def pick_nested_reference_otus(input_fasta_fp,
input_tree_fp,
output_dir,
run_id,
similarity_thresholds,
command_handler,
status_update_callback=print_to_stdout):
# Prepare some variables for the later steps
create_dir(output_dir)
otu_dir = join(output_dir,'otus')
create_dir(otu_dir)
rep_set_dir = join(output_dir,'rep_set')
create_dir(rep_set_dir)
# currently not doing anything with taxonomies and trees
# tax_dir = join(output_dir,'taxonomies')
# create_dir(tax_dir)
if input_tree_fp:
tree_dir = join(output_dir,'trees')
create_dir(tree_dir)
commands = []
files_to_remove = []
logger = WorkflowLogger(generate_log_fp(output_dir))
similarity_thresholds.sort()
similarity_thresholds.reverse()
current_inseqs_fp = input_fasta_fp
current_tree_fp = input_tree_fp
previous_otu_map = None
for similarity_threshold in similarity_thresholds:
current_inseqs_basename = splitext(split(current_inseqs_fp)[1])[0]
# pick otus command
otu_fp = '%s/%d_otu_map.txt' % (otu_dir,similarity_threshold)
clusters_fp = '%s/%d_clusters.uc' % (otu_dir,similarity_threshold)
temp_otu_fp = '%s/%s_otus.txt' % (otu_dir, current_inseqs_basename)
temp_log_fp = '%s/%s_otus.log' % (otu_dir, current_inseqs_basename)
temp_clusters_fp = '%s/%s_clusters.uc' % (otu_dir, current_inseqs_basename)
pick_otus_cmd = \
'pick_otus.py -m uclust -DBz -i %s -s %1.2f -o %s' % (
current_inseqs_fp,
similarity_threshold/100,
otu_dir)
commands.append([('Pick OTUs (%d)' % similarity_threshold,
pick_otus_cmd)])
commands.append([('Rename OTU file (%d)' % similarity_threshold,
'mv %s %s' % (temp_otu_fp,otu_fp))])
commands.append([('Rename uc file (%d)' % similarity_threshold,
'mv %s %s' % (temp_clusters_fp,clusters_fp))])
files_to_remove.append(temp_log_fp)
# rep set picking
temp_rep_set_fp = get_tmp_filename(prefix='NestedReference',
suffix='.fasta')
pick_rep_set_cmd = \
'pick_rep_set.py -m first -i %s -o %s -f %s' % (
otu_fp,
temp_rep_set_fp,
current_inseqs_fp)
commands.append([('Pick Rep Set (%d)' % similarity_threshold,
pick_rep_set_cmd)])
command_handler(commands, status_update_callback, logger, close_logger_on_success=False)
commands = []
# rename representative sequences
rep_set_fp = '%s/%d_otus_%s.fasta' % (
rep_set_dir,
similarity_threshold,
run_id)
logger.write('Renaming OTU representative sequences so OTU ids are reference sequence ids.')
rep_set_f = open(rep_set_fp,'w')
for e in rename_rep_seqs(open(temp_rep_set_fp,'U')):
rep_set_f.write('>%s\n%s\n' % e)
rep_set_f.close()
files_to_remove.append(temp_rep_set_fp)
# filter the tree, if provided
if current_tree_fp != None:
tree_fp = '%s/%d_otus_%s.tre' % (
tree_dir,
similarity_threshold,
run_id)
tree_cmd = 'filter_tree.py -i %s -f %s -o %s' %\
(current_tree_fp,rep_set_fp,tree_fp)
commands.append([('Filter tree (%d)' % similarity_threshold,tree_cmd)])
command_handler(commands, status_update_callback, logger, close_logger_on_success=False)
# prep for the next iteration
current_tree_fp = tree_fp
# prep for the next iteration
remove_files(files_to_remove)
commands = []
files_to_remove = []
current_inseqs_fp = rep_set_fp
logger.close()
def iterative_pick_subsampled_open_referenence_otus(
input_fps,
refseqs_fp,
output_dir,
percent_subsample,
new_ref_set_id,
command_handler,
params,
qiime_config,
prefilter_refseqs_fp=None,
prefilter_percent_id=0.60,
min_otu_size=2,
run_tax_align_tree=True,
step1_otu_map_fp=None,
step1_failures_fasta_fp=None,
parallel=False,
suppress_step4=False,
logger=None,
status_update_callback=print_to_stdout):
""" Call the pick_subsampled_open_referenence_otus workflow on multiple inputs
and handle processing of the results.
