def _read_taxonomy_files(self, options) -> Dict[str, Tuple[str, str, str, str, str, str, str]]:
"""Read and merge taxonomy files."""
self.logger.info('Reading GTDB taxonomy for representative genomes.')
taxonomy = Taxonomy().read(Config.TAXONOMY_FILE)
if options.gtdbtk_classification_file:
# add and overwrite taxonomy for genomes specified in the
# GTDB-Tk classification file
check_file_exists(options.gtdbtk_classification_file)
self.logger.info('Reading GTDB-Tk classification file.')
gtdbtk_taxonomy = Taxonomy().read(options.gtdbtk_classification_file)
del gtdbtk_taxonomy['user_genome']
num_reassigned = 0
for gid, taxa in gtdbtk_taxonomy.items():
if gid in taxonomy:
num_reassigned += 1
taxonomy[gid] = taxa
self.logger.info(f'Read GTDB-Tk classifications for {len(gtdbtk_taxonomy):,} genomes.')
self.logger.info(f'Reassigned taxonomy for {num_reassigned:,} GTDB representative genomes.')
if options.custom_taxonomy_file:
# add and overwrite taxonomy for genomes specified in the
# custom taxonomy file
check_file_exists(options.custom_taxonomy_file)
self.logger.info('Reading custom taxonomy file.')
custom_taxonomy = Taxonomy().read(options.custom_taxonomy_file)
num_reassigned = 0
for gid, taxa in custom_taxonomy.items():
if gid in taxonomy:
num_reassigned += 1
taxonomy[gid] = taxa
self.logger.info(f'Read custom taxonomy for {len(custom_taxonomy):,} genomes.')
self.logger.info(f'Reassigned taxonomy for {num_reassigned:,} GTDB representative genomes.')
if options.gtdbtk_classification_file and options.custom_taxonomy_file:
dup_genomes = set(gtdbtk_taxonomy).intersection(custom_taxonomy)
if len(dup_genomes) > 0:
self.logger.error('GTDB-Tk classification and custom taxonomy '
'files must not specify taxonomies for the '
'same genomes.')
self.logger.error('These files have {:,} genomes in common.'.format(len(dup_genomes)))
self.logger.error('Example duplicate genome: {}'.format(dup_genomes.pop()))
raise GTDBTkExit('Duplicated taxonomy information.')
self.logger.info(f'Read taxonomy for {len(taxonomy):,} genomes.')
return taxonomy
def root(self, options):
"""Root tree using outgroup.
Parameters
----------
options : argparse.Namespace
The CLI arguments input by the user.
"""
self.logger.warning("Tree rooting is still under development!")
check_file_exists(options.input_tree)
if options.custom_taxonomy_file:
check_file_exists(options.custom_taxonomy_file)
taxonomy = Taxonomy().read(options.custom_taxonomy_file)
else:
taxonomy = Taxonomy().read(Config.TAXONOMY_FILE)
self.logger.info('Identifying genomes from the specified outgroup.')
outgroup = set()
for genome_id, taxa in taxonomy.items():
if options.outgroup_taxon in taxa:
outgroup.add(genome_id)
reroot = RerootTree()
reroot.root_with_outgroup(options.input_tree, options.output_tree,
outgroup)
# Symlink to the tree summary file, if not run independently
if hasattr(options, 'suffix'):
if options.suffix == 'bac120':
symlink_f(
PATH_BAC120_ROOTED_TREE.format(prefix=options.prefix),
os.path.join(
options.out_dir,
os.path.basename(
PATH_AR122_ROOTED_TREE.format(
prefix=options.prefix))))
elif options.suffix == 'ar122':
symlink_f(
PATH_AR122_ROOTED_TREE.format(prefix=options.prefix),
os.path.join(
options.out_dir,
os.path.basename(
PATH_AR122_ROOTED_TREE.format(
prefix=options.prefix))))
else:
raise GenomeMarkerSetUnknown(
'There was an error determining the marker set.')
self.logger.info('Done.')