def main(args=None):
args = process_args(args)
global F_gc, N_gc, R_gc
data = np.loadtxt(args.GCbiasFrequenciesFile.name)
F_gc = data[:, 0]
N_gc = data[:, 1]
R_gc = data[:, 2]
global global_vars
global_vars = {}
global_vars['2bit'] = args.genome
global_vars['bam'] = args.bamfile
# compute the probability to find more than one read (a redundant read)
# at a certain position based on the gc of the read fragment
# the binomial function is used for that
max_dup_gc = [
binom.isf(1e-7, F_gc[x], 1.0 /
N_gc[x]) if F_gc[x] > 0 and N_gc[x] > 0 else 1
for x in range(len(F_gc))
]
global_vars['max_dup_gc'] = max_dup_gc
tbit = twobit.TwoBitFile(global_vars['2bit'])
bam = pysam.Samfile(global_vars['bam'])
global_vars['genome_size'] = sum(tbit.sequence_sizes().values())
global_vars['total_reads'] = bam.mapped
global_vars['reads_per_bp'] = \
float(global_vars['total_reads']) / args.effectiveGenomeSize
# apply correction
print("applying correction")
# divide the genome in fragments containing about 4e5 reads.
# This amount of reads takes about 20 seconds
# to process per core (48 cores, 256 Gb memory)
chunkSize = int(4e5 / global_vars['reads_per_bp'])
# chromSizes: list of tuples
chromSizes = [(bam.references[i], bam.lengths[i])
for i in range(len(bam.references))]
regionStart = 0
if args.region:
chromSizes, regionStart, regionEnd, chunkSize = \
mapReduce.getUserRegion(chromSizes, args.region,
max_chunk_size=chunkSize)
print("genome partition size for multiprocessing: {}".format(chunkSize))
print("using region {}".format(args.region))
mp_args = []
bedGraphStep = args.binSize
chrNameBitToBam = tbitToBamChrName(list(tbit.sequence_sizes().keys()),
bam.references)
chrNameBamToBit = dict([(v, k) for k, v in chrNameBitToBam.items()])
print(chrNameBitToBam, chrNameBamToBit)
c = 1
for chrom, size in chromSizes:
start = 0 if regionStart == 0 else regionStart
for i in range(start, size, chunkSize):
try:
chrNameBamToBit[chrom]
except KeyError:
print("no sequence information for ")
"chromosome {} in 2bit file".format(chrom)
print("Reads in this chromosome will be skipped")
continue
length = min(size, i + chunkSize)
mp_args.append(
(chrom, chrNameBamToBit[chrom], i, length, bedGraphStep))
c += 1
pool = multiprocessing.Pool(args.numberOfProcessors)
if args.correctedFile.name.endswith('bam'):
if len(mp_args) > 1 and args.numberOfProcessors > 1:
print(("using {} processors for {} "
"number of tasks".format(args.numberOfProcessors,
len(mp_args))))
res = pool.map_async(writeCorrectedSam_wrapper,
mp_args).get(9999999)
else:
res = list(map(writeCorrectedSam_wrapper, mp_args))
if len(res) == 1:
command = "cp {} {}".format(res[0], args.correctedFile.name)
run_shell_command(command)
else:
print("concatenating (sorted) intermediate BAMs")
header = pysam.Samfile(res[0])
of = pysam.Samfile(args.correctedFile.name, "wb", template=header)
header.close()
for f in res:
f = pysam.Samfile(f)
for e in f.fetch(until_eof=True):
of.write(e)
f.close()
of.close()
print("indexing BAM")
pysam.index(args.correctedFile.name)
for tempFileName in res:
os.remove(tempFileName)
if args.correctedFile.name.endswith('bg') or \
args.correctedFile.name.endswith('bw'):
_temp_bg_file_name = utilities.getTempFileName(suffix='_all.bg')
if len(mp_args) > 1 and args.numberOfProcessors > 1:
res = pool.map_async(writeCorrected_wrapper, mp_args).get(9999999)
else:
res = list(map(writeCorrected_wrapper, mp_args))
# concatenate intermediary bedgraph files
_temp_bg_file = open(_temp_bg_file_name, 'w')
for tempFileName in res:
if tempFileName:
# concatenate all intermediate tempfiles into one
# bedgraph file
shutil.copyfileobj(open(tempFileName, 'rb'), _temp_bg_file)
os.remove(tempFileName)
_temp_bg_file.close()
args.correctedFile.close()
if args.correctedFile.name.endswith('bg'):
shutil.move(_temp_bg_file_name, args.correctedFile.name)
else:
chromSizes = [(k, v) for k, v in tbit.sequence_sizes().items()]
writeBedGraph.bedGraphToBigWig(chromSizes, _temp_bg_file_name,
args.correctedFile.name)
os.remove(_temp_bg_file)
def main(args=None):
args = process_args(args)
global F_gc, N_gc, R_gc
data = np.loadtxt(args.GCbiasFrequenciesFile.name)
F_gc = data[:, 0]
N_gc = data[:, 1]
R_gc = data[:, 2]
global global_vars
global_vars = {}
global_vars['2bit'] = args.genome
global_vars['bam'] = args.bamfile
# compute the probability to find more than one read (a redundant read)
# at a certain position based on the gc of the read fragment
# the binomial function is used for that
max_dup_gc = [binom.isf(1e-7, F_gc[x], 1.0 / N_gc[x])
if F_gc[x] > 0 and N_gc[x] > 0 else 1
for x in range(len(F_gc))]
global_vars['max_dup_gc'] = max_dup_gc
tbit = py2bit.open(global_vars['2bit'])
bam, mapped, unmapped, stats = openBam(args.bamfile, returnStats=True, nThreads=args.numberOfProcessors)
global_vars['genome_size'] = sum(tbit.chroms().values())
global_vars['total_reads'] = mapped
global_vars['reads_per_bp'] = \
float(global_vars['total_reads']) / args.effectiveGenomeSize
# apply correction
print("applying correction")
# divide the genome in fragments containing about 4e5 reads.
# This amount of reads takes about 20 seconds
# to process per core (48 cores, 256 Gb memory)
chunkSize = int(4e5 / global_vars['reads_per_bp'])
# chromSizes: list of tuples
chromSizes = [(bam.references[i], bam.lengths[i])
for i in range(len(bam.references))]
regionStart = 0
if args.region:
chromSizes, regionStart, regionEnd, chunkSize = \
mapReduce.getUserRegion(chromSizes, args.region,
max_chunk_size=chunkSize)
print("genome partition size for multiprocessing: {}".format(chunkSize))
print("using region {}".format(args.region))
mp_args = []
bedGraphStep = args.binSize
chrNameBitToBam = tbitToBamChrName(list(tbit.chroms().keys()), bam.references)
chrNameBamToBit = dict([(v, k) for k, v in chrNameBitToBam.items()])
print(chrNameBitToBam, chrNameBamToBit)
c = 1
for chrom, size in chromSizes:
start = 0 if regionStart == 0 else regionStart
for i in range(start, size, chunkSize):
try:
chrNameBamToBit[chrom]
except KeyError:
print("no sequence information for ")
"chromosome {} in 2bit file".format(chrom)
print("Reads in this chromosome will be skipped")
continue
length = min(size, i + chunkSize)
mp_args.append((chrom, chrNameBamToBit[chrom], i, length,
bedGraphStep))
c += 1
pool = multiprocessing.Pool(args.numberOfProcessors)
if args.correctedFile.name.endswith('bam'):
if len(mp_args) > 1 and args.numberOfProcessors > 1:
print(("using {} processors for {} "
"number of tasks".format(args.numberOfProcessors,
len(mp_args))))
res = pool.map_async(
writeCorrectedSam_wrapper, mp_args).get(9999999)
