plots_dir,
command_handler,
status_update_callback,
logger,
)
personal_raw_data_files.extend(files_to_remove)
personal_raw_data_dirs.extend(dirs_to_remove)
taxa_summary_plots_html = create_taxa_summary_plots_html(output_dir, person_of_interest, cat_values)
# Generate OTU category significance tables (per body site).
otu_cat_sig_output_fps = []
otu_category_significance_html = ""
if not suppress_otu_category_significance:
otu_cat_sig_dir = join(output_dir, person_of_interest, "otu_category_significance")
create_dir(otu_cat_sig_dir)
output_directories.append(otu_cat_sig_dir)
# For each body-site rarefied OTU table, run
# otu_category_significance.py using self versus other category.
# Keep track of each output file that is created because we need to
# parse these later on.
commands = []
valid_body_sites = []
for cat_value in cat_values:
body_site_otu_table_fp = join(
per_body_site_dir, add_filename_suffix(rarefied_otu_table_fp, "_%s" % cat_value)
)
if exists(body_site_otu_table_fp):
# Make sure we have at least one sample for Self, otherwise
# otu_category_significance.py crashes with a division by
# zero error.
with open(body_site_otu_table_fp, "U") as body_site_otu_table_f, open(
personal_mapping_file_fp, "U"
) as personal_mapping_file_f:
personal_sample_count = _count_per_individual_samples(
body_site_otu_table_f, personal_mapping_file_f, personal_id_column, person_of_interest
)
if personal_sample_count < 1:
continue
else:
valid_body_sites.append(cat_value)
otu_cat_output_fp = join(otu_cat_sig_dir, "otu_cat_sig_%s.txt" % cat_value)
cmd_title = "Testing for significant differences in " 'OTU abundances in "%s" body site (%s)' % (
cat_value,
person_of_interest,
)
cmd = "otu_category_significance.py -i %s -m %s -c %s " "-o %s" % (
body_site_otu_table_fp,
personal_mapping_file_fp,
column_title,
otu_cat_output_fp,
)
commands.append([(cmd_title, cmd)])
personal_raw_data_files.append(otu_cat_output_fp)
otu_cat_sig_output_fps.append(otu_cat_output_fp)
# Hack to allow print-only mode.
if command_handler is not print_commands and not valid_body_sites:
raise ValueError(
"None of the body sites for personal ID '%s' "
"could be processed because there were no "
"matching samples in the rarefied OTU table." % person_of_interest
)
command_handler(commands, status_update_callback, logger, close_logger_on_success=False)
# Reformat otu category significance tables.
otu_cat_sig_html_filenames = create_otu_category_significance_html_tables(
otu_cat_sig_output_fps, alpha, otu_cat_sig_dir, individual_titles, rep_set_fp=rep_set_fp
)
# Create relative paths for use with the index page.
rel_otu_cat_sig_dir = basename(normpath(otu_cat_sig_dir))
otu_cat_sig_html_fps = [
join(rel_otu_cat_sig_dir, html_filename) for html_filename in otu_cat_sig_html_filenames
]
otu_category_significance_html = create_otu_category_significance_html(otu_cat_sig_html_fps)
# Create the index.html file for the current individual.
create_index_html(
person_of_interest,
html_fp,
taxa_summary_plots_html=taxa_summary_plots_html,
alpha_diversity_boxplots_html=alpha_diversity_boxplots_html,
otu_category_significance_html=otu_category_significance_html,
)
# Clean up the unnecessary raw data files and directories for the
# current individual. glob will only grab paths that exist.
if not retain_raw_data:
clean_up_raw_data_files(personal_raw_data_files, personal_raw_data_dirs)
# Clean up any remaining raw data files that weren't created on a
# per-individual basis.
if not retain_raw_data:
clean_up_raw_data_files(raw_data_files, raw_data_dirs)
logger.close()
return output_directories
def _generate_taxa_summary_plots(
otu_table_fp,
personal_map_fp,
personal_id,
personal_cat,
personal_cat_values,
body_site_cat,
body_site_cat_values,
time_series_cat,
output_dir,
command_handler,
status_update_callback,
logger,
):
files_to_remove = []
dirs_to_remove = []
## Split OTU table into self/other per-body-site tables
commands = []
cmd_title = "Splitting OTU table into self/other (%s)" % personal_id
cmd = "split_otu_table.py -i %s -m %s -f %s -o %s" % (otu_table_fp, personal_map_fp, personal_cat, output_dir)
commands.append([(cmd_title, cmd)])
command_handler(commands, status_update_callback, logger, close_logger_on_success=False)
# Prefix to be used for taxa summary dirs. Will be
# <taxa_summary_dir_prefix>_<self|other>_<body site>/.
ts_dir_prefix = "taxa_summaries"
