def create_pseudomolecules(in_contigs_file, in_unique_contigs, gap_size):
"""
Need to make a translation table for easy lift-over.
:param in_contigs_file:
:param in_unique_contigs:
:param gap_size:
:return:
"""
# First, read all of the contigs into memory
remaining_contig_headers = []
all_seqs = dict()
x = SeqReader('../' + in_contigs_file)
for header, seq in x.parse_fasta():
remaining_contig_headers.append(header.split(' ')[0])
all_seqs[header.split(' ')[0]] = seq
# Get all reference chromosomes
all_chroms = sorted(
list(
set([
in_unique_contigs[i].ref_chrom
for i in in_unique_contigs.keys()
])))
# Iterate through each orderings file and store sequence in a dictionary
all_pms = dict()
for this_chrom in all_chroms:
all_pms[this_chrom] = ''
orderings_file = 'orderings/' + this_chrom + '_orderings.txt'
orderings = get_orderings(orderings_file)
for line in orderings:
# Mark that we have seen this contig
remaining_contig_headers.pop(
remaining_contig_headers.index('>' + line[0]))
if line[1] == '+':
all_pms[this_chrom] += all_seqs['>' + line[0]]
all_pms[this_chrom] += ''.join('N' for i in range(gap_size))
else:
assert line[1] == '-'
all_pms[this_chrom] += reverse_complement(all_seqs['>' +
line[0]])
all_pms[this_chrom] += ''.join('N' for i in range(gap_size))
all_pms[this_chrom] += '\n'
# Get unincorporated sequences and place them in Chr0
all_pms['Chr0'] = ''
for header in remaining_contig_headers:
all_pms['Chr0'] += all_seqs[header]
all_pms['Chr0'] += ''.join('N' for i in range(gap_size))
all_pms['Chr0'] += '\n'
# Write the final sequences out to a file
with open('ragoo.fasta', 'w') as f:
f.write('>Chr0_RaGOO\n')
f.write(all_pms['Chr0'])
for header in all_chroms:
f.write('>' + header + '_RaGOO\n')
f.write(all_pms[header])
def create_pseudomolecules(in_contigs_file,
in_unique_contigs,
gap_size,
chr0=True):
"""
Need to make a translation table for easy lift-over.
:param in_contigs_file:
:param in_unique_contigs:
:param gap_size:
:return:
"""
# First, read all of the contigs into memory
remaining_contig_headers = []
all_seqs = OrderedDict()
x = SeqReader(in_contigs_file)
for header, seq in x.parse_fasta():
remaining_contig_headers.append(header.split(' ')[0])
all_seqs[header.split(' ')[0]] = seq
# Get all reference chromosomes
all_chroms = sorted(
list(
set([
in_unique_contigs[i].ref_chrom
for i in in_unique_contigs.keys()
])))
# Iterate through each orderings file and store sequence in a dictionary
all_pms = dict()
pad = ''.join('N' for i in range(gap_size))
for this_chrom in all_chroms:
orderings_file = 'orderings/' + this_chrom + '_orderings.txt'
orderings = get_orderings(orderings_file)
if orderings:
seq_list = []
for line in orderings:
# Mark that we have seen this contig
remaining_contig_headers.pop(
remaining_contig_headers.index('>' + line[0]))
if line[1] == '+':
seq_list.append(all_seqs['>' + line[0]])
else:
assert line[1] == '-'
seq_list.append(reverse_complement(all_seqs['>' +
line[0]]))
all_pms[this_chrom] = pad.join(seq_list)
all_pms[this_chrom] += '\n'
# Get unincorporated sequences and place them in Chr0
if remaining_contig_headers:
if chr0:
chr0_headers = []
chr0_seq_list = []
for header in remaining_contig_headers:
chr0_headers.append(header)
chr0_seq_list.append(all_seqs[header])
all_pms['Chr0'] = pad.join(chr0_seq_list)
all_pms['Chr0'] += '\n'
# Write out the list of chr0 headers
f_chr0_g = open('groupings/Chr0_contigs.txt', 'w')
f_chr0_o = open('orderings/Chr0_orderings.txt', 'w')
for i in chr0_headers:
f_chr0_g.write(i[1:] + "\t" + "0" + '\n')
f_chr0_o.write(i[1:] + '\t' + "+" + '\t' + "0" + '\t' + "0" +
'\n')
f_chr0_g.close()
f_chr0_o.close()
else:
# Instead of making a chromosome 0, add the unplaced sequences as is.
for header in remaining_contig_headers:
all_pms[header[1:]] = all_seqs[header] + "\n"
f_chr0_g = open('groupings/' + header[1:] + '_contigs.txt',
'w')
f_chr0_o = open('orderings/' + header[1:] + '_orderings.txt',
'w')
f_chr0_g.write(header[1:] + "\t" + "0" + '\n')
f_chr0_o.write(header[1:] + '\t' + "+" + '\t' + "0" + '\t' +
"0" + '\n')
f_chr0_g.close()
f_chr0_o.close()
# Write the final sequences out to a file
with open('ragoo.fasta', 'w') as f:
for out_header in all_pms:
f.write(">" + out_header + "_RaGOO\n")
f.write(all_pms[out_header])
def create_pseudomolecules(in_contigs_file,
out_folder,
in_ref,
gap_size=100,
chr0=True):
"""
Need to make a translation table for easy lift-over.
:param in_contigs_file:
:param in_unique_contigs:
:param gap_size:
:return:
"""
# First, read all of the contigs into memory
# remaining_contig_headers = []
x = pysam.FastaFile(in_contigs_file)
y = pysam.FastaFile(in_ref)
remaining_contig_headers = set(x.references)
# Get all reference chromosomes
# all_chroms = sorted(list(set([in_unique_contigs[i].ref_chrom for i in in_unique_contigs.keys()])))
# Iterate through each orderings file and store sequence in a dictionary
os.chdir(out_folder)
all_chroms = sorted([
os.path.basename(_).replace("_orderings.txt", "")
for _ in os.listdir(os.path.join("orderings"))
if os.path.basename(_).replace("_orderings.txt", "") in y.references
])
pad = 'N' * gap_size
with open('ragoo.fasta', 'w') as outfile:
for this_chrom in all_chroms:
orderings_file = os.path.join('orderings',
this_chrom + '_orderings.txt')
orderings = get_orderings(orderings_file)
curr_seq = []
curr_total = 0
if orderings:
print(">" + this_chrom + "_RaGOO", file=outfile)
for line in orderings:
# Mark that we have seen this contig
remaining_contig_headers.remove(line[0])
_ = x.fetch(line[0])
curr_total += x.get_reference_length(line[0])
if line[1] == '+':
curr_seq.append(_)
else:
assert line[1] == '-'
curr_seq.append(reverse_complement(_))
if curr_total >= 10**7: # Print out every 10Mbps
wrapped = re.findall(".{1,60}", pad.join(curr_seq))
print(*wrapped[:-1], sep="\n", file=outfile)
curr_seq = [wrapped[-1]]
curr_total = len(wrapped[-1])
wrapped = re.findall(".{1,60}", pad.join(curr_seq))
print(*wrapped, sep="\n", file=outfile)
# Get unincorporated sequences and place them in Chr0
if remaining_contig_headers:
if chr0:
curr_seq = []
curr_total = 0
chr0_headers = []
for header in remaining_contig_headers:
_ = x.fetch(header)
curr_total += x.get_reference_length(header)
curr_seq.append(_)
chr0_headers.append(header)
if curr_total >= 10**7: # Print out every 10Mbps
wrapped = re.findall(".{1,60}", pad.join(curr_seq))
print(*wrapped[:-1], sep="\n", file=outfile)
curr_seq = [wrapped[-1]]
curr_total = len(wrapped[-1])
wrapped = re.findall(".{1,60}", pad.join(curr_seq))
print(*wrapped, sep="\n", file=outfile)
# Write out the list of chr0 headers
f_chr0_g = open(os.path.join('groupings', 'Chr0_contigs.txt'),
'w')
f_chr0_o = open(
os.path.join('orderings', 'Chr0_orderings.txt'), 'w')
for i in chr0_headers:
f_chr0_g.write(i[1:] + "\t" + "0" + '\n')
f_chr0_o.write(i[1:] + '\t' + "+" + '\t' + "0" + '\t' +
"0" + '\n')
f_chr0_g.close()
f_chr0_o.close()
else:
# Instead of making a chromosome 0, add the unplaced sequences as is.
for header in remaining_contig_headers:
print(">{}".format(header), file=outfile)
print(*re.findall(".{1,60}", pad.join(x.fetch(header))),
sep="\n",
file=outfile)
f_chr0_g = open(
os.path.join('groupings', header[1:] + '_contigs.txt'),
'w')
f_chr0_o = open(
os.path.join('orderings' + header[1:] +
'_orderings.txt'), 'w')
f_chr0_g.write(header[1:] + "\t" + "0" + '\n')
f_chr0_o.write(header[1:] + '\t' + "+" + '\t' + "0" +
'\t' + "0" + '\n')
f_chr0_g.close()
f_chr0_o.close()