def main(table_loc, otu_list, collapsed_name, output_file, classic=False):
table = load_table(table_loc)
f = open(otu_list)
otus = f.read().strip().split()
otus = set(otus) & set(table.ids(axis="observation"))
table1 = table.filter(otus, axis="observation", inplace=False)
table2 = table.filter(otus, axis="observation", invert=True, inplace=False)
sums1 = table1.sum(axis='sample')
sums2 = table2.sum(axis='sample')
new_table = Table(numpy.array([sums1,sums2]), [collapsed_name, "not_"+collapsed_name], table.ids(axis="sample"), type="otu baptable")
if classic:
# print to tab delimited biom table
open(output_file, 'w').write(new_table.to_tsv())
else:
# print biom table
new_table.to_json("predict_reactions.py", open(output_file, 'w'))
# print "Taxonomy: %s" %Taxonomy
for taxon in observ_ids:
# print taxon
# print Taxonomy[taxon]
observation_metadata.append(Taxonomy[taxon])
#print "observation metadata:\n%s" %observation_metadata
#print len(observation_metadata)
table = Table(data,
observ_ids,
sample_id,
observation_metadata,
sample_metadata,
table_id='Example Table')
print table
out = open(args.prefix + ".biom", "w")
table.to_json('pplacer converted by jplace_to_biom.py v.' + VERSION,
direct_io=out)
out.close()
out = open(args.prefix + ".tsv", "w")
out.write(table.to_tsv(
header_key='taxonomy',
header_value='taxomomy')) #to_json('generaged by test', direct_io=out)
out.close()
print "\n##### DONE! #####\n"
# print "index: %i" %index
ind_taxonomy.append('%s%s' %(syn[levels[index]], taxon[0]['ScientificName']))
# print ind_taxonomy
Taxonomy[taxon[0]['ScientificName']]['taxonomy'] = ind_taxonomy
# print "Taxonomy: %s" %Taxonomy
for taxon in observ_ids:
# print taxon
# print Taxonomy[taxon]
observation_metadata.append(Taxonomy[taxon])
#print "observation metadata:\n%s" %observation_metadata
#print len(observation_metadata)
table = Table(data, observ_ids, sample_id, observation_metadata, sample_metadata, table_id='Example Table')
print table
out=open(args.prefix+".biom","w")
table.to_json('pplacer converted by jplace_to_biom.py v.'+VERSION, direct_io=out)
out.close()
out=open(args.prefix+".tsv","w")
out.write(table.to_tsv(header_key='taxonomy', header_value='taxomomy')) #to_json('generaged by test', direct_io=out)
out.close()
print "\n##### DONE! #####\n"
def main():
option_parser, opts, args = parse_command_line_parameters(**script_info)
lower_percentage = opts.lower_percentage
upper_percentage = opts.upper_percentage
otu_table_fp = opts.otu_table_fp
otu_table = load_table(otu_table_fp)
delimiter = opts.delimiter
mapping_fp = opts.mapping
md_as_string = opts.md_as_string
md_identifier = opts.md_identifier
levels = opts.level.split(',')
suppress_classic_table_output = opts.suppress_classic_table_output
suppress_biom_table_output = opts.suppress_biom_table_output
if upper_percentage is not None and lower_percentage is not None:
raise ValueError(
"upper_percentage and lower_percentage are mutually exclusive")
if upper_percentage is not None and lower_percentage is not None and \
mapping:
raise ValueError("upper_percentage and lower_percentage can not be "
"using with mapping file")
if upper_percentage is not None and \
(upper_percentage < 0 or upper_percentage > 1.0):
raise ValueError('max_otu_percentage should be between 0.0 and 1.0')
if lower_percentage is not None and \
(lower_percentage < 0 or lower_percentage > 1.0):
raise ValueError('lower_percentage should be between 0.0 and 1.0')
if mapping_fp:
mapping_file = open(mapping_fp, 'U')
mapping, header, comments = parse_mapping_file(mapping_file)
# use the input Mapping file for producing the output filenames
map_dir_path, map_fname = split(mapping_fp)
map_basename, map_fname_ext = splitext(map_fname)
else:
if suppress_classic_table_output and suppress_biom_table_output:
option_parser.error("Both classic and BIOM output formats were "
"suppressed.")
