def main(args=None):
args = process_args(args)
global debug
if args.verbose:
sys.stderr.write("Specified --scaleFactor: {}\n".format(
args.scaleFactor))
debug = 1
else:
debug = 0
if args.normalizeUsing == 'None':
args.normalizeUsing = None # For the sake of sanity
if args.normalizeUsing:
# if a normalization is required then compute the scale factors
bam, mapped, unmapped, stats = openBam(
args.bam, returnStats=True, nThreads=args.numberOfProcessors)
bam.close()
scale_factor = get_scale_factor(args, stats)
else:
scale_factor = args.scaleFactor
func_args = {'scaleFactor': scale_factor}
# This fixes issue #520, where --extendReads wasn't honored if --filterRNAstrand was used
if args.filterRNAstrand and not args.Offset:
args.Offset = [1, -1]
if args.MNase:
# check that library is paired end
# using getFragmentAndReadSize
from deeptools.getFragmentAndReadSize import get_read_and_fragment_length
frag_len_dict, read_len_dict = get_read_and_fragment_length(
args.bam,
return_lengths=False,
blackListFileName=args.blackListFileName,
numberOfProcessors=args.numberOfProcessors,
verbose=args.verbose)
if frag_len_dict is None:
sys.exit(
"*Error*: For the --MNAse function a paired end library is required. "
)
# Set some default fragment length bounds
if args.minFragmentLength == 0:
args.minFragmentLength = 130
if args.maxFragmentLength == 0:
args.maxFragmentLength = 200
wr = CenterFragment(
[args.bam],
binLength=args.binSize,
stepSize=args.binSize,
region=args.region,
blackListFileName=args.blackListFileName,
numberOfProcessors=args.numberOfProcessors,
extendReads=args.extendReads,
minMappingQuality=args.minMappingQuality,
ignoreDuplicates=args.ignoreDuplicates,
center_read=args.centerReads,
zerosToNans=args.skipNonCoveredRegions,
samFlag_include=args.samFlagInclude,
samFlag_exclude=args.samFlagExclude,
minFragmentLength=args.minFragmentLength,
maxFragmentLength=args.maxFragmentLength,
chrsToSkip=args.ignoreForNormalization,
verbose=args.verbose,
)
elif args.Offset:
if len(args.Offset) > 1:
if args.Offset[0] == 0:
sys.exit(
"*Error*: An offset of 0 isn't allowed, since offsets are 1-based positions inside each alignment."
)
if args.Offset[1] > 0 and args.Offset[1] < args.Offset[0]:
sys.exir(
"'Error*: The right side bound is less than the left-side bound. This is inappropriate."
)
else:
if args.Offset[0] == 0:
sys.exit(
"*Error*: An offset of 0 isn't allowed, since offsets are 1-based positions inside each alignment."
)
wr = OffsetFragment([args.bam],
binLength=args.binSize,
stepSize=args.binSize,
region=args.region,
numberOfProcessors=args.numberOfProcessors,
extendReads=args.extendReads,
minMappingQuality=args.minMappingQuality,
ignoreDuplicates=args.ignoreDuplicates,
center_read=args.centerReads,
zerosToNans=args.skipNonCoveredRegions,
samFlag_include=args.samFlagInclude,
samFlag_exclude=args.samFlagExclude,
minFragmentLength=args.minFragmentLength,
maxFragmentLength=args.maxFragmentLength,
chrsToSkip=args.ignoreForNormalization,
verbose=args.verbose)
wr.filter_strand = args.filterRNAstrand
wr.Offset = args.Offset
else:
wr = writeBedGraph.WriteBedGraph(
[args.bam],
binLength=args.binSize,
stepSize=args.binSize,
region=args.region,
blackListFileName=args.blackListFileName,
numberOfProcessors=args.numberOfProcessors,
extendReads=args.extendReads,
minMappingQuality=args.minMappingQuality,
ignoreDuplicates=args.ignoreDuplicates,
center_read=args.centerReads,
zerosToNans=args.skipNonCoveredRegions,
samFlag_include=args.samFlagInclude,
samFlag_exclude=args.samFlagExclude,
minFragmentLength=args.minFragmentLength,
maxFragmentLength=args.maxFragmentLength,
chrsToSkip=args.ignoreForNormalization,
verbose=args.verbose,
)
wr.run(writeBedGraph.scaleCoverage,
func_args,
args.outFileName,
blackListFileName=args.blackListFileName,
format=args.outFileFormat,
smoothLength=args.smoothLength)
def main(args=None):
