def __shift_cigar(align, new_start=None, new_end=None):
new_cigar = 'cs:Z:'
ctg_pos = align.s2
strand_direction = 1 if align.s2 < align.e2 else -1
diff_len = 0
if not align.cigar:
return diff_len
for op in parse_cs_tag(align.cigar):
if op.startswith('*'):
if (new_start and ctg_pos >= new_start) or \
(new_end and ctg_pos <= new_end):
new_cigar += op
ctg_pos += 1 * strand_direction
else:
if op.startswith(':'):
n_bases = int(op[1:])
else:
n_bases = len(op) - 1
corr_n_bases = n_bases
if new_end and (ctg_pos + n_bases * strand_direction > new_end
or ctg_pos > new_end):
corr_n_bases = new_end - ctg_pos + (
n_bases if strand_direction == -1 else 1)
elif new_start and (
ctg_pos < new_start
or ctg_pos + n_bases * strand_direction < new_start):
corr_n_bases = ctg_pos + (n_bases if strand_direction == 1
else 1) - new_start
if corr_n_bases < 1:
if not op.startswith('-'):
ctg_pos += n_bases * strand_direction
if op.startswith('-'):
diff_len -= n_bases
if op.startswith('+'):
diff_len += n_bases
continue
if op.startswith('+'):
ctg_pos += n_bases * strand_direction
diff_len += (n_bases - corr_n_bases)
if new_start:
new_cigar += '+' + op[1 + (corr_n_bases - n_bases):]
elif new_end:
new_cigar += op[:corr_n_bases + 1]
elif op.startswith('-'):
diff_len -= (n_bases - corr_n_bases)
if new_start:
new_cigar += '-' + op[1 + (corr_n_bases - n_bases):]
elif new_end:
new_cigar += op[:corr_n_bases + 1]
elif op.startswith(':'):
ctg_pos += n_bases * strand_direction
new_cigar += ':' + str(corr_n_bases)
align.cigar = new_cigar
return diff_len
def analyze_coverage(ref_aligns, reference_chromosomes, ns_by_chromosomes, used_snps_fpath):
indels_info = IndelsInfo()
genome_mapping = {}
for chr_name, chr_len in reference_chromosomes.items():
genome_mapping[chr_name] = [0] * (chr_len + 1)
with open(used_snps_fpath, 'w') as used_snps_f:
for chr_name, aligns in ref_aligns.items():
for align in aligns:
ref_pos, ctg_pos = align.s1, align.s2
strand_direction = 1 if align.s2 < align.e2 else -1
for op in parse_cs_tag(align.cigar):
if op.startswith(':'):
n_bases = int(op[1:])
else:
n_bases = len(op) - 1
if op.startswith('*'):
ref_nucl, ctg_nucl = op[1].upper(), op[2].upper()
if ctg_nucl != 'N' and ref_nucl != 'N':
indels_info.mismatches += 1
if qconfig.show_snps:
used_snps_f.write('%s\t%s\t%d\t%s\t%s\t%d\n' % (chr_name, align.contig, ref_pos, ref_nucl, ctg_nucl, ctg_pos))
ref_pos += 1
ctg_pos += 1 * strand_direction
elif op.startswith('+'):
indels_info.indels_list.append(n_bases)
indels_info.insertions += n_bases
if qconfig.show_snps and n_bases < qconfig.MAX_INDEL_LENGTH:
ref_nucl, ctg_nucl = '.', op[1:].upper()
used_snps_f.write('%s\t%s\t%d\t%s\t%s\t%d\n' % (chr_name, align.contig, ref_pos, ref_nucl, ctg_nucl, ctg_pos))
ctg_pos += n_bases * strand_direction
elif op.startswith('-'):
indels_info.indels_list.append(n_bases)
indels_info.deletions += n_bases
if qconfig.show_snps and n_bases < qconfig.MAX_INDEL_LENGTH:
ref_nucl, ctg_nucl = op[1:].upper(), '.'
