def main():
option_parser, opts, args = parse_command_line_parameters(**script_info)
verbose = opts.verbose
input_biom_fp = opts.input_biom_fp
output_dir = opts.output_dir
categories = opts.categories
if categories is not None:
categories = categories.split(',')
tree_fp = opts.tree_fp
mapping_fp = opts.mapping_fp
verbose = opts.verbose
parallel = opts.parallel
sampling_depth = opts.sampling_depth
nonphylogenetic_diversity = opts.nonphylogenetic_diversity
print_only = opts.print_only
suppress_taxa_summary = opts.suppress_taxa_summary
suppress_beta_diversity = opts.suppress_beta_diversity
suppress_alpha_diversity = opts.suppress_alpha_diversity
suppress_group_significance = opts.suppress_group_significance
if opts.parameter_fp is not None:
params = parse_qiime_parameters(open(opts.parameter_fp, 'U'))
else:
params = parse_qiime_parameters([])
if nonphylogenetic_diversity:
# if the user specified --nonphylogenetic_diversity and they
# didn't define metrics in a parameters file, define them here
if 'metrics' not in params['beta_diversity']:
params['beta_diversity']['metrics'] = 'bray_curtis'
if 'metrics' not in params['alpha_diversity']:
params['alpha_diversity']['metrics'] = 'observed_otus,chao1'
else:
if tree_fp is None:
option_parser.error(
"--tree_fp is required unless --nonphylogenetic_diversity "
"is passed.")
jobs_to_start = opts.jobs_to_start
default_jobs_to_start = qiime_config['jobs_to_start']
validate_and_set_jobs_to_start(params,
jobs_to_start,
default_jobs_to_start,
parallel,
option_parser)
# Create the output directory. If it already exists and the user
# isn't trying to recover from a failed run, raise an error.
create_dir(output_dir, fail_on_exist=not opts.recover_from_failure)
if print_only:
command_handler = print_commands
else:
command_handler = call_commands_serially
if verbose:
status_update_callback = print_to_stdout
else:
status_update_callback = no_status_updates
run_core_diversity_analyses(
biom_fp=input_biom_fp,
mapping_fp=mapping_fp,
sampling_depth=sampling_depth,
output_dir=output_dir,
qiime_config=load_qiime_config(),
command_handler=command_handler,
tree_fp=tree_fp,
params=params,
categories=categories,
arare_min_rare_depth=10,
arare_num_steps=10,
parallel=parallel,
suppress_taxa_summary=suppress_taxa_summary,
suppress_beta_diversity=suppress_beta_diversity,
suppress_alpha_diversity=suppress_alpha_diversity,
suppress_group_significance=suppress_group_significance,
status_update_callback=status_update_callback)
def main():
option_parser, opts, args = \
parse_command_line_parameters(**script_info)
verbose = opts.verbose
otu_table_fp = opts.otu_table_fp
output_dir = opts.output_dir
tree_fp = opts.tree_fp
seqs_per_sample = opts.seqs_per_sample
verbose = opts.verbose
print_only = opts.print_only
master_tree = opts.master_tree
parallel = opts.parallel
# No longer checking that jobs_to_start > 2, but
# commenting as we may change our minds about this.
#if parallel: raise_error_on_parallel_unavailable()
if opts.parameter_fp:
try:
parameter_f = open(opts.parameter_fp, 'U')
except IOError:
raise IOError("Can't open parameters file (%s). Does it exist? Do you have read access?"
% opts.parameter_fp)
params = parse_qiime_parameters(parameter_f)
parameter_f.close()
else:
params = parse_qiime_parameters([])
# empty list returns empty defaultdict for now
jobs_to_start = opts.jobs_to_start
default_jobs_to_start = qiime_config['jobs_to_start']
validate_and_set_jobs_to_start(params,
jobs_to_start,
default_jobs_to_start,
parallel,
option_parser)
try:
makedirs(output_dir)
except OSError:
if opts.force:
pass
else:
# Since the analysis can take quite a while, I put this check
# in to help users avoid overwriting previous output.
option_parser.error("Output directory already exists. Please choose"
" a different directory, or force overwrite with -f.")