"""
create_dir(output_dir)
commands = []
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 the user has not passed a different reference collection for the pre-filter,
# used the input refseqs_fp for all iterations. we want to pre-filter all data against
# the input data as lower percent identity searches with uclust can be slow, so we
# want the reference collection to stay at a reasonable size.
if prefilter_refseqs_fp == None:
prefilter_refseqs_fp = refseqs_fp
otu_table_fps = []
repset_fasta_fps = []
for i, input_fp in enumerate(input_fps):
iteration_output_dir = '%s/%d/' % (output_dir, i)
if iteration_output_exists(iteration_output_dir, min_otu_size):
# if the output from an iteration already exists, skip that
# iteration (useful for continuing failed runs)
log_input_md5s(logger, [input_fp, refseqs_fp])
logger.write(
'Iteration %d (input file: %s) output data already exists. '
'Skipping and moving to next.\n\n' % (i, input_fp))
else:
pick_subsampled_open_referenence_otus(
input_fp=input_fp,
refseqs_fp=refseqs_fp,
output_dir=iteration_output_dir,
percent_subsample=percent_subsample,
new_ref_set_id='.'.join([new_ref_set_id,
str(i)]),
command_handler=command_handler,
params=params,
qiime_config=qiime_config,
run_tax_align_tree=False,
prefilter_refseqs_fp=prefilter_refseqs_fp,
prefilter_percent_id=prefilter_percent_id,
min_otu_size=min_otu_size,
step1_otu_map_fp=step1_otu_map_fp,
step1_failures_fasta_fp=step1_failures_fasta_fp,
parallel=parallel,
suppress_step4=suppress_step4,
logger=logger,
status_update_callback=status_update_callback)
## perform post-iteration file shuffling whether the previous iteration's
## data previously existed or was just computed.
# step1 otu map and failures can only be used for the first iteration
# as subsequent iterations need to use updated refseqs files
step1_otu_map_fp = step1_failures_fasta_fp = None
new_refseqs_fp = '%s/new_refseqs.fna' % iteration_output_dir
refseqs_fp = new_refseqs_fp
otu_table_fps.append('%s/otu_table_mc%d.biom' %
(iteration_output_dir, min_otu_size))
repset_fasta_fps.append('%s/rep_set.fna' % iteration_output_dir)
# Merge OTU tables - check for existence first as this step has historically
# been a frequent failure, so is sometimes run manually in failed runs.
otu_table_fp = '%s/otu_table_mc%d.biom' % (output_dir, min_otu_size)
if not (exists(otu_table_fp) and getsize(otu_table_fp) > 0):
merge_cmd = 'merge_otu_tables.py -i %s -o %s' %\
(','.join(otu_table_fps),otu_table_fp)
commands.append([("Merge OTU tables", merge_cmd)])
# Build master rep set
final_repset_fp = '%s/rep_set.fna' % output_dir
final_repset_from_iteration_repsets_fps(repset_fasta_fps, final_repset_fp)
command_handler(commands,
status_update_callback,
logger=logger,
close_logger_on_success=False)
commands = []
if run_tax_align_tree:
otu_table_w_tax_fp = \
'%s/otu_table_mc%d_w_tax.biom' % (output_dir,min_otu_size)
final_otu_table_fp = \
'%s/otu_table_mc%d_w_tax_no_pynast_failures.biom' % (output_dir,min_otu_size)
if exists(final_otu_table_fp) and getsize(final_otu_table_fp) > 0:
logger.write("Final output file exists (%s). Will not rebuild." %
otu_table_fp)
else:
# remove files from partially completed runs
remove_files([otu_table_w_tax_fp, final_otu_table_fp],
error_on_missing=False)
taxonomy_fp, pynast_failures_fp = tax_align_tree(
repset_fasta_fp=final_repset_fp,
output_dir=output_dir,
command_handler=command_handler,
params=params,
qiime_config=qiime_config,
parallel=parallel,
logger=logger,
status_update_callback=status_update_callback)
# Add taxa to otu table
add_taxa_cmd = 'add_taxa.py -i %s -t %s -o %s' %\
(otu_table_fp,taxonomy_fp,otu_table_w_tax_fp)
commands.append([("Add taxa to OTU table", add_taxa_cmd)])
command_handler(commands,
status_update_callback,
logger=logger,
close_logger_on_success=False)
commands = []
# Build OTU table without PyNAST failures
filtered_otu_table = filter_otus_from_otu_table(
parse_biom_table(open(otu_table_w_tax_fp, 'U')),
get_seq_ids_from_fasta_file(open(pynast_failures_fp, 'U')),
0,
inf,
0,
inf,
negate_ids_to_keep=True)
otu_table_f = open(final_otu_table_fp, 'w')
otu_table_f.write(format_biom_table(filtered_otu_table))
otu_table_f.close()
command_handler(commands,
status_update_callback,
logger=logger,
close_logger_on_success=False)
commands = []
logger.close()
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 iterative_pick_subsampled_open_referenence_otus(
input_fps,
refseqs_fp,
output_dir,
percent_subsample,
new_ref_set_id,
command_handler,
params,
qiime_config,
prefilter_refseqs_fp=None,
prefilter_percent_id=0.60,
min_otu_size=2,
run_tax_align_tree=True,
step1_otu_map_fp=None,
step1_failures_fasta_fp=None,
parallel=False,
suppress_step4=False,
logger=None,
status_update_callback=print_to_stdout):
""" Call the pick_subsampled_open_referenence_otus workflow on multiple inputs
and handle processing of the results.