used_snps_f.write('%s\t%s\t%d\t%s\t%s\t%d\n' % (chr_name, align.contig, ref_pos, ref_nucl, ctg_nucl, ctg_pos))
ref_pos += n_bases
else:
ref_pos += n_bases
ctg_pos += n_bases * strand_direction
if align.s1 < align.e1:
for pos in range(align.s1, align.e1 + 1):
genome_mapping[align.ref][pos] = 1
else:
for pos in range(align.s1, len(genome_mapping[align.ref])):
genome_mapping[align.ref][pos] = 1
for pos in range(1, align.e1 + 1):
genome_mapping[align.ref][pos] = 1
for i in ns_by_chromosomes[align.ref]:
genome_mapping[align.ref][i] = 0
covered_bases = sum([sum(genome_mapping[chrom]) for chrom in genome_mapping])
return covered_bases, indels_info
def analyze_coverage(ref_aligns, reference_chromosomes, ns_by_chromosomes, used_snps_fpath):
indels_info = IndelsInfo()
genome_mapping = {}
for chr_name, chr_len in reference_chromosomes.items():
genome_mapping[chr_name] = [0] * (chr_len + 1)
with open(used_snps_fpath, 'w') as used_snps_f:
for chr_name, aligns in ref_aligns.items():
for align in aligns:
ref_pos, ctg_pos = align.s1, align.s2
strand_direction = 1 if align.s2 < align.e2 else -1
for op in parse_cs_tag(align.cigar):
if op.startswith(':'):
n_bases = int(op[1:])
else:
n_bases = len(op) - 1
if op.startswith('*'):
ref_nucl, ctg_nucl = op[1].upper(), op[2].upper()
if ctg_nucl != 'N' and ref_nucl != 'N':
indels_info.mismatches += 1
if qconfig.show_snps:
used_snps_f.write('%s\t%s\t%d\t%s\t%s\t%d\n' % (chr_name, align.contig, ref_pos, ref_nucl, ctg_nucl, ctg_pos))
ref_pos += 1
ctg_pos += 1 * strand_direction
elif op.startswith('+'):
indels_info.indels_list.append(n_bases)
indels_info.insertions += n_bases
if qconfig.show_snps and n_bases < qconfig.MAX_INDEL_LENGTH:
ref_nucl, ctg_nucl = '.', op[1:].upper()
used_snps_f.write('%s\t%s\t%d\t%s\t%s\t%d\n' % (chr_name, align.contig, ref_pos, ref_nucl, ctg_nucl, ctg_pos))
ctg_pos += n_bases * strand_direction
elif op.startswith('-'):
indels_info.indels_list.append(n_bases)
indels_info.deletions += n_bases
if qconfig.show_snps and n_bases < qconfig.MAX_INDEL_LENGTH:
ref_nucl, ctg_nucl = op[1:].upper(), '.'
used_snps_f.write('%s\t%s\t%d\t%s\t%s\t%d\n' % (chr_name, align.contig, ref_pos, ref_nucl, ctg_nucl, ctg_pos))
ref_pos += n_bases
else:
ref_pos += n_bases
ctg_pos += n_bases * strand_direction
if align.s1 < align.e1:
for pos in range(align.s1, align.e1 + 1):
genome_mapping[align.ref][pos] = 1
else:
for pos in range(align.s1, len(genome_mapping[align.ref])):
genome_mapping[align.ref][pos] = 1
for pos in range(1, align.e1 + 1):
genome_mapping[align.ref][pos] = 1
for i in ns_by_chromosomes[align.ref]:
genome_mapping[align.ref][i] = 0
covered_bases = sum([sum(genome_mapping[chrom]) for chrom in genome_mapping])
return covered_bases, indels_info
def split_align(coords_file, align_start, strand_direction, ref_start,
ref_name, contig, cs):
def _write_align():
if align_len < qconfig.min_alignment or not ref_len or not align_cs:
return
align_end = align_start + (align_len - 1) * strand_direction
ref_end = ref_start + ref_len - 1
align_idy = '%.2f' % (matched_bases * 100.0 / ref_len)
if float(align_idy) >= qconfig.min_IDY:
align = Mapping(s1=ref_start,
e1=ref_end,
s2=align_start,
e2=align_end,
len1=ref_len,
len2=align_len,
idy=align_idy,
ref=ref_name,
contig=contig,
cigar=align_cs)
coords_file.write(align.coords_str() + '\n')
ref_len, align_len, align_end = 0, 0, 0
align_cs = ''
matched_bases = 0
for op in parse_cs_tag(cs):
if op.startswith(':'):
n_bases = int(op[1:])
else:
n_bases = len(op) - 1
if op.startswith('*'):
align_cs += op
ref_len += 1
align_len += 1
elif op.startswith('+'):
_write_align()
align_start += (align_len + n_bases) * strand_direction
ref_start += ref_len
align_len, ref_len, matched_bases = 0, 0, 0
align_cs = ''
elif op.startswith('-'):
_write_align()
align_start += align_len * strand_direction
ref_start += ref_len + n_bases
align_len, ref_len, matched_bases = 0, 0, 0
align_cs = ''
else:
align_cs += op
ref_len += n_bases
align_len += n_bases
matched_bases += n_bases
_write_align()
def create_mismatches_plot(assembly, window_size, ref_len, root_dir,
output_dir):
assembly_label = qutils.label_from_fpath_for_fname(assembly.fpath)
aligner_dirpath = join(root_dir, '..',
qconfig.detailed_contigs_reports_dirname)
coords_basename = join(create_minimap_output_dir(aligner_dirpath),
assembly_label)
_, coords_filtered_fpath, _, _ = get_aux_out_fpaths(coords_basename)
if not exists(coords_filtered_fpath) or not qconfig.show_snps:
return None
mismatches_fpath = join(output_dir, assembly_label + '.mismatches.txt')
mismatch_density_by_chrom = defaultdict(lambda: [0] *
(ref_len // window_size + 1))
with open(coords_filtered_fpath) as coords_file:
for line in coords_file:
s1 = int(line.split('|')[0].split()[0])
chrom = line.split()[11].strip()
cigar = line.split()[-1].strip()
ref_pos = s1
for op in parse_cs_tag(cigar):
n_bases = len(op) - 1
if op.startswith('*'):
mismatch_density_by_chrom[chrom][int(ref_pos) //
window_size] += 1
ref_pos += 1
elif not op.startswith('+'):
ref_pos += n_bases
with open(mismatches_fpath, 'w') as out_f:
for chrom, density_list in mismatch_density_by_chrom.items():
start, end = 0, 0
for i, density in enumerate(density_list):
if density == 0:
end = (i + 1) * window_size
else:
if end:
out_f.write(
'\t'.join([chrom, str(start),
str(end), '0']) + '\n')
out_f.write('\t'.join([
chrom,
str(i * window_size),
str(((i + 1) * window_size)),
str(density)
]) + '\n')
start = (i + 1) * window_size
end = None
if end:
out_f.write('\t'.join([chrom, str(start),
str(end), '0']) + '\n')
return mismatches_fpath
def split_align(coords_file, align_start, strand_direction, ref_start, ref_name, contig, cs):
def _write_align():
if align_len < qconfig.min_alignment or not ref_len or not align_cs:
return
align_end = align_start + (align_len - 1) * strand_direction
ref_end = ref_start + ref_len - 1
align_idy = '%.2f' % (matched_bases * 100.0 / ref_len)
if float(align_idy) >= qconfig.min_IDY:
align = Mapping(s1=ref_start, e1=ref_end, s2=align_start, e2=align_end, len1=ref_len,
len2=align_len, idy=align_idy, ref=ref_name, contig=contig, cigar=align_cs)
coords_file.write(align.coords_str() + '\n')
ref_len, align_len, align_end = 0, 0, 0
align_cs = ''
matched_bases = 0
for op in parse_cs_tag(cs):
if op.startswith(':'):
n_bases = int(op[1:])
else:
n_bases = len(op) - 1
if op.startswith('*'):
align_cs += op
ref_len += 1
align_len += 1
## split alignment in positions of indels to get smaller alignments with higher identity
elif op.startswith('+'):
if n_bases > SHORT_INDEL_THRESHOLD:
_write_align()
align_start += (align_len + n_bases) * strand_direction
ref_start += ref_len
align_len, ref_len, matched_bases = 0, 0, 0
align_cs = ''
else:
align_cs += op
align_len += n_bases
elif op.startswith('-'):
if n_bases > SHORT_INDEL_THRESHOLD:
_write_align()
align_start += align_len * strand_direction
ref_start += ref_len + n_bases
align_len, ref_len, matched_bases = 0, 0, 0
align_cs = ''