if not opts.absolute_abundance:
otu_table = otu_table.norm(axis='sample', inplace=False)
# introduced output directory to will allow for multiple outputs
if opts.output_dir:
create_dir(opts.output_dir, False)
output_dir_path = opts.output_dir
else:
output_dir_path = './'
# use the input OTU table to produce the output filenames
dir_path, fname = split(otu_table_fp)
basename, fname_ext = splitext(fname)
# Iterate over the levels and generate a summarized taxonomy for each
for level in levels:
if mapping_fp:
# define output filename
output_fname = join(output_dir_path,
map_basename + '_L%s.txt' % (level))
summary, tax_order = add_summary_mapping(otu_table, mapping,
int(level), md_as_string,
md_identifier)
write_add_taxa_summary_mapping(summary, tax_order, mapping, header,
output_fname, delimiter)
else:
# define the output filename. The extension will be added to the
# end depending on the output format
output_fname = join(output_dir_path, basename + '_L%s' % level)
summary, header = make_summary(otu_table, int(level),
upper_percentage, lower_percentage,
md_as_string, md_identifier)
sample_ids = header[1:]
observation_ids = []
data = []
for row in summary:
# Join taxonomic levels to create an observation ID.
observation_ids.append(delimiter.join(row[0]))
data.append(row[1:])
table = Table(np.asarray(data), observation_ids, sample_ids)
if opts.transposed_output:
table = table.transpose()
if not suppress_classic_table_output:
with open(output_fname + '.txt', 'w') as outfile:
outfile.write(table.to_tsv())
if not suppress_biom_table_output:
write_biom_table(table, output_fname + '.biom')
def main():
option_parser, opts, args = parse_command_line_parameters(**script_info)
lower_percentage = opts.lower_percentage
upper_percentage = opts.upper_percentage
otu_table_fp = opts.otu_table_fp
otu_table = load_table(otu_table_fp)
delimiter = opts.delimiter
mapping_fp = opts.mapping
md_as_string = opts.md_as_string
md_identifier = opts.md_identifier
levels = opts.level.split(',')
suppress_classic_table_output = opts.suppress_classic_table_output
suppress_biom_table_output = opts.suppress_biom_table_output
if upper_percentage is not None and lower_percentage is not None:
raise ValueError(
"upper_percentage and lower_percentage are mutually exclusive")
if upper_percentage is not None and lower_percentage is not None and \
mapping:
raise ValueError("upper_percentage and lower_percentage can not be "
"using with mapping file")
if upper_percentage is not None and \
(upper_percentage < 0 or upper_percentage > 1.0):
raise ValueError('max_otu_percentage should be between 0.0 and 1.0')
if lower_percentage is not None and \
(lower_percentage < 0 or lower_percentage > 1.0):
raise ValueError('lower_percentage should be between 0.0 and 1.0')
if mapping_fp:
mapping_file = open(mapping_fp, 'U')
mapping, header, comments = parse_mapping_file(mapping_file)
# use the input Mapping file for producing the output filenames
map_dir_path, map_fname = split(mapping_fp)
map_basename, map_fname_ext = splitext(map_fname)
else:
if suppress_classic_table_output and suppress_biom_table_output:
option_parser.error("Both classic and BIOM output formats were "
"suppressed.")
if not opts.absolute_abundance:
otu_table = otu_table.norm(axis='sample', inplace=False)
# introduced output directory to will allow for multiple outputs
if opts.output_dir:
create_dir(opts.output_dir, False)
output_dir_path = opts.output_dir
else:
output_dir_path = './'
# use the input OTU table to produce the output filenames
dir_path, fname = split(otu_table_fp)
basename, fname_ext = splitext(fname)
# Iterate over the levels and generate a summarized taxonomy for each
for level in levels:
if mapping_fp:
# define output filename
output_fname = join(output_dir_path,
map_basename + '_L%s.txt' % (level))
summary, tax_order = add_summary_mapping(otu_table,
mapping,
int(level),
md_as_string,
md_identifier)
write_add_taxa_summary_mapping(summary, tax_order, mapping,
header, output_fname, delimiter)
else:
# define the output filename. The extension will be added to the
# end depending on the output format
output_fname = join(output_dir_path, basename + '_L%s' % level)
summary, header = make_summary(otu_table,
int(level),
upper_percentage,
lower_percentage,
md_as_string,
md_identifier)
sample_ids = header[1:]
observation_ids = []
data = []
for row in summary:
# Join taxonomic levels to create an observation ID.
observation_ids.append(delimiter.join(row[0]))
data.append(row[1:])
table = Table(np.asarray(data), observation_ids, sample_ids)
if opts.transposed_output:
table = table.transpose()
if not suppress_classic_table_output:
with open(output_fname + '.txt', 'w') as outfile:
outfile.write(table.to_tsv())
if not suppress_biom_table_output:
write_biom_table(table, output_fname + '.biom')