args = process_args(args)
global debug
if args.verbose:
debug = 1
else:
debug = 0
func_args = {'scaleFactor': get_scale_factor(args)}
if args.MNase:
# check that library is paired end
# using getFragmentAndReadSize
from deeptools.getFragmentAndReadSize import get_read_and_fragment_length
frag_len_dict, read_len_dict = get_read_and_fragment_length(
args.bam,
return_lengths=False,
blackListFileName=args.blackListFileName,
numberOfProcessors=args.numberOfProcessors,
verbose=args.verbose)
if frag_len_dict is None:
sys.exit(
"*Error*: For the --MNAse function a paired end library is required. "
)
# Set some default fragment length bounds
if args.minFragmentLength == 0:
args.minFragmentLength = 130
if args.maxFragmentLength == 0:
args.maxFragmentLength = 200
wr = CenterFragment(
[args.bam],
binLength=args.binSize,
stepSize=args.binSize,
region=args.region,
blackListFileName=args.blackListFileName,
numberOfProcessors=args.numberOfProcessors,
extendReads=args.extendReads,
minMappingQuality=args.minMappingQuality,
ignoreDuplicates=args.ignoreDuplicates,
center_read=args.centerReads,
zerosToNans=args.skipNonCoveredRegions,
samFlag_include=args.samFlagInclude,
samFlag_exclude=args.samFlagExclude,
minFragmentLength=args.minFragmentLength,
maxFragmentLength=args.maxFragmentLength,
verbose=args.verbose,
)
elif args.Offset:
if len(args.Offset) > 1:
if args.Offset[0] == 0:
sys.exit(
"*Error*: An offset of 0 isn't allowed, since offsets are 1-based positions inside each alignment."
)
if args.Offset[1] > 0 and args.Offset[1] < args.Offset[0]:
sys.exir(
"'Error*: The right side bound is less than the left-side bound. This is inappropriate."
)
else:
if args.Offset[0] == 0:
sys.exit(
"*Error*: An offset of 0 isn't allowed, since offsets are 1-based positions inside each alignment."
)
wr = OffsetFragment([args.bam],
binLength=args.binSize,
stepSize=args.binSize,
region=args.region,
numberOfProcessors=args.numberOfProcessors,
extendReads=args.extendReads,
minMappingQuality=args.minMappingQuality,
ignoreDuplicates=args.ignoreDuplicates,
center_read=args.centerReads,
zerosToNans=args.skipNonCoveredRegions,
samFlag_include=args.samFlagInclude,
samFlag_exclude=args.samFlagExclude,
minFragmentLength=args.minFragmentLength,
maxFragmentLength=args.maxFragmentLength,
verbose=args.verbose)
wr.filter_strand = args.filterRNAstrand
wr.Offset = args.Offset
elif args.filterRNAstrand:
wr = filterRnaStrand(
[args.bam],
binLength=args.binSize,
stepSize=args.binSize,
region=args.region,
numberOfProcessors=args.numberOfProcessors,
extendReads=args.extendReads,
minMappingQuality=args.minMappingQuality,
ignoreDuplicates=args.ignoreDuplicates,
center_read=args.centerReads,
zerosToNans=args.skipNonCoveredRegions,
samFlag_include=args.samFlagInclude,
samFlag_exclude=args.samFlagExclude,
minFragmentLength=args.minFragmentLength,
maxFragmentLength=args.maxFragmentLength,
verbose=args.verbose,
)
wr.filter_strand = args.filterRNAstrand
else:
wr = writeBedGraph.WriteBedGraph(
[args.bam],
binLength=args.binSize,
stepSize=args.binSize,
region=args.region,
blackListFileName=args.blackListFileName,
numberOfProcessors=args.numberOfProcessors,
extendReads=args.extendReads,
minMappingQuality=args.minMappingQuality,
ignoreDuplicates=args.ignoreDuplicates,
center_read=args.centerReads,
zerosToNans=args.skipNonCoveredRegions,
samFlag_include=args.samFlagInclude,
samFlag_exclude=args.samFlagExclude,
minFragmentLength=args.minFragmentLength,
maxFragmentLength=args.maxFragmentLength,
verbose=args.verbose,
)
wr.run(writeBedGraph.scaleCoverage,
func_args,
args.outFileName,
blackListFileName=args.blackListFileName,
format=args.outFileFormat,
smoothLength=args.smoothLength)
def main(args=None):
args = process_args(args)
global debug
if args.verbose:
sys.stderr.write("Specified --scaleFactor: {}\n".format(args.scaleFactor))
debug = 1
else:
debug = 0
if args.normalizeUsing == 'None':
args.normalizeUsing = None # For the sake of sanity
elif args.normalizeUsing == 'RPGC' and not args.effectiveGenomeSize:
sys.exit("RPGC normalization requires an --effectiveGenomeSize!\n")
if args.normalizeUsing:
# if a normalization is required then compute the scale factors
bam, mapped, unmapped, stats = openBam(args.bam, returnStats=True, nThreads=args.numberOfProcessors)
bam.close()
scale_factor = get_scale_factor(args, stats)
else:
scale_factor = args.scaleFactor
func_args = {'scaleFactor': scale_factor}
# This fixes issue #520, where --extendReads wasn't honored if --filterRNAstrand was used
if args.filterRNAstrand and not args.Offset:
args.Offset = [1, -1]
if args.MNase:
# check that library is paired end
# using getFragmentAndReadSize
from deeptools.getFragmentAndReadSize import get_read_and_fragment_length
frag_len_dict, read_len_dict = get_read_and_fragment_length(args.bam,
return_lengths=False,
blackListFileName=args.blackListFileName,
numberOfProcessors=args.numberOfProcessors,
verbose=args.verbose)
if frag_len_dict is None:
sys.exit("*Error*: For the --MNAse function a paired end library is required. ")
# Set some default fragment length bounds
if args.minFragmentLength == 0:
args.minFragmentLength = 130
if args.maxFragmentLength == 0:
args.maxFragmentLength = 200
wr = CenterFragment([args.bam],
binLength=args.binSize,
stepSize=args.binSize,
region=args.region,
blackListFileName=args.blackListFileName,
numberOfProcessors=args.numberOfProcessors,
extendReads=args.extendReads,
minMappingQuality=args.minMappingQuality,
ignoreDuplicates=args.ignoreDuplicates,
center_read=args.centerReads,
zerosToNans=args.skipNonCoveredRegions,
samFlag_include=args.samFlagInclude,
samFlag_exclude=args.samFlagExclude,
minFragmentLength=args.minFragmentLength,
maxFragmentLength=args.maxFragmentLength,
chrsToSkip=args.ignoreForNormalization,
verbose=args.verbose,
)
elif args.Offset:
if len(args.Offset) > 1:
if args.Offset[0] == 0:
sys.exit("*Error*: An offset of 0 isn't allowed, since offsets are 1-based positions inside each alignment.")
if args.Offset[1] > 0 and args.Offset[1] < args.Offset[0]:
sys.exir("'Error*: The right side bound is less than the left-side bound. This is inappropriate.")
else:
if args.Offset[0] == 0:
sys.exit("*Error*: An offset of 0 isn't allowed, since offsets are 1-based positions inside each alignment.")
wr = OffsetFragment([args.bam],
binLength=args.binSize,
stepSize=args.binSize,
region=args.region,
numberOfProcessors=args.numberOfProcessors,
extendReads=args.extendReads,
minMappingQuality=args.minMappingQuality,
ignoreDuplicates=args.ignoreDuplicates,
center_read=args.centerReads,
zerosToNans=args.skipNonCoveredRegions,
samFlag_include=args.samFlagInclude,
samFlag_exclude=args.samFlagExclude,
minFragmentLength=args.minFragmentLength,
maxFragmentLength=args.maxFragmentLength,
chrsToSkip=args.ignoreForNormalization,
verbose=args.verbose)
wr.filter_strand = args.filterRNAstrand
wr.Offset = args.Offset
else:
wr = writeBedGraph.WriteBedGraph([args.bam],
binLength=args.binSize,
stepSize=args.binSize,
region=args.region,
blackListFileName=args.blackListFileName,
numberOfProcessors=args.numberOfProcessors,
extendReads=args.extendReads,
minMappingQuality=args.minMappingQuality,
ignoreDuplicates=args.ignoreDuplicates,
center_read=args.centerReads,
zerosToNans=args.skipNonCoveredRegions,
samFlag_include=args.samFlagInclude,
samFlag_exclude=args.samFlagExclude,
minFragmentLength=args.minFragmentLength,
maxFragmentLength=args.maxFragmentLength,
chrsToSkip=args.ignoreForNormalization,
verbose=args.verbose,
)
wr.run(writeBedGraph.scaleCoverage, func_args, args.outFileName,
blackListFileName=args.blackListFileName,
format=args.outFileFormat, smoothLength=args.smoothLength)
def main(args=None):
"""
The algorithm is composed of two steps.
