def main():
option_parser, opts, args =\
parse_command_line_parameters(**script_info)
if opts.level <= 0:
option_parser.error("level must be greater than zero!")
collapse_f = make_collapse_f(opts.metadata_category, opts.level,
opts.ignore)
table = load_table(opts.input_fp)
if h5py.is_hdf5(opts.input_fp):
# metadata are not deserializing correctly. Duct tape it.
update_d = {}
for i, md in zip(table.ids(axis='observation'),
table.metadata(axis='observation')):
update_d[i] = {k: json.loads(v[0]) for k, v in md.items()}
table.add_metadata(update_d, axis='observation')
result = table.collapse(collapse_f,
axis='observation',
one_to_many=True,
norm=False,
one_to_many_md_key=opts.metadata_category)
if (opts.format_tab_delimited):
f = open(opts.output_fp, 'w')
f.write(
result.to_tsv(header_key=opts.metadata_category,
header_value=opts.metadata_category,
metadata_formatter=lambda s: '; '.join(s)))
f.close()
else:
format_fs = {opts.metadata_category: vlen_list_of_str_formatter}
write_biom_table(result, opts.output_fp, format_fs=format_fs)
def main():
option_parser, opts, args =\
parse_command_line_parameters(**script_info)
if opts.level <= 0:
option_parser.error("level must be greater than zero!")
collapse_f = make_collapse_f(opts.metadata_category, opts.level,
opts.ignore)
table = load_table(opts.input_fp)
if h5py.is_hdf5(opts.input_fp):
# metadata are not deserializing correctly. Duct tape it.
update_d = {}
for i, md in zip(table.ids(axis='observation'),
table.metadata(axis='observation')):
update_d[i] = {k: json.loads(v[0]) for k, v in md.items()}
table.add_metadata(update_d, axis='observation')
result = table.collapse(collapse_f, axis='observation', one_to_many=True,
norm=False,
one_to_many_md_key=opts.metadata_category)
if(opts.format_tab_delimited):
f = open(opts.output_fp, 'w')
f.write(result.to_tsv(header_key=opts.metadata_category,
header_value=opts.metadata_category,
metadata_formatter=lambda s: '; '.join(s)))
f.close()
else:
format_fs = {opts.metadata_category: vlen_list_of_str_formatter}
write_biom_table(result, opts.output_fp, format_fs=format_fs)
def write_metagenome_to_file(
predicted_metagenome,
output_fp,
tab_delimited=False,
verbose_filetype_message="metagenome prediction",
verbose=False,
):
"""Write a BIOM Table object to a file, creating the directory if needed
predicted_metagenome -- a BIOM table object
output_fp -- the filepath to write the output
tab_delimited -- if False, write in BIOm format, otherwise write as a tab-delimited file
verbose -- if True output verbose info to StdOut
"""
if verbose:
print "Writing %s results to output file: %s" % (verbose_filetype_message, output_fp)
make_output_dir_for_file(output_fp)
if tab_delimited:
# peek at first observation to decide on what observeration metadata
# to output in tab-delimited format
(obs_val, obs_id, obs_metadata) = predicted_metagenome.iter(axis="observation").next()
# see if there is a metadata field that contains the "Description"
# (e.g. KEGG_Description or COG_Description)
h = re.compile(".*Description")
metadata_names = filter(h.search, obs_metadata.keys())
if metadata_names:
# use the "Description" field we found
metadata_name = metadata_names[0]
elif obs_metadata.keys():
# if no "Description" metadata then just output the first
# observation metadata
metadata_name = (obs_metadata.keys())[0]
else:
# if no observation metadata then don't output any
metadata_name = None
open(output_fp, "w").write(
predicted_metagenome.to_tsv(
header_key=metadata_name, header_value=metadata_name, metadata_formatter=biom_meta_to_string
)
)
else:
# output in BIOM format
format_fs = {
"KEGG_Description": picrust_formatter,
"COG_Description": picrust_formatter,
"KEGG_Pathways": picrust_formatter,
"COG_Category": picrust_formatter,
}
write_biom_table(predicted_metagenome, output_fp, format_fs=format_fs)
def write_metagenome_to_file(predicted_metagenome,output_fp,\
tab_delimited=False,verbose_filetype_message="metagenome prediction",\
verbose=False):
"""Write a BIOM Table object to a file, creating the directory if needed
predicted_metagenome -- a BIOM table object
output_fp -- the filepath to write the output
tab_delimited -- if False, write in BIOm format, otherwise write as a tab-delimited file
verbose -- if True output verbose info to StdOut
"""
if verbose:
print "Writing %s results to output file: %s"\
%(verbose_filetype_message,output_fp)
make_output_dir_for_file(output_fp)
if tab_delimited:
#peek at first observation to decide on what observeration metadata
#to output in tab-delimited format
(obs_val,obs_id,obs_metadata)=\
predicted_metagenome.iter(axis='observation').next()
#see if there is a metadata field that contains the "Description"
#(e.g. KEGG_Description or COG_Description)
h = re.compile('.*Description')
metadata_names = filter(h.search, obs_metadata.keys())
if metadata_names:
#use the "Description" field we found
metadata_name = metadata_names[0]
elif (obs_metadata.keys()):
#if no "Description" metadata then just output the first
#observation metadata
metadata_name = (obs_metadata.keys())[0]
else:
#if no observation metadata then don't output any
metadata_name = None
open(output_fp,'w').write(predicted_metagenome.to_tsv(\
header_key=metadata_name,header_value=metadata_name,metadata_formatter=biom_meta_to_string))
else:
#output in BIOM format
format_fs = {
'KEGG_Description': picrust_formatter,
'COG_Description': picrust_formatter,
'KEGG_Pathways': picrust_formatter,
'COG_Category': picrust_formatter
}
write_biom_table(predicted_metagenome, output_fp, format_fs=format_fs)
def main():
option_parser, opts, args = parse_command_line_parameters(**script_info)
if opts.verbose:
print "Loading sequencing depth table: ", opts.input_seq_depth_file
scaling_factors = {}
for sample_id, depth in parse_seq_count_file(open(opts.input_seq_depth_file, "U")):
scaling_factors[sample_id] = depth
if opts.verbose:
print "Loading count table: ", opts.input_count_table
genome_table = load_table(opts.input_count_table)
if opts.verbose:
print "Scaling the metagenome..."