if print_only:
command_handler = print_commands
else:
command_handler = call_commands_serially
if verbose:
status_update_callback = print_to_stdout
else:
status_update_callback = no_status_updates
run_jackknifed_beta_diversity(otu_table_fp=otu_table_fp,
tree_fp=tree_fp,
seqs_per_sample=seqs_per_sample,
output_dir=output_dir,
command_handler=command_handler,
params=params,
qiime_config=qiime_config,
mapping_fp=opts.mapping_fp,
parallel=parallel,
status_update_callback=status_update_callback,
master_tree=master_tree)
def main():
option_parser, opts, args = parse_command_line_parameters(**script_info)
verbose = opts.verbose
input_fps = opts.input_fps
refseqs_fp = opts.reference_fp
output_dir = opts.output_dir
otu_picking_method = opts.otu_picking_method
verbose = opts.verbose
print_only = False
percent_subsample = opts.percent_subsample
new_ref_set_id = opts.new_ref_set_id
prefilter_refseqs_fp = opts.prefilter_refseqs_fp
prefilter_percent_id = opts.prefilter_percent_id
if prefilter_percent_id == 0.0:
prefilter_percent_id = None
if otu_picking_method == 'uclust':
denovo_otu_picking_method = 'uclust'
reference_otu_picking_method = 'uclust_ref'
elif otu_picking_method == 'usearch61':
denovo_otu_picking_method = 'usearch61'
reference_otu_picking_method = 'usearch61_ref'
elif otu_picking_method == 'sortmerna_sumaclust':
denovo_otu_picking_method = 'sumaclust'
reference_otu_picking_method = 'sortmerna'
# SortMeRNA uses the E-value to filter out erroneous
# sequences, this option does not apply for this
# tool
if prefilter_percent_id > 0.0:
prefilter_percent_id = None
else:
# it shouldn't be possible to get here
option_parser.error('Unkown OTU picking method: %s' %
otu_picking_method)
parallel = opts.parallel
# No longer checking that jobs_to_start > 2, but
# commenting as we may change our minds about this.
#if parallel: raise_error_on_parallel_unavailable()
if opts.parameter_fp:
try:
parameter_f = open(opts.parameter_fp, 'U')
except IOError:
raise IOError("Can't open parameters file (%s). Does it exist? "
"Do you have read access?" % opts.parameter_fp)
params = parse_qiime_parameters(parameter_f)
parameter_f.close()
else:
params = parse_qiime_parameters([])
# empty list returns empty defaultdict for now
jobs_to_start = opts.jobs_to_start
default_jobs_to_start = qiime_config['jobs_to_start']
validate_and_set_jobs_to_start(params, jobs_to_start,
default_jobs_to_start, parallel, option_parser)
try:
makedirs(output_dir)
except OSError:
if opts.force:
pass
else:
option_parser.error("Output directory already exists. Please "
"choose a different directory, or force overwrite with -f.")
if print_only:
command_handler = print_commands
else:
command_handler = call_commands_serially
if verbose:
status_update_callback = print_to_stdout
else:
status_update_callback = no_status_updates
if len(input_fps) == 1:
pick_subsampled_open_reference_otus(input_fp=input_fps[0],
refseqs_fp=refseqs_fp, output_dir=output_dir,
percent_subsample=percent_subsample, new_ref_set_id=new_ref_set_id,
command_handler=command_handler, params=params,
min_otu_size=opts.min_otu_size,
run_assign_tax=not opts.suppress_taxonomy_assignment,
run_align_and_tree=not opts.suppress_align_and_tree,
qiime_config=qiime_config,
prefilter_refseqs_fp=prefilter_refseqs_fp,
prefilter_percent_id=prefilter_percent_id,
step1_otu_map_fp=opts.step1_otu_map_fp,
step1_failures_fasta_fp=opts.step1_failures_fasta_fp,
parallel=parallel, suppress_step4=opts.suppress_step4, logger=None,
denovo_otu_picking_method=denovo_otu_picking_method,
reference_otu_picking_method=reference_otu_picking_method,
status_update_callback=status_update_callback)
else:
iterative_pick_subsampled_open_reference_otus(input_fps=input_fps,
refseqs_fp=refseqs_fp, output_dir=output_dir,
percent_subsample=percent_subsample, new_ref_set_id=new_ref_set_id,
command_handler=command_handler, params=params,
min_otu_size=opts.min_otu_size,
run_assign_tax=not opts.suppress_taxonomy_assignment,
run_align_and_tree=not opts.suppress_align_and_tree,
qiime_config=qiime_config,
prefilter_refseqs_fp=prefilter_refseqs_fp,
prefilter_percent_id=prefilter_percent_id,
step1_otu_map_fp=opts.step1_otu_map_fp,
step1_failures_fasta_fp=opts.step1_failures_fasta_fp,
parallel=parallel, suppress_step4=opts.suppress_step4, logger=None,
denovo_otu_picking_method=denovo_otu_picking_method,
reference_otu_picking_method=reference_otu_picking_method,
status_update_callback=status_update_callback)
def main():
option_parser, opts, args = parse_command_line_parameters(**script_info)
