# This function emulates the exact formating that perl uses for
# float values. It is of no functional importance for this script.
def perl_like_float_format(value):
int_part = str(int(value))
format_string = "{0:." + str(15 - len(int_part)) + "f}"
return format_string.format(value).rstrip('0').rstrip('.')
outfile.write(chromo + '\t' + str(position) + '\t' +
perl_like_float_format(normal) + '\t' +
perl_like_float_format(tumor) + '\n')
for chromo in [str(n) for n in range(1, 22 + 1)] + ["X", "Y"]:
print chromo
input_filename = options["inputpath"] + chromo + options["inputsuffix"]
infile = Tabfile.Input(gzip.open(input_filename, 'rb'))
accum_lines = [infile.readline()]
for line in infile:
if (int(line["normal"]) < options["coverage"]
or float(line["map"]) < options["mappability"]):
continue
if (line["chr"] == accum_lines[0]["chr"]
and int(line["pos"]) // 10000
== int(accum_lines[0]["pos"]) // 10000):
accum_lines.append(line)
else:
process_accumulated_lines(accum_lines)
parser.add_argument('--file',
'-f',
type=file,
help="segment file with copy number information")
parser.add_argument('--out',
'-o',
default=sys.stdout,
type=str,
help='outputfile')
parser.add_argument('--length', '-l', default=900, type=str, help='outputfile')
args = parser.parse_args()
out = args.out
try:
infile = Tabfile.Input(args.file)
except IOError as (errno, strerr):
sys.stderr.write("IOError %i: %s\n" % (errno, strerr))
sys.exit(2)
if out != sys.stdout:
try:
out = open(args.out, 'w')
except IOError as (errno, strerr):
sys.exit("IOError %i: %s\n" % (errno, strerr))
def merge_lines_CN(prior_line, newline, next_line):
start = ""
end = ""
#check whether segment could be merged
# This script replaces segments_to_data.pl and segments_to_data_2.pl.
#
# usage: segments_to_data.py --pscbs [FILE] --input [FILE] --output [FILE]
from python_modules import Tabfile
from python_modules import Options
import subprocess
import gzip
import sys
options = Options.parse({"pscbs": str, "input": str, "output": str})
if options:
pscbsfile = Tabfile.Input(gzip.open(options["pscbs"]))
#SNPs could be gzipped or not
try:
outfile = subprocess.Popen("bgzip >%s" % options["output"],
shell=True,
stdin=subprocess.PIPE)
except IOError as (errno, strerror):
syst.stderr.write("I/O error (%i): %s\n" % (errno, strerror))
pscbs_line = pscbsfile.readline()
while pscbs_line:
current_chromo = pscbs_line["chromosome"]
print current_chromo
)
sys.exit(2)
if not args.sv_out or not args.output:
sys.stderr.write(
"Please specify all output files. For more information use -h\n")
sys.exit(2)
if not args.DDI_length:
sys.stderr.write(
"Please specify all minimum duplication deletion and inversion (DDI) lengths. For more information use -h\n"
)
sys.exit(2)
try:
sv_file = Tabfile.Input(open(args.variants, "r"))
sv_out = open(args.sv_out, "w")
knownseg_file = Tabfile.Input(open(args.known_segments, "r"))
file_out = open(args.output, "w")
files = [sv_file]
except IOError as (errno, strerr):
sys.stderr.write("IOError %i: %s\n" % (errno, strerr))
sys.exit(errno)
breakpoints = []
chromosomes = [str(a) for a in range(1, 24 + 1)]
for f in files:
for line in f:
if line['svtype'] == 'INV' or line['svtype'] == 'DUP' or line[
if not args.snps:
args.snps = ""
out = args.out
if args.out != sys.stdout:
try:
out = subprocess.Popen("bgzip >%s" % args.out,
shell=True,
stdin=subprocess.PIPE)
except IOError as (errno, strerr):
sys.stderr.write("IOError %i: %s\n" % (errno, strerr))
sys.exit(errno)
try:
snpFile = Tabfile.Input(gzip.open(args.snps))
except IOError as (errno, strerr):
try:
snpFile = Tabfile.Input(sys.stdin)
except IOError:
sys.stderr.write("IOError %i: %s\n" % (errno, strerr))
sys.exit(errno)
curr_chrom = ''
for line in snpFile:
chrom = line['chr']
if chrom.startswith('chr'):
chrom = chrom.replace('chr', '')
line['chr'] = line['chr'].replace('chr', '')
pos = int(line['startPos'])
if options:
outfile = subprocess.Popen("bgzip >%s" % options["output"],
shell=True,
stdin=subprocess.PIPE)
outfile.stdin.write(
"chr\tstartPos\tAnormal\tBnormal\tAtumor\tBtumor\thaplotype\n"
) #header
for chromo in [str(n) for n in range(1, 22 + 1)] + ["X", "Y"]:
infile = gzip.open(
options["inputpath"] + chromo + options["inputsuffix"], 'rb')
for line in Tabfile.Input(infile):
if (int(line["An"]) + int(line["Bn"]) >= options["coverage"]):
line['haplotype'] = 0
if line["chr"].startswith("chr"):
line["chr"] = line["chr"].replace("chr", "")
line["chr"] = line["chr"].replace("X", "23")
line["chr"] = line["chr"].replace("Y", "24")
outfile.stdin.write(line["chr"] + '\t' + line["pos"] + '\t' +
line["An"] + '\t' + line["Bn"] + '\t' +
line["At"] + '\t' + line["Bt"] + '\t' +
str(line['haplotype']) + '\n')