# Create taxa summaries for self and other, per body site.
for personal_cat_value in personal_cat_values:
personal_cat_biom_fp = join(output_dir, add_filename_suffix(otu_table_fp, "_%s" % personal_cat_value))
personal_cat_map_fp = join(output_dir, "mapping_%s.txt" % personal_cat_value)
files_to_remove.append(personal_cat_biom_fp)
files_to_remove.append(personal_cat_map_fp)
body_site_dir = join(output_dir, personal_cat_value)
commands = []
cmd_title = 'Splitting "%s" OTU table by body site (%s)' % (personal_cat_value, personal_id)
cmd = "split_otu_table.py -i %s -m %s -f %s -o %s" % (
personal_cat_biom_fp,
personal_map_fp,
body_site_cat,
body_site_dir,
)
commands.append([(cmd_title, cmd)])
dirs_to_remove.append(body_site_dir)
command_handler(commands, status_update_callback, logger, close_logger_on_success=False)
commands = []
for body_site_cat_value in body_site_cat_values:
body_site_otu_table_fp = join(
body_site_dir, add_filename_suffix(personal_cat_biom_fp, "_%s" % body_site_cat_value)
)
# We won't always get an OTU table if the mapping file
# category contains samples that aren't in the OTU table
# (e.g. the 'na' state for body site).
if exists(body_site_otu_table_fp):
ts_dir = join(output_dir, "%s_%s_%s" % (ts_dir_prefix, personal_cat_value, body_site_cat_value))
create_dir(ts_dir)
dirs_to_remove.append(ts_dir)
# Summarize.
summarized_otu_table_fp = join(ts_dir, "%s_otu_table.biom" % time_series_cat)
cmd_title = "Summarizing OTU table by category (%s)" % personal_id
cmd = "summarize_otu_by_cat.py -i %s -c %s -o %s " "-m %s " % (
personal_map_fp,
body_site_otu_table_fp,
summarized_otu_table_fp,
time_series_cat,
)
commands.append([(cmd_title, cmd)])
# Sort.
sorted_otu_table_fp = join(ts_dir, "%s_otu_table_sorted.biom" % time_series_cat)
cmd_title = "Sorting OTU table (%s)" % personal_id
cmd = "sort_otu_table.py -i %s -o %s" % (summarized_otu_table_fp, sorted_otu_table_fp)
commands.append([(cmd_title, cmd)])
# Summarize taxa.
cmd_title = "Summarizing taxa (%s)" % personal_id
cmd = "summarize_taxa.py -i %s -o %s" % (sorted_otu_table_fp, ts_dir)
commands.append([(cmd_title, cmd)])
create_comparative_taxa_plots_html(
body_site_cat_value, join(output_dir, "%s_comparative.html" % body_site_cat_value)
)
command_handler(commands, status_update_callback, logger, close_logger_on_success=False)
# Make each corresponding taxa summary compatible so that coloring matches
# between them. We want to be able to compare self versus other at each
# body site.
commands = []
valid_body_sites = []
for body_site_cat_value in body_site_cat_values:
personal_cat_vals = list(personal_cat_values)
ts_dir = join(output_dir, "%s_%s_%s" % (ts_dir_prefix, personal_cat_vals[0], body_site_cat_value))
if not exists(ts_dir):
continue
# Check that we have 2+ weeks (samples were previously collapsed into
# weeks for self and other). If we don't have 2+ weeks,
# plot_taxa_summary.py will fail, so we'll skip this body site.
weeks_otu_table_fp = join(ts_dir, "%s_otu_table_sorted.biom" % time_series_cat)
with open(weeks_otu_table_fp, "U") as weeks_otu_table_f:
if _count_num_samples(weeks_otu_table_f) < 2:
continue
ts_fps1 = sorted(glob(join(ts_dir, "%s_otu_table_sorted_L*.txt" % time_series_cat)))
ts_dir = join(output_dir, "%s_%s_%s" % (ts_dir_prefix, personal_cat_vals[1], body_site_cat_value))
if not exists(ts_dir):
continue
weeks_otu_table_fp = join(ts_dir, "%s_otu_table_sorted.biom" % time_series_cat)
with open(weeks_otu_table_fp, "U") as weeks_otu_table_f:
if _count_num_samples(weeks_otu_table_f) < 2:
continue
ts_fps2 = sorted(glob(join(ts_dir, "%s_otu_table_sorted_L*.txt" % time_series_cat)))
if len(ts_fps1) != len(ts_fps2):
raise ValueError("There are not an equal number of taxa summaries " "to compare between self and other.")
compatible_ts_dir = join(output_dir, "compatible_ts_%s" % body_site_cat_value)
dirs_to_remove.append(compatible_ts_dir)
compatible_ts_fps = defaultdict(list)
for ts_fp1, ts_fp2 in zip(ts_fps1, ts_fps2):
if basename(ts_fp1) != basename(ts_fp2):
raise ValueError("Could not find matching taxa summaries " "between self and other to compare.")