verbose = opts.verbose
otu_table_fp = opts.otu_table_fp
output_dir = opts.output_dir
mapping_fp = opts.mapping_fp
tree_fp = opts.tree_fp
verbose = opts.verbose
print_only = opts.print_only
seqs_per_sample = opts.seqs_per_sample
parallel = opts.parallel
# No longer checking that jobs_to_start > 2, but
# commenting as we may change our minds about this.
#if parallel: raise_error_on_parallel_unavailable()
if opts.parameter_fp:
try:
parameter_f = open(opts.parameter_fp, 'U')
except IOError:
raise IOError,\
"Can't open parameters file (%s). Does it exist? Do you have read access?"\
% opts.parameter_fp
params = parse_qiime_parameters(parameter_f)
parameter_f.close()
else:
params = parse_qiime_parameters([])
# empty list returns empty defaultdict for now
jobs_to_start = opts.jobs_to_start
default_jobs_to_start = qiime_config['jobs_to_start']
validate_and_set_jobs_to_start(params,
jobs_to_start,
default_jobs_to_start,
parallel,
option_parser)
try:
makedirs(output_dir)
except OSError:
if opts.force:
pass
else:
# Since the analysis can take quite a while, I put this check
# in to help users avoid overwriting previous output.
option_parser.error("Output directory already exists. Please choose"
" a different directory, or force overwrite with -f.")
if print_only:
command_handler = print_commands
else:
command_handler = call_commands_serially
if verbose:
status_update_callback = print_to_stdout
else:
status_update_callback = no_status_updates
run_beta_diversity_through_plots(otu_table_fp=otu_table_fp,
mapping_fp=mapping_fp,
output_dir=output_dir,
command_handler=command_handler,
params=params,
qiime_config=qiime_config,
color_by_interesting_fields_only=not opts.color_by_all_fields,
sampling_depth=seqs_per_sample,
tree_fp=tree_fp,
parallel=parallel,
suppress_emperor_plots=opts.suppress_emperor_plots,
status_update_callback=status_update_callback)
def main():
option_parser, opts, args =\
parse_command_line_parameters(**script_info)
verbose = opts.verbose
input_fps = opts.input_fps
refseqs_fp = opts.reference_fp
output_dir = opts.output_dir
verbose = opts.verbose
print_only = False
percent_subsample = opts.percent_subsample
new_ref_set_id = opts.new_ref_set_id
prefilter_refseqs_fp = opts.prefilter_refseqs_fp
prefilter_percent_id = opts.prefilter_percent_id
if prefilter_percent_id == 0.0:
prefilter_percent_id = None
parallel = opts.parallel
# No longer checking that jobs_to_start > 2, but
# commenting as we may change our minds about this.
#if parallel: raise_error_on_parallel_unavailable()
if opts.parameter_fp:
try:
parameter_f = open(opts.parameter_fp, 'U')
except IOError:
raise IOError,\
"Can't open parameters file (%s). Does it exist? Do you have read access?"\
% opts.parameter_fp
params = parse_qiime_parameters(parameter_f)
parameter_f.close()
else:
params = parse_qiime_parameters([])
# empty list returns empty defaultdict for now
jobs_to_start = opts.jobs_to_start
default_jobs_to_start = qiime_config['jobs_to_start']
validate_and_set_jobs_to_start(params,
jobs_to_start,
default_jobs_to_start,
parallel,
option_parser)
try:
makedirs(output_dir)
except OSError:
if opts.force:
pass
else:
option_parser.error("Output directory already exists. Please choose"
" a different directory, or force overwrite with -f.")
