def parse_aligner_contig_report(report_fpath):
aligned_blocks = []
misassembled_id_to_structure = defaultdict(list)
with open(report_fpath) as report_file:
contig_id = None
start_col = None
end_col = None
ref_col = None
contig_col = None
ambig_col = None
best_col = None
for i, line in enumerate(report_file):
split_line = line.replace('\n', '').split('\t')
if i == 0:
start_col = split_line.index('S1')
end_col = split_line.index('E1')
ref_col = split_line.index('Reference')
contig_col = split_line.index('Contig')
idy_col = split_line.index('IDY')
ambig_col = split_line.index('Ambiguous')
best_col = split_line.index('Best_group')
elif split_line and split_line[0] == 'CONTIG':
continue
elif split_line and len(split_line) < 5:
misassembled_id_to_structure[contig_id].append(line.strip())
elif split_line and len(split_line) > 5:
start, end, ref_name, contig_id, ambiguity, is_best = int(split_line[start_col]), int(split_line[end_col]), \
split_line[ref_col], split_line[contig_col], \
split_line[ambig_col], split_line[best_col]
block = Alignment(name=contig_id,
start=start,
end=end,
ref_name=ref_name,
is_best_set=is_best == 'True')
block.ambiguous = ambiguity
if block.is_best_set:
aligned_blocks.append(block)
misassembled_id_to_structure[contig_id].append(block)
return aligned_blocks, misassembled_id_to_structure
def parse_nucmer_contig_report(report_fpath):
aligned_blocks = []
misassembled_id_to_structure = defaultdict(list)
with open(report_fpath) as report_file:
contig_id = None
start_col = None
end_col = None
ref_col = None
contig_col = None
ambig_col = None
best_col = None
for i, line in enumerate(report_file):
split_line = line.replace('\n', '').split('\t')
if i == 0:
start_col = split_line.index('S1')
end_col = split_line.index('E1')
ref_col = split_line.index('Reference')
contig_col = split_line.index('Contig')
idy_col = split_line.index('IDY')
ambig_col = split_line.index('Ambiguous')
best_col = split_line.index('Best_group')
elif split_line and split_line[0] == 'CONTIG':
continue
elif split_line and len(split_line) < 5:
misassembled_id_to_structure[contig_id].append(line.strip())
elif split_line and len(split_line) > 5:
start, end, ref_name, contig_id, ambiguity, is_best = int(split_line[start_col]), int(split_line[end_col]), \
split_line[ref_col], split_line[contig_col], \
split_line[ambig_col], split_line[best_col]
block = Alignment(name=contig_id, start=start, end=end, ref_name=ref_name, is_best_set=is_best == 'True')
block.ambiguous = ambiguity
if block.is_best_set:
aligned_blocks.append(block)
misassembled_id_to_structure[contig_id].append(block)
return aligned_blocks, misassembled_id_to_structure
def parse_nucmer_contig_report(report_fpath, ref_names,
cumulative_ref_lengths):
aligned_blocks = []
contigs = []
with open(report_fpath) as report_file:
misassembled_id_to_structure = defaultdict(list)
ambiguity_alignments = defaultdict(list)
contig_id = None
start_col = None
end_col = None
start_in_contig_col = None
end_in_contig_col = None
ref_col = None
contig_col = None
idy_col = None
ambig_col = None
best_col = None
for i, line in enumerate(report_file):
split_line = line.replace('\n', '').split('\t')
if i == 0:
start_col = split_line.index('S1')
end_col = split_line.index('E1')
start_in_contig_col = split_line.index('S2')
end_in_contig_col = split_line.index('E2')
ref_col = split_line.index('Reference')
contig_col = split_line.index('Contig')
idy_col = split_line.index('IDY')
ambig_col = split_line.index('Ambiguous')
best_col = split_line.index('Best_group')
elif split_line and split_line[0] == 'CONTIG':
_, name, size, contig_type = split_line
contig = Contig(name=name,
size=int(size),
contig_type=contig_type)
contigs.append(contig)
elif split_line and len(split_line) < 5:
misassembled_id_to_structure[contig_id].append(line.strip())