# Make taxa summaries compatible.
cmd_title = "Making compatible taxa summaries (%s)" % personal_id
cmd = "compare_taxa_summaries.py -i %s,%s -o %s -m paired -n 0" % (ts_fp1, ts_fp2, compatible_ts_dir)
commands.append([(cmd_title, cmd)])
compatible_ts_fps[personal_cat_vals[0]].append(
join(compatible_ts_dir, add_filename_suffix(ts_fp1, "_sorted_and_filled_0"))
)
compatible_ts_fps[personal_cat_vals[1]].append(
join(compatible_ts_dir, add_filename_suffix(ts_fp2, "_sorted_and_filled_1"))
)
for personal_cat_value in personal_cat_values:
# Plot taxa summaries.
ts_fps = ",".join(sorted(compatible_ts_fps[personal_cat_value]))
ts_plots_dir = join(
output_dir, "taxa_plots_%s_%s" % (personal_cat_value, body_site_cat_value), "taxa_summary_plots"
)
cmd_title = "Plot taxa summaries (%s)" % personal_id
cmd = "plot_taxa_summary.py -i %s -o %s -a numeric" % (ts_fps, ts_plots_dir)
commands.append([(cmd_title, cmd)])
# If we've gotten this far, we'll be able to process this body site
# (i.e. there are enough weeks).
valid_body_sites.append(body_site_cat_value)
# Hack to allow print-only mode.
if command_handler is not print_commands and not valid_body_sites:
raise ValueError(
"None of the body sites for personal ID '%s' could "
"be processed because there were not enough weeks "
"to create taxa summary plots." % personal_id
)
command_handler(commands, status_update_callback, logger, close_logger_on_success=False)
return files_to_remove, dirs_to_remove
def create_personal_results(output_dir,
mapping_fp,
coord_fp,
collated_dir,
otu_table_fp,
prefs_fp,
personal_id_column,
personal_ids=None,
column_title='Self',
individual_titles=None,
category_to_split='BodySite',
time_series_category='WeeksSinceStart',
rarefaction_depth=10000,
alpha=0.05,
rep_set_fp=None,
parameter_fp=None,
body_site_rarefied_otu_table_dir=None,
retain_raw_data=False,
suppress_alpha_rarefaction=False,
suppress_beta_diversity=False,
suppress_taxa_summary_plots=False,
suppress_alpha_diversity_boxplots=False,
suppress_otu_category_significance=False,
command_handler=call_commands_serially,
status_update_callback=no_status_updates):
# Create our output directory and copy over the resources the personalized
# pages need (e.g. javascript, images, etc.).
create_dir(output_dir)
support_files_dir = join(output_dir, 'support_files')
if not exists(support_files_dir):
copytree(join(get_project_dir(), 'my_microbes', 'support_files'),
support_files_dir)
logger = WorkflowLogger(generate_log_fp(output_dir))
mapping_data, header, comments = parse_mapping_file(open(mapping_fp, 'U'))
try:
personal_id_index = header.index(personal_id_column)
except ValueError:
raise ValueError("Personal ID field '%s' is not a mapping file column "
"header." % personal_id_column)
try:
bodysite_index = header.index(category_to_split)
except ValueError:
raise ValueError("Category to split field '%s' is not a mapping file "
"column header." % category_to_split)
header = header[:-1] + [column_title] + [header[-1]]
# column that differentiates between body-sites within a single individual
# used for the creation of the vectors in make_3d_plots.py, this data is
# created by concatenating the two columns when writing the mapping file
site_id_category = '%s&&%s' % (personal_id_column, category_to_split)
header.insert(len(header)-1, site_id_category)
all_personal_ids = get_personal_ids(mapping_data, personal_id_index)
if personal_ids == None:
personal_ids = all_personal_ids
else:
for pid in personal_ids:
if pid not in all_personal_ids:
raise ValueError("'%s' is not a personal ID in the mapping "
"file column '%s'." %
(pid, personal_id_column))
if time_series_category not in header:
raise ValueError("Time series field '%s' is not a mapping file column "
"header." % time_series_category)
otu_table_title = splitext(basename(otu_table_fp))
output_directories = []
raw_data_files = []
raw_data_dirs = []