else:
align_cs += op
ref_len += n_bases
else:
align_cs += op
ref_len += n_bases
align_len += n_bases
matched_bases += n_bases
_write_align()
def __shift_cigar(align, new_start=None, new_end=None):
new_cigar = 'cs:Z:'
ctg_pos = align.s2
strand_direction = 1 if align.s2 < align.e2 else -1
diff_len = 0
if not align.cigar:
return diff_len
for op in parse_cs_tag(align.cigar):
if op.startswith('*'):
if (new_start and ctg_pos >= new_start) or \
(new_end and ctg_pos <= new_end):
new_cigar += op
ctg_pos += 1 * strand_direction
else:
if op.startswith(':'):
n_bases = int(op[1:])
else:
n_bases = len(op) - 1
corr_n_bases = n_bases
if new_end and (ctg_pos + n_bases * strand_direction > new_end or ctg_pos > new_end):
corr_n_bases = new_end - ctg_pos + (n_bases if strand_direction == -1 else 1)
elif new_start and (ctg_pos < new_start or ctg_pos + n_bases * strand_direction < new_start):
corr_n_bases = ctg_pos + (n_bases if strand_direction == 1 else 1) - new_start
if corr_n_bases < 1:
if not op.startswith('-'):
ctg_pos += n_bases * strand_direction
if op.startswith('-'):
diff_len -= n_bases
if op.startswith('+'):
diff_len += n_bases
continue
if op.startswith('+'):
ctg_pos += n_bases * strand_direction
diff_len += (n_bases - corr_n_bases)
if new_start:
new_cigar += '+' + op[1 + (corr_n_bases - n_bases):]
elif new_end:
new_cigar += op[:corr_n_bases + 1]
elif op.startswith('-'):
diff_len -= (n_bases - corr_n_bases)
if new_start:
new_cigar += '-' + op[1 + (corr_n_bases - n_bases):]
elif new_end:
new_cigar += op[:corr_n_bases + 1]
elif op.startswith(':'):
ctg_pos += n_bases * strand_direction
new_cigar += ':' + str(corr_n_bases)
align.cigar = new_cigar
return diff_len
def create_mismatches_plot(assembly, window_size, ref_len, root_dir, output_dir):
assembly_label = qutils.label_from_fpath_for_fname(assembly.fpath)
aligner_dirpath = join(root_dir, '..', 'contigs_reports')
coords_basename = join(create_minimap_output_dir(aligner_dirpath), assembly_label)
_, coords_filtered_fpath, _, _ = get_aux_out_fpaths(coords_basename)
if not exists(coords_filtered_fpath) or not qconfig.show_snps:
return None
mismatches_fpath = join(output_dir, assembly_label + '.mismatches.txt')
mismatch_density_by_chrom = defaultdict(lambda : [0] * (ref_len // window_size + 1))
with open(coords_filtered_fpath) as coords_file:
for line in coords_file:
s1 = int(line.split('|')[0].split()[0])
chrom = line.split()[11].strip()
cigar = line.split()[-1].strip()
ref_pos = s1
for op in parse_cs_tag(cigar):
n_bases = len(op) - 1
if op.startswith('*'):
mismatch_density_by_chrom[chrom][int(ref_pos) // window_size] += 1
ref_pos += 1
elif not op.startswith('+'):
ref_pos += n_bases
with open(mismatches_fpath, 'w') as out_f:
for chrom, density_list in mismatch_density_by_chrom.items():
start, end = 0, 0
for i, density in enumerate(density_list):
if density == 0:
end = (i + 1) * window_size
else:
if end:
out_f.write('\t'.join([chrom, str(start), str(end), '0']) + '\n')
out_f.write('\t'.join([chrom, str(i * window_size), str(((i + 1) * window_size)), str(density)]) + '\n')
start = (i + 1) * window_size
end = None
if end:
out_f.write('\t'.join([chrom, str(start), str(end), '0']) + '\n')
return mismatches_fpath
def split_align(coords_file, align_start, strand_direction, ref_start,
ref_name, contig, cs):
def _write_align():
if align.len2 < qconfig.min_alignment or not align.len1 or not align.cigar:
return
align.e1 = align.s1 + align.len1 - 1
