#!/usr/bin/python
# Copyright (c) 2017 The ACEseq workflow developers.
# Distributed under the MIT License (license terms are at https://www.github.com/eilslabs/ACEseqWorkflow/LICENSE.txt).
from python_modules import Options
options = Options.parse( { "hap_file" : str, "vcf_file" : str,
"outfile" : str } )
if options:
hap_infile = open( options["hap_file"], "r" )
vcf_infile = open( options["vcf_file"], "r" )
outfile = open( options["outfile" ], "w" )
haplo_line = hap_infile.readline()
if haplo_line:
haplo_line = haplo_line.rstrip().split()
for vcf_line in vcf_infile:
if vcf_line[0] != "#":
vcf_line = vcf_line.rstrip().split("\t")
vcf_line[0] = vcf_line[0].replace('chr', '')
vcf_line[0] = vcf_line[0].replace( 'X', '23' )
if len(vcf_line) >= 9 and haplo_line:
while haplo_line and int(haplo_line[2]) < int(vcf_line[1]):
# This script generates a file name ( inputpath + chromosome + inputsuffix ) for
# each chromosome.
# For example "~/Data/patient.chr" and ".snp" result in
# "~/Data/patient.chr1.snp", ... "~/Data/patient.chr22.snp",
# "~/Data/patient.chrX.snp", "~/Data/patient.chrY.snp".
# It than merges these files into one output file while filtering for coverage
# and combining the 1k windows into 10k windows.
import gzip
from python_modules import Tabfile
from python_modules import Options
options = Options.parse({
"inputpath": str,
"inputsuffix": str,
"output": str,
"coverage": int,
"mappability": float,
"NoOfWindows": int
})
if options:
outfile = gzip.open(options["output"], "wb")
def process_accumulated_lines(lines):
if len(lines) >= options["NoOfWindows"]:
chromo = lines[0]["chr"]
if chromo.startswith("chr"):
chromo = chromo.replace("chr", "")
#!/usr/bin/python
# Copyright (c) 2017 The ACEseq workflow developers.
# Distributed under the MIT License (license terms are at https://www.github.com/eilslabs/ACEseqWorkflow/LICENSE.txt).
# 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:
# "~/Data/patient.chrX.snp", "~/Data/patient.chrY.snp".
# It than merges these files into one output file with some filtering for
# coverage and a randomization of the A/B alleles.
#
# The functionality is described in the Bachelor thesis of Isabell Bludau at
# page 17, lines 11-17.
import gzip
import subprocess
from python_modules import Tabfile
from python_modules import Options
options = Options.parse({
"inputpath": str,
"inputsuffix": str,
"output": str,
"coverage": int
})
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(
# usage: merge_and_filter_cnv.py --inputpath [PATH] --inputsuffix [SUFFIX] --output [FILE] --coverage [INT]
#
# This script generates a file name ( inputpath + chromosome + inputsuffix ) for
# each chromosome.
# For example "~/Data/patient.chr" and ".snp" result in
# "~/Data/patient.chr1.snp", ... "~/Data/patient.chr22.snp",
# "~/Data/patient.chrX.snp", "~/Data/patient.chrY.snp".
# It than merges these files into one output file while filtering for coverage
# and combining the 1k windows into 10k windows.
import gzip
from python_modules import Tabfile
from python_modules import Options
options = Options.parse( { "inputfile" : str,
"output" : str, "coverage" : int,
"mappability" : float, "NoOfWindows" : int } )
if options:
outfile = gzip.open( options["output"], "wb" )
def process_accumulated_lines( lines ):
if len( lines ) >= options["NoOfWindows"]:
chromo = lines[0]["chr"]
if not chromo.startswith( "chr" ):
chromo = "chr" + chromo
chromo = chromo.replace( "chrX", "chr23" )
#!/usr/bin/python
# Copyright (c) 2017 The ACEseq workflow developers.
# Distributed under the MIT License (license terms are at https://www.github.com/eilslabs/ACEseqWorkflow/LICENSE.txt).
# 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)