# Rarefy the OTU table and split by body site here (instead of on a
# per-individual basis) as we can use the same rarefied and split tables
# for each individual.
if not suppress_otu_category_significance:
rarefied_otu_table_fp = join(output_dir,
add_filename_suffix(otu_table_fp,
'_even%d' % rarefaction_depth))
if body_site_rarefied_otu_table_dir is None:
commands = []
cmd_title = 'Rarefying OTU table'
cmd = 'single_rarefaction.py -i %s -o %s -d %s' % (otu_table_fp,
rarefied_otu_table_fp, rarefaction_depth)
commands.append([(cmd_title, cmd)])
raw_data_files.append(rarefied_otu_table_fp)
per_body_site_dir = join(output_dir, 'per_body_site_otu_tables')
cmd_title = 'Splitting rarefied OTU table by body site'
cmd = 'split_otu_table.py -i %s -m %s -f %s -o %s' % (
rarefied_otu_table_fp, mapping_fp, category_to_split,
per_body_site_dir)
commands.append([(cmd_title, cmd)])
raw_data_dirs.append(per_body_site_dir)
command_handler(commands, status_update_callback, logger,
close_logger_on_success=False)
else:
per_body_site_dir = body_site_rarefied_otu_table_dir
for person_of_interest in personal_ids:
create_dir(join(output_dir, person_of_interest))
personal_mapping_file_fp = join(output_dir, person_of_interest,
'mapping_file.txt')
html_fp = join(output_dir, person_of_interest, 'index.html')
personal_mapping_data = create_personal_mapping_file(mapping_data,
person_of_interest, personal_id_index, bodysite_index,
individual_titles)
personal_mapping_f = open(personal_mapping_file_fp, 'w')
personal_mapping_f.write(
format_mapping_file(header, personal_mapping_data, comments))
personal_mapping_f.close()
raw_data_files.append(personal_mapping_file_fp)
column_title_index = header.index(column_title)
column_title_values = set([e[column_title_index]
for e in personal_mapping_data])
cat_index = header.index(category_to_split)
cat_values = set([e[cat_index] for e in personal_mapping_data])
# Generate alpha diversity boxplots, split by body site, one per
# metric. We run this one first because it completes relatively
# quickly and it does not call any QIIME scripts.
alpha_diversity_boxplots_html = ''
if not suppress_alpha_diversity_boxplots:
adiv_boxplots_dir = join(output_dir, person_of_interest,
'adiv_boxplots')
create_dir(adiv_boxplots_dir)
output_directories.append(adiv_boxplots_dir)
logger.write("\nGenerating alpha diversity boxplots (%s)\n\n" %
person_of_interest)
plot_filenames = _generate_alpha_diversity_boxplots(
collated_dir, personal_mapping_file_fp,
category_to_split, column_title, rarefaction_depth,
adiv_boxplots_dir)
# Create relative paths for use with the index page.
rel_boxplot_dir = basename(normpath(adiv_boxplots_dir))
plot_fps = [join(rel_boxplot_dir, plot_filename)
for plot_filename in plot_filenames]
alpha_diversity_boxplots_html = \
create_alpha_diversity_boxplots_html(plot_fps)
## Alpha rarefaction steps
if not suppress_alpha_rarefaction:
rarefaction_dir = join(output_dir, person_of_interest,
'alpha_rarefaction')
output_directories.append(rarefaction_dir)
commands = []
cmd_title = 'Creating rarefaction plots (%s)' % person_of_interest
cmd = 'make_rarefaction_plots.py -i %s -m %s -p %s -o %s' % (
collated_dir, personal_mapping_file_fp, prefs_fp,
rarefaction_dir)
commands.append([(cmd_title, cmd)])
raw_data_dirs.append(join(rarefaction_dir, 'average_plots'))
raw_data_dirs.append(join(rarefaction_dir, 'average_tables'))
command_handler(commands, status_update_callback, logger,
close_logger_on_success=False)
## Beta diversity steps
if not suppress_beta_diversity:
pcoa_dir = join(output_dir, person_of_interest, 'beta_diversity')
pcoa_time_series_dir = join(output_dir, person_of_interest,
'beta_diversity_time_series')
output_directories.append(pcoa_dir)
output_directories.append(pcoa_time_series_dir)
commands = []
cmd_title = 'Creating beta diversity time series plots (%s)' % \
person_of_interest
cmd = 'make_3d_plots.py -m %s -p %s -i %s -o %s --custom_axes=' % (
personal_mapping_file_fp, prefs_fp, coord_fp, pcoa_time_series_dir) +\
'\'%s\' --add_vectors=\'%s,%s\'' % (time_series_category,
site_id_category, time_series_category)
commands.append([(cmd_title, cmd)])
cmd_title = 'Creating beta diversity plots (%s)' % \
person_of_interest
cmd = 'make_3d_plots.py -m %s -p %s -i %s -o %s' % (personal_mapping_file_fp,
prefs_fp, coord_fp,
pcoa_dir)
commands.append([(cmd_title, cmd)])
command_handler(commands, status_update_callback, logger,
close_logger_on_success=False)
## Time series taxa summary plots steps
if not suppress_taxa_summary_plots:
area_plots_dir = join(output_dir, person_of_interest, 'time_series')
create_dir(area_plots_dir)
output_directories.append(area_plots_dir)
## Split OTU table into self/other per-body-site tables
commands = []
cmd_title = 'Splitting OTU table into self/other (%s)' % \
person_of_interest