# This script merges all segmentation approaches into a final segmentation.
from python_modules import Tabfile
from python_modules import Options
options = Options.parse({
"crest_deldupinv": str,
"crest_tx": str,
"known_segments": str,
"output": str,
"crest_out": str,
"DDI_length": int
})
if options:
crest_ddi_file = Tabfile.Input(open(options["crest_deldupinv"], "r"))
crest_tx_file = Tabfile.Input(open(options["crest_tx"], "r"))
crest_out = open(options["crest_out"], "w")
file_out = open(options["output"], "w")
breakpoints = []
for line in crest_ddi_file:
line["LENGTH"] = str(int(line["END"]) - int(line["POS"]) + 1)
if (line["SOMATIC_GERMLINE_CLASSIFICATION"] == "somatic"
and int(line["LENGTH"]) >= options["DDI_length"]
and "CHROM" in line):
line["CHROM"] = line["CHROM"].replace("chr", "").replace(
coverage = sum([float(line["coverage"])
for line in lines]) * 10 / len(lines)
# This function emulates the exact formating that perl uses for
# float values. It is of no functional importance for this script.
def perl_like_float_format(value):
int_part = str(int(value))
format_string = "{0:." + str(15 - len(int_part)) + "f}"
return format_string.format(value).rstrip('0').rstrip('.')
outfile.write(chromo + '\t' + str(position) + '\t' +
perl_like_float_format(coverage) + '\t' + '\n')
# input_filename = options["inputpath"] + chromo + options["inputsuffix"]
infile = Tabfile.Input(gzip.open(options['inputfile'], 'rb'))
accum_lines = [infile.readline()]
for line in infile:
if (int(line["coverage"]) < options["coverage"]
or float(line["map"]) < options["mappability"]):
continue
if (line["chr"] == accum_lines[0]["chr"] and int(line["pos"]) // 10000
== int(accum_lines[0]["pos"]) // 10000):
accum_lines.append(line)
else:
process_accumulated_lines(accum_lines)
accum_lines = [line]
distances.append(float(fields[3]) )
ploidies.append(float(fields[1]) )
entries.append(fields)
contin=1
except:
sys.stderr.write( "FILE for %s does not exist\n"% pid)
sys.exit(2)
m = min( [ abs( j-2.0 ) for j in ploidies ] )
index = [i for i,j in enumerate(ploidies) if abs(j-2.0)==m ]
solutions={1: "%s_%s"% (entries[index[0]][1], entries[index[0]][2] ) }
count=2
for i,j in enumerate(entries):
if i==index[0]: continue
solutions[count]="%s_%s"% ( entries[i][1], entries[i][2] )
count+=1
jsonMain={}
for key in solutions.keys():
try:
infile="%s/%s_cnv_parameter_%s.txt"% (path, pid, solutions[key])
tabfile = Tabfile.Input( open(infile) )
except IOError as (errno, strerr ):
sys.exit("IOError %i:%s\n" % (errno, strerr))
#convert simple tab seperated file wit header
jsonMain[key]=tabfile.readline()
out.write( json.dumps(jsonMain, indent=2, separators=(",",":")) )