def test_ncbi_type_material(self):
"""Test identification of genome being type material according to NCBI."""
g = copy.copy(test_genome)
# test type material flagged as untrustworthy within the GTDB
g.excluded_from_refseq_note = ""
g.gtdb_untrustworthy_as_type = True
g.ncbi_type_material = 'assembly from type material'
assert not g.is_ncbi_type_strain()
g.ncbi_unfiltered_taxa = Taxa(
"d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Escherichia;s__Escherichia flexneri;sb__Escherichia flexneri subsp. testus"
)
assert not g.is_ncbi_type_subspecies()
# test type material flagged as untrustworthy at NCBI
g.excluded_from_refseq_note = "untrustworthy as type"
g.gtdb_untrustworthy_as_type = False
g.ncbi_type_material = 'assembly from type material'
assert not g.is_ncbi_type_strain()
g.ncbi_unfiltered_taxa = Taxa(
"d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Escherichia;s__Escherichia flexneri;sb__Escherichia flexneri subsp. testus"
)
assert not g.is_ncbi_type_subspecies()
# test valid type material
g.excluded_from_refseq_note = ""
g.gtdb_untrustworthy_as_type = False
g.ncbi_unfiltered_taxa = Taxa(
"d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Escherichia;s__Escherichia flexneri;sb__Escherichia flexneri"
)
g.ncbi_type_material = 'assembly from type material'
assert g.is_ncbi_type_strain()
assert not g.is_ncbi_type_subspecies()
# test type material for NCBI subspecies
g.ncbi_unfiltered_taxa = Taxa(
"d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Escherichia;s__Escherichia flexneri;sb__Escherichia flexneri subsp. testus"
)
g.ncbi_type_material = 'assembly from type material'
assert not g.is_ncbi_type_strain()
assert g.is_ncbi_type_subspecies()
def set_gtdbtk_classification(self, gtdbtk_classify_file, prev_genomes):
"""Update classification of genomes based on GTDB-Tk results."""
# get species names in previous GTDB release
prev_ncbi_sp = set()
prev_gtdb_sp = set()
for gid in prev_genomes:
prev_ncbi_sp.add(prev_genomes[gid].ncbi_taxa.species)
prev_gtdb_sp.add(prev_genomes[gid].gtdb_taxa.species)
# set new genomes to the predicted GTDB-Tk classification, but
# change genus and species classifications of a genome if it has
# a previously unseen NCBI species assignment. This is a problematic
# case for curation as GTDB-Tk is unaware of these assignments.
# A common example is a new genome being the most basal
# member of a genus, this genome being classified to this genus by
# GTDB-Tk, but this genome being from a newly proposed genera which
# should be favored in order to have the GTDB reflect the opinion
# of the community. New NCBI taxa above the rank of genus are not considered
# as these are relatively uncommon and are picked up for manual curation
# using curation trees that specifically highlight genomes with previously
# unseen NCBI taxon names (see update_curation_trees)
gtdbtk_classifications = read_gtdbtk_classifications(
gtdbtk_classify_file)
num_updated = 0
num_ncbi_sp = 0
for gid in self.genomes:
if gid in gtdbtk_classifications:
num_updated += 1
gtdbtk_taxa = Taxa(';'.join(gtdbtk_classifications[gid]))
self.genomes[gid].gtdb_taxa.update_taxa(gtdbtk_taxa)
ncbi_sp = self.genomes[gid].ncbi_taxa.species
if (ncbi_sp == 's__' or ncbi_sp in prev_ncbi_sp
or ncbi_sp in prev_gtdb_sp):
continue
self.genomes[gid].gtdb_taxa.set_taxa(
5, self.genomes[gid].ncbi_taxa.genus)
self.genomes[gid].gtdb_taxa.set_taxa(6, ncbi_sp)
num_ncbi_sp += 1
return num_updated, num_ncbi_sp
def test_ncbi_subspecies(self):
"""Test identification of genomes classified as a subspecies at NCBI."""