"""
create_dir(output_dir)
commands = []
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 the user has not passed a different reference collection for the pre-filter,
# used the input refseqs_fp for all iterations. we want to pre-filter all data against
# the input data as lower percent identity searches with uclust can be slow, so we
# want the reference collection to stay at a reasonable size.
if prefilter_refseqs_fp == None:
prefilter_refseqs_fp = refseqs_fp
otu_table_fps = []
repset_fasta_fps = []
for i,input_fp in enumerate(input_fps):
iteration_output_dir = '%s/%d/' % (output_dir,i)
if iteration_output_exists(iteration_output_dir,min_otu_size):
# if the output from an iteration already exists, skip that
# iteration (useful for continuing failed runs)
log_input_md5s(logger,[input_fp,refseqs_fp])
logger.write('Iteration %d (input file: %s) output data already exists. '
'Skipping and moving to next.\n\n' % (i,input_fp))
else:
pick_subsampled_open_referenence_otus(input_fp=input_fp,
refseqs_fp=refseqs_fp,
output_dir=iteration_output_dir,
percent_subsample=percent_subsample,
new_ref_set_id='.'.join([new_ref_set_id,str(i)]),
command_handler=command_handler,
params=params,
qiime_config=qiime_config,
run_tax_align_tree=False,
prefilter_refseqs_fp=prefilter_refseqs_fp,
prefilter_percent_id=prefilter_percent_id,
min_otu_size=min_otu_size,
step1_otu_map_fp=step1_otu_map_fp,
step1_failures_fasta_fp=step1_failures_fasta_fp,
parallel=parallel,
suppress_step4=suppress_step4,
logger=logger,
status_update_callback=status_update_callback)
## perform post-iteration file shuffling whether the previous iteration's
## data previously existed or was just computed.
# step1 otu map and failures can only be used for the first iteration
# as subsequent iterations need to use updated refseqs files
step1_otu_map_fp = step1_failures_fasta_fp = None
new_refseqs_fp = '%s/new_refseqs.fna' % iteration_output_dir
refseqs_fp = new_refseqs_fp
otu_table_fps.append('%s/otu_table_mc%d.biom' % (iteration_output_dir,min_otu_size))
repset_fasta_fps.append('%s/rep_set.fna' % iteration_output_dir)