cmd = 'split_otu_table.py -i %s -m %s -f %s -o %s' % (otu_table_fp,
personal_mapping_file_fp, column_title, area_plots_dir)
commands.append([(cmd_title, cmd)])
command_handler(commands, status_update_callback, logger,
close_logger_on_success=False)
for column_title_value in column_title_values:
biom_fp = join(area_plots_dir,
add_filename_suffix(otu_table_fp,
'_%s' % column_title_value))
column_title_map_fp = join(area_plots_dir, 'mapping_%s.txt' %
column_title_value)
raw_data_files.append(biom_fp)
raw_data_files.append(column_title_map_fp)
body_site_dir = join(area_plots_dir, column_title_value)
commands = []
cmd_title = 'Splitting "%s" OTU table by body site (%s)' % \
(column_title_value, person_of_interest)
cmd = 'split_otu_table.py -i %s -m %s -f %s -o %s' % (biom_fp,
personal_mapping_file_fp, category_to_split,
body_site_dir)
commands.append([(cmd_title, cmd)])
raw_data_dirs.append(body_site_dir)
command_handler(commands, status_update_callback, logger,
close_logger_on_success=False)
commands = []
for cat_value in cat_values:
body_site_otu_table_fp = join(body_site_dir,
add_filename_suffix(biom_fp, '_%s' % cat_value))
# We won't always get an OTU table if the mapping file
# category contains samples that aren't in the OTU table
# (e.g. the 'na' state for body site).
if exists(body_site_otu_table_fp):
plots = join(area_plots_dir, 'taxa_plots_%s_%s' % (
column_title_value, cat_value))
cmd_title = 'Creating taxa summary plots (%s)' % \
person_of_interest
cmd = ('summarize_taxa_through_plots.py -i %s '
'-o %s -c %s -m %s -s' %
(body_site_otu_table_fp, plots,
time_series_category,
personal_mapping_file_fp))
if parameter_fp is not None:
cmd += ' -p %s' % parameter_fp
commands.append([(cmd_title, cmd)])
raw_data_files.append(join(plots, '*.biom'))
raw_data_files.append(join(plots, '*.txt'))
create_comparative_taxa_plots_html(cat_value,
join(area_plots_dir, '%s_comparative.html' %
cat_value))
command_handler(commands, status_update_callback, logger,
close_logger_on_success=False)
# Generate OTU category significance tables (per body site).
otu_cat_sig_output_fps = []
otu_category_significance_html = ''
if not suppress_otu_category_significance:
otu_cat_sig_dir = join(output_dir, person_of_interest,
'otu_category_significance')
create_dir(otu_cat_sig_dir)
output_directories.append(otu_cat_sig_dir)
# For each body-site rarefied OTU table, run
# otu_category_significance.py using self versus other category.
# Keep track of each output file that is created because we need to
# parse these later on.
commands = []
for cat_value in cat_values:
body_site_otu_table_fp = join(per_body_site_dir,
add_filename_suffix(rarefied_otu_table_fp,
'_%s' % cat_value))
if exists(body_site_otu_table_fp):
otu_cat_output_fp = join(otu_cat_sig_dir,
'otu_cat_sig_%s.txt' % cat_value)
cmd_title = ('Testing for significant differences in '
'OTU abundances in "%s" body site (%s)' % (
cat_value, person_of_interest))
cmd = ('otu_category_significance.py -i %s -m %s -c %s '
'-o %s' % (body_site_otu_table_fp,
personal_mapping_file_fp,
column_title,
otu_cat_output_fp))
commands.append([(cmd_title, cmd)])
raw_data_files.append(otu_cat_output_fp)
otu_cat_sig_output_fps.append(otu_cat_output_fp)
command_handler(commands, status_update_callback, logger,
close_logger_on_success=False)
# Reformat otu category significance tables.
otu_cat_sig_html_filenames = \
format_otu_category_significance_tables_as_html(
otu_cat_sig_output_fps, alpha, otu_cat_sig_dir,
individual_titles, rep_set_fp=rep_set_fp)
# Create relative paths for use with the index page.
rel_otu_cat_sig_dir = basename(normpath(otu_cat_sig_dir))
otu_cat_sig_html_fps = [join(rel_otu_cat_sig_dir, html_filename)
for html_filename in otu_cat_sig_html_filenames]
otu_category_significance_html = \
create_otu_category_significance_html(otu_cat_sig_html_fps)
# Create the index.html file for the current individual.
create_index_html(person_of_interest, html_fp,
alpha_diversity_boxplots_html=alpha_diversity_boxplots_html,
otu_category_significance_html=otu_category_significance_html)
logger.close()
# Clean up the unnecessary raw data files and directories. glob will only
# grab paths that exist.
if not retain_raw_data:
for raw_data_fp_glob in raw_data_files:
remove_files(glob(raw_data_fp_glob))
for raw_data_dir_glob in raw_data_dirs:
for dir_to_remove in glob(raw_data_dir_glob):
rmtree(dir_to_remove)
return output_directories
def generate_most_wanted_list(output_dir, otu_table_fp, rep_set_fp, gg_fp,
nt_fp, mapping_fp, mapping_category, top_n, min_abundance,
max_abundance, min_categories, max_gg_similarity, e_value,
word_size, jobs_to_start, command_handler, status_update_callback,
force):
try:
makedirs(output_dir)
except OSError:
if not force:
raise WorkflowError("Output directory '%s' already exists. Please "
"choose a different directory, or force overwrite with -f."