if print_only:
command_handler = print_commands
else:
command_handler = call_commands_serially
if verbose:
status_update_callback = print_to_stdout
else:
status_update_callback = no_status_updates
if len(input_fps) == 1:
pick_subsampled_open_reference_otus(input_fp=input_fps[0],
refseqs_fp=refseqs_fp,
output_dir=output_dir,
percent_subsample=percent_subsample,
new_ref_set_id=new_ref_set_id,
command_handler=command_handler,
params=params,
min_otu_size=opts.min_otu_size,
run_assign_tax=not opts.suppress_taxonomy_assignment,
run_align_and_tree=not opts.suppress_align_and_tree,
qiime_config=qiime_config,
prefilter_refseqs_fp=prefilter_refseqs_fp,
prefilter_percent_id=prefilter_percent_id,
step1_otu_map_fp=opts.step1_otu_map_fp,
step1_failures_fasta_fp=opts.step1_failures_fasta_fp,
parallel=parallel,
suppress_step4=opts.suppress_step4,
logger=None,
status_update_callback=status_update_callback)
else:
iterative_pick_subsampled_open_reference_otus(input_fps=input_fps,
refseqs_fp=refseqs_fp,
output_dir=output_dir,
percent_subsample=percent_subsample,
new_ref_set_id=new_ref_set_id,
command_handler=command_handler,
params=params,
min_otu_size=opts.min_otu_size,
run_assign_tax=not opts.suppress_taxonomy_assignment,
run_align_and_tree=not opts.suppress_align_and_tree,
qiime_config=qiime_config,
prefilter_refseqs_fp=prefilter_refseqs_fp,
prefilter_percent_id=prefilter_percent_id,
step1_otu_map_fp=opts.step1_otu_map_fp,
step1_failures_fasta_fp=opts.step1_failures_fasta_fp,
parallel=parallel,
suppress_step4=opts.suppress_step4,
logger=None,
status_update_callback=status_update_callback)
def main():
option_parser, opts, args = parse_command_line_parameters(**script_info)
verbose = opts.verbose
input_biom_fp = opts.input_biom_fp
output_dir = opts.output_dir
categories = opts.categories
if categories is not None:
categories = categories.split(',')
tree_fp = opts.tree_fp
mapping_fp = opts.mapping_fp
verbose = opts.verbose
parallel = opts.parallel
sampling_depth = opts.sampling_depth
nonphylogenetic_diversity = opts.nonphylogenetic_diversity
print_only = opts.print_only
suppress_taxa_summary = opts.suppress_taxa_summary
suppress_beta_diversity = opts.suppress_beta_diversity
suppress_alpha_diversity = opts.suppress_alpha_diversity
suppress_group_significance = opts.suppress_group_significance
if opts.parameter_fp is not None:
params = parse_qiime_parameters(open(opts.parameter_fp, 'U'))
else:
params = parse_qiime_parameters([])
if nonphylogenetic_diversity:
# if the user specified --nonphylogenetic_diversity and they
# didn't define metrics in a parameters file, define them here
if 'metrics' not in params['beta_diversity']:
params['beta_diversity']['metrics'] = 'bray_curtis'
if 'metrics' not in params['alpha_diversity']:
params['alpha_diversity']['metrics'] = 'observed_otus,chao1'
jobs_to_start = opts.jobs_to_start
default_jobs_to_start = qiime_config['jobs_to_start']
validate_and_set_jobs_to_start(params, jobs_to_start,
default_jobs_to_start, parallel,
option_parser)
# Create the output directory. If it already exists and the user
# isn't trying to recover from a failed run, raise an error.
create_dir(output_dir, fail_on_exist=not opts.recover_from_failure)
if print_only:
command_handler = print_commands
else:
command_handler = call_commands_serially
if verbose:
status_update_callback = print_to_stdout
else:
status_update_callback = no_status_updates
run_core_diversity_analyses(
biom_fp=input_biom_fp,
mapping_fp=mapping_fp,
sampling_depth=sampling_depth,
output_dir=output_dir,
qiime_config=load_qiime_config(),
command_handler=command_handler,
tree_fp=tree_fp,
params=params,
categories=categories,
arare_min_rare_depth=10,
arare_num_steps=10,
parallel=parallel,
suppress_taxa_summary=suppress_taxa_summary,
suppress_beta_diversity=suppress_beta_diversity,
suppress_alpha_diversity=suppress_alpha_diversity,
suppress_group_significance=suppress_group_significance,
status_update_callback=status_update_callback)
def main():
option_parser, opts, args = parse_command_line_parameters(**script_info)
