def _apply_mask(self, gtdb_msa, user_msa, msa_mask, min_perc_aa):
"""Apply canonical mask to MSA file."""
aligned_genomes = merge_two_dicts(gtdb_msa, user_msa)
list_mask = np.fromfile(msa_mask, dtype='S1') == b'1'
output_seqs, pruned_seqs = dict(), dict()
for seq_id, seq in tqdm_log(aligned_genomes.items(), unit='sequence'):
list_seq = np.fromiter(seq, dtype='S1')
if list_mask.shape[0] != list_seq.shape[0]:
raise MSAMaskLengthMismatch(
f'Mask ({list_mask.shape[0]}) and alignment ({list_seq.shape[0]}) length do not match.'
)
list_masked_seq = list_seq[list_mask]
masked_seq_unique = np.unique(list_masked_seq, return_counts=True)
masked_seq_counts = defaultdict(lambda: 0)
for aa_char, aa_count in zip(masked_seq_unique[0],
masked_seq_unique[1]):
masked_seq_counts[aa_char.decode('utf-8')] = aa_count
masked_seq = list_masked_seq.tostring().decode('utf-8')
valid_bases = list_masked_seq.shape[0] - \
masked_seq_counts['.'] - masked_seq_counts['-']
if seq_id in user_msa and valid_bases < list_masked_seq.shape[
0] * min_perc_aa:
pruned_seqs[seq_id] = masked_seq
continue
output_seqs[seq_id] = masked_seq
return output_seqs, pruned_seqs
def _apply_mask(self, gtdb_msa, user_msa, msa_mask, min_perc_aa):
"""Apply canonical mask to MSA file."""
aligned_genomes = merge_two_dicts(gtdb_msa, user_msa)
list_mask = np.fromfile(msa_mask, dtype='S1') == b'1'
output_seqs = {}
pruned_seqs = {}
bar_fmt = '==> Masked {n_fmt}/{total_fmt} ({percentage:.0f}%) ' \
'alignments [{rate_fmt}, ETA {remaining}]'
for seq_id, seq in tqdm(aligned_genomes.items(), bar_format=bar_fmt):
list_seq = np.fromiter(seq, dtype='S1')
if list_mask.shape[0] != list_seq.shape[0]:
raise MSAMaskLengthMismatch(
'Mask and alignment length do not match.')
list_masked_seq = list_seq[list_mask]
masked_seq_unique = np.unique(list_masked_seq, return_counts=True)
masked_seq_counts = defaultdict(lambda: 0)
for aa_char, aa_count in zip(masked_seq_unique[0],
masked_seq_unique[1]):
masked_seq_counts[aa_char.decode('utf-8')] = aa_count
masked_seq = list_masked_seq.tostring().decode('utf-8')
valid_bases = list_masked_seq.shape[0] - masked_seq_counts[
'.'] - masked_seq_counts['-']
if seq_id in user_msa and valid_bases < list_masked_seq.shape[
0] * min_perc_aa:
pruned_seqs[seq_id] = masked_seq
continue
output_seqs[seq_id] = masked_seq
return output_seqs, pruned_seqs
def test_merge_two_dicts(self):
a = {'k1': 'v1', 'k2': 'v2'}
b = {'k3': 'v3', 'k4': 'v4'}
join_dict = tools.merge_two_dicts(a, b)
self.assertIn('k1', join_dict)
self.assertIn('k3', join_dict)
self.assertEqual(len(join_dict), 4)
def _apply_mask(self, gtdb_msa, user_msa, msa_mask, min_perc_aa):
"""Apply canonical mask to MSA file."""
aligned_genomes = merge_two_dicts(gtdb_msa, user_msa)
with open(msa_mask, 'r') as f:
mask = f.readline().strip()
list_mask = np.array([True if c == '1' else False for c in mask],
dtype=bool)
output_seqs = {}
pruned_seqs = {}
for seq_id, seq in aligned_genomes.iteritems():
if len(mask) != len(seq):
self.logger.error('Mask and alignment length do not match.')