# Merge OTU tables - check for existence first as this step has historically
# been a frequent failure, so is sometimes run manually in failed runs.
otu_table_fp = '%s/otu_table_mc%d.biom' % (output_dir,min_otu_size)
if not (exists(otu_table_fp) and getsize(otu_table_fp) > 0):
merge_cmd = 'merge_otu_tables.py -i %s -o %s' %\
(','.join(otu_table_fps),otu_table_fp)
commands.append([("Merge OTU tables",merge_cmd)])
# Build master rep set
final_repset_fp = '%s/rep_set.fna' % output_dir
final_repset_from_iteration_repsets_fps(repset_fasta_fps,final_repset_fp)
command_handler(commands,
status_update_callback,
logger=logger,
close_logger_on_success=False)
commands = []
if run_tax_align_tree:
otu_table_w_tax_fp = \
'%s/otu_table_mc%d_w_tax.biom' % (output_dir,min_otu_size)
final_otu_table_fp = \
'%s/otu_table_mc%d_w_tax_no_pynast_failures.biom' % (output_dir,min_otu_size)
if exists(final_otu_table_fp) and getsize(final_otu_table_fp) > 0:
logger.write("Final output file exists (%s). Will not rebuild." % otu_table_fp)
else:
# remove files from partially completed runs
remove_files([otu_table_w_tax_fp,final_otu_table_fp],error_on_missing=False)
taxonomy_fp, pynast_failures_fp = tax_align_tree(
repset_fasta_fp=final_repset_fp,
output_dir=output_dir,
command_handler=command_handler,
params=params,
qiime_config=qiime_config,
parallel=parallel,
logger=logger,
status_update_callback=status_update_callback)
# Add taxa to otu table
add_taxa_cmd = 'add_taxa.py -i %s -t %s -o %s' %\
(otu_table_fp,taxonomy_fp,otu_table_w_tax_fp)
commands.append([("Add taxa to OTU table",add_taxa_cmd)])
command_handler(commands,
status_update_callback,
logger=logger,
close_logger_on_success=False)
commands = []
# Build OTU table without PyNAST failures
filtered_otu_table = filter_otus_from_otu_table(
parse_biom_table(open(otu_table_w_tax_fp,'U')),
get_seq_ids_from_fasta_file(open(pynast_failures_fp,'U')),
0,inf,0,inf,negate_ids_to_keep=True)
otu_table_f = open(final_otu_table_fp,'w')
otu_table_f.write(format_biom_table(filtered_otu_table))
otu_table_f.close()
command_handler(commands,
status_update_callback,
logger=logger,
close_logger_on_success=False)
commands = []
logger.close()
class QiimeCommand(object):
""" Base class for abstracted QIIME command
"""
_standard_options = [
make_option('--master_script_log_dir',type='existing_dirpath',
help='directory where master script log will be stored [default: %default]',
default='./')]
_input_file_parameter_ids = []
_brief_description = """ """
_script_description = """ """
_script_usage = []
_script_usage_output_to_remove = []
_output_description = """ """
_required_options = []
_optional_options = []
_version = __version__
def __init__(self):
"""
"""
self._optional_options.extend(self._standard_options)
def __call__(self,options,arguments,argv,logger=None):
"""
"""
close_logger_on_success = self._start_logging(options,arguments,argv,logger)
self.run_command(options,arguments)
self._stop_logging(options,arguments,argv,close_logger_on_success)
def _start_logging(self,
params,
args,
argv,
logger):
if logger == None:
self.logger = WorkflowLogger(generate_log_fp(params['master_script_log_dir']),
params={},
qiime_config=qiime_config)
close_logger_on_success = True
else:
self.logger = logger
close_logger_on_success = False
self.logger.write('Command:\n')
self.logger.write(' '.join(argv))
self.logger.write('\n\n')
log_input_md5s(self.logger,
[params[p] for p in self._input_file_parameter_ids])
return close_logger_on_success
def _stop_logging(self,
params,
args,
argv,
close_logger_on_success):
if close_logger_on_success:
self.logger.close()
def getScriptInfo(self):
result = {}
result['brief_description'] = self._brief_description
result['script_description'] = self._script_description
result['script_usage'] = self._script_usage
result['script_usage_output_to_remove'] = self._script_usage_output_to_remove
result['output_description'] = self._output_description
result['required_options'] = self._required_options
result['optional_options'] = self._optional_options
result['version'] = self._version
return result
def run_command(self,params,args):
raise NotImplementedError, "All subclasses must implement run_command."
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 pick_subsampled_open_reference_otus(input_fp,
refseqs_fp,
output_dir,
percent_subsample,
new_ref_set_id,
command_handler,
params,
qiime_config,
prefilter_refseqs_fp=None,
run_assign_tax=True,
run_align_and_tree=True,
prefilter_percent_id=0.60,
min_otu_size=2,
step1_otu_map_fp=None,
step1_failures_fasta_fp=None,
parallel=False,
suppress_step4=False,
logger=None,
status_update_callback=print_to_stdout):
""" Run the data preparation steps of Qiime
The steps performed by this function are:
- Pick reference OTUs against refseqs_fp
- Subsample the failures to n sequences.
- Pick OTUs de novo on the n failures.
- Pick representative sequences for the resulting OTUs.
- Pick reference OTUs on all failures using the
representative set from step 4 as the reference set.