g = copy.copy(test_genome)
# no subspecies defined
g.ncbi_unfiltered_taxa = Taxa(
"d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Escherichia;s__Escherichia flexneri"
)
assert not g.is_ncbi_subspecies()
# subspecies defined
g.ncbi_unfiltered_taxa = Taxa(
"d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Escherichia;s__Escherichia flexneri;sb__Escherichia flexneri subsp. testus"
)
assert g.is_ncbi_subspecies()
# a variety or str is not a subspecies
g.ncbi_unfiltered_taxa = Taxa(
"d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Escherichia;s__Escherichia flexneri;sb__Escherichia flexneri var. testus"
)
assert not g.is_ncbi_subspecies()
g.ncbi_unfiltered_taxa = Taxa(
"d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Escherichia;s__Escherichia flexneri;sb__Escherichia flexneri str testus"
)
assert not g.is_ncbi_subspecies()
# a variety is not a subspecies
g.ncbi_unfiltered_taxa = Taxa(
"d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Escherichia;s__Escherichia flexneri;sb__Escherichia flexneri var. testus"
)
assert not g.is_ncbi_subspecies()
# genome is not from a subspecies if the subspecies and specific name are the same since it should be considered from the species itself;
# this is critical for identifying a genome as the type strain of the species and not the type strain of a subspecies
g.ncbi_unfiltered_taxa = Taxa(
"d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Escherichia;s__Escherichia flexneri;sb__Escherichia flexneri subsp. flexneri"
)
assert not g.is_ncbi_subspecies()
def load_from_metadata_file(self,
metadata_file,
species_exception_file=None,
genus_exception_file=None,
gtdb_type_strains_ledger=None,
create_sp_clusters=True,
uba_genome_file=None,
qc_passed_file=None,
ncbi_genbank_assembly_file=None,
untrustworthy_type_ledger=None):
"""Create genome set from file(s)."""
pass_qc_gids = set()
if qc_passed_file:
with open(qc_passed_file) as f:
f.readline()
for line in f:
line_split = line.strip().split('\t')
pass_qc_gids.add(line_split[0].strip())
self.logger.info(f' - identified {len(pass_qc_gids):,} genomes passing QC.')
valid_uba_ids = set()
if uba_genome_file:
with open(uba_genome_file) as f:
for line in f:
line_split = line.strip().split('\t')
valid_uba_ids.add(line_split[0].strip())
self.logger.info(f' - identified {len(valid_uba_ids):,} UBA genomes to retain.')
gtdb_type_strains = set()
if gtdb_type_strains_ledger:
with open(gtdb_type_strains_ledger) as f:
f.readline()
for line in f:
tokens = line.strip().split('\t')
gid = canonical_gid(tokens[0].strip())
gtdb_type_strains.add(gid)
self.logger.info(f' - identified {len(gtdb_type_strains):,} manually annotated as type strain genomes.')
excluded_from_refseq_note = {}
if ncbi_genbank_assembly_file:
excluded_from_refseq_note = exclude_from_refseq(ncbi_genbank_assembly_file)
untrustworthy_as_type = set()
if untrustworthy_type_ledger:
untrustworthy_as_type = self.parse_untrustworthy_type_ledger(untrustworthy_type_ledger)
self.logger.info(f' - identified {len(untrustworthy_as_type):,} genomes annotated as untrustworthy as type.')