scaled_metagenomes = scale_metagenomes(genome_table, scaling_factors)
if opts.verbose:
print "Writing results to output file: ", opts.output_metagenome_table
make_output_dir_for_file(opts.output_metagenome_table)
write_biom_table(scaled_metagenomes, opts.output_metagenome_table)
def main():
option_parser, opts, args =\
parse_command_line_parameters(**script_info)
if opts.level <= 0:
parser.error("level must be greater than zero!")
collapse_f = make_collapse_f(opts.metadata_category, opts.level,
opts.ignore)
table = load_table(opts.input_fp)
result = table.collapse(collapse_f, axis='observation', one_to_many=True,
norm=False,one_to_many_md_key=opts.metadata_category)
if(opts.format_tab_delimited):
f = open(opts.output_fp,'w')
f.write(result.to_tsv(header_key=opts.metadata_category,
header_value=opts.metadata_category,
metadata_formatter=lambda s: '; '.join(s)))
f.close()
else:
format_fs = {opts.metadata_category: vlen_list_of_str_formatter}
write_biom_table(result, opts.output_fp, format_fs=format_fs)
def main():
option_parser, opts, args =\
parse_command_line_parameters(**script_info)
if opts.verbose:
print "Loading sequencing depth table: ",opts.input_seq_depth_file
scaling_factors = {}
for sample_id,depth in parse_seq_count_file(open(opts.input_seq_depth_file,'U')):
scaling_factors[sample_id]=depth
if opts.verbose:
print "Loading count table: ", opts.input_count_table
genome_table = load_table(opts.input_count_table)
if opts.verbose:
print "Scaling the metagenome..."
scaled_metagenomes = scale_metagenomes(genome_table,scaling_factors)
if opts.verbose:
print "Writing results to output file: ",opts.output_metagenome_table
make_output_dir_for_file(opts.output_metagenome_table)
write_biom_table(scaled_metagenomes, opts.output_metagenome_table)
def main():
option_parser, opts, args =\
parse_command_line_parameters(**script_info)
#if we specify we want NSTI only then we have to calculate it first
if opts.output_accuracy_metrics_only:
opts.calculate_accuracy_metrics = True
if opts.verbose:
print "Loading tree from file:", opts.tree
# Load Tree
#tree = LoadTree(opts.tree)
tree = load_picrust_tree(opts.tree, opts.verbose)
table_headers = []
traits = {}
#load the asr trait table using the previous list of functions to order the arrays
if opts.reconstructed_trait_table:
table_headers,traits =\
update_trait_dict_from_file(opts.reconstructed_trait_table)
#Only load confidence intervals on the reconstruction
#If we actually have ASR values in the analysis
if opts.reconstruction_confidence:
if opts.verbose:
print "Loading ASR confidence data from file:",\
opts.reconstruction_confidence
print "Assuming confidence data is of type:", opts.confidence_format
asr_confidence_output = open(opts.reconstruction_confidence)
asr_min_vals,asr_max_vals, params,column_mapping =\
parse_asr_confidence_output(asr_confidence_output,format=opts.confidence_format)
if 'sigma' in params:
brownian_motion_parameter = params['sigma'][0]
else:
brownian_motion_parameter = None
if opts.verbose:
print "Done. Loaded %i confidence interval values." % (
len(asr_max_vals))
print "Brownian motion parameter:", brownian_motion_parameter
else:
brownian_motion_parameter = None
#load the trait table into a dict with organism names as keys and arrays as functions
table_headers,genome_traits =\
update_trait_dict_from_file(opts.observed_trait_table,table_headers)
#Combine the trait tables overwriting the asr ones if they exist in the genome trait table.
traits.update(genome_traits)
# Specify the attribute where we'll store the reconstructions
trait_label = "Reconstruction"
if opts.verbose:
print "Assigning traits to tree..."
# Decorate tree using the traits
tree = assign_traits_to_tree(traits, tree, trait_label=trait_label)
if opts.reconstruction_confidence:
if opts.verbose:
print "Assigning trait confidence intervals to tree..."
tree = assign_traits_to_tree(asr_min_vals,tree,\
trait_label="lower_bound")
tree = assign_traits_to_tree(asr_max_vals,tree,\
trait_label="upper_bound")
if brownian_motion_parameter is None:
if opts.verbose:
print "No Brownian motion parameters loaded. Inferring these from 95% confidence intervals..."
brownian_motion_parameter = get_brownian_motion_param_from_confidence_intervals(tree,\
upper_bound_trait_label="upper_bound",\
lower_bound_trait_label="lower_bound",\
trait_label=trait_label,\
confidence=0.95)
if opts.verbose:
print "Inferred the following rate parameters:", brownian_motion_parameter
if opts.verbose:
print "Collecting list of nodes to predict..."
#Start by predict all tip nodes.
