def vcf_main(args):
# generate bedpe file
hout = open(args.output, 'w')
with open(args.result_file, 'r') as hin:
for line in hin:
if line.startswith("Chr_1" + '\t' + "Pos_1"):
header_info.read(line.rstrip('\n'))
continue
F = line.rstrip('\n').split('\t')
if F[header_info.variant_type] in ["inversion", "translocation"]: continue
if abs(int(F[header_info.pos_1]) - int(F[header_info.pos_2])) > int(args.max_size_thres): continue
if F[header_info.variant_type] == "deletion":
ref_seq = my_seq.get_seq(args.reference, F[header_info.chr_1], int(F[header_info.pos_1]), int(F[header_info.pos_2]) - 1)
alt_seq = ref_seq[0] if F[header_info.inserted_seq] == "---" else ref_seq[0] + F[header_info.inserted_seq]
pos = F[1]
elif F[header_info.variant_type] == "tandem_duplication":
alt_seq = my_seq.get_seq(args.reference, F[header_info.chr_1], int(F[header_info.pos_1]) - 1, int(F[header_info.pos_2]))
alt_seq = alt_seq if F[header_info.inserted_seq] == "---" else alt_seq + F[header_info.inserted_seq]
ref_seq = alt_seq[0]
pos = str(int(F[header_info.pos_1]) - 1)
print >> hout, '\t'.join([F[header_info.chr_1], pos, '.', ref_seq, alt_seq, '.', "PASS", '.'])
hout.close()
def generate_contig(input_file, output_file, tumor_bp_file, tumor_bam,
reference_genome, min_contig_length):
tumor_bp_db = pysam.TabixFile(tumor_bp_file)
readid2key = {}
with open(input_file, 'r') as hin:
for line in hin:
F = line.rstrip('\n').split('\t')
if F[0] == "Chr": continue
tabixErrorFlag = 0
try:
records = tumor_bp_db.fetch(F[0], int(F[1]) - 1, int(F[1]) + 1)
except Exception as inst:
print >> sys.stderr, "%s: %s" % (type(inst), inst.args)
tabixErrorMsg = str(inst.args)
tabixErrorFlag = 1
if tabixErrorFlag == 0:
for record_line in records:
record = record_line.split('\t')
if record[0] == F[0] and (int(record[1]) + 1) == int(
F[1]) and record[3] == F[2] and record[4] == F[3]:
for readid in record[5].split(';'):
readid2key[re.sub(r'/\d$', '',
readid)] = ','.join(F[:4])
bamfile = pysam.Samfile(tumor_bam, "rb")
hout = open(output_file + ".tmp2.contig.unsorted", 'w')
for read in bamfile.fetch():
if read.qname in readid2key:
flags = format(int(read.flag), "#014b")[:1:-1]
# skip supplementary alignment
if flags[8] == "1" or flags[11] == "1": continue
# skip duplicated reads
if flags[10] == "1": continue
print >> hout, readid2key[read.qname] + '\t' + read.qname + (
"/1" if flags[6] == "1" else "/2") + '\t' + read.query_sequence
hout.close()
hout = open(output_file + ".tmp2.contig.sorted", 'w')
subprocess.call(["sort", "-k1,1", output_file + ".tmp2.contig.unsorted"],
stdout=hout)
hout.close()
temp_key = ""
temp_id2seq = {}
temp_junc_seq = ""
key2contig = {}
with open(output_file + ".tmp2.contig.sorted") as hin:
for line in hin:
F = line.rstrip('\n').split('\t')
if temp_key != F[0]:
if len(temp_id2seq) > 0:
key2contig[temp_key] = assemble_seq(
temp_id2seq, temp_junc_seq, output_file)
temp_key = F[0]
temp_id2seq = {}
FF = temp_key.split(',')
if FF[2] == "+":
temp_junc_seq = my_seq.get_seq(reference_genome, FF[0],
int(FF[1]) - 20, int(FF[1]))
else:
temp_junc_seq = my_seq.reverse_complement(
my_seq.get_seq(reference_genome, FF[0], int(FF[1]),
int(FF[1]) + 20))
temp_id2seq[F[1]] = F[2]
if len(temp_id2seq) > 0:
key2contig[temp_key] = assemble_seq(temp_id2seq, temp_junc_seq,
output_file)
hout = open(output_file, 'w')
with open(input_file, 'r') as hin:
for line in hin:
F = line.rstrip('\n').split('\t')
key = ','.join(F[:4])
if key not in key2contig: continue
contig = key2contig[key]
if len(contig) < min_contig_length: continue
# if contig[:8] != F[3][:8]: continue
print >> hout, '\t'.join(F) + '\t' + contig
hout.close()
def generate_template_seq(output_file, reference, mut_chr, mut_start, mut_end, mut_ref, mut_alt,
motif_chr, motif_start, motif_end, motif_type, motif_strand,
junc_list, donor_size, acceptor_size, template_size):
donor_size_exon, donor_size_intron = [int(x) for x in donor_size.split(',')]
acceptor_size_intron, acceptor_size_exon = [int(x) for x in acceptor_size.split(',')]
unique_junc_list = list(set(junc_list.split(',')))
if motif_type == "donor":
if motif_strand == '+':
motif_exon_start, motif_exon_end = motif_start, motif_start + donor_size_exon - 1
motif_intron_start, motif_intron_end = motif_start + donor_size_exon, motif_start + donor_size_exon + donor_size_intron - 1
else:
motif_intron_start, motif_intron_end = motif_start, motif_start + donor_size_intron - 1
motif_exon_start, motif_exon_end = motif_start + donor_size_intron, motif_start + donor_size_exon + donor_size_intron - 1
else: # acceptor
if motif_strand == '+':
motif_intron_start, motif_intron_end = motif_start, motif_start + acceptor_size_intron - 1
motif_exon_start, motif_exon_end = motif_start + acceptor_size_intron, motif_start + acceptor_size_exon + acceptor_size_intron - 1
else:
motif_exon_start, motif_exon_end = motif_start, motif_start + acceptor_size_exon - 1
motif_intron_start, motif_intron_end = motif_start + acceptor_size_exon, motif_start + acceptor_size_exon + acceptor_size_intron - 1
key2seq = {}
# annotated splice junction without mutation
cnum = 0
for junc in sorted(unique_junc_list):
junc_match = re.match(r'([^ \t\n\r\f\v,]+)\:(\d+)\-(\d+)', junc)
junc_chr, junc_start, junc_end = junc_match.group(1), int(junc_match.group(2)), int(junc_match.group(3))
seq = my_seq.get_seq(reference, junc_chr, junc_start - template_size + 1, junc_start) + \
my_seq.get_seq(reference, junc_chr, junc_end, junc_end + template_size - 1)
key2seq["splice_junction_negative_" + str(cnum)] = seq
cnum = cnum + 1
# annotated splice junction with mutation (only when mutations occur within exonic motif region)
if mut_start >= motif_exon_start and mut_end <= motif_exon_end:
cnum = 0
for junc in sorted(unique_junc_list):
junc_match = re.match(r'([^ \t\n\r\f\v,]+)\:(\d+)\-(\d+)', junc)
junc_chr, junc_start, junc_end = junc_match.group(1), int(junc_match.group(2)), int(junc_match.group(3))
if (motif_type == "donor" and motif_strand == '+') or (motif_type == "acceptor" and motif_strand == '-'):
mut_seq_tmp = my_seq.get_seq(reference, junc_chr, junc_start - mut_seq_margin + 1, junc_start)
mut_start_rel, mut_end_rel = mut_start - junc_start + mut_seq_margin - 1, mut_end - junc_start + mut_seq_margin - 1
else:
mut_seq_tmp = my_seq.get_seq(reference, junc_chr, junc_end, junc_end + mut_seq_margin - 1)
mut_start_rel, mut_end_rel = mut_start - junc_end, mut_end - junc_end
# for debug
if mut_ref != '-' and mut_seq_tmp[mut_start_rel:(mut_end_rel + 1)] != mut_ref:
print >> sys.stderr, '\t'.join([mut_chr, str(mut_start), str(mut_end), mut_ref, mut_alt, junc])
print >> sys.stderr, '\t'.join([mut_seq_tmp[mut_start_rel:(mut_end_rel + 1)], mut_ref])
print >> sys.stderr, "mutation inconsistent!!!"