1. Per-sample scaling / depth Normalization:
+ If scaling is used (using the SES or read counts method), appropriate scaling
factors are determined to account for sequencing depth differences.
+ Optionally scaling can be turned off and individual samples could be depth normalized using
RPKM, BPM or CPM methods
2. Ratio calculation between two bam files:
+ The genome is transversed and computing
the log ratio/ratio/difference etc. for bins of fixed width
given by the user.
"""
args = process_args(args)
if args.normalizeUsing == "RPGC":
sys.exit(
"RPGC normalization (--normalizeUsing RPGC) is not supported with bamCompare!"
)
if args.normalizeUsing == 'None':
args.normalizeUsing = None # For the sake of sanity
if args.scaleFactorsMethod != 'None' and args.normalizeUsing:
sys.exit(
"`--normalizeUsing {}` is only valid if you also use `--scaleFactorsMethod None`! To prevent erroneous output, I will quit now.\n"
.format(args.normalizeUsing))
# Get mapping statistics
bam1, mapped1, unmapped1, stats1 = bamHandler.openBam(
args.bamfile1, returnStats=True, nThreads=args.numberOfProcessors)
bam1.close()
bam2, mapped2, unmapped2, stats2 = bamHandler.openBam(
args.bamfile2, returnStats=True, nThreads=args.numberOfProcessors)
bam2.close()
scale_factors = get_scale_factors(args, [stats1, stats2],
[mapped1, mapped2])
if scale_factors is None:
# check whether one of the depth norm methods are selected
if args.normalizeUsing is not None:
args.scaleFactor = 1.0
# if a normalization is required then compute the scale factors
args.bam = args.bamfile1
scale_factor_bam1 = get_scale_factor(args, stats1)
args.bam = args.bamfile2
scale_factor_bam2 = get_scale_factor(args, stats2)
scale_factors = [scale_factor_bam1, scale_factor_bam2]
else:
scale_factors = [1, 1]
if args.verbose:
print("Individual scale factors are {0}".format(scale_factors))
# the getRatio function is called and receives
# the func_args per each tile that is considered
FUNC = getRatio
func_args = {
'valueType': args.operation,
'scaleFactors': scale_factors,
'pseudocount': args.pseudocount
}
wr = writeBedGraph.WriteBedGraph(
[args.bamfile1, args.bamfile2],
args.binSize,
0,
stepSize=args.binSize,
region=args.region,
numberOfProcessors=args.numberOfProcessors,
extendReads=args.extendReads,
blackListFileName=args.blackListFileName,
minMappingQuality=args.minMappingQuality,
ignoreDuplicates=args.ignoreDuplicates,
center_read=args.centerReads,
zerosToNans=args.skipNonCoveredRegions,
skipZeroOverZero=args.skipZeroOverZero,
samFlag_include=args.samFlagInclude,
samFlag_exclude=args.samFlagExclude,
minFragmentLength=args.minFragmentLength,
maxFragmentLength=args.maxFragmentLength,
chrsToSkip=args.ignoreForNormalization,
verbose=args.verbose)
wr.run(FUNC,
func_args,
args.outFileName,
blackListFileName=args.blackListFileName,
format=args.outFileFormat,
smoothLength=args.smoothLength)
def main(args=None):
args = process_args(args)
global debug
if args.verbose:
debug = 1
else:
debug = 0
if args.normalizeTo1x or args.normalizeUsingRPKM:
# if a normalization is required then compute the scale factors
scale_factor = get_scale_factor(args)
else:
scale_factor = args.scaleFactor
func_args = {'scaleFactor': scale_factor}
if args.MNase:
# check that library is paired end
# using getFragmentAndReadSize
from deeptools.getFragmentAndReadSize import get_read_and_fragment_length
frag_len_dict, read_len_dict = get_read_and_fragment_length(args.bam,
return_lengths=False,
blackListFileName=args.blackListFileName,
numberOfProcessors=args.numberOfProcessors,
verbose=args.verbose)
if frag_len_dict is None:
sys.exit("*Error*: For the --MNAse function a paired end library is required. ")
# Set some default fragment length bounds
if args.minFragmentLength == 0:
args.minFragmentLength = 130
if args.maxFragmentLength == 0:
args.maxFragmentLength = 200
wr = CenterFragment([args.bam],
binLength=args.binSize,
stepSize=args.binSize,
region=args.region,
blackListFileName=args.blackListFileName,
numberOfProcessors=args.numberOfProcessors,
extendReads=args.extendReads,
minMappingQuality=args.minMappingQuality,
ignoreDuplicates=args.ignoreDuplicates,
center_read=args.centerReads,
zerosToNans=args.skipNonCoveredRegions,
samFlag_include=args.samFlagInclude,
samFlag_exclude=args.samFlagExclude,
minFragmentLength=args.minFragmentLength,
maxFragmentLength=args.maxFragmentLength,
verbose=args.verbose,
)
elif args.Offset:
if len(args.Offset) > 1:
if args.Offset[0] == 0:
sys.exit("*Error*: An offset of 0 isn't allowed, since offsets are 1-based positions inside each alignment.")