else:
res = list(map(writeCorrectedSam_wrapper, mp_args))
if len(res) == 1:
command = "cp {} {}".format(res[0], args.correctedFile.name)
run_shell_command(command)
else:
print("concatenating (sorted) intermediate BAMs")
header = pysam.Samfile(res[0])
of = pysam.Samfile(args.correctedFile.name, "wb", template=header)
header.close()
for f in res:
f = pysam.Samfile(f)
for e in f.fetch(until_eof=True):
of.write(e)
f.close()
of.close()
print("indexing BAM")
pysam.index(args.correctedFile.name)
for tempFileName in res:
os.remove(tempFileName)
if args.correctedFile.name.endswith('bg') or \
args.correctedFile.name.endswith('bw'):
if len(mp_args) > 1 and args.numberOfProcessors > 1:
res = pool.map_async(writeCorrected_wrapper, mp_args).get(9999999)
else:
res = list(map(writeCorrected_wrapper, mp_args))
oname = args.correctedFile.name
args.correctedFile.close()
if oname.endswith('bg'):
f = open(oname, 'wb')
for tempFileName in res:
if tempFileName:
shutil.copyfileobj(open(tempFileName, 'rb'), f)
os.remove(tempFileName)
f.close()
else:
chromSizes = [(k, v) for k, v in tbit.chroms().items()]
writeBedGraph.bedGraphToBigWig(chromSizes, res, oname)
def main(args=None):
args = parse_arguments().parse_args(args)
if args.extraSampling:
extra_sampling_file = args.extraSampling.name
args.extraSampling.close()
else:
extra_sampling_file = None
global global_vars
global_vars = {}
global_vars['2bit'] = args.genome
global_vars['bam'] = args.bamfile
global_vars['filter_out'] = args.blackListFileName
global_vars['extra_sampling_file'] = extra_sampling_file
tbit = py2bit.open(global_vars['2bit'])
bam = bamHandler.openBam(global_vars['bam'])
if args.fragmentLength:
fragment_len_dict = \
{'median': args.fragmentLength}
else:
fragment_len_dict, __ = \
get_read_and_fragment_length(args.bamfile, None,
numberOfProcessors=args.numberOfProcessors,
verbose=args.verbose)
if not fragment_len_dict:
print("\nPlease provide the fragment length used for the "
"sample preparation.\n")
exit(1)
fragment_len_dict = {'median': int(fragment_len_dict['median'])}
chrNameBitToBam = tbitToBamChrName(list(tbit.chroms().keys()), bam.references)
global_vars['genome_size'] = sum(tbit.chroms().values())
global_vars['total_reads'] = bam.mapped
global_vars['reads_per_bp'] = \
float(global_vars['total_reads']) / args.effectiveGenomeSize
confidence_p_value = float(1) / args.sampleSize
# chromSizes: list of tuples
chromSizes = [(bam.references[i], bam.lengths[i])
for i in range(len(bam.references))]
# use poisson distribution to identify peaks that should be discarted.
# I multiply by 4, because the real distribution of reads
# vary depending on the gc content
# and the global number of reads per bp may a be too low.
# empirically, a value of at least 4 times as big as the
# reads_per_bp was found.
# Similarly for the min value, I divide by 4.
global_vars['max_reads'] = \
poisson(4 * global_vars['reads_per_bp'] *
fragment_len_dict['median']).isf(confidence_p_value)
# this may be of not use, unless the depth of sequencing is really high
# as this value is close to 0
global_vars['min_reads'] = \
poisson(0.25 * global_vars['reads_per_bp'] *
fragment_len_dict['median']).ppf(confidence_p_value)
for key in global_vars:
print("{}: {}".format(key, global_vars[key]))
print("computing frequencies")