align.e2 = align.s2 + (align.len2 - 1) * strand_direction
align.idy = '%.2f' % (matched_bases * 100.0 /
max(align.len1, align.len2))
if float(align.idy) >= qconfig.min_IDY:
coords_file.write(align.coords_str() + '\n')
def _try_split(matched_bases, prev_op, n_refbases=0, n_alignbases=0):
## split alignment in positions of indels or stretch of mismatches to get smaller alignments with higher identity
if n_alignbases > SPLIT_ALIGN_THRESHOLD or n_refbases > SPLIT_ALIGN_THRESHOLD:
_write_align()
align.s1 += align.len1 + n_refbases
align.s2 += (align.len2 + n_alignbases) * strand_direction
align.len1, align.len2 = 0, 0
align.cigar = ''
matched_bases = 0
else:
align.len1 += n_refbases
align.len2 += n_alignbases
align.cigar += prev_op
return matched_bases
matched_bases = 0
align = Mapping(s1=ref_start,
e1=ref_start,
s2=align_start,
e2=align_start,
len1=0,
len2=0,
ref=ref_name,
contig=contig,
cigar='')
cur_mismatch_stretch = ''
for op in parse_cs_tag(cs):
if op.startswith('*'):
cur_mismatch_stretch += op
continue
if cur_mismatch_stretch:
n_bases = cur_mismatch_stretch.count('*')
matched_bases = _try_split(matched_bases, cur_mismatch_stretch,
n_bases, n_bases)
cur_mismatch_stretch = ''
if op.startswith(':'):
n_bases = int(op[1:])
align.cigar += op
align.len1 += n_bases
align.len2 += n_bases
matched_bases += n_bases
else:
n_bases = len(op) - 1
if op.startswith('+'):
matched_bases = _try_split(matched_bases,
op,
n_alignbases=n_bases)
elif op.startswith('-'):
matched_bases = _try_split(matched_bases,
op,
n_refbases=n_bases)
_write_align()
def analyze_coverage(ref_aligns, reference_chromosomes, ns_by_chromosomes,
used_snps_fpath):
logger.info(" Enter analyze_coverage")
#logger.info(f" {ref_aligns=}")
indels_info = IndelsInfo()
maximum_contig_align_size_per_ref_base = {}
strict_maximum_contig_align_size_per_ref_base = {}
genome_mapping = {}
genome_length = 0
for chr_name, chr_len in reference_chromosomes.items():
genome_mapping[chr_name] = [0] * (chr_len + 1)
maximum_contig_align_size_per_ref_base[chr_name] = [0] * (chr_len + 1)
strict_maximum_contig_align_size_per_ref_base[chr_name] = [0] * (
chr_len + 1)
genome_length += chr_len
logger.info(" Genome length: " + str(genome_length))
alignment_total_length = 0
with open(used_snps_fpath, 'w') as used_snps_f:
for chr_name, aligns in ref_aligns.items():
for align in aligns:
# Vars with 1 are on the reference, vars with 2 are on the contig
ref_pos, ctg_pos = align.s1, align.s2
strand_direction = 1 if align.s2 < align.e2 else -1
for op in parse_cs_tag(align.cigar):
if op.startswith(':'):
n_bases = int(op[1:])
else:
n_bases = len(op) - 1
if op.startswith('*'):
ref_nucl, ctg_nucl = op[1].upper(), op[2].upper()
if ctg_nucl != 'N' and ref_nucl != 'N':
indels_info.mismatches += 1
if qconfig.show_snps:
used_snps_f.write(
'%s\t%s\t%d\t%s\t%s\t%d\n' %
(chr_name, align.contig, ref_pos, ref_nucl,
ctg_nucl, ctg_pos))
ref_pos += 1
ctg_pos += 1 * strand_direction
elif op.startswith('+'):
indels_info.indels_list.append(n_bases)
indels_info.insertions += n_bases
if qconfig.show_snps and n_bases < qconfig.MAX_INDEL_LENGTH:
ref_nucl, ctg_nucl = '.', op[1:].upper()
used_snps_f.write('%s\t%s\t%d\t%s\t%s\t%d\n' %
(chr_name, align.contig, ref_pos,
ref_nucl, ctg_nucl, ctg_pos))
ctg_pos += n_bases * strand_direction
elif op.startswith('-'):
indels_info.indels_list.append(n_bases)
indels_info.deletions += n_bases
if qconfig.show_snps and n_bases < qconfig.MAX_INDEL_LENGTH:
ref_nucl, ctg_nucl = op[1:].upper(), '.'