sys.exit(1)
# SNV
if mut_ref != '-' and mut_alt != '-': mut_seq_tmp = mut_seq_tmp[:mut_start_rel] + mut_alt + mut_seq_tmp[(mut_end_rel + 1):]
# deletion
if mut_alt == '-': mut_seq_tmp = mut_seq_tmp[:mut_start_rel] + mut_seq_tmp[(mut_end_rel + 1):]
# insertion
if mut_ref == '-': mut_seq_tmp = mut_seq_tmp[:(mut_start_rel + 1)] + mut_alt + mut_seq_tmp[(mut_start_rel + 1):]
if (motif_type == "donor" and motif_strand == '+') or (motif_type == "acceptor" and motif_strand == '-'):
seq = mut_seq_tmp[(-template_size):] + my_seq.get_seq(reference, junc_chr, junc_end, junc_end + template_size - 1)
else:
seq = my_seq.get_seq(reference, junc_chr, junc_start - template_size + 1, junc_start) + mut_seq_tmp[:(template_size)]
key2seq["splice_junction_positive_" + str(cnum)] = seq
cnum = cnum + 1
# intron retention without mutation
if (motif_type == "donor" and motif_strand == '+') or (motif_type == "acceptor" and motif_strand == '-'):
seq_left_tmp = my_seq.get_seq(reference, junc_chr, motif_exon_end - mut_seq_margin + 1, motif_exon_end)
seq_right_tmp = my_seq.get_seq(reference, junc_chr, motif_intron_start, motif_intron_start + mut_seq_margin - 1)
boundary_pos = motif_exon_end
else:
seq_left_tmp = my_seq.get_seq(reference, junc_chr, motif_intron_end - mut_seq_margin + 1, motif_intron_end)
seq_right_tmp = my_seq.get_seq(reference, junc_chr, motif_exon_start, motif_exon_start + mut_seq_margin - 1)
boundary_pos = motif_intron_end
key2seq["intron_retention_negative"] = seq_left_tmp[(-template_size):] + seq_right_tmp[:(template_size)]
# intron retention with mutation
mut_seq_left_tmp, mut_seq_right_tmp = seq_left_tmp, seq_right_tmp
# in this case, we remove nucleotides from concatenated sequences
mut_start_rel, mut_end_rel = mut_start - boundary_pos + mut_seq_margin - 1, mut_end - boundary_pos + mut_seq_margin - 1
mut_seq_tmp = mut_seq_left_tmp + mut_seq_right_tmp
# SNV
if mut_ref != '-' and mut_alt != '-':
# for debug
if mut_seq_tmp[mut_start_rel] != mut_ref:
print >> sys.stderr, "mutation inconsistent!!!"
sys.exit(1)
mut_seq_tmp = mut_seq_tmp[:mut_start_rel] + mut_alt + mut_seq_tmp[(mut_end_rel + 1):]
mut_seq_start_pos = mut_seq_margin - template_size
mut_seq_end_pos = mut_seq_start_pos + 2 * template_size
key2seq["intron_retention_positive"] = mut_seq_tmp[mut_seq_start_pos:mut_seq_end_pos]
elif mut_alt == '-': # deletion
# for debug
if mut_seq_tmp[mut_start_rel:(mut_end_rel + 1)] != mut_ref != '-':
print >> sys.stderr, "mutation inconsistent!!!"