# the GC of the genome is sampled each stepSize bp.
stepSize = max(int(global_vars['genome_size'] / args.sampleSize), 1)
print("stepSize: {}".format(stepSize))
data = tabulateGCcontent(fragment_len_dict,
chrNameBitToBam, stepSize,
chromSizes,
numberOfProcessors=args.numberOfProcessors,
verbose=args.verbose,
region=args.region)
np.savetxt(args.GCbiasFrequenciesFile.name, data)
if args.biasPlot:
reads_per_gc = countReadsPerGC(args.regionSize,
chrNameBitToBam, stepSize * 10,
chromSizes,
numberOfProcessors=args.numberOfProcessors,
verbose=args.verbose,
region=args.region)
plotGCbias(args.biasPlot, data, reads_per_gc, args.regionSize, image_format=args.plotFileFormat)
def main(args=None):
args = parse_arguments().parse_args(args)
if args.extraSampling:
extra_sampling_file = args.extraSampling.name
args.extraSampling.close()
else:
extra_sampling_file = None
global global_vars
global_vars = {}
global_vars['2bit'] = args.genome
global_vars['bam'] = args.bamfile
global_vars['filter_out'] = args.blackListFileName
global_vars['extra_sampling_file'] = extra_sampling_file
bit = twobit.TwoBitFile(open(global_vars['2bit']))
bam = bamHandler.openBam(global_vars['bam'])
if args.fragmentLength:
fragment_len_dict = \
{'median': args.fragmentLength}
else:
fragment_len_dict, __ = \
get_read_and_fragment_length(args.bamfile, None,
numberOfProcessors=args.numberOfProcessors,
verbose=args.verbose)
if not fragment_len_dict:
print "\nPlease provide the fragment length used for the " \
"sample preparation.\n"
exit(1)
fragment_len_dict = {'median': int(fragment_len_dict['median'])}
chrNameBitToBam = tbitToBamChrName(bit.index.keys(), bam.references)
global_vars['genome_size'] = sum([bit[x].size for x in bit.index])
global_vars['total_reads'] = bam.mapped
global_vars['reads_per_bp'] = \
float(global_vars['total_reads']) / args.effectiveGenomeSize
confidence_p_value = float(1) / args.sampleSize
# chromSizes: list of tuples
chromSizes = [(bam.references[i], bam.lengths[i])
for i in range(len(bam.references))]
# use poisson distribution to identify peaks that should be discarted.
# I multiply by 4, because the real distribution of reads
# vary depending on the gc content
# and the global number of reads per bp may a be too low.
# empirically, a value of at least 4 times as big as the
# reads_per_bp was found.
# Similarly for the min value, I divide by 4.
global_vars['max_reads'] = \
poisson(4 * global_vars['reads_per_bp'] *
fragment_len_dict['median']).isf(confidence_p_value)
# this may be of not use, unless the depth of sequencing is really high
# as this value is close to 0
global_vars['min_reads'] = \
poisson(0.25 * global_vars['reads_per_bp'] *
fragment_len_dict['median']).ppf(confidence_p_value)
for key in global_vars:
print "{}: {}".format(key, global_vars[key])
print "computing frequencies"
# the GC of the genome is sampled each stepSize bp.
stepSize = max(int(global_vars['genome_size'] / args.sampleSize), 1)
print "stepSize: {}".format(stepSize)
data = tabulateGCcontent(fragment_len_dict,
chrNameBitToBam, stepSize,
chromSizes,
numberOfProcessors=args.numberOfProcessors,
verbose=args.verbose,
region=args.region)
np.savetxt(args.GCbiasFrequenciesFile.name, data)
if args.biasPlot:
reads_per_gc = countReadsPerGC(args.regionSize,
chrNameBitToBam, stepSize * 10,
chromSizes,
numberOfProcessors=args.numberOfProcessors,
verbose=args.verbose,
region=args.region)
plotGCbias(args.biasPlot, data, reads_per_gc, args.regionSize, image_format=args.plotFileFormat)
