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
ext=path.splitext(opts.input_count_table)[1]
if opts.verbose:
print "Loading count table: ", opts.input_count_table
if (ext == '.gz'):
genome_table = parse_biom_table(gzip.open(opts.input_count_table,'rb'))
else:
genome_table = parse_biom_table(open(opts.input_count_table,'U'))
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)
open(opts.output_metagenome_table,'w').write(format_biom_table(scaled_metagenomes))
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
ext = path.splitext(opts.input_count_table)[1]
if opts.verbose:
print "Loading count table: ", opts.input_count_table
if (ext == '.gz'):
genome_table = parse_biom_table(gzip.open(opts.input_count_table,
'rb'))
else:
genome_table = parse_biom_table(open(opts.input_count_table, 'U'))
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)
open(opts.output_metagenome_table,
'w').write(format_biom_table(scaled_metagenomes))
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.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)
else:
#If we don't need confidence intervals, we can do a faster pure numpy prediction
if opts.verbose:
print "Predicting the metagenome..."
predicted_metagenomes = predict_metagenomes(otu_table,
genome_table,
whole_round=round_flag)
if opts.normalize_by_otu:
#normalize (e.g. divide) the abundances by the sum of the OTUs per sample
if opts.verbose:
print "Normalizing functional abundances by sum of OTUs per sample"
inverse_otu_sums = [1 / x for x in otu_table.sum(axis='sample')]
scaling_factors = dict(zip(otu_table.ids(), inverse_otu_sums))
predicted_metagenomes = scale_metagenomes(predicted_metagenomes,
scaling_factors)
if opts.normalize_by_function:
#normalize (e.g. divide) the abundances by the sum of the functions per sample
#Sum of functional abundances per sample will equal 1 (e.g. relative abundance).
if opts.verbose:
print "Normalizing functional abundances by sum of functions per sample"
predicted_metagenomes = predicted_metagenomes.norm(axis='sample',
inplace=False)
write_metagenome_to_file(predicted_metagenomes,opts.output_metagenome_table,\
opts.format_tab_delimited,"metagenome prediction",verbose=opts.verbose)
if opts.with_confidence:
output_path, output_filename = split(opts.output_metagenome_table)
predicted_metagenomes_lower_CI_95,predicted_metagenomes_upper_CI_95=\
predict_metagenome_variances(otu_table,genome_table,variance_table)
else:
#If we don't need confidence intervals, we can do a faster pure numpy prediction
if opts.verbose:
print "Predicting the metagenome..."
predicted_metagenomes = predict_metagenomes(otu_table,genome_table)
if opts.normalize_by_otu:
#normalize (e.g. divide) the abundances by the sum of the OTUs per sample
if opts.verbose:
print "Normalizing functional abundances by sum of OTUs per sample"
inverse_otu_sums = [1/x for x in otu_table.sum(axis='sample')]
scaling_factors = dict(zip(otu_table.SampleIds,inverse_otu_sums))
predicted_metagenomes = scale_metagenomes(predicted_metagenomes,scaling_factors)
if opts.normalize_by_function:
#normalize (e.g. divide) the abundances by the sum of the functions per sample
#Sum of functional abundances per sample will equal 1 (e.g. relative abundance).
if opts.verbose:
print "Normalizing functional abundances by sum of functions per sample"
predicted_metagenomes = predicted_metagenomes.normObservationBySample()
write_metagenome_to_file(predicted_metagenomes,opts.output_metagenome_table,\
opts.format_tab_delimited,"metagenome prediction",verbose=opts.verbose)
if opts.with_confidence:
output_path,output_filename = split(opts.output_metagenome_table)
base_output_filename,ext = splitext(output_filename)