raise MSAMaskLengthMismatch(
'Mask and alignment length do not match.')
masked_seq = ''.join(np.array(list(seq), dtype=str)[list_mask])
valid_bases = len(masked_seq) - masked_seq.count(
'.') - masked_seq.count('-')
if seq_id in user_msa and valid_bases < len(
masked_seq) * min_perc_aa:
pruned_seqs[seq_id] = masked_seq
continue
output_seqs[seq_id] = masked_seq
return output_seqs, pruned_seqs
def align(self,
identify_dir,
skip_gtdb_refs,
taxa_filter,
min_perc_aa,
custom_msa_filters,
skip_trimming,
rnd_seed,
cols_per_gene,
min_consensus,
max_consensus,
min_per_taxa,
out_dir,
prefix,
outgroup_taxon,
genomes_to_process=None):
"""Align marker genes in genomes."""
# read genomes that failed identify steps to skip them
failed_genomes_file = os.path.join(
os.path.join(identify_dir, PATH_FAILS.format(prefix=prefix)))
if os.path.isfile(failed_genomes_file):
with open(failed_genomes_file) as fgf:
failed_genomes = [row.split()[0] for row in fgf]
else:
failed_genomes = list()
# If the user is re-running this step, check if the identify step is consistent.
genomic_files = self._path_to_identify_data(identify_dir,
identify_dir != out_dir)
if genomes_to_process is not None and len(genomic_files) != len(
genomes_to_process):
if list(
set(genomic_files.keys()) - set(genomes_to_process.keys())
).sort() != failed_genomes.sort():
self.logger.error(
'{} are not present in the input list of genome to process.'
.format(
list(
set(genomic_files.keys()) -
set(genomes_to_process.keys()))))
raise InconsistentGenomeBatch(
'You are attempting to run GTDB-Tk on a non-empty directory that contains extra '
'genomes not present in your initial identify directory. Remove them, or run '
'GTDB-Tk on a new directory.')
# If this is being run as a part of classify_wf, copy the required files.
if identify_dir != out_dir:
identify_path = os.path.join(out_dir, DIR_IDENTIFY)
make_sure_path_exists(identify_path)
copy(
CopyNumberFileBAC120(identify_dir, prefix).path, identify_path)
copy(CopyNumberFileAR53(identify_dir, prefix).path, identify_path)
copy(TlnTableSummaryFile(identify_dir, prefix).path, identify_path)
# Create the align intermediate directory.
make_sure_path_exists(os.path.join(out_dir, DIR_ALIGN_INTERMEDIATE))
# Write out files with marker information
ar53_marker_info_file = MarkerInfoFileAR53(out_dir, prefix)
ar53_marker_info_file.write()
bac120_marker_info_file = MarkerInfoFileBAC120(out_dir, prefix)
bac120_marker_info_file.write()
# Determine what domain each genome belongs to.
bac_gids, ar_gids, _bac_ar_diff = self.genome_domain(
identify_dir, prefix)
if len(bac_gids) + len(ar_gids) == 0:
raise GTDBTkExit(f'Unable to assign a domain to any genomes, '
f'please check the identify marker summary file, '
f'and verify genome quality.')
# # Create a temporary directory that will be used to generate each of the alignments.
# with tempfile.TemporaryDirectory(prefix='gtdbtk_tmp_') as dir_tmp_arc, \
# tempfile.TemporaryDirectory(prefix='gtdbtk_tmp_') as dir_tmp_bac:
#
# cur_gid_dict = {x: genomic_files[x] for x in ar_gids}
# self.logger.info(f'Collecting marker sequences from {len(cur_gid_dict):,} '
# f'genomes identified as archaeal.')
# align.concat_single_copy_hits(dir_tmp_arc,
# cur_gid_dict,
# ar53_marker_info_file)
#
self.logger.info(
f'Aligning markers in {len(genomic_files):,} genomes with {self.cpus} CPUs.'