verbose = opts.verbose
input_fp = opts.input_fp
reference_fp = opts.reference_fp
taxonomy_fp = opts.taxonomy_fp
output_dir = opts.output_dir
verbose = opts.verbose
print_only = opts.print_only
parallel = opts.parallel
# No longer checking that jobs_to_start > 2, but
# commenting as we may change our minds about this.
#if parallel: raise_error_on_parallel_unavailable()
if opts.parameter_fp:
try:
parameter_f = open(opts.parameter_fp, 'U')
except IOError:
raise IOError,\
"Can't open parameters file (%s). Does it exist? Do you have read access?"\
% opts.parameter_fp
params = parse_qiime_parameters(parameter_f)
parameter_f.close()
else:
params = parse_qiime_parameters([])
# empty list returns empty defaultdict for now
jobs_to_start = opts.jobs_to_start
default_jobs_to_start = qiime_config['jobs_to_start']
validate_and_set_jobs_to_start(params,
jobs_to_start,
default_jobs_to_start,
parallel,
option_parser)
try:
makedirs(output_dir)
except OSError:
if opts.force:
pass
else:
option_parser.error("Output directory already exists. Please choose"
" a different directory, or force overwrite with -f.")
if print_only:
command_handler = print_commands
else:
command_handler = call_commands_serially
if verbose:
status_update_callback = print_to_stdout
else:
status_update_callback = no_status_updates
run_pick_closed_reference_otus(
input_fp,
reference_fp,
output_dir,
taxonomy_fp,
command_handler=command_handler,
params=params,
qiime_config=qiime_config,
parallel=parallel,
status_update_callback=status_update_callback)
def main():
option_parser, opts, args = parse_command_line_parameters(**script_info)
verbose = opts.verbose
otu_table_fp = opts.otu_table_fp
output_dir = opts.output_dir
mapping_fp = opts.mapping_fp
tree_fp = opts.tree_fp
verbose = opts.verbose
print_only = opts.print_only
seqs_per_sample = opts.seqs_per_sample
parallel = opts.parallel
# No longer checking that jobs_to_start > 2, but
# commenting as we may change our minds about this.
#if parallel: raise_error_on_parallel_unavailable()
if opts.parameter_fp:
try:
parameter_f = open(opts.parameter_fp, 'U')
except IOError:
raise IOError(
"Can't open parameters file (%s). Does it exist? Do you have read access?"
% opts.parameter_fp)
params = parse_qiime_parameters(parameter_f)
parameter_f.close()
else:
params = parse_qiime_parameters([])
# empty list returns empty defaultdict for now
jobs_to_start = opts.jobs_to_start
default_jobs_to_start = qiime_config['jobs_to_start']
validate_and_set_jobs_to_start(params, jobs_to_start,
default_jobs_to_start, parallel,
option_parser)
create_dir(output_dir, fail_on_exist=not opts.force)
if print_only:
command_handler = print_commands
else:
command_handler = call_commands_serially
if verbose:
status_update_callback = print_to_stdout
else:
status_update_callback = no_status_updates
run_beta_diversity_through_plots(
otu_table_fp=otu_table_fp,
mapping_fp=mapping_fp,
output_dir=output_dir,
command_handler=command_handler,
params=params,
qiime_config=qiime_config,
color_by_interesting_fields_only=not opts.color_by_all_fields,
sampling_depth=seqs_per_sample,
tree_fp=tree_fp,
parallel=parallel,
suppress_emperor_plots=opts.suppress_emperor_plots,
status_update_callback=status_update_callback)
def main():
option_parser, opts, args = parse_command_line_parameters(**script_info)
verbose = opts.verbose
otu_table_fp = opts.otu_table_fp
output_dir = opts.output_dir
mapping_fp = opts.mapping_fp
tree_fp = opts.tree_fp
num_steps = opts.num_steps
verbose = opts.verbose
print_only = opts.print_only
parallel = opts.parallel
min_rare_depth = opts.min_rare_depth
max_rare_depth = opts.max_rare_depth
retain_intermediate_files = opts.retain_intermediate_files
if opts.parameter_fp:
try:
parameter_f = open(opts.parameter_fp, 'U')
except IOError:
raise IOError,\
"Can't open parameters file (%s). Does it exist? Do you have read access?"\
% opts.parameter_fp
params = parse_qiime_parameters(parameter_f)
parameter_f.close()
else:
params = parse_qiime_parameters([])
# empty list returns empty defaultdict for now
jobs_to_start = opts.jobs_to_start
default_jobs_to_start = qiime_config['jobs_to_start']
validate_and_set_jobs_to_start(params,
jobs_to_start,
default_jobs_to_start,
parallel,
option_parser)
try:
makedirs(output_dir)
except OSError:
if opts.force:
pass
else:
# Since the analysis can take quite a while, I put this check
# in to help users avoid overwriting previous output.
option_parser.error("Output directory already exists. Please choose"
" a different directory, or force overwrite with -f.")
if print_only:
command_handler = print_commands
else:
command_handler = call_commands_serially
if verbose:
status_update_callback = print_to_stdout
else:
status_update_callback = no_status_updates
run_alpha_rarefaction(otu_table_fp=otu_table_fp,\
mapping_fp=mapping_fp,\
output_dir=output_dir,\
command_handler=command_handler,\
params=params,
qiime_config=qiime_config,\
tree_fp=tree_fp,\
num_steps=num_steps,\
parallel=parallel,\
min_rare_depth=min_rare_depth,
max_rare_depth=max_rare_depth,
status_update_callback=status_update_callback,
retain_intermediate_files=retain_intermediate_files)
def main():
option_parser, opts, args = parse_command_line_parameters(**script_info)
verbose = opts.verbose
input_fp = opts.input_fp
reference_fp = opts.reference_fp
taxonomy_fp = opts.taxonomy_fp
output_dir = opts.output_dir
verbose = opts.verbose
print_only = opts.print_only
assign_taxonomy = opts.assign_taxonomy
parallel = opts.parallel
# No longer checking that jobs_to_start > 2, but
# commenting as we may change our minds about this.
# if parallel: raise_error_on_parallel_unavailable()
if opts.parameter_fp:
try:
parameter_f = open(opts.parameter_fp, 'U')
except IOError:
raise IOError(
"Can't open parameters file (%s). Does it exist? Do you have read access?"
% opts.parameter_fp)
params = parse_qiime_parameters(parameter_f)
parameter_f.close()
else:
params = parse_qiime_parameters([])
# empty list returns empty defaultdict for now
jobs_to_start = opts.jobs_to_start
default_jobs_to_start = qiime_config['jobs_to_start']
validate_and_set_jobs_to_start(params, jobs_to_start,
default_jobs_to_start, parallel,
option_parser)
if print_only:
command_handler = print_commands
else:
command_handler = call_commands_serially
try:
makedirs(output_dir)
except OSError:
if opts.force:
pass
else:
option_parser.error(
"Output directory already exists. Please choose"
" a different directory, or force overwrite with -f.")
if verbose:
status_update_callback = print_to_stdout
else:
status_update_callback = no_status_updates
run_pick_closed_reference_otus(
input_fp,
reference_fp,
output_dir,
taxonomy_fp,
assign_taxonomy=assign_taxonomy,
command_handler=command_handler,
params=params,
qiime_config=qiime_config,
parallel=parallel,
status_update_callback=status_update_callback)
def main():
option_parser, opts, args = parse_command_line_parameters(**script_info)
verbose = opts.verbose
otu_table_fp = opts.otu_table_fp
output_dir = opts.output_dir
mapping_fp = opts.mapping_fp
tree_fp = opts.tree_fp
verbose = opts.verbose
print_only = opts.print_only
seqs_per_sample = opts.seqs_per_sample
parallel = opts.parallel
# No longer checking that jobs_to_start > 2, but
# commenting as we may change our minds about this.
#if parallel: raise_error_on_parallel_unavailable()
if opts.parameter_fp:
try:
parameter_f = open(opts.parameter_fp, 'U')
except IOError:
raise IOError("Can't open parameters file (%s). Does it exist? Do you have read access?"