"""
# for now only allowing uclust for otu picking
denovo_otu_picking_method = 'uclust'
reference_otu_picking_method = 'uclust_ref'
# Prepare some variables for the later steps
input_dir, input_filename = split(input_fp)
input_basename, input_ext = splitext(input_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
log_input_md5s(logger,[input_fp,refseqs_fp,step1_otu_map_fp,step1_failures_fasta_fp])
# if the user has not passed a different reference collection for the pre-filter,
# used the main refseqs_fp. this is useful if the user wants to provide a smaller
# reference collection, or to use the input reference collection when running in
# iterative mode (rather than an iteration's new refseqs)
if prefilter_refseqs_fp == None:
prefilter_refseqs_fp = refseqs_fp
## Step 1: Closed-reference OTU picking on the input file (if not already complete)
if step1_otu_map_fp and step1_failures_fasta_fp:
step1_dir = '%s/step1_otus' % output_dir
create_dir(step1_dir)
logger.write("Using pre-existing reference otu map and failures.\n\n")
else:
if prefilter_percent_id != None:
prefilter_dir = '%s/prefilter_otus/' % output_dir
prefilter_otu_map_fp = \
'%s/%s_otus.txt' % (prefilter_dir,input_basename)
prefilter_failures_list_fp = '%s/%s_failures.txt' % \
(prefilter_dir,input_basename)
prefilter_pick_otu_cmd = pick_reference_otus(\
input_fp,prefilter_dir,reference_otu_picking_method,
prefilter_refseqs_fp,parallel,params,logger,prefilter_percent_id)
commands.append([('Pick Reference OTUs (prefilter)', prefilter_pick_otu_cmd)])
prefiltered_input_fp = '%s/prefiltered_%s%s' %\
(prefilter_dir,input_basename,input_ext)
filter_fasta_cmd = 'filter_fasta.py -f %s -o %s -s %s -n' %\
(input_fp,prefiltered_input_fp,prefilter_failures_list_fp)
commands.append([('Filter prefilter failures from input', filter_fasta_cmd)])
input_fp = prefiltered_input_fp
input_dir, input_filename = split(input_fp)
input_basename, input_ext = splitext(input_filename)
## Build the OTU picking command
step1_dir = \
'%s/step1_otus' % output_dir
step1_otu_map_fp = \
'%s/%s_otus.txt' % (step1_dir,input_basename)
step1_pick_otu_cmd = pick_reference_otus(\
input_fp,step1_dir,reference_otu_picking_method,
refseqs_fp,parallel,params,logger)
commands.append([('Pick Reference OTUs', step1_pick_otu_cmd)])
## Build the failures fasta file
step1_failures_list_fp = '%s/%s_failures.txt' % \
(step1_dir,input_basename)
step1_failures_fasta_fp = \
'%s/failures.fasta' % step1_dir
step1_filter_fasta_cmd = 'filter_fasta.py -f %s -s %s -o %s' %\
(input_fp,step1_failures_list_fp,step1_failures_fasta_fp)
commands.append([('Generate full failures fasta file',
step1_filter_fasta_cmd)])
# Call the command handler on the list of commands
command_handler(commands,
status_update_callback,
logger=logger,
close_logger_on_success=False)
commands = []
step1_repset_fasta_fp = \
'%s/step1_rep_set.fna' % step1_dir
step1_pick_rep_set_cmd = 'pick_rep_set.py -i %s -o %s -f %s' %\
(step1_otu_map_fp, step1_repset_fasta_fp, input_fp)
commands.append([('Pick rep set',step1_pick_rep_set_cmd)])
## Subsample the failures fasta file to retain (roughly) the
## percent_subsample
step2_input_fasta_fp = \
'%s/subsampled_failures.fasta' % step1_dir
subsample_fasta(step1_failures_fasta_fp,
step2_input_fasta_fp,
percent_subsample)
## Prep the OTU picking command for the subsampled failures
step2_dir = '%s/step2_otus/' % output_dir
step2_cmd = pick_denovo_otus(step2_input_fasta_fp,
step2_dir,
new_ref_set_id,
denovo_otu_picking_method,
params,
logger)
step2_otu_map_fp = '%s/subsampled_failures_otus.txt' % step2_dir
commands.append([('Pick de novo OTUs for new clusters', step2_cmd)])
## Prep the rep set picking command for the subsampled failures
step2_repset_fasta_fp = '%s/step2_rep_set.fna' % step2_dir
