def _write(self):
with open(self.path, 'w') as fh:
fh.write('user_genome\treference_genome\tfastani_ani\tfastani_af\t'
'reference_taxonomy\tsatisfies_gtdb_circumscription_criteria\n')
for gid in sorted(self.genomes):
if gid in self.results:
thresh_results = [(ref_gid, hit) for (ref_gid, hit) in
self.results[gid].items() if hit['af'] >= self.min_af]
closest = sorted(thresh_results, key=lambda x: (-x[1]['ani'], -x[1]['af']))
if len(closest) > 0:
ref_gid = closest[0][0]
canonical_rid = canonical_gid(ref_gid)
taxonomy_str = ';'.join(self.taxonomy[canonical_rid])
gtdb_ani_radius = self.gtdb_radii.get_rep_ani(canonical_rid)
closest_ani = closest[0][1]["ani"]
closest_af = closest[0][1]["af"]
fh.write(f'{gid}\t{ref_gid}')
fh.write(f'\t{closest_ani}\t{closest_af}')
fh.write(f'\t{taxonomy_str}')
fh.write(f'\t{closest_ani >= gtdb_ani_radius and closest_af >= self.gtdb_min_af}\n')
else:
fh.write(f'{gid}\tno result\tno result\tno result\tno result\tno result\n')
else:
fh.write(f'{gid}\tno result\tno result\tno result\tno result\n')
self.logger.info(f'Closest representative hits saved to: {self.path}')
def _read(self):
"""Read the file and create any data."""
self._rep_idx, self._species_idx = dict(), dict()
with open(self.path) as fh:
for line in fh.readlines():
species, genome, ani = line.strip().split('\t')
genome = canonical_gid(genome)
ani = float(ani)
self._rep_idx[genome] = {'species': species, 'ani': ani}
self._species_idx[species] = {'rep': genome, 'ani': ani}
def _write(self):
with open(self.path, 'w') as fh:
fh.write('user_genome\treference_genome\tfastani_ani\tfastani_af\treference_taxonomy\n')
for qry_gid, ref_hits in sorted(self.results.items()):
for ref_gid, ref_hit in sorted(ref_hits.items(), key=lambda x: (-x[1]['af'], -x[1]['ani'], x[0])):
canonical_rid = canonical_gid(ref_gid)
taxonomy_str = ';'.join(self.taxonomy[canonical_rid])
fh.write(f'{qry_gid}\t{ref_gid}')
fh.write(f'\t{ref_hit["ani"]}\t{ref_hit["af"]}')
fh.write(f'\t{taxonomy_str}\n')
self.logger.info(f'Summary of results saved to: {self.path}')
def read(self,
taxonomy_file: str,
canonical_ids: bool = False) -> Dict[str, List[str]]:
"""Read Greengenes-style taxonomy file.
Expected format is:
<id>\t<taxonomy string>
where the taxonomy string has the formats:
d__; p__; c__; o__; f__; g__; s__
Parameters
----------
taxonomy_file : str
Path to a Greengenes-style taxonomy file.
canonical_ids : bool
True if to use the canonical ID format, False otherwise.
"""
try:
d = {}
with open(taxonomy_file, 'r') as f:
for row, line in enumerate(f.readlines()):
line_split = line.split('\t')
if len(line_split) != 2:
raise GTDBTkExit(f'Not a tab-separated line: {line}')
unique_id = line_split[0]
if canonical_ids:
unique_id = canonical_gid(unique_id)
tax_str = line_split[1].rstrip()
if tax_str[-1] == ';':
# remove trailing semicolons which sometimes
# appear in Greengenes-style taxonomy files
tax_str = tax_str[0:-1]
d[unique_id] = [x.strip() for x in tax_str.split(';')]
except:
self.logger.error('Failed to parse taxonomy file on line %d' %
(row + 1))
raise
return d
def read(self, taxonomy_file, canonical_ids=False):
"""Read Greengenes-style taxonomy file.
Expected format is:
<id>\t<taxonomy string>
where the taxonomy string has the formats:
d__; c__; o__; f__; g__; s__
Parameters
----------
taxonomy_file : str
Greengenes-style taxonomy file.
Returns
-------
dict[str, tuple[str, str, str, str, str, str, str]]
d[unique_id] -> [d__<taxon>, ..., s__<taxon>]
"""
try:
d = {}
with open(taxonomy_file, 'r') as f:
for row, line in enumerate(f.readlines()):
line_split = line.split('\t')
unique_id = line_split[0]
if canonical_ids:
unique_id = canonical_gid(unique_id)
tax_str = line_split[1].rstrip()
if tax_str[-1] == ';':
# remove trailing semicolons which sometimes
# appear in Greengenes-style taxonomy files
tax_str = tax_str[0:-1]
d[unique_id] = [x.strip() for x in tax_str.split(';')]
except:
self.logger.error('Failed to parse taxonomy file on line %d' %
(row + 1))
raise
return d
def _write(self):
with open(self.path, 'w') as fh:
fh.write('user_genome\treference_genome\tfastani_ani\tfastani_af\treference_taxonomy\n')
for gid in sorted(self.genomes):
if gid in self.results:
thresh_results = [(ref_gid, hit) for (ref_gid, hit) in
self.results[gid].items() if hit['af'] >= self.min_af]
closest = sorted(thresh_results, key=lambda x: (-x[1]['ani'], -x[1]['af']))
if len(closest) > 0:
ref_gid = closest[0][0]
canonical_rid = canonical_gid(ref_gid)
taxonomy_str = ';'.join(self.taxonomy[canonical_rid])
fh.write(f'{gid}\t{ref_gid}')
fh.write(f'\t{closest[0][1]["ani"]}\t{closest[0][1]["af"]}')
fh.write(f'\t{taxonomy_str}\n')
else:
fh.write(f'{gid}\tno result\tno result\tno result\tno result\n')
else:
fh.write(f'{gid}\tno result\tno result\tno result\n')
self.logger.info(f'Closest representative hits saved to: {self.path}')