used_snps_f.write('%s\t%s\t%d\t%s\t%s\t%d\n' %
(chr_name, align.contig, ref_pos,
ref_nucl, ctg_nucl, ctg_pos))
ref_pos += n_bases
else:
ref_pos += n_bases
ctg_pos += n_bases * strand_direction
alignment_total_length += align.len2_excluding_local_misassemblies
if align.s1 < align.e1:
align_size = align.len2_excluding_local_misassemblies # Use the same len that is used to compute NGAx
strict_align_size = align.len2_including_local_misassemblies # Use the same len that is used to strict compute NGAx
for pos in range(align.s1, align.e1 + 1):
genome_mapping[align.ref][pos] = 1
maximum_contig_align_size_per_ref_base[
align.ref][pos] = max(
align_size,
maximum_contig_align_size_per_ref_base[
align.ref][pos])
strict_maximum_contig_align_size_per_ref_base[
align.ref][pos] = max(
strict_align_size,
strict_maximum_contig_align_size_per_ref_base[
align.ref][pos])
else:
align_size = align.len2_excluding_local_misassemblies # Use the same len that is used to compute NGAx
strict_align_size = align.len2_including_local_misassemblies # Use the same len that is used to strict compute NGAx
for pos in range(align.s1, len(genome_mapping[align.ref])):
genome_mapping[align.ref][pos] = 1
maximum_contig_align_size_per_ref_base[
align.ref][pos] = max(
align_size,
maximum_contig_align_size_per_ref_base[
align.ref][pos])
strict_maximum_contig_align_size_per_ref_base[
align.ref][pos] = max(
strict_align_size,
strict_maximum_contig_align_size_per_ref_base[
align.ref][pos])
for pos in range(1, align.e1 + 1):
genome_mapping[align.ref][pos] = 1
maximum_contig_align_size_per_ref_base[
align.ref][pos] = max(
align_size,
maximum_contig_align_size_per_ref_base[
align.ref][pos])
strict_maximum_contig_align_size_per_ref_base[
align.ref][pos] = max(
strict_align_size,
strict_maximum_contig_align_size_per_ref_base[
align.ref][pos])
for i in ns_by_chromosomes[align.ref]:
genome_mapping[align.ref][i] = 0
maximum_contig_align_size_per_ref_base[align.ref][pos] = 0
strict_maximum_contig_align_size_per_ref_base[
align.ref][pos] = 0
covered_bases = sum(
[sum(genome_mapping[chrom]) for chrom in genome_mapping])
maximum_contig_align_size_per_ref_base = [
align_size
for contig in maximum_contig_align_size_per_ref_base.values()
for align_size in contig
]
maximum_contig_align_size_per_ref_base.sort(reverse=True)
ea_x_max = [0] * 101
for i in range(0, 100):
ea_x_max[i] = maximum_contig_align_size_per_ref_base[
(len(maximum_contig_align_size_per_ref_base) * i) // 100]
ea_x_max[100] = maximum_contig_align_size_per_ref_base[-1]
ea_mean_max = int(
sum(maximum_contig_align_size_per_ref_base) /
len(maximum_contig_align_size_per_ref_base))
p5k = P(maximum_contig_align_size_per_ref_base, 5000)
p10k = P(maximum_contig_align_size_per_ref_base, 10000)
p15k = P(maximum_contig_align_size_per_ref_base, 15000)
p20k = P(maximum_contig_align_size_per_ref_base, 20000)
strict_maximum_contig_align_size_per_ref_base = [
align_size
for contig in strict_maximum_contig_align_size_per_ref_base.values()
for align_size in contig
]
strict_maximum_contig_align_size_per_ref_base.sort(reverse=True)
strict_ea_x_max = [0] * 101
for i in range(0, 100):
strict_ea_x_max[i] = strict_maximum_contig_align_size_per_ref_base[
(len(strict_maximum_contig_align_size_per_ref_base) * i) // 100]
strict_ea_x_max[100] = strict_maximum_contig_align_size_per_ref_base[-1]
strict_ea_mean_max = int(
sum(strict_maximum_contig_align_size_per_ref_base) /
len(strict_maximum_contig_align_size_per_ref_base))
strict_p5k = P(strict_maximum_contig_align_size_per_ref_base, 5000)
strict_p10k = P(strict_maximum_contig_align_size_per_ref_base, 10000)
strict_p15k = P(strict_maximum_contig_align_size_per_ref_base, 15000)
strict_p20k = P(strict_maximum_contig_align_size_per_ref_base, 20000)
#print("computed ea_x_max as " + str(ea_x_max))
logger.info(" Duplication ratio = %.2f = %d/%d" %
((alignment_total_length / covered_bases),
alignment_total_length, covered_bases))
logger.info(" EA50max = {}".format(ea_x_max[50]))
logger.info(" Strict EA50max = {}".format(strict_ea_x_max[50]))
logger.info(" len2 NGA50 = {}".format(
N50.NG50_and_LG50(
[align.len2 for aligns in ref_aligns.values() for align in aligns],
genome_length,
need_sort=True)[0]))
logger.info(" len2_excluding_local_misassemblies NGA50 = {}".format(
N50.NG50_and_LG50([
align.len2_excluding_local_misassemblies
for aligns in ref_aligns.values() for align in aligns
],
genome_length,
need_sort=True)[0]))
return covered_bases, indels_info, ea_x_max, strict_ea_x_max, ea_mean_max, strict_ea_mean_max, p5k, p10k, p15k, p20k, strict_p5k, strict_p10k, strict_p15k, strict_p20k