nodes_to_predict = [tip.Name for tip in tree.tips()]
if opts.verbose:
print "Found %i nodes to predict." % len(nodes_to_predict)
if opts.limit_predictions_to_organisms:
organism_id_str = opts.limit_predictions_to_organisms
ok_organism_ids = organism_id_str.split(',')
ok_organism_ids = [n.strip() for n in ok_organism_ids]
for f in set_label_conversion_fns(True, True):
ok_organism_ids = [f(i) for i in ok_organism_ids]
if opts.verbose:
print "Limiting predictions to user-specified ids:",\
",".join(ok_organism_ids)
if not ok_organism_ids:
raise RuntimeError(\
"Found no valid ids in input: %s. Were comma-separated ids specified on the command line?"\
% opts.limit_predictions_to_organisms)
nodes_to_predict =\
[n for n in nodes_to_predict if n in ok_organism_ids]
if not nodes_to_predict:
raise RuntimeError(\
"Filtering by user-specified ids resulted in an empty set of nodes to predict. Are the ids on the commmand-line and tree ids in the same format? Example tree tip name: %s, example OTU id name: %s" %([tip.Name for tip in tree.tips()][0],ok_organism_ids[0]))
if opts.verbose:
print "After filtering organisms to predict by the ids specified on the commandline, %i nodes remain to be predicted" % (
len(nodes_to_predict))
if opts.limit_predictions_by_otu_table:
if opts.verbose:
print "Limiting predictions to ids in user-specified OTU table:",\
opts.limit_predictions_by_otu_table
otu_table = open(opts.limit_predictions_by_otu_table, "U")
#Parse OTU table for ids
otu_ids =\
extract_ids_from_table(otu_table.readlines(),delimiter="\t")
if not otu_ids:
raise RuntimeError(\
"Found no valid ids in input OTU table: %s. Is the path correct?"\
% opts.limit_predictions_by_otu_table)
nodes_to_predict =\
[n for n in nodes_to_predict if n in otu_ids]
if not nodes_to_predict:
raise RuntimeError(\
"Filtering by OTU table resulted in an empty set of nodes to predict. Are the OTU ids and tree ids in the same format? Example tree tip name: %s, example OTU id name: %s" %([tip.Name for tip in tree.tips()][0],otu_ids[0]))
if opts.verbose:
print "After filtering by OTU table, %i nodes remain to be predicted" % (
len(nodes_to_predict))
# Calculate accuracy of PICRUST for the given tree, sequenced genomes
# and set of ndoes to predict
accuracy_metrics = ['NSTI']
accuracy_metric_results = None
if opts.calculate_accuracy_metrics:
if opts.verbose:
print "Calculating accuracy metrics: %s" % (
[",".join(accuracy_metrics)])
accuracy_metric_results = {}
if 'NSTI' in accuracy_metrics:
nsti_result,min_distances =\
calc_nearest_sequenced_taxon_index(tree,\
limit_to_tips = nodes_to_predict,\
trait_label = trait_label, verbose=opts.verbose)
#accuracy_metric_results['NSTI'] = nsti_result
for organism in min_distances.keys():
accuracy_metric_results[organism] = {
'NSTI': min_distances[organism]
}
if opts.verbose:
print "NSTI:", nsti_result
if opts.output_accuracy_metrics_only:
#Write accuracy metrics to file
if opts.verbose:
print "Writing accuracy metrics to file:", opts.output_accuracy_metrics
f = open(opts.output_accuracy_metrics_only, 'w+')
f.write("metric\torganism\tvalue\n")
lines = []
for organism in accuracy_metric_results.keys():
for metric in accuracy_metric_results[organism].keys():
lines.append('\t'.join([metric,organism,\
str(accuracy_metric_results[organism][metric])])+'\n')
f.writelines(sorted(lines))
f.close()
exit()
if opts.verbose:
print "Generating predictions using method:", opts.prediction_method
if opts.weighting_method == 'exponential':
#For now, use exponential weighting
weight_fn = make_neg_exponential_weight_fn(e)
variances = None #Overwritten by methods that calc variance
confidence_intervals = None #Overwritten by methods that calc variance
if opts.prediction_method == 'asr_and_weighting':
# Perform predictions using reconstructed ancestral states
if opts.reconstruction_confidence:
predictions,variances,confidence_intervals =\
predict_traits_from_ancestors(tree,nodes_to_predict,\
trait_label=trait_label,\
lower_bound_trait_label="lower_bound",\
upper_bound_trait_label="upper_bound",\
calc_confidence_intervals = True,\
brownian_motion_parameter=brownian_motion_parameter,\
weight_fn =weight_fn,verbose=opts.verbose)
else:
predictions =\
predict_traits_from_ancestors(tree,nodes_to_predict,\
trait_label=trait_label,\
weight_fn =weight_fn,verbose=opts.verbose)
elif opts.prediction_method == 'weighting_only':
#Ignore ancestral information
predictions =\
weighted_average_tip_prediction(tree,nodes_to_predict,\
trait_label=trait_label,\
weight_fn =weight_fn,verbose=opts.verbose)
elif opts.prediction_method == 'nearest_neighbor':
predictions = predict_nearest_neighbor(tree,nodes_to_predict,\
trait_label=trait_label,tips_only = True)
elif opts.prediction_method == 'random_neighbor':
predictions = predict_random_neighbor(tree,\
nodes_to_predict,trait_label=trait_label)
if opts.verbose:
print "Done making predictions."
make_output_dir_for_file(opts.output_trait_table)
out_fh = open(opts.output_trait_table, 'w')
#Generate the table of biom predictions
if opts.verbose:
print "Converting results to .biom format for output..."