sys.exit(1)
mut_seq_tmp = mut_seq_tmp[:mut_start_rel] + mut_seq_tmp[(mut_end_rel + 1):]
del_size_left = max(0, (min(boundary_pos, mut_end) - mut_start))
mut_seq_start_pos = mut_seq_margin - template_size - del_size_left
mut_seq_end_pos = mut_seq_start_pos + 2 * template_size
key2seq["intron_retention_positive"] = mut_seq_tmp[mut_seq_start_pos:mut_seq_end_pos]
elif mut_ref == '-': #insertion
mut_seq_tmp = mut_seq_tmp[:(mut_start_rel + 1)] + mut_alt + mut_seq_tmp[(mut_start_rel + 1):]
ins_size_left = len(mut_alt)
mut_seq_start_pos = mut_seq_margin - template_size + ins_size_left
mut_seq_end_pos = mut_seq_start_pos + 2 * template_size
key2seq["intron_retention_positive"] = mut_seq_tmp[mut_seq_start_pos:mut_seq_end_pos]
hout = open(output_file, 'w')
for key in sorted(key2seq):
print >> hout, ">" + key + '\n' + key2seq[key]
hout.close()
def make_mut_db(input_file, output_file_prefix, reference):
hout = open(output_file_prefix + ".bed", "w")
with open(input_file, "r") as hin:
ref_ind = -1
alt_ind = -1
tum_ref_ind = -1
nor_ref_ind = -1
tum_var_ind = -1
nor_var_ind = -1
fisher_ind = -1
header = hin.readline().rstrip("\n").split("\t")
for i in range(0, len(header)):
if header[i] == "Ref":
ref_ind = i
if header[i] == "Alt":
alt_ind = i
if header[i] == "readPairNum_tumor":
tum_ref_ind = i
if header[i] == "variantPairNum_tumor":
tum_var_ind = i
if header[i] == "readPairNum_normal":
nor_ref_ind = i
if header[i] == "variantPairNum_normal":
nor_var_ind = i
if header[i] == "P-value(fhsher_realignment)":
fisher_ind = i
for line in hin:
F = line.rstrip("\n").split("\t")
if len(F[ref_ind]) >= 10 or len(F[alt_ind]) >= 10:
bed_key = F[0] + "\t" + str(int(F[1]) - 1) + "\t" + F[2]
read_info = (
F[tum_ref_ind]
+ "\t"
+ F[tum_var_ind]
+ "\t"
+ str(round(float(F[tum_var_ind]) / (float(F[tum_ref_ind]) + float(F[tum_var_ind])), 3))
+ "\t"
+ F[nor_ref_ind]
+ "\t"
+ F[nor_var_ind]
+ "\t"
+ str(round(float(F[nor_var_ind]) / (float(F[nor_ref_ind]) + float(F[nor_var_ind])), 3))
+ "\t"
+ F[fisher_ind]
)
var_info = ""
# deletion
if len(F[ref_ind]) >= 10:
var_info = (
F[0]
+ "\t"
+ str(int(F[1]) - 1)
+ "\t"
+ "+"
+ "\t"
+ F[0]
+ "\t"
+ str(int(F[1]) + len(F[ref_ind]))
+ "\t"
+ "-"
+ "\t"
+ "---"
+ "\t"
+ "deletion"
)
# gene_annotation = get_gene_annotation(F[0], str(int(F[1]) - 1), F[0], str(int(F[1]) + len(F[ref_ind])), gene_tb, exon_tb)
gene_annotation = "---" + "\t" + "---" + "\t" + "---" + "\t" + "---"
print >> hout, bed_key + "\t" + var_info + "\t" + gene_annotation + "\t" + read_info
# tandem_duplication
elif len(F[alt_ind]) >= 10:
# tandem_duplication check
flanking_seq_1 = my_seq.get_seq(reference, F[0], int(F[1]) + 1, int(F[1]) + len(F[alt_ind]))
flanking_seq_1_match = my_seq.exact_alignment(F[alt_ind], flanking_seq_1)
flanking_seq_2 = my_seq.get_seq(reference, F[0], int(F[1]) - len(F[alt_ind]) + 1, int(F[1]))
flanking_seq_2_match = my_seq.exact_alignment(F[alt_ind], flanking_seq_2)
# print '\t'.join(F[0:4])
# print F[alt_ind] + '\t' + flanking_seq_1 + '\t' + str(flanking_seq_1_match)
# print F[alt_ind] + '\t' + flanking_seq_2 + '\t' + str(flanking_seq_2_match)
if flanking_seq_1_match == len(F[alt_ind]) or flanking_seq_2_match == len(F[alt_ind]):
var_info = (
F[0]
+ "\t"
+ str(int(F[1]) + 1)
+ "\t"
+ "-"
+ "\t"
+ F[0]
+ "\t"
+ str(int(F[1]) + len(F[alt_ind]))
+ "\t"
+ "+"
+ "\t"
+ "---"
+ "\t"
+ "tandem_duplication"
)
# gene_annotation = get_gene_annotation(F[0], str(int(F[1]) + 1), F[0], str(int(F[1]) + len(F[alt_ind])), gene_tb, exon_tb)
gene_annotation = "---" + "\t" + "---" + "\t" + "---" + "\t" + "---"
print >> hout, bed_key + "\t" + var_info + "\t" + gene_annotation + "\t" + read_info
hout.close()
subprocess.call(["bgzip", "-f", output_file_prefix + ".bed"])
subprocess.call(["tabix", "-p", "bed", output_file_prefix + ".bed.gz"])