)
dom_iter = ((bac_gids, Config.CONCAT_BAC120, Config.MASK_BAC120,
"bac120", 'bacterial', CopyNumberFileBAC120),
(ar_gids, Config.CONCAT_AR53, Config.MASK_AR53, "ar53",
'archaeal', CopyNumberFileAR53))
gtdb_taxonomy = Taxonomy().read(self.taxonomy_file)
for gids, msa_file, mask_file, marker_set_id, domain_str, copy_number_f in dom_iter:
# No genomes identified as this domain.
if len(gids) == 0:
continue
self.logger.info(
f'Processing {len(gids):,} genomes identified as {domain_str}.'
)
if marker_set_id == 'bac120':
marker_info_file = bac120_marker_info_file
marker_filtered_genomes = os.path.join(
out_dir,
PATH_BAC120_FILTERED_GENOMES.format(prefix=prefix))
marker_msa_path = os.path.join(
out_dir, PATH_BAC120_MSA.format(prefix=prefix))
marker_user_msa_path = os.path.join(
out_dir, PATH_BAC120_USER_MSA.format(prefix=prefix))
else:
marker_info_file = ar53_marker_info_file
marker_filtered_genomes = os.path.join(
out_dir, PATH_AR53_FILTERED_GENOMES.format(prefix=prefix))
marker_msa_path = os.path.join(
out_dir, PATH_AR53_MSA.format(prefix=prefix))
marker_user_msa_path = os.path.join(
out_dir, PATH_AR53_USER_MSA.format(prefix=prefix))
cur_genome_files = {
gid: f
for gid, f in genomic_files.items() if gid in gids
}
if skip_gtdb_refs:
gtdb_msa = {}
else:
gtdb_msa = self._msa_filter_by_taxa(msa_file, gtdb_taxonomy,
taxa_filter,
outgroup_taxon)
gtdb_msa_mask = os.path.join(Config.MASK_DIR, mask_file)
# Generate the user MSA.
user_msa = align.align_marker_set(cur_genome_files,
marker_info_file, copy_number_f,
self.cpus)
if len(user_msa) == 0:
self.logger.warning(
f'Identified {len(user_msa):,} single copy {domain_str} hits.'
)
continue
# Write the individual marker alignments to disk
if self.debug:
self._write_individual_markers(user_msa, marker_set_id,
marker_info_file.path, out_dir,
prefix)
# filter columns without sufficient representation across taxa
if skip_trimming:
self.logger.info(
'Skipping custom filtering and selection of columns.')
pruned_seqs = {}
trimmed_seqs = merge_two_dicts(gtdb_msa, user_msa)
elif custom_msa_filters:
aligned_genomes = merge_two_dicts(gtdb_msa, user_msa)
self.logger.info(
'Performing custom filtering and selection of columns.')
trim_msa = TrimMSA(
cols_per_gene, min_perc_aa / 100.0, min_consensus / 100.0,
max_consensus / 100.0, min_per_taxa / 100.0, rnd_seed,
os.path.join(out_dir, f'filter_{marker_set_id}'))
trimmed_seqs, pruned_seqs = trim_msa.trim(
aligned_genomes, marker_info_file.path)
if trimmed_seqs:
self.logger.info(
'Filtered MSA from {:,} to {:,} AAs.'.format(
len(list(aligned_genomes.values())[0]),
len(list(trimmed_seqs.values())[0])))
self.logger.info(
'Filtered {:,} genomes with amino acids in <{:.1f}% of columns in filtered MSA.'
.format(len(pruned_seqs), min_perc_aa))
filtered_user_genomes = set(pruned_seqs).intersection(user_msa)
if len(filtered_user_genomes):
self.logger.info(
f'Filtered genomes include {len(filtered_user_genomes)} user submitted genomes.'
)
else:
self.logger.log(
Config.LOG_TASK,
f'Masking columns of {domain_str} multiple sequence alignment using canonical mask.'