biom_predictions=biom_table_from_predictions(predictions,table_headers,\
observation_metadata=None,\
sample_metadata=accuracy_metric_results,convert_to_int=False)
if opts.verbose:
print "Writing prediction results to file: ", opts.output_trait_table
if opts.output_precalc_file_in_biom:
#write biom table to file
write_biom_table(biom_predictions, opts.output_trait_table)
else:
#convert to precalc (tab-delimited) format
out_fh = open(opts.output_trait_table, 'w')
out_fh.write(convert_biom_to_precalc(biom_predictions))
out_fh.close()
#Write out variance information to file
if variances:
if opts.verbose:
print "Converting variances to BIOM format"
if opts.output_precalc_file_in_biom:
suffix = '.biom'
else:
suffix = '.tab'
biom_prediction_variances=biom_table_from_predictions({k:v['variance'] for k,v in variances.iteritems()},table_headers,\
observation_metadata=None,\
sample_metadata=None,convert_to_int=False)
outfile_base, extension = splitext(opts.output_trait_table)
variance_outfile = outfile_base + "_variances" + suffix
make_output_dir_for_file(variance_outfile)
if opts.verbose:
print "Writing variance information to file:", variance_outfile
if opts.output_precalc_file_in_biom:
write_biom_table(biom_prediction_variances, variance_outfile)
else:
open(variance_outfile,'w').write(\
convert_biom_to_precalc(biom_prediction_variances))
if confidence_intervals:
if opts.verbose:
print "Converting upper confidence interval values to BIOM format"
biom_prediction_upper_CI=biom_table_from_predictions({k:v['upper_CI'] for k,v in confidence_intervals.iteritems()},table_headers,\
observation_metadata=None,\
sample_metadata=None,convert_to_int=False)
outfile_base, extension = splitext(opts.output_trait_table)
upper_CI_outfile = outfile_base + "_upper_CI" + suffix
make_output_dir_for_file(upper_CI_outfile)
if opts.verbose:
print "Writing upper confidence limit information to file:", upper_CI_outfile
if opts.output_precalc_file_in_biom:
write_biom_table(biom_prediction_upper_CI, upper_CI_outfile)
else:
open(upper_CI_outfile,'w').write(\
convert_biom_to_precalc(biom_prediction_upper_CI))
biom_prediction_lower_CI=biom_table_from_predictions({k:v['lower_CI'] for k,v in confidence_intervals.iteritems()},table_headers,\
observation_metadata=None,\
sample_metadata=None,convert_to_int=False)
outfile_base, extension = splitext(opts.output_trait_table)
lower_CI_outfile = outfile_base + "_lower_CI" + suffix
make_output_dir_for_file(lower_CI_outfile)
if opts.verbose:
print "Writing lower confidence limit information to file", lower_CI_outfile
if opts.output_precalc_file_in_biom:
write_biom_table(biom_prediction_lower_CI, lower_CI_outfile)
else:
open(lower_CI_outfile,'w').write(\
convert_biom_to_precalc(biom_prediction_lower_CI))
def main():
option_parser, opts, args =\
parse_command_line_parameters(**script_info)
#if we specify we want NSTI only then we have to calculate it first
if opts.output_accuracy_metrics_only:
opts.calculate_accuracy_metrics=True
if opts.verbose:
print "Loading tree from file:", opts.tree
if opts.no_round:
round_opt = False
else:
round_opt = True
# Load Tree
tree = load_picrust_tree(opts.tree, opts.verbose)
table_headers=[]
traits={}
#load the asr trait table using the previous list of functions to order the arrays
if opts.reconstructed_trait_table:
table_headers,traits =\
update_trait_dict_from_file(opts.reconstructed_trait_table)
#Only load confidence intervals on the reconstruction
#If we actually have ASR values in the analysis
if opts.reconstruction_confidence:
if opts.verbose:
print "Loading ASR confidence data from file:",\
opts.reconstruction_confidence
print "Assuming confidence data is of type:",opts.confidence_format
asr_confidence_output = open(opts.reconstruction_confidence)
asr_min_vals,asr_max_vals, params,column_mapping =\
parse_asr_confidence_output(asr_confidence_output,format=opts.confidence_format)
if 'sigma' in params:
brownian_motion_parameter = params['sigma'][0]
else:
brownian_motion_parameter = None
if opts.verbose:
print "Done. Loaded %i confidence interval values." %(len(asr_max_vals))
print "Brownian motion parameter:",brownian_motion_parameter
else:
brownian_motion_parameter = None
#load the trait table into a dict with organism names as keys and arrays as functions
table_headers,genome_traits =\
update_trait_dict_from_file(opts.observed_trait_table,table_headers)
#Combine the trait tables overwriting the asr ones if they exist in the genome trait table.
traits.update(genome_traits)
# Specify the attribute where we'll store the reconstructions
trait_label = "Reconstruction"
if opts.verbose:
print "Assigning traits to tree..."
# Decorate tree using the traits
tree = assign_traits_to_tree(traits,tree, trait_label=trait_label)
if opts.reconstruction_confidence:
if opts.verbose:
print "Assigning trait confidence intervals to tree..."
tree = assign_traits_to_tree(asr_min_vals,tree,\
trait_label="lower_bound")
tree = assign_traits_to_tree(asr_max_vals,tree,\
trait_label="upper_bound")
if brownian_motion_parameter is None:
if opts.verbose:
print "No Brownian motion parameters loaded. Inferring these from 95% confidence intervals..."
brownian_motion_parameter = get_brownian_motion_param_from_confidence_intervals(tree,\
upper_bound_trait_label="upper_bound",\
lower_bound_trait_label="lower_bound",\
trait_label=trait_label,\
confidence=0.95)
if opts.verbose:
print "Inferred the following rate parameters:",brownian_motion_parameter
if opts.verbose:
print "Collecting list of nodes to predict..."
#Start by predict all tip nodes.