step2_rep_set_cmd = 'pick_rep_set.py -i %s -o %s -f %s' %\
(step2_otu_map_fp,step2_repset_fasta_fp,step2_input_fasta_fp)
commands.append([('Pick representative set for subsampled failures',step2_rep_set_cmd)])
step3_dir = '%s/step3_otus/' % output_dir
step3_otu_map_fp = '%s/failures_otus.txt' % step3_dir
step3_failures_list_fp = '%s/failures_failures.txt' % step3_dir
step3_cmd = pick_reference_otus(
step1_failures_fasta_fp,
step3_dir,
reference_otu_picking_method,
step2_repset_fasta_fp,
parallel,
params,
logger)
commands.append([
('Pick reference OTUs using de novo rep set',step3_cmd)])
# name the final otu map
merged_otu_map_fp = '%s/final_otu_map.txt' % output_dir
if not suppress_step4:
step3_failures_fasta_fp = '%s/failures_failures.fasta' % step3_dir
step3_filter_fasta_cmd = 'filter_fasta.py -f %s -s %s -o %s' %\
(step1_failures_fasta_fp,step3_failures_list_fp,step3_failures_fasta_fp)
commands.append([('Create fasta file of step3 failures',
step3_filter_fasta_cmd)])
step4_dir = '%s/step4_otus/' % output_dir
step4_cmd = pick_denovo_otus(step3_failures_fasta_fp,
step4_dir,
'.'.join([new_ref_set_id,'CleanUp']),
denovo_otu_picking_method,
params,
logger)
step4_otu_map_fp = '%s/failures_failures_otus.txt' % step4_dir
commands.append([('Pick de novo OTUs on step3 failures', step4_cmd)])
# Merge the otu maps
cat_otu_tables_cmd = 'cat %s %s %s >> %s' %\
(step1_otu_map_fp,step3_otu_map_fp,step4_otu_map_fp,merged_otu_map_fp)
commands.append([('Merge OTU maps',cat_otu_tables_cmd)])
step4_repset_fasta_fp = '%s/step4_rep_set.fna' % step4_dir
step4_rep_set_cmd = 'pick_rep_set.py -i %s -o %s -f %s' %\
(step4_otu_map_fp,step4_repset_fasta_fp,step3_failures_fasta_fp)
commands.append([('Pick representative set for subsampled failures',step4_rep_set_cmd)])
else:
# Merge the otu maps
cat_otu_tables_cmd = 'cat %s %s >> %s' %\
(step1_otu_map_fp,step3_otu_map_fp,merged_otu_map_fp)
commands.append([('Merge OTU maps',cat_otu_tables_cmd)])
# Move the step 3 failures file to the top-level directory
commands.append([('Move final failures file to top-level directory',
'mv %s %s/final_failures.txt' % (step3_failures_list_fp,output_dir))])
command_handler(commands,
status_update_callback,
logger=logger,
close_logger_on_success=False)
commands = []
otu_fp = merged_otu_map_fp
# Filter singletons from the otu map
otu_no_singletons_fp = '%s/final_otu_map_mc%d.txt' % (output_dir,min_otu_size)
otus_to_keep = filter_otus_from_otu_map(otu_fp,otu_no_singletons_fp,min_otu_size)
## make the final representative seqs file and a new refseqs file that
## could be used in subsequent otu picking runs.
## this is clunky. first, we need to do this without singletons to match
## the otu map without singletons. next, there is a difference in what
## we need the reference set to be and what we need the repseqs to be.
## the reference set needs to be a superset of the input reference set
## to this set. the repset needs to be only the sequences that were observed
## in this data set, and we want reps for the step1 reference otus to be
## reads from this run so we don't hit issues building a tree using
## sequences of very different lengths. so...
final_repset_fp = '%s/rep_set.fna' % output_dir
final_repset_f = open(final_repset_fp,'w')
new_refseqs_fp = '%s/new_refseqs.fna' % output_dir
# write non-singleton otus representative sequences from step1 to the
# final rep set file
for otu_id, seq in MinimalFastaParser(open(step1_repset_fasta_fp,'U')):
if otu_id.split()[0] in otus_to_keep:
final_repset_f.write('>%s\n%s\n' % (otu_id,seq))
# copy the full input refseqs file to the new refseqs_fp
copy(refseqs_fp,new_refseqs_fp)
new_refseqs_f = open(new_refseqs_fp,'a')
new_refseqs_f.write('\n')
