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 convert(self, infile, count=False):
class Mock:
def __init_(self):
self.__dict__ = {}
import anvio.dbops as dbops
args = Mock()
args.__dict__['pan_db'] = infile
pan = dbops.PanSuperclass(args)
gene_cluster_ids = pan.gene_cluster_names
pan.init_gene_clusters(gene_cluster_ids)
gene_cluster = set(pan.gene_clusters.keys())
genomes = {g for k, v in pan.gene_clusters.items() for g in v}
genome2genecluster = {g: [] for g in genomes}
for gc, hits in pan.gene_clusters.items():
for genome, genes in hits.items():
if len(genes) > 0:
if gc not in genome2genecluster[genome]:
genome2genecluster[genome].append(gc)
if count:
return {
k: {vv: v.count(vv)
for vv in set(v)}
for k, v in genome2genecluster.items()
}
else:
return {k: list(set(v)) for k, v in genome2genecluster.items()}