nodes_to_predict = [tip.Name for tip in tree.tips()]
if opts.verbose:
print "Found %i nodes to predict." % len(nodes_to_predict)
if opts.limit_predictions_to_organisms:
organism_id_str = opts.limit_predictions_to_organisms
ok_organism_ids = organism_id_str.split(',')
ok_organism_ids = [n.strip() for n in ok_organism_ids]
for f in set_label_conversion_fns(True,True):
ok_organism_ids = [f(i) for i in ok_organism_ids]
if opts.verbose:
print "Limiting predictions to user-specified ids:",\
",".join(ok_organism_ids)
if not ok_organism_ids:
raise RuntimeError(\
"Found no valid ids in input: %s. Were comma-separated ids specified on the command line?"\
% opts.limit_predictions_to_organisms)
nodes_to_predict =\
[n for n in nodes_to_predict if n in ok_organism_ids]
if not nodes_to_predict:
raise RuntimeError(\
"Filtering by user-specified ids resulted in an empty set of nodes to predict. Are the ids on the commmand-line and tree ids in the same format? Example tree tip name: %s, example OTU id name: %s" %([tip.Name for tip in tree.tips()][0],ok_organism_ids[0]))
if opts.verbose:
print "After filtering organisms to predict by the ids specified on the commandline, %i nodes remain to be predicted" %(len(nodes_to_predict))
if opts.limit_predictions_by_otu_table:
if opts.verbose:
print "Limiting predictions to ids in user-specified OTU table:",\
opts.limit_predictions_by_otu_table
otu_table = open(opts.limit_predictions_by_otu_table,"U")
#Parse OTU table for ids
otu_ids =\
extract_ids_from_table(otu_table.readlines(),delimiter="\t")
if not otu_ids:
raise RuntimeError(\
"Found no valid ids in input OTU table: %s. Is the path correct?"\
% opts.limit_predictions_by_otu_table)
nodes_to_predict =\
[n for n in nodes_to_predict if n in otu_ids]
if not nodes_to_predict:
raise RuntimeError(\
"Filtering by OTU table resulted in an empty set of nodes to predict. Are the OTU ids and tree ids in the same format? Example tree tip name: %s, example OTU id name: %s" %([tip.Name for tip in tree.tips()][0],otu_ids[0]))
if opts.verbose:
print "After filtering by OTU table, %i nodes remain to be predicted" %(len(nodes_to_predict))
# Calculate accuracy of PICRUST for the given tree, sequenced genomes
# and set of ndoes to predict
accuracy_metrics = ['NSTI']
accuracy_metric_results = None
if opts.calculate_accuracy_metrics:
if opts.verbose:
print "Calculating accuracy metrics: %s" %([",".join(accuracy_metrics)])
accuracy_metric_results = {}
if 'NSTI' in accuracy_metrics:
nsti_result,min_distances =\
calc_nearest_sequenced_taxon_index(tree,\
limit_to_tips = nodes_to_predict,\
trait_label = trait_label, verbose=opts.verbose)
#accuracy_metric_results['NSTI'] = nsti_result
for organism in min_distances.keys():
accuracy_metric_results[organism] = {'NSTI': min_distances[organism]}
if opts.verbose:
print "NSTI:", nsti_result
if opts.output_accuracy_metrics_only:
#Write accuracy metrics to file
if opts.verbose:
print "Writing accuracy metrics to file:",opts.output_accuracy_metrics
f = open(opts.output_accuracy_metrics_only,'w+')
f.write("metric\torganism\tvalue\n")
lines =[]
for organism in accuracy_metric_results.keys():
for metric in accuracy_metric_results[organism].keys():
lines.append('\t'.join([metric,organism,\
str(accuracy_metric_results[organism][metric])])+'\n')
f.writelines(sorted(lines))
f.close()
exit()
if opts.verbose:
print "Generating predictions using method:",opts.prediction_method
if opts.weighting_method == 'exponential':
#For now, use exponential weighting
weight_fn = make_neg_exponential_weight_fn(e)
variances=None #Overwritten by methods that calc variance
confidence_intervals=None #Overwritten by methods that calc variance
if opts.prediction_method == 'asr_and_weighting':
# Perform predictions using reconstructed ancestral states
if opts.reconstruction_confidence:
predictions,variances,confidence_intervals =\
predict_traits_from_ancestors(tree,nodes_to_predict,\
trait_label=trait_label,\
lower_bound_trait_label="lower_bound",\
upper_bound_trait_label="upper_bound",\
calc_confidence_intervals = True,\
brownian_motion_parameter=brownian_motion_parameter,\
weight_fn=weight_fn,verbose=opts.verbose,
round_predictions=round_opt)
else:
predictions =\
predict_traits_from_ancestors(tree,nodes_to_predict,\
trait_label=trait_label,\
weight_fn =weight_fn,verbose=opts.verbose,
round_predictions=round_opt)
elif opts.prediction_method == 'weighting_only':
#Ignore ancestral information
predictions =\
weighted_average_tip_prediction(tree,nodes_to_predict,\
trait_label=trait_label,\
weight_fn =weight_fn,verbose=opts.verbose)
elif opts.prediction_method == 'nearest_neighbor':
predictions = predict_nearest_neighbor(tree,nodes_to_predict,\
trait_label=trait_label,tips_only = True)
elif opts.prediction_method == 'random_neighbor':
predictions = predict_random_neighbor(tree,\
nodes_to_predict,trait_label=trait_label)
if opts.verbose:
print "Done making predictions."
make_output_dir_for_file(opts.output_trait_table)
out_fh=open(opts.output_trait_table,'w')
#Generate the table of biom predictions
if opts.verbose:
print "Converting results to .biom format for output..."