# iterate over all representative sequences from step2 and step4 and write
# those corresponding to non-singleton otus to the final representative set
# file and the new reference sequences file.
for otu_id, seq in MinimalFastaParser(open(step2_repset_fasta_fp,'U')):
if otu_id.split()[0] in otus_to_keep:
new_refseqs_f.write('>%s\n%s\n' % (otu_id,seq))
final_repset_f.write('>%s\n%s\n' % (otu_id,seq))
if not suppress_step4:
for otu_id, seq in MinimalFastaParser(open(step4_repset_fasta_fp,'U')):
if otu_id.split()[0] in otus_to_keep:
new_refseqs_f.write('>%s\n%s\n' % (otu_id,seq))
final_repset_f.write('>%s\n%s\n' % (otu_id,seq))
new_refseqs_f.close()
final_repset_f.close()
# Prep the make_otu_table.py command
otu_table_fp = '%s/otu_table_mc%d.biom' % (output_dir,min_otu_size)
make_otu_table_cmd = 'make_otu_table.py -i %s -o %s' %\
(otu_no_singletons_fp,otu_table_fp)
commands.append([("Make the otu table",make_otu_table_cmd)])
command_handler(commands,
status_update_callback,
logger=logger,
close_logger_on_success=False)
commands = []
# initialize output file names - these differ based on what combination of
# taxonomy assignment and alignment/tree building is happening.
if run_assign_tax and run_align_and_tree:
tax_input_otu_table_fp = otu_table_fp
otu_table_w_tax_fp = \
'%s/otu_table_mc%d_w_tax.biom' % (output_dir,min_otu_size)
align_and_tree_input_otu_table = otu_table_w_tax_fp
pynast_failure_filtered_otu_table_fp = \
'%s/otu_table_mc%d_w_tax_no_pynast_failures.biom' % (output_dir,min_otu_size)
elif run_assign_tax:
tax_input_otu_table_fp = otu_table_fp
otu_table_w_tax_fp = \
'%s/otu_table_mc%d_w_tax.biom' % (output_dir,min_otu_size)
elif run_align_and_tree:
align_and_tree_input_otu_table = otu_table_fp
pynast_failure_filtered_otu_table_fp = \
'%s/otu_table_mc%d_no_pynast_failures.biom' % (output_dir,min_otu_size)
if run_assign_tax:
if exists(otu_table_w_tax_fp) and getsize(otu_table_w_tax_fp) > 0:
logger.write("Final output file exists (%s). Will not rebuild." % otu_table_w_tax_fp)
else:
# remove files from partially completed runs
remove_files([otu_table_w_tax_fp],error_on_missing=False)
taxonomy_fp = assign_tax(
repset_fasta_fp=final_repset_fp,
output_dir=output_dir,
command_handler=command_handler,
params=params,
qiime_config=qiime_config,
parallel=parallel,
logger=logger,
status_update_callback=status_update_callback)
# Add taxa to otu table
# Add taxa to otu table
add_metadata_cmd = 'add_metadata.py -i %s --observation_mapping_fp %s -o %s --sc_separated taxonomy --observation_header OTUID,taxonomy' %\
(tax_input_otu_table_fp,taxonomy_fp,otu_table_w_tax_fp)
commands.append([("Add taxa to OTU table",add_metadata_cmd)])
command_handler(commands,
status_update_callback,
logger=logger,
close_logger_on_success=False)
commands = []
if run_align_and_tree:
if exists(pynast_failure_filtered_otu_table_fp) and\
getsize(pynast_failure_filtered_otu_table_fp) > 0:
logger.write("Final output file exists (%s). Will not rebuild." %\
pynast_failure_filtered_otu_table_fp)
else:
# remove files from partially completed runs
remove_files([pynast_failure_filtered_otu_table_fp],
error_on_missing=False)
pynast_failures_fp = align_and_tree(
repset_fasta_fp=final_repset_fp,
output_dir=output_dir,
command_handler=command_handler,
params=params,
qiime_config=qiime_config,
parallel=parallel,
logger=logger,
status_update_callback=status_update_callback)
# Build OTU table without PyNAST failures
filtered_otu_table = filter_otus_from_otu_table(
parse_biom_table(open(align_and_tree_input_otu_table,'U')),
get_seq_ids_from_fasta_file(open(pynast_failures_fp,'U')),
0,inf,0,inf,negate_ids_to_keep=True)
otu_table_f = open(pynast_failure_filtered_otu_table_fp,'w')
otu_table_f.write(format_biom_table(filtered_otu_table))
otu_table_f.close()
command_handler(commands,
status_update_callback,
logger=logger,
close_logger_on_success=False)
commands = []
if close_logger_on_success:
logger.close()
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 assign_taxonomy_multiple_times(input_dirs,
output_dir,
assignment_methods,
reference_seqs_fp,
input_fasta_filename,
clean_otu_table_filename,
id_to_taxonomy_fp=None,
confidences=None,
e_values=None,
command_handler=call_commands_serially,
rdp_max_memory=None,
status_update_callback=print_to_stdout,
force=False,
read_1_seqs_fp=None,
read_2_seqs_fp=None):
""" Performs sanity checks on passed arguments and directories. Builds
commands for each method and sends them off to be executed. """
## Check if temp output directory exists
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)
## Check for inputs that are universally required
if assignment_methods is None:
raise WorkflowError("You must specify at least one method:"
"'rdp', 'blast', 'mothur', or 'rtax'.")
