def test_write(self):
tln = TlnTableSummaryFile(self.dir_tmp, 'tst')
tln.add_genome('a', 4)
tln.add_genome('b', 11)
tln.write()
lines = set()
with open(tln.path) as fh:
[lines.add(x) for x in fh.readlines()]
self.assertSetEqual({'a\t4\n', 'b\t11\n'}, lines)
def _report_identified_marker_genes(self, gene_dict, outdir, prefix):
"""Report statistics for identified marker genes."""
# Summarise the copy number of each AR122 and BAC120 markers.
tln_summary_file = TlnTableSummaryFile(outdir, prefix)
ar122_copy_number_file = CopyNumberFileAR122(outdir, prefix)
bac120_copy_number_file = CopyNumberFileBAC120(outdir, prefix)
# Process each genome.
for db_genome_id, info in sorted(gene_dict.items()):
cur_marker_dir = os.path.join(outdir, DIR_MARKER_GENE)
pfam_tophit_file = TopHitPfamFile(cur_marker_dir, db_genome_id)
tigr_tophit_file = TopHitTigrFile(cur_marker_dir, db_genome_id)
pfam_tophit_file.read()
tigr_tophit_file.read()
# Summarise each of the markers for this genome.
ar122_copy_number_file.add_genome(db_genome_id,
info.get("aa_gene_path"),
pfam_tophit_file,
tigr_tophit_file)
bac120_copy_number_file.add_genome(db_genome_id,
info.get("aa_gene_path"),
pfam_tophit_file,
tigr_tophit_file)
# Write the best translation table to disk for this genome.
tln_summary_file.add_genome(db_genome_id,
info.get("best_translation_table"))
# Write each of the summary files to disk.
ar122_copy_number_file.write()
bac120_copy_number_file.write()
tln_summary_file.write()
# Create a symlink to store the summary files in the root.
symlink_f(
PATH_BAC120_MARKER_SUMMARY.format(prefix=prefix),
os.path.join(
outdir,
os.path.basename(
PATH_BAC120_MARKER_SUMMARY.format(prefix=prefix))))
symlink_f(
PATH_AR122_MARKER_SUMMARY.format(prefix=prefix),
os.path.join(
outdir,
os.path.basename(
PATH_AR122_MARKER_SUMMARY.format(prefix=prefix))))
symlink_f(
PATH_TLN_TABLE_SUMMARY.format(prefix=prefix),
os.path.join(
outdir,
os.path.basename(
PATH_TLN_TABLE_SUMMARY.format(prefix=prefix))))
def _report_identified_marker_genes(self, gene_dict, outdir, prefix,
write_single_copy_genes):
"""Report statistics for identified marker genes."""
# Summarise the copy number of each AR53 and BAC120 markers.
tln_summary_file = TlnTableSummaryFile(outdir, prefix)
ar53_copy_number_file = CopyNumberFileAR53(outdir, prefix)
bac120_copy_number_file = CopyNumberFileBAC120(outdir, prefix)
# Process each genome.
for db_genome_id, info in tqdm_log(sorted(gene_dict.items()),
unit='genome'):
cur_marker_dir = os.path.join(outdir, DIR_MARKER_GENE)
pfam_tophit_file = TopHitPfamFile(cur_marker_dir, db_genome_id)
tigr_tophit_file = TopHitTigrFile(cur_marker_dir, db_genome_id)
pfam_tophit_file.read()
tigr_tophit_file.read()
# Summarise each of the markers for this genome.
ar53_copy_number_file.add_genome(db_genome_id,
info.get("aa_gene_path"),
pfam_tophit_file,
tigr_tophit_file)
bac120_copy_number_file.add_genome(db_genome_id,
info.get("aa_gene_path"),
pfam_tophit_file,
tigr_tophit_file)
# Write the best translation table to disk for this genome.
tln_summary_file.add_genome(db_genome_id,
info.get("best_translation_table"))
# Write each of the summary files to disk.
ar53_copy_number_file.write()
bac120_copy_number_file.write()
tln_summary_file.write()
# Create a symlink to store the summary files in the root.
# symlink_f(PATH_BAC120_MARKER_SUMMARY.format(prefix=prefix),
# os.path.join(outdir, os.path.basename(PATH_BAC120_MARKER_SUMMARY.format(prefix=prefix))))
# symlink_f(PATH_AR53_MARKER_SUMMARY.format(prefix=prefix),
# os.path.join(outdir, os.path.basename(PATH_AR53_MARKER_SUMMARY.format(prefix=prefix))))
# symlink_f(PATH_TLN_TABLE_SUMMARY.format(prefix=prefix),
# os.path.join(outdir, os.path.basename(PATH_TLN_TABLE_SUMMARY.format(prefix=prefix))))
symlink_f(
PATH_FAILS.format(prefix=prefix),
os.path.join(outdir,
os.path.basename(PATH_FAILS.format(prefix=prefix))))
# Write the single copy AR53/BAC120 FASTA files to disk.
if write_single_copy_genes:
fasta_dir = os.path.join(outdir, DIR_IDENTIFY_FASTA)
self.logger.info(
f'Writing unaligned single-copy genes to: {fasta_dir}')
# Iterate over each domain.
marker_doms = list()
marker_doms.append(
(Config.AR53_MARKERS['PFAM'] + Config.AR53_MARKERS['TIGRFAM'],
ar53_copy_number_file, 'ar53'))
marker_doms.append((Config.BAC120_MARKERS['PFAM'] +
Config.BAC120_MARKERS['TIGRFAM'],
bac120_copy_number_file, 'bac120'))
for marker_names, marker_file, marker_d in marker_doms:
# Create the domain-specific subdirectory.
fasta_d_dir = os.path.join(fasta_dir, marker_d)
make_sure_path_exists(fasta_d_dir)
# Iterate over each marker.
for marker_name in marker_names:
marker_name = marker_name.rstrip(r'\.[HMMhmm]')
marker_path = os.path.join(fasta_d_dir,
f'{marker_name}.fa')
to_write = list()
for genome_id in sorted(gene_dict):
unq_hits = marker_file.get_single_copy_hits(genome_id)
if marker_name in unq_hits:
to_write.append(f'>{genome_id}')
to_write.append(unq_hits[marker_name]['seq'])
if len(to_write) > 0:
with open(marker_path, 'w') as fh:
fh.write('\n'.join(to_write))
def test_add_genome_raises_exception(self):
tln = TlnTableSummaryFile(self.dir_tmp, 'tst')
tln.add_genome('a', 4)
self.assertRaises(GTDBTkExit, tln.add_genome, 'a', 11)
def test_add_genome(self):
tln = TlnTableSummaryFile(self.dir_tmp, 'tst')
tln.add_genome('a', 4)
tln.add_genome('b', 11)
self.assertDictEqual({'a': 4, 'b': 11}, tln.genomes)