biom_predictions=biom_table_from_predictions(predictions,table_headers,\
observation_metadata=None,\
sample_metadata=accuracy_metric_results,convert_to_int=False)
if opts.verbose:
print "Writing prediction results to file: ",opts.output_trait_table
if opts.output_precalc_file_in_biom:
#write biom table to file
write_biom_table(biom_predictions, opts.output_trait_table)
else:
#convert to precalc (tab-delimited) format
out_fh = open(opts.output_trait_table, 'w')
out_fh.write(convert_biom_to_precalc(biom_predictions))
out_fh.close()
#Write out variance information to file
if variances:
if opts.verbose:
print "Converting variances to BIOM format"
if opts.output_precalc_file_in_biom:
suffix='.biom'
else:
suffix='.tab'
biom_prediction_variances=biom_table_from_predictions({k:v['variance'] for k,v in variances.iteritems()},table_headers,\
observation_metadata=None,\
sample_metadata=None,convert_to_int=False)
outfile_base,extension = splitext(opts.output_trait_table)
variance_outfile = outfile_base+"_variances"+suffix
make_output_dir_for_file(variance_outfile)
if opts.verbose:
print "Writing variance information to file:",variance_outfile
if opts.output_precalc_file_in_biom:
write_biom_table(biom_prediction_variances, variance_outfile)
else:
open(variance_outfile,'w').write(\
convert_biom_to_precalc(biom_prediction_variances))
if confidence_intervals:
if opts.verbose:
print "Converting upper confidence interval values to BIOM format"
biom_prediction_upper_CI=biom_table_from_predictions({k:v['upper_CI'] for k,v in confidence_intervals.iteritems()},table_headers,\
observation_metadata=None,\
sample_metadata=None,convert_to_int=False)
outfile_base,extension = splitext(opts.output_trait_table)
upper_CI_outfile = outfile_base+"_upper_CI"+suffix
make_output_dir_for_file(upper_CI_outfile)
if opts.verbose:
print "Writing upper confidence limit information to file:",upper_CI_outfile
if opts.output_precalc_file_in_biom:
write_biom_table(biom_prediction_upper_CI, upper_CI_outfile)
else:
open(upper_CI_outfile,'w').write(\
convert_biom_to_precalc(biom_prediction_upper_CI))
biom_prediction_lower_CI=biom_table_from_predictions({k:v['lower_CI'] for k,v in confidence_intervals.iteritems()},table_headers,\
observation_metadata=None,\
sample_metadata=None,convert_to_int=False)
outfile_base,extension = splitext(opts.output_trait_table)
lower_CI_outfile = outfile_base+"_lower_CI"+suffix
make_output_dir_for_file(lower_CI_outfile)
if opts.verbose:
print "Writing lower confidence limit information to file",lower_CI_outfile
if opts.output_precalc_file_in_biom:
write_biom_table(biom_prediction_lower_CI, lower_CI_outfile)
else:
open(lower_CI_outfile,'w').write(\
convert_biom_to_precalc(biom_prediction_lower_CI))
def main():
option_parser, opts, args =\
parse_command_line_parameters(**script_info)
otu_table = load_table(opts.input_otu_fp)
ids_to_load = otu_table.ids(axis='observation')
if(opts.input_count_fp is None):
#precalc file has specific name (e.g. 16S_13_5_precalculated.tab.gz)
precalc_file_name='_'.join(['16S',opts.gg_version,'precalculated.tab.gz'])
input_count_table=join(get_picrust_project_dir(),'picrust','data',precalc_file_name)
else:
input_count_table=opts.input_count_fp
if opts.verbose:
print "Loading trait table: ", input_count_table
ext=path.splitext(input_count_table)[1]
if (ext == '.gz'):
count_table_fh = gzip.open(input_count_table,'rb')
else:
count_table_fh = open(input_count_table,'U')
if opts.load_precalc_file_in_biom:
count_table = load_table(count_table_fh)
else:
count_table = convert_precalc_to_biom(count_table_fh, ids_to_load)
#Need to only keep data relevant to our otu list
ids=[]
for x in otu_table.iter(axis='observation'):
ids.append(str(x[1]))
ob_id=count_table.ids(axis='observation')[0]
filtered_otus=[]
filtered_values=[]
for x in ids:
if count_table.exists(x, axis='sample'):
filtered_otus.append(x)
filtered_values.append(otu_table.data(x, axis='observation'))
filtered_otu_table = Table(filtered_values, filtered_otus, otu_table.ids())
copy_numbers_filtered={}
for x in filtered_otus:
value = count_table.get_value_by_ids(ob_id,x)
try:
#data can be floats so round them and make them integers
value = int(round(float(value)))
except ValueError:
raise ValueError,\
"Invalid type passed as copy number for OTU ID %s. Must be int-able." % (value)
if value < 1:
raise ValueError, "Copy numbers must be greater than or equal to 1."
copy_numbers_filtered[x]={opts.metadata_identifer:value}
filtered_otu_table.add_metadata(copy_numbers_filtered, axis='observation')
def metadata_norm(v, i, md):
return v / float(md[opts.metadata_identifer])
normalized_table = filtered_otu_table.transform(metadata_norm, axis='observation')
#move Observation Metadata from original to filtered OTU table
normalized_table = transfer_observation_metadata(otu_table, normalized_table, 'observation')
make_output_dir_for_file(opts.output_otu_fp)
write_biom_table(normalized_table, opts.output_otu_fp)
def main():
"""Generate test trees given parameters"""
option_parser, opts, args =\
parse_command_line_parameters(**script_info)
if opts.verbose:
print "Loading trait table..."
input_trait_table = open(opts.input_trait_table,"U")
if opts.verbose:
print "Loading tree..."
#PicrustNode seems to run into very slow/memory intentsive perfromance...
#tree = DndParser(open(opts.input_tree),constructor=PicrustNode)
tree = DndParser(open(opts.input_tree))
if opts.verbose:
print "Parsing trait table..."
#Find which taxa are to be used in tests
#(by default trait table taxa)
trait_table_header,trait_table_fields = \
parse_trait_table(input_trait_table)
if opts.verbose:
print "Ensuring tree and trait table labels are formatted consistently..."
label_conversion_fns = set_label_conversion_fns(verbose=opts.verbose)
fix_tree_labels(tree,label_conversion_fns)
trait_table_fields = convert_trait_table_entries(trait_table_fields,\
value_conversion_fns = [],\
label_conversion_fns = label_conversion_fns)
trait_table_fields = [t for t in trait_table_fields]
print "Number of trait table fields with single quotes:",\
len([t for t in trait_table_fields if "'" in t[0]])
if opts.verbose:
print "Making output directory..."
