def generate_variabile_positions_table(self):
if self.skip_SNV_profiling:
# there is nothing to generate really..
self.run.info('variable_nts_table', False, quiet=True)
return
variable_nts_table = dbops.TableForVariability(
self.profile_db_path,
anvio.__profile__version__,
progress=self.progress)
self.progress.new('Storing variability information')
for contig in self.contigs.values():
for split in contig.splits:
for column_profile in split.column_profiles.values():
# let's figure out more about this particular variable position
pos_in_contig = column_profile['pos_in_contig']
column_profile['in_partial_gene_call'], \
column_profile['in_complete_gene_call'],\
column_profile['pos_in_codon'] = self.get_nt_position_info(contig.name, pos_in_contig)
column_profile['sample_id'] = self.sample_id
variable_nts_table.append(column_profile)
variable_nts_table.store()
self.progress.end()
self.run.info('variable_nts_table', True, quiet=True)
def generate_variabile_nts_table(self):
if self.skip_SNV_profiling:
# there is nothing to generate really..
self.run.info('variable_nts_table', False, quiet=True)
return
self.progress.new('NT Variability')
variable_nts_table = dbops.TableForVariability(
self.profile_db_path,
anvio.__profile__version__,
progress=self.progress)
for contig in self.contigs.values():
for split in contig.splits:
for column_profile in split.column_profiles.values():
# let's figure out more about this particular variable position
pos_in_contig = column_profile['pos_in_contig']
column_profile['in_partial_gene_call'], \
column_profile['in_complete_gene_call'],\
column_profile['base_pos_in_codon'] = self.get_nt_position_info(contig.name, pos_in_contig)
column_profile['sample_id'] = self.sample_id
column_profile[
'corresponding_gene_call'] = -1 # this means there is no gene call that corresponds to this
# nt position, which will be updated in the following lines.
# yeah, we use '-1', because genecaller ids start from 0 :/
column_profile['codon_order_in_gene'] = -1
# if this particular position (`pos_in_contig`) falls within a COMPLETE gene call,
# we would like to find out which unique gene caller id(s) match to this position.
if column_profile['in_complete_gene_call']:
corresponding_gene_caller_ids = self.get_corresponding_gene_caller_ids_for_base_position(
contig.name, pos_in_contig)
# if there are more than one corresponding gene call, this usually indicates an assembly error
# just to be on the safe side, we will not report a corresopnding unique gene callers id for this
# position
if len(corresponding_gene_caller_ids) == 1:
# if we are here, it means this nucleotide position is in a complete gene call. we will do two things here.
# first, we will store the gene_caller_id that corresponds to this nt position, and then we will store the
# order of the corresponding codon in the gene for this nt position.
gene_caller_id = corresponding_gene_caller_ids[0]
column_profile[
'corresponding_gene_call'] = gene_caller_id
column_profile[
'codon_order_in_gene'] = self.get_corresponding_codon_order_in_gene(
gene_caller_id, contig.name, pos_in_contig)
# save this information for later use
self.codons_in_genes_to_profile_AA_frequencies.add(
(gene_caller_id,
column_profile['codon_order_in_gene']), )
variable_nts_table.append(column_profile)
variable_nts_table.store()
self.progress.end()
self.run.info('variable_nts_table', True, quiet=True)
def merge_variable_nts_tables(self):
variable_nts_table = dbops.TableForVariability(
self.merged_profile_db_path, progress=self.progress)
for input_profile_db_path in self.profile_dbs_info_dict:
sample_profile_db = dbops.ProfileDatabase(input_profile_db_path,
quiet=True)
sample_variable_nts_table = sample_profile_db.db.get_table_as_list_of_tuples(
tables.variable_nts_table_name,
tables.variable_nts_table_structure)
sample_profile_db.disconnect()
for tpl in sample_variable_nts_table:
entry = tuple([
variable_nts_table.next_id(tables.variable_nts_table_name)
] + list(tpl[1:]))
variable_nts_table.db_entries.append(entry)
variable_nts_table.store()
def merge_variable_nts_tables(self):
self.is_all_samples_have_it('variable_nts_table')
variable_nts_table = dbops.TableForVariability(self.profile_db_path,
progress=self.progress)
for runinfo in self.input_runinfo_dicts.values():
sample_profile_db = dbops.ProfileDatabase(runinfo['profile_db'],
quiet=True)
sample_variable_nts_table = sample_profile_db.db.get_table_as_list_of_tuples(
tables.variable_nts_table_name,
tables.variable_nts_table_structure)
sample_profile_db.disconnect()
for tpl in sample_variable_nts_table:
entry = tuple([
variable_nts_table.next_id(tables.variable_nts_table_name)
] + list(tpl[1:]))
variable_nts_table.db_entries.append(entry)
variable_nts_table.store()