)
trimmed_seqs, pruned_seqs = self._apply_mask(
gtdb_msa, user_msa, gtdb_msa_mask, min_perc_aa / 100.0)
self.logger.info(
'Masked {} alignment from {:,} to {:,} AAs.'.format(
domain_str, len(list(user_msa.values())[0]),
len(list(trimmed_seqs.values())[0])))
if min_perc_aa > 0:
self.logger.info(
'{:,} {} user genomes have amino acids in <{:.1f}% of columns in filtered MSA.'
.format(len(pruned_seqs), domain_str, min_perc_aa))
# write out filtering information
with open(marker_filtered_genomes, 'w') as fout:
for pruned_seq_id, pruned_seq in pruned_seqs.items():
if len(pruned_seq) == 0:
perc_alignment = 0
else:
valid_bases = sum(
[1 for c in pruned_seq if c.isalpha()])
perc_alignment = valid_bases * 100.0 / len(pruned_seq)
fout.write(
f'{pruned_seq_id}\tInsufficient number of amino acids in MSA ({perc_alignment:.1f}%)\n'
)
# write out MSAs
if not skip_gtdb_refs:
self.logger.info(
f'Creating concatenated alignment for {len(trimmed_seqs):,} '
f'{domain_str} GTDB and user genomes.')
self._write_msa(trimmed_seqs,
marker_msa_path,
gtdb_taxonomy,
zip_output=True)
trimmed_user_msa = {
k: v
for k, v in trimmed_seqs.items() if k in user_msa
}
if len(trimmed_user_msa) > 0:
self.logger.info(
f'Creating concatenated alignment for {len(trimmed_user_msa):,} '
f'{domain_str} user genomes.')
self._write_msa(trimmed_user_msa,
marker_user_msa_path,
gtdb_taxonomy,
zip_output=True)
else:
self.logger.info(
f'All {domain_str} user genomes have been filtered out.')
def align(self,
identify_dir,
skip_gtdb_refs,
taxa_filter,
min_perc_aa,
custom_msa_filters,
skip_trimming,
rnd_seed,
cols_per_gene,
min_consensus,
max_consensus,
min_per_taxa,
out_dir,
prefix,
outgroup_taxon,
genomes_to_process=None):
"""Align marker genes in genomes."""
if identify_dir != out_dir:
if not os.path.isdir(os.path.join(out_dir, DIR_IDENTIFY)):
os.makedirs(os.path.join(out_dir, DIR_IDENTIFY))
copy(
os.path.join(identify_dir,
PATH_BAC120_MARKER_SUMMARY.format(prefix=prefix)),
os.path.join(out_dir, DIR_IDENTIFY))
copy(
os.path.join(identify_dir,
PATH_AR122_MARKER_SUMMARY.format(prefix=prefix)),
os.path.join(out_dir, DIR_IDENTIFY))
identify_gene_file = os.path.join(
identify_dir, PATH_TLN_TABLE_SUMMARY.format(prefix=prefix))
copy(identify_gene_file, os.path.join(out_dir, DIR_IDENTIFY))
if not os.path.exists(os.path.join(out_dir, DIR_ALIGN_INTERMEDIATE)):
os.makedirs(os.path.join(out_dir, DIR_ALIGN_INTERMEDIATE))
# write out files with marker information
bac120_marker_info_file = os.path.join(
out_dir, PATH_BAC120_MARKER_INFO.format(prefix=prefix))
self._write_marker_info(Config.BAC120_MARKERS, bac120_marker_info_file)
ar122_marker_info_file = os.path.join(
out_dir, PATH_AR122_MARKER_INFO.format(prefix=prefix))
self._write_marker_info(Config.AR122_MARKERS, ar122_marker_info_file)
genomic_files = self._path_to_identify_data(identify_dir,
identify_dir != out_dir)
if genomes_to_process is not None and len(genomic_files) != len(
genomes_to_process):
self.logger.error(
'{} are not present in the input list of genome to process.'.