make_output_dir(opts.output_dir)
if opts.limit_to_tips:
included_tips = opts.limit_to_tips.split(",")
if opts.verbose:
print "Limiting test datasets to %i tips: %s" %(len(included_tips),included_tips)
else:
included_tips = False
method_fns =\
{"exclude_tips_by_distance":\
make_distance_based_exclusion_fn,\
"randomize_tip_labels_by_distance":\
make_distance_based_tip_label_randomizer
}
test_fn_factory = method_fns[opts.method]
if opts.verbose:
print "Setting tree modification method to:", opts.method
print "(%s)" % test_fn_factory.__doc__
modify_tree = True
if opts.suppress_tree_modification:
if opts.verbose:
print "Suppressing modification of tree when making test datasets"
modify_tree = False
if opts.verbose:
print "Starting generation of test datsets"
test_datasets = \
yield_genome_test_data_by_distance(tree,trait_table_fields,\
test_fn_factory,min_dist = opts.min_dist,\
max_dist=opts.max_dist,increment=opts.dist_increment,\
modify_tree=modify_tree,limit_to_tips= included_tips,verbose = opts.verbose)
if opts.verbose:
print "Writing files for test datasets"
for curr_dist,test_tree,tip_to_predict,\
expected_traits,test_trait_table_fields in test_datasets:
if included_tips is not False:
if tip_to_predict not in included_tips:
if opts.verbose:
print "Skipping tip %s: limiting to tip(s): %s" %(tip_to_predict,included_tips)
continue
#Make a safe version of tip to predict
# So odd characters like | don't mess up OS
safe_tip_to_predict = "'%s'"%tip_to_predict
#Write tree
base_name = "--".join(map(str,["test_tree",opts.method,curr_dist]))
curr_filepath = write_tree(opts.output_dir,base_name,test_tree,safe_tip_to_predict)
if opts.verbose:
print "Wrote test tree to: %s" % curr_filepath
#Write expected trait table
base_name = "--".join(map(str,["exp_traits",opts.method,curr_dist,safe_tip_to_predict]))
exp_trait_table_lines = [trait_table_header]
exp_trait_table_lines.append("\t".join(expected_traits)+"\n")
#print "Expected_trait_table_lines:",exp_trait_table_lines
filename=os.path.join(opts.output_dir,base_name)
if opts.verbose:
print "Writing expected trait table to:", filename
f=open(filename,"w")
f.write("".join(exp_trait_table_lines))
f.close()
#Output a transposed, BIOM format expectation table for comparison with predict_traits output
#NOTE: this is a clumsy way of getting the translated trait table
# but more elegant, direct methods (directly feeding data to biom's table_factory)
# weren't working for me readily. In the future, we should streamline this process
# Leaving as is for now since this code is mostly for developers so speed/elegence
# are probably not essential here.
#Let the hackishness begin
#Reload the tab-delimited trait table
header, fields = parse_trait_table(open(filename,"U"))
fields = [f for f in fields] #converts generator to list
#Transpose table for .BIOM format so that Observation ids are KOs
transposed_header, transposed_trait_table_lines =\
transpose_trait_table_fields(fields,header,\
id_row_idx=0, input_header_delimiter="\t",output_delimiter="\t")
#Eliminate newline in header
trans_trait_table_lines = [transposed_header.strip()]
trans_trait_table_lines.extend(["\t".join(r) for r in transposed_trait_table_lines])
trans_trait_table = '\n'.join(trans_trait_table_lines)
#Write BIOM format expected trait table
base_name = "--".join(map(str,["exp_biom_traits",opts.method,curr_dist,safe_tip_to_predict]))
expected_biom_table = parse_table_to_biom(trans_trait_table.split('\n'),\
table_format = "tab-delimited")
#print "Expected_trait_table_lines:",exp_trait_table_lines
filename=os.path.join(opts.output_dir,base_name)
if opts.verbose:
print "Writing BIOM-format expected trait table to:", filename
write_biom_table(expected_biom_table, filename)
#Write test trait table
test_trait_table_fields = test_trait_table_fields
if expected_traits in test_trait_table_fields:
test_trait_table_fields.remove(expected_traits)
test_trait_table_lines = [trait_table_header]
test_trait_table_lines.extend(["\t".join(r)+"\n" for r in test_trait_table_fields])
#print "Test_trait_table_lines:",test_trait_table_lines
base_name = "--".join(map(str,["test_trait_table",opts.method,curr_dist,safe_tip_to_predict]))
filename=os.path.join(opts.output_dir,base_name)
if opts.verbose:
print "Writing test trait table to:", filename
f=open(filename,"w")
f.write("".join(test_trait_table_lines))
f.close()
if opts.verbose:
print "Done generating test datasets"
def main():
"""Generate test trees given parameters"""
option_parser, opts, args =\
parse_command_line_parameters(**script_info)
if opts.verbose:
print "Loading trait table..."
input_trait_table = open(opts.input_trait_table,"U")
if opts.verbose:
print "Loading tree..."
#PicrustNode seems to run into very slow/memory intentsive perfromance...
#tree = DndParser(open(opts.input_tree),constructor=PicrustNode)
tree = DndParser(open(opts.input_tree))
if opts.verbose:
print "Parsing trait table..."
#Find which taxa are to be used in tests
#(by default trait table taxa)
trait_table_header,trait_table_fields = \
parse_trait_table(input_trait_table)
if opts.verbose:
print "Ensuring tree and trait table labels are formatted consistently..."
label_conversion_fns = set_label_conversion_fns(verbose=opts.verbose)
fix_tree_labels(tree,label_conversion_fns)
trait_table_fields = convert_trait_table_entries(trait_table_fields,\
value_conversion_fns = [],\
label_conversion_fns = label_conversion_fns)
trait_table_fields = [t for t in trait_table_fields]
print "Number of trait table fields with single quotes:",\
len([t for t in trait_table_fields if "'" in t[0]])
if opts.verbose:
print "Making output directory..."