elif split_line and len(split_line) > 5:
unshifted_start, unshifted_end, start_in_contig, end_in_contig, ref_name, contig_id, idy, ambiguity, is_best = \
split_line[start_col], split_line[end_col], split_line[start_in_contig_col], split_line[end_in_contig_col], \
split_line[ref_col], split_line[contig_col], split_line[idy_col], split_line[ambig_col], split_line[best_col]
unshifted_start, unshifted_end, start_in_contig, end_in_contig = int(unshifted_start), int(unshifted_end),\
int(start_in_contig), int(end_in_contig)
cur_shift = cumulative_ref_lengths[ref_names.index(ref_name)]
start = unshifted_start + cur_shift
end = unshifted_end + cur_shift
is_rc = ((start - end) * (start_in_contig - end_in_contig)) < 0
position_in_ref = unshifted_start
block = Alignment(name=contig_id,
start=start,
end=end,
unshifted_start=unshifted_start,
unshifted_end=unshifted_end,
is_rc=is_rc,
start_in_contig=start_in_contig,
end_in_contig=end_in_contig,
position_in_ref=position_in_ref,
ref_name=ref_name,
idy=idy,
is_best_set=is_best == 'True')
block.ambiguous = ambiguity
if block.is_best_set:
misassembled_id_to_structure[contig_id].append(block)
else:
ambiguity_alignments[contig_id].append(block)
aligned_blocks.append(block)
return aligned_blocks, misassembled_id_to_structure, contigs, ambiguity_alignments
def parse_nucmer_contig_report(report_fpath, ref_names, cumulative_ref_lengths):
aligned_blocks = []
contigs = []
with open(report_fpath) as report_file:
misassembled_id_to_structure = defaultdict(list)
ambiguity_alignments = defaultdict(list)
contig_id = None
start_col = None
end_col = None
start_in_contig_col = None
end_in_contig_col = None
ref_col = None
contig_col = None
idy_col = None
ambig_col = None
best_col = None
for i, line in enumerate(report_file):
split_line = line.replace('\n', '').split('\t')
if i == 0:
start_col = split_line.index('S1')
end_col = split_line.index('E1')
start_in_contig_col = split_line.index('S2')
end_in_contig_col = split_line.index('E2')
ref_col = split_line.index('Reference')
contig_col = split_line.index('Contig')
idy_col = split_line.index('IDY')
ambig_col = split_line.index('Ambiguous')
best_col = split_line.index('Best_group')
elif split_line and split_line[0] == 'CONTIG':
_, name, size, contig_type = split_line
contig = Contig(name=name, size=int(size), contig_type=contig_type)
contigs.append(contig)
elif split_line and len(split_line) < 5:
misassembled_id_to_structure[contig_id].append(line.strip())
elif split_line and len(split_line) > 5:
unshifted_start, unshifted_end, start_in_contig, end_in_contig, ref_name, contig_id, idy, ambiguity, is_best = \
split_line[start_col], split_line[end_col], split_line[start_in_contig_col], split_line[end_in_contig_col], \
split_line[ref_col], split_line[contig_col], split_line[idy_col], split_line[ambig_col], split_line[best_col]
unshifted_start, unshifted_end, start_in_contig, end_in_contig = int(unshifted_start), int(unshifted_end),\
int(start_in_contig), int(end_in_contig)
cur_shift = cumulative_ref_lengths[ref_names.index(ref_name)] or 1
start = unshifted_start + cur_shift - 1
end = unshifted_end + cur_shift - 1
is_rc = ((start - end) * (start_in_contig - end_in_contig)) < 0
position_in_ref = unshifted_start
block = Alignment(
name=contig_id, start=start, end=end, unshifted_start=unshifted_start, unshifted_end=unshifted_end,
is_rc=is_rc, start_in_contig=start_in_contig, end_in_contig=end_in_contig, position_in_ref=position_in_ref, ref_name=ref_name,
idy=idy, is_best_set=is_best == 'True')
block.ambiguous = ambiguity
if block.is_best_set:
misassembled_id_to_structure[contig_id].append(block)
else:
ambiguity_alignments[contig_id].append(block)
aligned_blocks.append(block)
return aligned_blocks, misassembled_id_to_structure, contigs, ambiguity_alignments