with open(metadata_file, encoding='utf-8') as f:
headers = f.readline().strip().split('\t')
genome_index = headers.index('accession')
gtdb_taxonomy_index = headers.index('gtdb_taxonomy')
ncbi_taxonomy_index = headers.index('ncbi_taxonomy')
ncbi_taxonomy_unfiltered_index = headers.index('ncbi_taxonomy_unfiltered')
gtdb_type_index = headers.index('gtdb_type_designation')
gtdb_type_sources_index = headers.index('gtdb_type_designation_sources')
gtdb_type_species_of_genus_index = headers.index('gtdb_type_species_of_genus')
ncbi_strain_identifiers_index = headers.index('ncbi_strain_identifiers')
ncbi_type_index = headers.index('ncbi_type_material_designation')
ncbi_asm_level_index = headers.index('ncbi_assembly_level')
ncbi_genome_representation_index = headers.index('ncbi_genome_representation')
ncbi_refseq_cat_index = headers.index('ncbi_refseq_category')
ncbi_genome_cat_index = headers.index('ncbi_genome_category')
comp_index = headers.index('checkm_completeness')
cont_index = headers.index('checkm_contamination')
sh_100_index = None
if 'checkm_strain_heterogeneity_100' in headers:
sh_100_index = headers.index('checkm_strain_heterogeneity_100')
gs_index = headers.index('genome_size')
contig_count_index = headers.index('contig_count')
n50_index = headers.index('n50_contigs')
scaffold_count_index = headers.index('scaffold_count')
ambiguous_bases_index = headers.index('ambiguous_bases')
total_gap_len_index = headers.index('total_gap_length')
ssu_count_index = headers.index('ssu_count')
ssu_length_index = headers.index('ssu_length')
ncbi_molecule_count_index = headers.index('ncbi_molecule_count')
ncbi_unspanned_gaps_index = headers.index('ncbi_unspanned_gaps')
ncbi_spanned_gaps_index = headers.index('ncbi_spanned_gaps')
gtdb_genome_rep_index = headers.index('gtdb_genome_representative')
gtdb_rep_index = headers.index('gtdb_representative')
if 'lpsn_priority_year' in headers:
# this information will be missing from the previous
# GTDB metadata file as we strip this out due to
# concerns over republishing this information
lpsn_priority_index = headers.index('lpsn_priority_year')
dsmz_priority_index = headers.index('dsmz_priority_year')
straininfo_priority_index = headers.index('straininfo_priority_year')
for line in f:
line_split = line.strip().split('\t')
ncbi_accn = line_split[genome_index]
gid = canonical_gid(ncbi_accn)
if gid.startswith('U_'):
# check if genome has a UBA identifier
org_name_index = headers.index('organism_name')
org_name = line_split[org_name_index]
if '(UBA' in org_name:
uba_id = org_name[org_name.find('(')+1:-1]
if uba_id in valid_uba_ids:
self.user_uba_id_map[gid] = uba_id
self.uba_user_id_map[uba_id] = gid
gid = uba_id
else:
continue # retain only valid UBA genomes
else:
continue # skip non-UBA user genomes
if pass_qc_gids and gid not in pass_qc_gids:
continue
gtdb_taxonomy = Taxa(line_split[gtdb_taxonomy_index])
ncbi_taxonomy = Taxa(line_split[ncbi_taxonomy_index])
ncbi_taxonomy_unfiltered = Taxa(line_split[ncbi_taxonomy_unfiltered_index])
gtdb_type = line_split[gtdb_type_index]
gtdb_type_sources = line_split[gtdb_type_sources_index]
if gid in gtdb_type_strains:
gtdb_type = 'type strain of species'
gtdb_type_sources = 'GTDB curator'
gtdb_type_species_of_genus = line_split[gtdb_type_species_of_genus_index] == 't'
ncbi_type = line_split[ncbi_type_index]
ncbi_strain_identifiers = line_split[ncbi_strain_identifiers_index]
ncbi_asm_level = line_split[ncbi_asm_level_index]
ncbi_genome_representation = line_split[ncbi_genome_representation_index]
ncbi_refseq_cat = line_split[ncbi_refseq_cat_index]
ncbi_genome_cat = line_split[ncbi_genome_cat_index]
comp = float(line_split[comp_index])
cont = float(line_split[cont_index])
sh_100 = 0
if sh_100_index:
sh_100 = self._convert_float(line_split[sh_100_index])
gs = int(line_split[gs_index])