make_output_dir(opts.output_dir)
if opts.limit_to_tips:
included_tips = opts.limit_to_tips.split(",")
if opts.verbose:
print "Limiting test datasets to %i tips: %s" %(len(included_tips),included_tips)
else:
included_tips = False
method_fns =\
{"exclude_tips_by_distance":\
make_distance_based_exclusion_fn,\
"randomize_tip_labels_by_distance":\
make_distance_based_tip_label_randomizer
}
test_fn_factory = method_fns[opts.method]
if opts.verbose:
print "Setting tree modification method to:", opts.method
print "(%s)" % test_fn_factory.__doc__
modify_tree = True
if opts.suppress_tree_modification:
if opts.verbose:
print "Suppressing modification of tree when making test datasets"
modify_tree = False
if opts.verbose:
print "Starting generation of test datsets"
test_datasets = \
yield_genome_test_data_by_distance(tree,trait_table_fields,\
test_fn_factory,min_dist = opts.min_dist,\
max_dist=opts.max_dist,increment=opts.dist_increment,\
modify_tree=modify_tree,limit_to_tips= included_tips,verbose = opts.verbose)
if opts.verbose:
print "Writing files for test datasets"
for curr_dist,test_tree,tip_to_predict,\
expected_traits,test_trait_table_fields in test_datasets:
if included_tips is not False:
if tip_to_predict not in included_tips:
if opts.verbose:
print "Skipping tip %s: limiting to tip(s): %s" %(tip_to_predict,included_tips)
continue
#Make a safe version of tip to predict
# So odd characters like | don't mess up OS
safe_tip_to_predict = "'%s'"%tip_to_predict
#Write tree
base_name = "--".join(map(str,["test_tree",opts.method,curr_dist]))
curr_filepath = write_tree(opts.output_dir,base_name,test_tree,safe_tip_to_predict)
if opts.verbose:
print "Wrote test tree to: %s" % curr_filepath
#Write expected trait table
base_name = "--".join(map(str,["exp_traits",opts.method,curr_dist,safe_tip_to_predict]))
exp_trait_table_lines = [trait_table_header]
exp_trait_table_lines.append("\t".join(expected_traits)+"\n")
#print "Expected_trait_table_lines:",exp_trait_table_lines
filename=os.path.join(opts.output_dir,base_name)
if opts.verbose:
print "Writing expected trait table to:", filename
f=open(filename,"w")
f.write("".join(exp_trait_table_lines))
f.close()
#Output a transposed, BIOM format expectation table for comparison with predict_traits output
#NOTE: this is a clumsy way of getting the translated trait table
# but more elegant, direct methods (directly feeding data to biom's table_factory)
# weren't working for me readily. In the future, we should streamline this process
# Leaving as is for now since this code is mostly for developers so speed/elegence
# are probably not essential here.
#Let the hackishness begin
#Reload the tab-delimited trait table
header, fields = parse_trait_table(open(filename,"U"))
fields = [f for f in fields] #converts generator to list
#Transpose table for .BIOM format so that Observation ids are KOs
transposed_header, transposed_trait_table_lines =\
transpose_trait_table_fields(fields,header,\
id_row_idx=0, input_header_delimiter="\t",output_delimiter="\t")
#Eliminate newline in header
trans_trait_table_lines = [transposed_header.strip()]
trans_trait_table_lines.extend(["\t".join(r) for r in transposed_trait_table_lines])
trans_trait_table = '\n'.join(trans_trait_table_lines)
#Write BIOM format expected trait table
base_name = "--".join(map(str,["exp_biom_traits",opts.method,curr_dist,safe_tip_to_predict]))
expected_biom_table = parse_table_to_biom(trans_trait_table.split('\n'),\
table_format = "tab-delimited")
#print "Expected_trait_table_lines:",exp_trait_table_lines
filename=os.path.join(opts.output_dir,base_name)
if opts.verbose:
print "Writing BIOM-format expected trait table to:", filename
write_biom_table(expected_biom_table, filename)
#Write test trait table
test_trait_table_fields = test_trait_table_fields
if expected_traits in test_trait_table_fields:
test_trait_table_fields.remove(expected_traits)
test_trait_table_lines = [trait_table_header]
test_trait_table_lines.extend(["\t".join(r)+"\n" for r in test_trait_table_fields])
#print "Test_trait_table_lines:",test_trait_table_lines
base_name = "--".join(map(str,["test_trait_table",opts.method,curr_dist,safe_tip_to_predict]))
filename=os.path.join(opts.output_dir,base_name)
if opts.verbose:
print "Writing test trait table to:", filename
f=open(filename,"w")
f.write("".join(test_trait_table_lines))
f.close()
if opts.verbose:
print "Done generating test datasets"
def main():
option_parser, opts, args = parse_command_line_parameters(**script_info)
otu_table = load_table(opts.input_otu_fp)
ids_to_load = otu_table.ids(axis="observation")
if opts.input_count_fp is None:
# precalc file has specific name (e.g. 16S_13_5_precalculated.tab.gz)
precalc_file_name = "_".join(["16S", opts.gg_version, "precalculated.tab.gz"])
input_count_table = join(get_picrust_project_dir(), "picrust", "data", precalc_file_name)
else:
input_count_table = opts.input_count_fp
if opts.verbose:
print "Loading trait table: ", input_count_table
ext = path.splitext(input_count_table)[1]
if ext == ".gz":
count_table_fh = gzip.open(input_count_table, "rb")
else:
count_table_fh = open(input_count_table, "U")
if opts.load_precalc_file_in_biom:
count_table = load_table(count_table_fh)
else:
count_table = convert_precalc_to_biom(count_table_fh, ids_to_load)
# Need to only keep data relevant to our otu list
ids = []
for x in otu_table.iter(axis="observation"):
ids.append(str(x[1]))
ob_id = count_table.ids(axis="observation")[0]
filtered_otus = []
filtered_values = []
for x in ids:
if count_table.exists(x, axis="sample"):
filtered_otus.append(x)
filtered_values.append(otu_table.data(x, axis="observation"))
filtered_otu_table = Table(filtered_values, filtered_otus, otu_table.ids())
copy_numbers_filtered = {}
for x in filtered_otus:
value = count_table.get_value_by_ids(ob_id, x)
try:
# data can be floats so round them and make them integers
value = int(round(float(value)))
except ValueError:
raise ValueError, "Invalid type passed as copy number for OTU ID %s. Must be int-able." % (value)
if value < 1:
raise ValueError, "Copy numbers must be greater than or equal to 1."
copy_numbers_filtered[x] = {opts.metadata_identifer: value}
filtered_otu_table.add_metadata(copy_numbers_filtered, axis="observation")
def metadata_norm(v, i, md):
return v / float(md[opts.metadata_identifer])
normalized_table = filtered_otu_table.transform(metadata_norm, axis="observation")
# move Observation Metadata from original to filtered OTU table
normalized_table = transfer_observation_metadata(otu_table, normalized_table, "observation")
make_output_dir_for_file(opts.output_otu_fp)
write_biom_table(normalized_table, opts.output_otu_fp)