format(
list(
set(genomic_files.keys()) -
set(genomes_to_process.keys()))))
raise InconsistentGenomeBatch(
'You are attempting to run GTDB-Tk on a non-empty directory that contains extra '
'genomes not present in your initial identify directory. Remove them, or run '
'GTDB-Tk on a new directory.')
self.logger.info('Aligning markers in %d genomes with %d threads.' %
(len(genomic_files), self.cpus))
# determine marker set for each user genome
bac_gids, ar_gids, _bac_ar_diff = self.genome_domain(
identify_dir, prefix)
# align user genomes
gtdb_taxonomy = Taxonomy().read(self.taxonomy_file)
for gids, msa_file, mask_file, marker_set_id in ((bac_gids,
Config.CONCAT_BAC120,
Config.MASK_BAC120,
"bac120"),
(ar_gids,
Config.CONCAT_AR122,
Config.MASK_AR122,
"ar122")):
domain_str = 'archaeal'
if marker_set_id == 'bac120':
domain_str = 'bacterial'
if len(gids) == 0:
continue
self.logger.info(
'Processing {:,} genomes identified as {}.'.format(
len(gids), domain_str))
if marker_set_id == 'bac120':
marker_info_file = bac120_marker_info_file
marker_filtered_genomes = os.path.join(
out_dir,
PATH_BAC120_FILTERED_GENOMES.format(prefix=prefix))
marker_msa_path = os.path.join(
out_dir, PATH_BAC120_MSA.format(prefix=prefix))
marker_user_msa_path = os.path.join(
out_dir, PATH_BAC120_USER_MSA.format(prefix=prefix))
else:
marker_info_file = ar122_marker_info_file
marker_filtered_genomes = os.path.join(
out_dir, PATH_AR122_FILTERED_GENOMES.format(prefix=prefix))
marker_msa_path = os.path.join(
out_dir, PATH_AR122_MSA.format(prefix=prefix))
marker_user_msa_path = os.path.join(
out_dir, PATH_AR122_USER_MSA.format(prefix=prefix))
cur_genome_files = {
gid: f
for gid, f in genomic_files.items() if gid in gids
}
if skip_gtdb_refs:
gtdb_msa = {}
else:
gtdb_msa = self._msa_filter_by_taxa(msa_file, gtdb_taxonomy,
taxa_filter,
outgroup_taxon)
gtdb_msa_mask = os.path.join(Config.MASK_DIR, mask_file)
hmm_aligner = HmmAligner(self.cpus, self.pfam_top_hit_suffix,
self.tigrfam_top_hit_suffix,
self.protein_file_suffix,
self.pfam_hmm_dir, self.tigrfam_hmms,
Config.BAC120_MARKERS,
Config.AR122_MARKERS)
user_msa = hmm_aligner.align_marker_set(cur_genome_files,
marker_set_id)
# Write the individual marker alignments to disk
if self.debug:
self._write_individual_markers(user_msa, marker_set_id,
marker_info_file, out_dir,
prefix)
# filter columns without sufficient representation across taxa
if skip_trimming:
self.logger.info(
'Skipping custom filtering and selection of columns.')
pruned_seqs = {}
trimmed_seqs = merge_two_dicts(gtdb_msa, user_msa)
elif custom_msa_filters:
aligned_genomes = merge_two_dicts(gtdb_msa, user_msa)
self.logger.info(
'Performing custom filtering and selection of columns.')
trim_msa = TrimMSA(
cols_per_gene, min_perc_aa / 100.0, min_consensus / 100.0,
max_consensus / 100.0, min_per_taxa / 100.0, rnd_seed,
os.path.join(out_dir, 'filter_%s' % marker_set_id))
trimmed_seqs, pruned_seqs = trim_msa.trim(
aligned_genomes, marker_info_file)
if trimmed_seqs:
self.logger.info(
'Filtered MSA from {:,} to {:,} AAs.'.format(
len(list(aligned_genomes.values())[0]),
len(list(trimmed_seqs.values())[0])))
self.logger.info(
'Filtered {:,} genomes with amino acids in <{:.1f}% of columns in filtered MSA.'
