def populate_gene_cluster_homogeneity_index(self, gene_clusters_dict):
if self.skip_alignments:
self.run.warning(
'Skipping homogeneity calculations because gene clusters are not alligned.'
)
return
if self.skip_homogeneity:
self.run.warning(
"Skipping homogeneity calculations per the '--skip-homogeneity' flag."
)
return
pan = dbops.PanSuperclass(args=self.args, r=self.run, p=self.progress)
gene_cluster_names = set(list(gene_clusters_dict.keys()))
d = pan.compute_homogeneity_indices_for_gene_clusters(
gene_cluster_names=gene_cluster_names,
num_threads=self.num_threads)
if d is None:
self.run.warning(
"Anvi'o received an empty dictionary for homogeneity indices. Not good :/ Returning empty handed,\
without updating anything in the pan database..."
)
return
miscdata.TableForItemAdditionalData(self.args).add(
d, [
'functional_homogeneity_index', 'geometric_homogeneity_index',
'combined_homogeneity_index'
],
skip_check_names=True)
def process_gene_clusters(self, gene_clusters_dict):
self.progress.new('Generating view data')
self.progress.update('...')
gene_clusters = list(gene_clusters_dict.keys())
for genome_name in self.genomes:
self.genomes[genome_name]['singleton_gene_clusters'] = 0
self.genomes[genome_name]['num_gene_clusters_raw'] = 0
for gene_cluster in gene_clusters:
self.view_data[gene_cluster] = dict([(genome_name, 0) for genome_name in self.genomes])
self.view_data_presence_absence[gene_cluster] = dict([(genome_name, 0) for genome_name in self.genomes])
self.additional_view_data[gene_cluster] = {'num_genes_in_gene_cluster': 0, 'num_genomes_gene_cluster_has_hits': 0, 'SCG': 0, 'max_num_paralogs': 0}
for gene_entry in gene_clusters_dict[gene_cluster]:
genome_name = gene_entry['genome_name']
self.view_data[gene_cluster][genome_name] += 1
self.view_data_presence_absence[gene_cluster][genome_name] = 1
self.additional_view_data[gene_cluster]['num_genes_in_gene_cluster'] += 1
self.genomes[genome_name]['num_gene_clusters_raw'] += 1
genomes_contributing_to_gene_cluster = [t[0] for t in self.view_data_presence_absence[gene_cluster].items() if t[1]]
if len(genomes_contributing_to_gene_cluster) == 1:
self.genomes[genomes_contributing_to_gene_cluster[0]]['singleton_gene_clusters'] += 1
self.additional_view_data[gene_cluster]['SCG'] = 1 if set(self.view_data[gene_cluster].values()) == set([1]) else 0
self.additional_view_data[gene_cluster]['max_num_paralogs'] = max(self.view_data[gene_cluster].values())
self.additional_view_data[gene_cluster]['num_genomes_gene_cluster_has_hits'] = len([True for genome in self.view_data[gene_cluster] if self.view_data[gene_cluster][genome] > 0])
self.progress.end()
########################################################################################
# FILTERING BASED ON OCCURRENCE
########################################################################################
gene_clusters_of_interest = set([])
for gene_cluster in gene_clusters:
if self.additional_view_data[gene_cluster]['num_genomes_gene_cluster_has_hits'] >= self.gene_cluster_min_occurrence:
gene_clusters_of_interest.add(gene_cluster)
removed_gene_clusters = 0
for gene_cluster in gene_clusters:
if gene_cluster not in gene_clusters_of_interest:
self.view_data.pop(gene_cluster)
self.view_data_presence_absence.pop(gene_cluster)
self.additional_view_data.pop(gene_cluster)
gene_clusters_dict.pop(gene_cluster)
removed_gene_clusters += 1
if self.gene_cluster_min_occurrence > 1:
self.run.info('gene_clusters min occurrence', '%d (the filter removed %d gene_clusters)' % (self.gene_cluster_min_occurrence, removed_gene_clusters))
########################################################################################
# CAN WE CLUSTER THIS STUFF? DOES THE USER WANT US TO TRY REGARDLESS?
########################################################################################
if len(gene_clusters_dict) > self.max_num_gene_clusters_for_hierarchical_clustering:
if self.enforce_hierarchical_clustering:
self.run.warning("You have %s gene_clusters, which exceeds the number of gene_clusters anvi'o is comfortable to cluster. But\
since you have used the flag `--enforce-hierarchical-clustering`, anvi'o will attempt\
to create a hierarchical clustering of your gene_clusters anyway. It may take a bit of \
time. Pour yourself a coffee. Or go to a nice vacation. See you in 10 mins, or next year \
or never." % pp(len(gene_clusters_dict)))
else:
self.run.warning("It seems you have %s gene clusters in your pangenome. This exceeds the soft limit\
of %s for anvi'o to attempt to create a hierarchical clustering of your gene clusters\
(which becomes the center tree in all anvi'o displays). If you want a hierarchical\
clustering to be done anyway, please see the flag `--enforce-hierarchical-clustering`." \
% (pp(len(gene_clusters_dict)), pp(self.max_num_gene_clusters_for_hierarchical_clustering)))
self.skip_hierarchical_clustering = True
########################################################################################
# STORING FILTERED DATA IN THE DB
########################################################################################
table_structure=['gene_cluster'] + sorted(self.genomes.keys())
table_types=['text'] + ['numeric'] * len(self.genomes)
TablesForViews(self.pan_db_path).create_new_view(
data_dict=self.view_data,
table_name='gene_cluster_frequencies',
table_structure=table_structure,
table_types=table_types,
view_name = 'gene_cluster_frequencies')
TablesForViews(self.pan_db_path).create_new_view(
data_dict=self.view_data_presence_absence,
table_name='gene_cluster_presence_absence',
table_structure=table_structure,
table_types=table_types,
view_name = 'gene_cluster_presence_absence')
item_additional_data_table = miscdata.TableForItemAdditionalData(self.args)
item_additional_data_keys = ['num_genomes_gene_cluster_has_hits', 'num_genes_in_gene_cluster', 'max_num_paralogs', 'SCG']
item_additional_data_table.add(self.additional_view_data, item_additional_data_keys, skip_check_names=True)
# ^^^^^^^^^^^^^^^^^^^^^
# /
# here we say skip_check_names=True, simply because there is no gene_clusters table has not been
# generated yet, but the check names functionality in dbops looks for the gene clsuters table to
# be certain. it is not a big deal here, since we absoluely know what gene cluster names we are
# working with.
########################################################################################
# RETURN THE -LIKELY- UPDATED PROTEIN CLUSTERS DICT
########################################################################################
return gene_clusters_dict