if input_fasta_filename is None:
raise WorkflowError("You must provide an input fasta filename.")
if clean_otu_table_filename is None:
raise WorkflowError("You must provide a clean otu table filename.")
if id_to_taxonomy_fp is None:
raise WorkflowError("You must provide an ID to taxonomy map filename.")
logger = WorkflowLogger(generate_log_fp(output_dir))
time_results = []
for input_dir in input_dirs:
## Make sure the input dataset directory exists.
if not isdir(input_dir):
raise WorkflowError("The input directory '%s' does not exist." %
input_dir)
input_dir_name = split(normpath(input_dir))[1]
output_dataset_dir = join(output_dir, input_dir_name)
input_fasta_fp = join(input_dir, input_fasta_filename)
clean_otu_table_fp = join(input_dir, clean_otu_table_filename)
logger.write("\nCreating output subdirectory '%s' if it doesn't "
"already exist.\n" % output_dataset_dir)
try:
makedirs(output_dataset_dir)
except OSError:
# It already exists, which is okay since we already know we are in
# 'force' mode from above.
pass
for method in assignment_methods:
## Method is RDP
if method == 'rdp':
## Check for execution parameters required by RDP method
if confidences is None:
raise WorkflowError("You must specify at least one "
"confidence level.")
## Generate command for RDP
commands = _generate_rdp_commands(
output_dataset_dir,
input_fasta_fp,
reference_seqs_fp,
id_to_taxonomy_fp,
clean_otu_table_fp,
confidences,
rdp_max_memory=rdp_max_memory)
## Method is BLAST
elif method == 'blast':
## Check for execution parameters required by BLAST method
if e_values is None:
raise WorkflowError("You must specify at least one "
"E value.")
## Generate command for BLAST
commands = _generate_blast_commands(
output_dataset_dir, input_fasta_fp, reference_seqs_fp,
id_to_taxonomy_fp, clean_otu_table_fp, e_values)
## Method is Mothur
elif method == 'mothur':
## Check for execution parameters required by Mothur method
if confidences is None:
raise WorkflowError("You must specify at least one "
"confidence level.")
## Generate command for mothur
commands = _generate_mothur_commands(
output_dataset_dir, input_fasta_fp, reference_seqs_fp,
id_to_taxonomy_fp, clean_otu_table_fp, confidences)
## Method is RTAX
elif method == 'rtax':
## Check for execution parameters required by RTAX method
if read_1_seqs_fp is None:
raise WorkflowError("You must specify a file containing "
"the first read from pair-end "
"sequencing.")
## Generate command for rtax
commands = _generate_rtax_commands(
output_dataset_dir,
input_fasta_fp,
reference_seqs_fp,
id_to_taxonomy_fp,
clean_otu_table_fp,
read_1_seqs_fp,
read_2_seqs_fp=read_2_seqs_fp)
## Unsupported method
else:
raise WorkflowError("Unrecognized or unsupported taxonomy "
"assignment method '%s'." % method)
# send command for current method to command handler
for command in commands:
#call_commands_serially needs a list of commands so here's a length one commmand list.
c = list()
c.append(command)
start = time()
command_handler(c,
status_update_callback,
logger,
close_logger_on_success=False)
end = time()
input_file = command[0][1].split()[
command[0][1].split().index('-i') + 1].split('/')[-2]
if 'Assigning' in command[0][0]:
time_results.append(
(input_file, ' '.join(command[0][0].split()[2:]),
end - start))
# removes and writes out the title we initialized with earlier
logger.write('\n\nAssignment times (seconds):\n')
for t in time_results:
# write out each time result as (method, params)\ttime (seconds)
#First clean up the output
method, param = t[1].split(', ')
method = method.lstrip('(')
param = param.rstrip(')')
logger.write('%s\t%s\t%s\t%s\n' % (t[0], method, param, str(t[2])))
logger.close()