.format(len(pruned_seqs), min_perc_aa))
filtered_user_genomes = set(pruned_seqs).intersection(user_msa)
if len(filtered_user_genomes):
self.logger.info(
'Filtered genomes include {:.} user submitted genomes.'
.format(len(filtered_user_genomes)))
else:
self.logger.info(
f'Masking columns of {domain_str} multiple sequence alignment using canonical mask.'
)
trimmed_seqs, pruned_seqs = self._apply_mask(
gtdb_msa, user_msa, gtdb_msa_mask, min_perc_aa / 100.0)
self.logger.info(
'Masked {} alignment from {:,} to {:,} AAs.'.format(
domain_str, len(list(user_msa.values())[0]),
len(list(trimmed_seqs.values())[0])))
if min_perc_aa > 0:
self.logger.info(
'{:,} {} user genomes have amino acids in <{:.1f}% of columns in filtered MSA.'
.format(len(pruned_seqs), domain_str, min_perc_aa))
# write out filtering information
with open(marker_filtered_genomes, 'w') as fout:
for pruned_seq_id, pruned_seq in pruned_seqs.items():
if len(pruned_seq) == 0:
perc_alignment = 0
else:
valid_bases = sum(
[1 for c in pruned_seq if c.isalpha()])
perc_alignment = valid_bases * 100.0 / len(pruned_seq)
fout.write(
'%s\t%s\n' %
(pruned_seq_id,
'Insufficient number of amino acids in MSA ({:.1f}%)'.
format(perc_alignment)))
# write out MSAs
if not skip_gtdb_refs:
self.logger.info(
'Creating concatenated alignment for {:,} {} GTDB and user genomes.'
.format(len(trimmed_seqs), domain_str))
self._write_msa(trimmed_seqs, marker_msa_path, gtdb_taxonomy)
trimmed_user_msa = {
k: v
for k, v in trimmed_seqs.items() if k in user_msa
}
if len(trimmed_user_msa) > 0:
self.logger.info(
'Creating concatenated alignment for {:,} {} user genomes.'
.format(len(trimmed_user_msa), domain_str))
self._write_msa(trimmed_user_msa, marker_user_msa_path,
gtdb_taxonomy)
else:
self.logger.info(
f'All {domain_str} user genomes have been filtered out.')
# Create symlinks to the summary files
if marker_set_id == 'bac120':
symlink_f(
PATH_BAC120_FILTERED_GENOMES.format(prefix=prefix),
os.path.join(
out_dir,
os.path.basename(
PATH_BAC120_FILTERED_GENOMES.format(
prefix=prefix))))
if len(trimmed_user_msa) > 0:
symlink_f(
PATH_BAC120_USER_MSA.format(prefix=prefix),
os.path.join(
out_dir,
os.path.basename(
PATH_BAC120_USER_MSA.format(prefix=prefix))))
if not skip_gtdb_refs:
symlink_f(
PATH_BAC120_MSA.format(prefix=prefix),
os.path.join(
out_dir,
os.path.basename(
PATH_BAC120_MSA.format(prefix=prefix))))
elif marker_set_id == 'ar122':
symlink_f(
PATH_AR122_FILTERED_GENOMES.format(prefix=prefix),
os.path.join(
out_dir,
os.path.basename(
PATH_AR122_FILTERED_GENOMES.format(
prefix=prefix))))
if len(trimmed_user_msa) > 0:
symlink_f(
PATH_AR122_USER_MSA.format(prefix=prefix),
os.path.join(
out_dir,
os.path.basename(
PATH_AR122_USER_MSA.format(prefix=prefix))))
if not skip_gtdb_refs:
symlink_f(
PATH_AR122_MSA.format(prefix=prefix),
os.path.join(
out_dir,
os.path.basename(
PATH_AR122_MSA.format(prefix=prefix))))
else:
self.logger.error(
'There was an error determining the marker set.')
raise GenomeMarkerSetUnknown