% output_dir)
logger = WorkflowLogger(generate_log_fp(output_dir))
commands = []
# First filter to keep only new (non-GG) OTUs.
novel_otu_table_fp = join(output_dir, add_filename_suffix(otu_table_fp,
'_novel'))
commands.append([('Filtering out all GG reference OTUs',
'filter_otus_from_otu_table.py -i %s -o %s -e %s' %
(otu_table_fp, novel_otu_table_fp, gg_fp))])
# Next filter to keep only abundant otus in the specified range (looking
# only at extremely abundant OTUs has the problem of yielding too many
# that are similar to stuff in the nt database).
novel_abund_otu_table_fp = join(output_dir,
add_filename_suffix(novel_otu_table_fp, '_min%d_max%d' %
(min_abundance, max_abundance)))
commands.append([('Filtering out all OTUs that do not fall within the '
'specified abundance threshold',
'filter_otus_from_otu_table.py -i %s -o %s -n %d -x %d' %
(novel_otu_table_fp, novel_abund_otu_table_fp, min_abundance,
max_abundance))])
# Next, collapse by mapping_category.
otu_table_by_samp_type_fp = join(output_dir,
add_filename_suffix(novel_abund_otu_table_fp, '_%s' %
mapping_category))
commands.append([('Collapsing OTU table by %s' % mapping_category,
'summarize_otu_by_cat.py -c %s -o %s -m %s -i %s' %
(novel_abund_otu_table_fp, otu_table_by_samp_type_fp,
mapping_category, mapping_fp))])
# Filter to contain only otus in the specified minimum number of sample
# types.
otu_table_by_samp_type_ms_fp = join(output_dir, add_filename_suffix(
otu_table_by_samp_type_fp, '_ms%d' % min_categories))
commands.append([('Filtering OTU table to include only OTUs that appear '
'in at least %d sample groups' % min_categories,
'filter_otus_from_otu_table.py -i %s -o %s -s %d' %
(otu_table_by_samp_type_fp, otu_table_by_samp_type_ms_fp,
min_categories))])
# Now that we have a filtered down OTU table of good candidate OTUs, filter
# the corresponding representative set to include only these candidate
# sequences.
candidate_rep_set_fp = join(output_dir, add_filename_suffix(
rep_set_fp, '_most_wanted_candidates'))
commands.append([('Filtering representative set to include only the '
'latest candidate OTUs',
'filter_fasta.py -f %s -o %s -b %s' %
(rep_set_fp, candidate_rep_set_fp, otu_table_by_samp_type_ms_fp))])
# Find the otus that don't hit GG at a certain maximum similarity
# threshold.
uclust_output_dir = join(output_dir, 'most_wanted_candidates_%s_%s' %
(basename(gg_fp), str(max_gg_similarity)))
commands.append([('Running uclust to get list of sequences that don\'t '
'hit the maximum GG similarity threshold',
'parallel_pick_otus_uclust_ref.py -i %s -o %s -r %s -s %s -O %d' %
(candidate_rep_set_fp, uclust_output_dir, gg_fp,
str(max_gg_similarity), jobs_to_start))])
# Filter the candidate sequences to only include the failures from uclust.
cand_gg_dis_rep_set_fp = join(output_dir,
add_filename_suffix(candidate_rep_set_fp, '_failures'))
commands.append([('Filtering candidate sequences to only include uclust '
'failures',
'filter_fasta.py -f %s -s %s -o %s' %
(candidate_rep_set_fp, join(uclust_output_dir,
splitext(basename(candidate_rep_set_fp))[0] + '_failures.txt'),
cand_gg_dis_rep_set_fp))])
# BLAST the failures against nt.
blast_output_dir = join(output_dir, 'blast_output')
commands.append([('BLASTing candidate sequences against nt database',
'parallel_blast.py -i %s -o %s -r %s -D -e %f -w %d -O %d' %
(cand_gg_dis_rep_set_fp, blast_output_dir, nt_fp, e_value,
word_size, jobs_to_start))])
# Execute the commands we have so far, but keep the logger open because
# we're going to write additional status updates as we process the data.
command_handler(commands, status_update_callback, logger,
close_logger_on_success=False)