% opts.parameter_fp)
params = parse_qiime_parameters(parameter_f)
parameter_f.close()
else:
params = parse_qiime_parameters([])
# empty list returns empty defaultdict for now
jobs_to_start = opts.jobs_to_start
default_jobs_to_start = qiime_config['jobs_to_start']
validate_and_set_jobs_to_start(params,
jobs_to_start,
default_jobs_to_start,
parallel,
option_parser)
create_dir(output_dir, fail_on_exist=not opts.force)
if print_only:
command_handler = print_commands
else:
command_handler = call_commands_serially
if verbose:
status_update_callback = print_to_stdout
else:
status_update_callback = no_status_updates
run_beta_diversity_through_plots(otu_table_fp=otu_table_fp,
mapping_fp=mapping_fp,
output_dir=output_dir,
command_handler=command_handler,
params=params,
qiime_config=qiime_config,
color_by_interesting_fields_only=not opts.color_by_all_fields,
sampling_depth=seqs_per_sample,
tree_fp=tree_fp,
parallel=parallel,
suppress_emperor_plots=opts.suppress_emperor_plots,
status_update_callback=status_update_callback)
def main():
option_parser, opts, args = parse_command_line_parameters(**script_info)
verbose = opts.verbose
otu_table_fp = opts.otu_table_fp
output_dir = opts.output_dir
mapping_fp = opts.mapping_fp
tree_fp = opts.tree_fp
verbose = opts.verbose
print_only = opts.print_only
seqs_per_sample = opts.seqs_per_sample
histogram_categories = opts.histogram_categories
if histogram_categories != None:
histogram_categories = histogram_categories.split(",")
parallel = opts.parallel
# No longer checking that jobs_to_start > 2, but
# commenting as we may change our minds about this.
# if parallel: raise_error_on_parallel_unavailable()
if opts.parameter_fp:
try:
parameter_f = open(opts.parameter_fp, "U")
except IOError:
raise IOError, "Can't open parameters file (%s). Does it exist? Do you have read access?" % opts.parameter_fp
params = parse_qiime_parameters(parameter_f)
parameter_f.close()
else:
params = parse_qiime_parameters([])
# empty list returns empty defaultdict for now
jobs_to_start = opts.jobs_to_start
default_jobs_to_start = qiime_config["jobs_to_start"]
validate_and_set_jobs_to_start(params, jobs_to_start, default_jobs_to_start, parallel, option_parser)
try:
makedirs(output_dir)
except OSError:
if opts.force:
pass
else:
# Since the analysis can take quite a while, I put this check
# in to help users avoid overwriting previous output.
option_parser.error(
"Output directory already exists. Please choose" " a different directory, or force overwrite with -f."
)
if print_only:
command_handler = print_commands
else:
command_handler = call_commands_serially
if verbose:
status_update_callback = print_to_stdout
else:
status_update_callback = no_status_updates
run_beta_diversity_through_plots(
otu_table_fp=otu_table_fp,
mapping_fp=mapping_fp,
output_dir=output_dir,
command_handler=command_handler,
params=params,
qiime_config=qiime_config,
color_by_interesting_fields_only=not opts.color_by_all_fields,
sampling_depth=seqs_per_sample,
histogram_categories=histogram_categories,
tree_fp=tree_fp,
parallel=parallel,
suppress_3d_plots=opts.suppress_3d_plots,
suppress_2d_plots=opts.suppress_2d_plots,
status_update_callback=status_update_callback,
)
def main():
option_parser, opts, args =\
parse_command_line_parameters(**script_info)
otu_table_fp = opts.otu_table_fp
output_dir = opts.output_dir
mapping_fp = opts.mapping_fp
tree_fp = opts.tree_fp
verbose = opts.verbose
print_only = opts.print_only
seqs_per_sample = int(opts.seqs_per_sample)
parallel = opts.parallel
min_seqs_sample = opts.min_seqs_sample
subject_category = opts.subject_name
try:
makedirs(output_dir)
except OSError:
if opts.force:
pass
else:
# Since the analysis can take quite a while, I put this check
# in to help users avoid overwriting previous output.
option_parser.error("Output directory already exists. Please choose"
" a different directory, or force overwrite with -f.")