contig_count = int(line_split[contig_count_index])
n50 = int(line_split[n50_index])
scaffold_count = int(line_split[scaffold_count_index])
ambiguous_bases = int(line_split[ambiguous_bases_index])
total_gap_len = int(line_split[total_gap_len_index])
ssu_count = int(line_split[ssu_count_index])
ssu_length = self._convert_int(line_split[ssu_length_index])
ncbi_molecule_count = self._convert_int(line_split[ncbi_molecule_count_index])
ncbi_unspanned_gaps = self._convert_int(line_split[ncbi_unspanned_gaps_index])
ncbi_spanned_gaps = self._convert_int(line_split[ncbi_spanned_gaps_index])
gtdb_is_rep = line_split[gtdb_rep_index] == 't'
gtdb_rid = canonical_gid(line_split[gtdb_genome_rep_index])
if create_sp_clusters:
self.sp_clusters.update_sp_cluster(gtdb_rid, gid, gtdb_taxonomy.species)
if 'lpsn_priority_year' in headers:
lpsn_priority_year = self._convert_int(line_split[lpsn_priority_index], Genome.NO_PRIORITY_YEAR)
dsmz_priority_year = self._convert_int(line_split[dsmz_priority_index], Genome.NO_PRIORITY_YEAR)
straininfo_priority_year = self._convert_int(line_split[straininfo_priority_index], Genome.NO_PRIORITY_YEAR)
else:
lpsn_priority_year = Genome.NO_PRIORITY_YEAR
dsmz_priority_year = Genome.NO_PRIORITY_YEAR
straininfo_priority_year = Genome.NO_PRIORITY_YEAR
self.genomes[gid] = Genome(gid,
ncbi_accn,
gtdb_rid,
gtdb_is_rep,
gtdb_taxonomy,
ncbi_taxonomy,
ncbi_taxonomy_unfiltered,
gtdb_type,
gtdb_type_sources,
gtdb_type_species_of_genus,
gid in untrustworthy_as_type,
ncbi_type,
ncbi_strain_identifiers,
ncbi_asm_level,
ncbi_genome_representation,
ncbi_refseq_cat,
ncbi_genome_cat,
excluded_from_refseq_note.get(gid, ''),
comp,
cont,
sh_100,
gs,
contig_count,
n50,
scaffold_count,
ambiguous_bases,
total_gap_len,
ssu_count,
ssu_length,
ncbi_molecule_count,
ncbi_unspanned_gaps,
ncbi_spanned_gaps,
lpsn_priority_year,
dsmz_priority_year,
straininfo_priority_year)
self._apply_ncbi_taxonomy_ledgers(species_exception_file,
genus_exception_file)
# Test methods in Genome class
from collections import defaultdict
import copy
from gtdb_species_clusters.genome import Genome
from gtdb_species_clusters.taxa import Taxa
test_genome = Genome(
"G012345678", "GCA_012345678.1", "G012345678", True,
Taxa(
"d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Escherichia;s__Escherichia flexneri"
),
Taxa(
"d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Escherichia;s__Escherichia flexneri"
),
Taxa(
"d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Escherichia;s__Escherichia flexneri"
), "type strain of species", "LPSN", True, False, False,
'assembly from type material', "K-12", "Complete genome", "Full",
"Reference genome", None, "", 100, 0, 0, 3500000, 1, 3500000, 1, 0, 0, 1,
1600, 1, 0, 0, "1900")
class TestGenome:
"""Test Genome class."""
def test_ncbi_subspecies(self):
"""Test identification of genomes classified as a subspecies at NCBI."""
g = copy.copy(test_genome)
def load_from_metadata_file(self,
metadata_file,
species_exception_file=None,
genus_exception_file=None,
gtdb_type_strains_ledger=None,
create_sp_clusters=True,
qc_passed_file=None,
ncbi_genbank_assembly_file=None,
untrustworthy_type_ledger=None,
ncbi_untrustworthy_sp_ledger=None,
ncbi_env_bioproject_ledger=None):
"""Create genome set from file(s)."""
pass_qc_gids = set()
if qc_passed_file:
with open(qc_passed_file) as f:
f.readline()
for line in f:
line_split = line.strip().split('\t')
pass_qc_gids.add(line_split[0].strip())
self.logger.info(
f' - identified {len(pass_qc_gids):,} genomes passing QC.')
gtdb_type_strains = set()
if gtdb_type_strains_ledger:
with open(gtdb_type_strains_ledger) as f:
f.readline()
for line in f:
tokens = line.strip().split('\t')
gid = canonical_gid(tokens[0].strip())
gtdb_type_strains.add(gid)
self.logger.info(
f' - identified {len(gtdb_type_strains):,} manually annotated as type strain genomes.'
