def cluster_contigs(self):
default_clustering = constants.blank_default if self.blank else constants.single_default
for config_name in self.clustering_configs:
config_path = self.clustering_configs[config_name]
config = ClusteringConfiguration(
config_path,
self.output_directory,
db_paths=self.database_paths,
row_ids_of_interest=self.split_names)
try:
clustering_id, newick = clustering.order_contigs_simple(
config,
distance=self.distance,
linkage=self.linkage,
progress=self.progress)
except Exception as e:
self.run.warning('Clustering has failed for "%s": "%s"' %
(config_name, e))
self.progress.end()
continue
dbops.add_hierarchical_clustering_to_db(self.profile_db_path, config_name, newick, distance=self.distance, linkage=self.linkage, \
make_default=config_name == default_clustering, run=self.run)
def cluster_splits_of_interest(self):
# clustering of contigs is done for each configuration file under static/clusterconfigs/merged directory;
# at this point we don't care what those recipes really require because we already merged and generated
# any data that may be required.
clusterings = {}
for config_name in self.clustering_configs:
config_path = self.clustering_configs[config_name]
config = ClusteringConfiguration(
config_path,
self.input_directory,
db_paths=self.database_paths,
row_ids_of_interest=self.split_names_of_interest)
try:
clustering_id, newick = clustering.order_contigs_simple(
config, progress=self.progress)
except Exception as e:
self.run.warning('Clustering has failed for "%s": "%s"' %
(config_name, e))
self.progress.end()
continue
clusterings[clustering_id] = {'newick': newick}
self.run.info('available_clusterings', list(clusterings.keys()))
return clusterings
def cluster_contigs_anvio(self):
# clustering of contigs is done for each configuration file under static/clusterconfigs/merged directory;
# at this point we don't care what those recipes really require because we already merged and generated
# every data file that may be required.
if not self.skip_hierarchical_clustering:
for config_name in self.clustering_configs:
config_path = self.clustering_configs[config_name]
config = ClusteringConfiguration(
config_path,
self.output_directory,
db_paths=self.database_paths,
row_ids_of_interest=self.split_names)
try:
newick = clustering.order_contigs_simple(
config, progress=self.progress)
except Exception as e:
self.run.warning('Clustering has failed for "%s": "%s"' %
(config_name, e))
self.progress.end()
continue
dbops.add_hierarchical_clustering_to_db(
self.profile_db_path,
config_name,
newick,
make_default=config_name == constants.merged_default,
run=self.run)
def cluster_contigs_anvio(self):
# clustering of contigs is done for each configuration file under static/clusterconfigs/merged directory;
# at this point we don't care what those recipes really require because we already merged and generated
# every data file that may be required.
self.run.info_single("Anvi'o hierarchical clustering of contigs...", nl_before=1, nl_after=1, mc="blue")
if not self.skip_hierarchical_clustering:
for config_name in self.clustering_configs:
config_path = self.clustering_configs[config_name]
config = ClusteringConfiguration(config_path, self.output_directory, db_paths=self.database_paths, row_ids_of_interest=self.split_names)
try:
clustering_id, newick = clustering.order_contigs_simple(config, distance=self.distance, linkage=self.linkage, progress=self.progress)
except Exception as e:
self.run.warning('Clustering has failed for "%s": "%s"' % (config_name, e))
self.progress.end()
continue
_, distance, linkage = clustering_id.split(':')
dbops.add_items_order_to_db(anvio_db_path=self.profile_db_path,
order_name=config_name,
order_data=newick,
distance=distance,
linkage=linkage,
make_default=config_name == constants.merged_default,
run=self.run)