## ******************** make_evident_selectors ********************
## The code for make_evident_selectors.py is here and has to go before the params
## validation as we need to know the main cats before creating the params file
map_data, headers, comments = parse_mapping_file(open(mapping_fp, 'U'))
biom_table = parse_biom_table(open(otu_table_fp, 'U'))
# getting valid samples from biom file
real_map_headers, real_map_data = filter_mapping_file(map_data, headers,\
biom_table.SampleIds, include_repeat_cols=False)
if subject_category not in real_map_headers:
option_parser.error('This column: %s is not in the mapping file, try %s'%\
(subject_category, real_map_headers))
sorted_counts_per_sample = get_sorted_counts_per_sample(biom_table)
mapping_file_tuple = (real_map_data, real_map_headers)
# calculate the available subjects at each rarefaction level
results, main_map_cat = make_selectors(sorted_counts_per_sample, min_seqs_sample,\
mapping_file_tuple, subject_category, verbose=verbose)
fout = open(join(output_dir,'selectors.txt'),'w')
fout.write('#Sequences\tSubjects\tSamples\tMetadata\n')
fout.write('\n'.join(results))
fout.close()
fout = open(join(output_dir,'mapping_file.txt'),'w')
fout.write(format_mapping_file(real_map_headers, real_map_data))
fout.close()
## ******************** make_evident_selectors ********************
fout = open(join(output_dir,'study_preferences.txt'),'w')
fout.write('%d\n' % seqs_per_sample)
fout.write('%s\n' % subject_category)
fout.close()
## ******************** filter_samples_from_otu_table ********************
## Filtering original biom file to only have samples above the max length to avoid
## ugly plots
alpha_biom_file = join(output_dir,'filtered_otu_table_for_alpha.biom')
fout = open(alpha_biom_file,'w')
sample_ids_to_keep = biom_table.SampleIds
filtered_otu_table = filter_samples_from_otu_table(biom_table,
sample_ids_to_keep,
min_count=seqs_per_sample,
max_count=inf)
fout.write(format_biom_table(filtered_otu_table))
fout.close()
## ******************** filter_samples_from_otu_table ********************
if opts.parameter_fp:
try:
parameter_f = open(opts.parameter_fp, 'U')
except IOError:
option_parser.error("Can't open parameters file (%s). Does it exist? " \
"Do you have read access?" % opts.parameter_fp)
params = parse_qiime_parameters(parameter_f)
parameter_f.close()
else:
params = parse_qiime_parameters(
['beta_diversity:metrics unweighted_unifrac',\
'make_rarefaction_plots:prefs_path %s' % join(output_dir,'prefs.txt'),
'make_rarefaction_plots:colorby %s' % ','.join(main_map_cat),
'make_rarefaction_plots:output_type memory',
'multiple_rarefactions:min %d' % int(seqs_per_sample/4),
'multiple_rarefactions:max %d' % (seqs_per_sample+1),
'multiple_rarefactions:step %d' % int(seqs_per_sample/4),
'multiple_rarefactions:num-reps 4',
])
# empty list returns empty defaultdict for now
jobs_to_start = opts.jobs_to_start
default_jobs_to_start = qiime_config['jobs_to_start']
validate_and_set_jobs_to_start(params,
jobs_to_start,
default_jobs_to_start,
parallel,
option_parser)
if print_only:
command_handler = print_commands
else:
command_handler = call_commands_serially
if verbose:
status_update_callback = print_to_stdout
else:
status_update_callback = no_status_updates
copyfile(otu_table_fp, join(output_dir,'raw.biom'))
run_beta_diversity_through_plots(otu_table_fp=otu_table_fp,
mapping_fp=mapping_fp,
output_dir=output_dir,
command_handler=command_handler,
params=params,
qiime_config=qiime_config,
color_by_interesting_fields_only=False,
sampling_depth=seqs_per_sample,
histogram_categories=None,
tree_fp=tree_fp,
parallel=parallel,
suppress_3d_plots=True,
suppress_2d_plots=True,
status_update_callback=status_update_callback)
output_dir = join(output_dir,'alpha')
run_alpha_rarefaction(otu_table_fp=alpha_biom_file,\
mapping_fp=mapping_fp,\
output_dir=output_dir,\
command_handler=command_handler,\
params=params,
qiime_config=qiime_config,\
tree_fp=tree_fp,\
num_steps=4,\
parallel=parallel,\
min_rare_depth=10,
max_rare_depth=20,
status_update_callback=status_update_callback,
plot_stderr_and_stddev=True)