)
excluded_from_refseq_note = {}
ncbi_bioproject = {}
if ncbi_genbank_assembly_file:
ncbi_bioproject = parse_ncbi_bioproject(ncbi_genbank_assembly_file)
excluded_from_refseq_note = exclude_from_refseq(
ncbi_genbank_assembly_file)
ncbi_env_bioproject = set()
if ncbi_env_bioproject_ledger:
with open(ncbi_env_bioproject_ledger) as f:
f.readline()
for line in f:
tokens = line.strip().split('\t')
ncbi_env_bioproject.add(tokens[0].strip())
untrustworthy_as_type = set()
if untrustworthy_type_ledger:
untrustworthy_as_type = self.parse_untrustworthy_type_ledger(
untrustworthy_type_ledger)
self.logger.info(
f' - identified {len(untrustworthy_as_type):,} genomes annotated as untrustworthy as type by GTDB.'
)
untrustworthy_ncbi_sp = set()
if ncbi_untrustworthy_sp_ledger:
untrustworthy_ncbi_sp = self.parse_ncbi_untrustworthy_sp_ledger(
ncbi_untrustworthy_sp_ledger)
self.logger.info(
f' - identified {len(untrustworthy_ncbi_sp):,} genomes annotated as having untrustworthy NCBI species assignments.'
)
with open(metadata_file, encoding='utf-8') as f:
headers = f.readline().strip().split('\t')
genome_index = headers.index('accession')
gtdb_taxonomy_index = headers.index('gtdb_taxonomy')
ncbi_taxonomy_index = headers.index('ncbi_taxonomy')
ncbi_taxonomy_unfiltered_index = headers.index(
'ncbi_taxonomy_unfiltered')
gtdb_type_index = headers.index('gtdb_type_designation')
gtdb_type_sources_index = headers.index(
'gtdb_type_designation_sources')
gtdb_type_species_of_genus_index = headers.index(
'gtdb_type_species_of_genus')
ncbi_strain_identifiers_index = headers.index(
'ncbi_strain_identifiers')
ncbi_type_index = headers.index('ncbi_type_material_designation')
ncbi_asm_level_index = headers.index('ncbi_assembly_level')
ncbi_genome_representation_index = headers.index(
'ncbi_genome_representation')
ncbi_refseq_cat_index = headers.index('ncbi_refseq_category')
ncbi_genome_cat_index = headers.index('ncbi_genome_category')
comp_index = headers.index('checkm_completeness')
cont_index = headers.index('checkm_contamination')
sh_100_index = None
if 'checkm_strain_heterogeneity_100' in headers:
sh_100_index = headers.index('checkm_strain_heterogeneity_100')
gs_index = headers.index('genome_size')
contig_count_index = headers.index('contig_count')
n50_index = headers.index('n50_contigs')
scaffold_count_index = headers.index('scaffold_count')
ambiguous_bases_index = headers.index('ambiguous_bases')
total_gap_len_index = headers.index('total_gap_length')
ssu_count_index = headers.index('ssu_count')
ssu_length_index = headers.index('ssu_length')
ncbi_molecule_count_index = headers.index('ncbi_molecule_count')
ncbi_unspanned_gaps_index = headers.index('ncbi_unspanned_gaps')
ncbi_spanned_gaps_index = headers.index('ncbi_spanned_gaps')
gtdb_genome_rep_index = headers.index('gtdb_genome_representative')
gtdb_rep_index = headers.index('gtdb_representative')
if 'lpsn_priority_year' in headers:
# this information will be missing from the previous
# GTDB metadata file as we strip this out due to
# concerns over republishing this information
lpsn_priority_index = headers.index('lpsn_priority_year')
for line in f:
line_split = line.strip().split('\t')
ncbi_accn = line_split[genome_index]
gid = canonical_gid(ncbi_accn)
self.full_gid[gid] = ncbi_accn
if gid.startswith('U_'):
continue
if pass_qc_gids and gid not in pass_qc_gids:
continue
gtdb_taxonomy = Taxa(line_split[gtdb_taxonomy_index])
ncbi_taxonomy = Taxa(line_split[ncbi_taxonomy_index])
ncbi_taxonomy_unfiltered = Taxa(
line_split[ncbi_taxonomy_unfiltered_index], filtered=False)
gtdb_type = line_split[gtdb_type_index]
gtdb_type_sources = line_split[gtdb_type_sources_index]
if gid in gtdb_type_strains:
gtdb_type = 'type strain of species'
gtdb_type_sources = 'GTDB curator'
gtdb_type_species_of_genus = line_split[
gtdb_type_species_of_genus_index] == 't'
ncbi_type = line_split[ncbi_type_index]
ncbi_strain_identifiers = line_split[
ncbi_strain_identifiers_index]
ncbi_asm_level = line_split[ncbi_asm_level_index]
ncbi_genome_representation = line_split[
ncbi_genome_representation_index]
ncbi_refseq_cat = line_split[ncbi_refseq_cat_index]
ncbi_genome_cat = line_split[ncbi_genome_cat_index]
if ncbi_bioproject.get(gid,
None) in ncbi_env_bioproject: # ***
# HACK to force genomes from MAG mining projects
# to be indicated as MAGs which are currently
# not correctly annotated at NCBI
ncbi_genome_cat = 'derived from environmental source'
comp = float(line_split[comp_index])
cont = float(line_split[cont_index])
sh_100 = 0
if sh_100_index:
sh_100 = self._convert_float(line_split[sh_100_index])
gs = int(line_split[gs_index])
contig_count = int(line_split[contig_count_index])
n50 = int(line_split[n50_index])
scaffold_count = int(line_split[scaffold_count_index])
ambiguous_bases = int(line_split[ambiguous_bases_index])
total_gap_len = int(line_split[total_gap_len_index])
ssu_count = int(line_split[ssu_count_index])
ssu_length = self._convert_int(line_split[ssu_length_index])
ncbi_molecule_count = self._convert_int(
line_split[ncbi_molecule_count_index])
ncbi_unspanned_gaps = self._convert_int(
line_split[ncbi_unspanned_gaps_index])
ncbi_spanned_gaps = self._convert_int(
line_split[ncbi_spanned_gaps_index])
gtdb_is_rep = line_split[gtdb_rep_index] == 't'
gtdb_rid = canonical_gid(line_split[gtdb_genome_rep_index])
if create_sp_clusters:
self.sp_clusters.update_sp_cluster(gtdb_rid, gid,
gtdb_taxonomy.species)
lpsn_priority_year = Genome.NO_PRIORITY_YEAR
if 'lpsn_priority_year' in headers:
lpsn_priority_year = self._convert_int(
line_split[lpsn_priority_index],
Genome.NO_PRIORITY_YEAR)
self.genomes[gid] = Genome(
gid, ncbi_accn, gtdb_rid, gtdb_is_rep, gtdb_taxonomy,
ncbi_taxonomy, ncbi_taxonomy_unfiltered, gtdb_type,
gtdb_type_sources, gtdb_type_species_of_genus, gid
in untrustworthy_as_type, gid in untrustworthy_ncbi_sp,
ncbi_type, ncbi_strain_identifiers, ncbi_asm_level,
ncbi_genome_representation,
ncbi_refseq_cat, ncbi_genome_cat,
excluded_from_refseq_note.get(gid, ''), comp, cont, sh_100,
gs, contig_count, n50, scaffold_count, ambiguous_bases,
total_gap_len, ssu_count, ssu_length, ncbi_molecule_count,
ncbi_unspanned_gaps, ncbi_spanned_gaps, lpsn_priority_year)
self._apply_ncbi_taxonomy_ledgers(species_exception_file,
genus_exception_file)