# We'll sort the BLAST results by percent identity (ascending) and pick the
# top n.
logger.write("Reading in BLAST results, sorting by percent identity, "
"and picking the top %d OTUs.\n\n" % top_n)
blast_results = open(join(blast_output_dir,
splitext(basename(cand_gg_dis_rep_set_fp))[0] + '_blast_out.txt'), 'U')
top_n_mw = []
for line in blast_results:
# Skip headers.
line = line.strip()
if line and not line.startswith('#'):
line = line.split('\t')
top_n_mw.append((line[0], line[1], float(line[2])))
top_n_mw = sorted(top_n_mw, key=itemgetter(2))[:top_n]
# Read in our filtered down candidate seqs file and latest filtered and
# collapsed OTU table. We'll need to compute some stats on these to include
# in our report.
logger.write("Reading in candidate sequences and latest filtered and "
"collapsed OTU table.\n\n")
mw_seqs = {}
for seq_id, seq in MinimalFastaParser(open(cand_gg_dis_rep_set_fp, 'U')):
seq_id = seq_id.strip().split()[0]
mw_seqs[seq_id] = seq
otu_table_by_samp_type_ms = parse_biom_table(
open(otu_table_by_samp_type_ms_fp, 'U'))
# Write results out to tsv and HTML table.
logger.write("Writing most wanted OTUs results to TSV and HTML "
"tables.\n\n")
mw_tsv_f = open(join(output_dir,
'top_%d_most_wanted_otus.txt' % top_n), 'w')
mw_html_f = open(join(output_dir,
'top_%d_most_wanted_otus.html' % top_n), 'w')
tsv_header = 'OTU ID\tSequence\tGreengenes taxonomy\t' + \
'NCBI nt closest match\tNCBI nt % identity'
mw_tsv_f.write(tsv_header + '\n')
tsv_header += '\tAbundance by %s' % mapping_category
html_header = ''
for col in tsv_header.split('\t'):
html_header += '<th>%s</th>' % col
mw_html_f.write('<table><tr>' + html_header + '</tr>')
for otu_id, subject_id, percent_identity in top_n_mw:
# Grab all necessary information to be included in our report.
seq = mw_seqs[otu_id]
tax = otu_table_by_samp_type_ms.ObservationMetadata[
otu_table_by_samp_type_ms.getObservationIndex(otu_id)]['taxonomy']
gb_id = subject_id.split('|')[3]
ncbi_link = 'http://www.ncbi.nlm.nih.gov/nuccore/%s' % gb_id
# Compute the abundance of each most wanted OTU in each sample
# grouping and create a pie chart to go in the HTML table.
samp_types = otu_table_by_samp_type_ms.SampleIds
counts = otu_table_by_samp_type_ms.observationData(otu_id)
if len(counts) != len(samp_types):
raise WorkflowError("The number of observation counts does not "
"match the number of samples in the OTU "
"table.")
# Piechart code modified from matplotlib example:
# http://matplotlib.sourceforge.net/examples/pylab_examples/
# pie_demo.html
figure(figsize=(6,6))
ax = axes([0.1, 0.1, 0.8, 0.8])
# Will auto-normalize the counts.
pie(counts, labels=samp_types, autopct='%1.1f%%', shadow=True)
output_img_dir = join(output_dir, 'img')
try:
makedirs(output_img_dir)
except OSError:
# It already exists, which is okay since we already know we are in
# 'force' mode from above.
pass
# We need a relative path to the image.
pie_chart_fp = join('img', 'abundance_by_%s_%s.png' %
(mapping_category, otu_id))
savefig(join(output_dir, pie_chart_fp))
mw_tsv_f.write('%s\t%s\t%s\t%s\t%s\n' %
(otu_id, seq, tax, gb_id, percent_identity))
mw_html_f.write('<tr><td>%s</td><td>%s</td><td>%s</td>'
'<td><a href="%s" target="_blank">%s</a></td><td>%s</td><td>'
'<img src="%s" /></td></tr>' % (otu_id, seq, tax, ncbi_link,
gb_id, percent_identity, pie_chart_fp))
mw_html_f.write('</table>')
mw_tsv_f.close()
mw_html_f.close()
logger.close()
def _get_most_wanted_filtering_commands(output_dir, otu_table_fps, rep_set_fp,
gg_fp, nt_fp, mapping_fp,
mapping_category, min_abundance,
max_abundance, min_categories,
max_gg_similarity, e_value, word_size,
merged_otu_table_fp, jobs_to_start):
commands = []
otu_tables_to_merge = []
if merged_otu_table_fp is None:
for otu_table_fp in otu_table_fps:
# First filter to keep only new (non-GG) OTUs.
novel_otu_table_fp = join(
output_dir, add_filename_suffix(otu_table_fp, '_novel'))
commands.append([
('Filtering out all GG reference OTUs',
'filter_otus_from_otu_table.py -i %s -o %s -e %s' %
(otu_table_fp, novel_otu_table_fp, gg_fp))
])
# Next filter to keep only abundant otus in the specified range
# (looking only at extremely abundant OTUs has the problem of yielding
# too many that are similar to stuff in the nt database).
novel_abund_otu_table_fp = join(
output_dir,
add_filename_suffix(
novel_otu_table_fp,
'_min%d_max%d' % (min_abundance, max_abundance)))
commands.append([
('Filtering out all OTUs that do not fall within the '
'specified abundance threshold',
'filter_otus_from_otu_table.py -i %s -o %s -n %d -x %d' %
(novel_otu_table_fp, novel_abund_otu_table_fp, min_abundance,
max_abundance))
])
# Remove samples from the table that aren't in the mapping file.
novel_abund_filtered_otu_table_fp = join(
output_dir,
add_filename_suffix(novel_abund_otu_table_fp,
'_known_samples'))
commands.append([
('Filtering out samples that are not in the mapping '
'file', 'filter_samples_from_otu_table.py -i %s -o %s '
'--sample_id_fp %s' %
(novel_abund_otu_table_fp, novel_abund_filtered_otu_table_fp,
mapping_fp))
])
# Next, collapse by mapping_category.
otu_table_by_samp_type_fp = join(
output_dir,
add_filename_suffix(novel_abund_filtered_otu_table_fp,
'_%s' % mapping_category))
commands.append([
('Collapsing OTU table by %s' % mapping_category,
'summarize_otu_by_cat.py -c %s -o %s -m %s -i %s' %
(novel_abund_filtered_otu_table_fp, otu_table_by_samp_type_fp,
mapping_category, mapping_fp))
])
otu_tables_to_merge.append(otu_table_by_samp_type_fp)
# Merge all collapsed OTU tables.
master_otu_table_fp = join(
output_dir, 'master_otu_table_novel_min%d_max%d_%s.biom' %
(min_abundance, max_abundance, mapping_category))
commands.append([('Merging collapsed OTU tables',
'merge_otu_tables.py -i %s -o %s' %
(','.join(otu_tables_to_merge), master_otu_table_fp))
])
else:
master_otu_table_fp = merged_otu_table_fp
# Filter to contain only otus in the specified minimum number of sample
# types.
master_otu_table_ms_fp = join(
output_dir,
add_filename_suffix(master_otu_table_fp, '_ms%d' % min_categories))
commands.append([
('Filtering OTU table to include only OTUs that appear '
'in at least %d sample groups' % min_categories,
'filter_otus_from_otu_table.py -i %s -o %s -s %d' %
(master_otu_table_fp, master_otu_table_ms_fp, min_categories))
])
# Now that we have a filtered down OTU table of good candidate OTUs, filter
# the corresponding representative set to include only these candidate
# sequences.
rep_set_cands_fp = join(output_dir,
add_filename_suffix(rep_set_fp, '_candidates'))
commands.append([
('Filtering representative set to include only the '
'latest candidate OTUs', 'filter_fasta.py -f %s -o %s -b %s' %
(rep_set_fp, rep_set_cands_fp, master_otu_table_ms_fp))
])
# Find the otus that don't hit GG at a certain maximum similarity
# threshold.
uclust_output_dir = join(
output_dir, 'most_wanted_candidates_%s_%s' %
(basename(gg_fp), str(max_gg_similarity)))
commands.append([
('Running uclust to get list of sequences that don\'t '
'hit the maximum GG similarity threshold',
'parallel_pick_otus_uclust_ref.py -i %s -o %s -r %s -s %s -O %d' %
(rep_set_cands_fp, uclust_output_dir, gg_fp, str(max_gg_similarity),
jobs_to_start))
])
# Filter the rep set to only include the failures from uclust.
rep_set_cands_failures_fp = join(
output_dir, add_filename_suffix(rep_set_cands_fp, '_failures'))
commands.append([
('Filtering candidate sequences to only include uclust '
'failures', 'filter_fasta.py -f %s -s %s -o %s' %
(rep_set_cands_fp,
join(uclust_output_dir,
splitext(basename(rep_set_cands_fp))[0] + '_failures.txt'),
rep_set_cands_failures_fp))
])
# BLAST the failures against nt.
blast_output_dir = join(output_dir, 'blast_output')
commands.append([
('BLASTing filtered candidate sequences against nt '
'database',
'parallel_blast.py -i %s -o %s -r %s -D -e %f -w %d -O %d' %
(rep_set_cands_failures_fp, blast_output_dir, nt_fp, e_value,
word_size, jobs_to_start))
])
blast_results_fp = join(
blast_output_dir,
splitext(basename(rep_set_cands_failures_fp))[0] + '_blast_out.txt')
return commands, blast_results_fp, rep_set_cands_failures_fp, \
master_otu_table_ms_fp