def reMergeBamfiles(infiles, sentinel):
infiles = [P.snip(x, ".sentinel") + ".bam" for x in infiles]
outfile = P.snip(sentinel, ".sentinel") + ".bam"
bad_samples = PARAMS["options_to_remove"].split(",")
to_merge = IDR.filterBadLibraries(infiles, bad_samples)
IDR.mergeBams(to_merge, outfile)
P.touch(sentinel)
def summarizePeaksForPooledPseudoreplicates(infiles, outfile):
outf = iotools.openFile(outfile, "w")
outf.write("Sample_id\t"
"Experiment\t"
"Tissue\t"
"Condition\t"
"Pseudoreplicate\t"
"n_peaks\n")
IDR.countPeaks(infiles, outf)
def poolSampleBamfiles(infiles, sentinel):
"""
Merge filtered sample files for each tissue
"""
infiles = [P.snip(x, ".sentinel") + ".bam" for x in infiles]
outfile = P.snip(sentinel, ".sentinel") + ".bam"
IDR.mergeBams(infiles, outfile)
P.touch(sentinel)
def callPeaksOnPseudoreplicates(infile, outfile):
# fetch peak calling parameters
PARAMS_PEAKCALLER = get_peak_caller_parameters(
PARAMS["options_peak_caller"])
# call peaks on pseudoreplicates
IDR.callIDRPeaks(infile,
outfile,
PARAMS["options_peak_caller"],
PARAMS["options_control_type"],
PARAMS_PEAKCALLER,
pseudoreplicate=True)
def callPeaksOnIndividualReplicates(infile, outfile):
infile = P.snip(infile, ".sentinel") + ".bam"
# fetch peak calling parameters
PARAMS_PEAKCALLER = get_peak_caller_parameters(
PARAMS["options_peak_caller"])
# call peaks
IDR.callIDRPeaks(infile,
outfile,
PARAMS["options_peak_caller"],
PARAMS["options_control_type"],
PARAMS_PEAKCALLER)
P.touch(outfile)
def poolInputBamfiles(infiles, sentinel):
"""
Merge filtered input files for each tissue, with the option of excluding
undesirable libraries.
"""
infiles = [P.snip(x, ".sentinel") + ".bam" for x in infiles]
outfile = P.snip(sentinel, ".sentinel") + ".bam"
bad_samples = PARAMS["filter_remove_inputs"].split(",")
if len(infiles) > 1:
to_merge = IDR.filterBadLibraries(infiles, bad_samples)
IDR.mergeBams(to_merge, outfile)
else:
os.symlink(os.path.abspath(infiles[0]), outfile)
os.symlink(os.path.abspath(infiles[0]) + ".bai", outfile + ".bai")
P.touch(sentinel)
def runIDROnPooledPseudoreplicates(infiles, outfile):
"""
Run IDR analysis on pooled pseudoreplicates for each EXPERIMENT
"""
# set IDR parameters
chr_table = os.path.join(PARAMS["annotations_dir"],
PARAMS["annotations_interface_contigs"])
# get statement
statement = IDR.getIDRStatement(infiles[0],
infiles[1],
outfile,
PARAMS["idr_options_overlap_ratio"],
PARAMS["idr_options_ranking_measure"],
chr_table)
# run
E.info("applyIDR: processing %s and %s" % (infiles[0], infiles[1]))
job_memory = "5G"
P.run()
def runIDROnIndividualReplicates(infiles, outfile):
"""
Run IDR consecutively for each pairwise combination of a particular
EXPERIMENT
"""
# set IDR parameters (HACK!) WrapperIDR is in /ifs/devel/cgat
chr_table = os.path.join(PARAMS["annotations_dir"],
PARAMS["annotations_interface_contigs"])
# iterate through pairwise combinations of infiles
for infile1, infile2 in itertools.combinations(infiles, 2):
# get statement
statement = IDR.getIDRStatement(infile1,
infile2,
outfile,
PARAMS["idr_options_overlap_ratio"],
PARAMS["idr_options_ranking_measure"],
chr_table)
# run
E.info("applyIDR: processing %s and %s" % (infile1, infile2))
job_memory = "5G"
P.run()
def plotBatchConsistencyForPooledPseudoreplicates(infiles, outfile):
statement = IDR.getIDRPlotStatement(infiles[0], outfile)
P.run()
def plotBatchConsistencyForIndividualReplicates(infiles, outfile):
# HACK!
statement = IDR.getIDRPlotStatement(infiles, outfile)
P.run()