if args.Offset[1] > 0 and args.Offset[1] < args.Offset[0]:
sys.exir("'Error*: The right side bound is less than the left-side bound. This is inappropriate.")
else:
if args.Offset[0] == 0:
sys.exit("*Error*: An offset of 0 isn't allowed, since offsets are 1-based positions inside each alignment.")
wr = OffsetFragment([args.bam],
binLength=args.binSize,
stepSize=args.binSize,
region=args.region,
numberOfProcessors=args.numberOfProcessors,
extendReads=args.extendReads,
minMappingQuality=args.minMappingQuality,
ignoreDuplicates=args.ignoreDuplicates,
center_read=args.centerReads,
zerosToNans=args.skipNonCoveredRegions,
samFlag_include=args.samFlagInclude,
samFlag_exclude=args.samFlagExclude,
minFragmentLength=args.minFragmentLength,
maxFragmentLength=args.maxFragmentLength,
verbose=args.verbose)
wr.filter_strand = args.filterRNAstrand
wr.Offset = args.Offset
elif args.filterRNAstrand:
wr = filterRnaStrand([args.bam],
binLength=args.binSize,
stepSize=args.binSize,
region=args.region,
numberOfProcessors=args.numberOfProcessors,
extendReads=args.extendReads,
minMappingQuality=args.minMappingQuality,
ignoreDuplicates=args.ignoreDuplicates,
center_read=args.centerReads,
zerosToNans=args.skipNonCoveredRegions,
samFlag_include=args.samFlagInclude,
samFlag_exclude=args.samFlagExclude,
minFragmentLength=args.minFragmentLength,
maxFragmentLength=args.maxFragmentLength,
verbose=args.verbose,
)
wr.filter_strand = args.filterRNAstrand
else:
wr = writeBedGraph.WriteBedGraph([args.bam],
binLength=args.binSize,
stepSize=args.binSize,
region=args.region,
blackListFileName=args.blackListFileName,
numberOfProcessors=args.numberOfProcessors,
extendReads=args.extendReads,
minMappingQuality=args.minMappingQuality,
ignoreDuplicates=args.ignoreDuplicates,
center_read=args.centerReads,
zerosToNans=args.skipNonCoveredRegions,
samFlag_include=args.samFlagInclude,
samFlag_exclude=args.samFlagExclude,
minFragmentLength=args.minFragmentLength,
maxFragmentLength=args.maxFragmentLength,
verbose=args.verbose,
)
wr.run(writeBedGraph.scaleCoverage, func_args, args.outFileName,
blackListFileName=args.blackListFileName,
format=args.outFileFormat, smoothLength=args.smoothLength)
def main(args=None):
"""
The algorithm is composed of two steps.
1. Per-sample scaling / depth Normalization:
+ If scaling is used (using the SES or read counts method), appropriate scaling
factors are determined to account for sequencing depth differences.
+ Optionally scaling can be turned off and individual samples could be depth normalized using
RPKM, BPM or CPM methods
2. Ratio calculation between two bam files:
+ The genome is transversed and computing
the log ratio/ratio/difference etc. for bins of fixed width
given by the user.
"""
args = process_args(args)
if args.normalizeUsing == "RPGC":
sys.exit("RPGC normalization (--normalizeUsing RPGC) is not supported with bamCompare!")
if args.normalizeUsing == 'None':
args.normalizeUsing = None # For the sake of sanity
if args.scaleFactorsMethod != 'None' and args.normalizeUsing:
sys.exit("`--normalizeUsing {}` is only valid if you also use `--scaleFactorMethod None`! To prevent erroneous output, I will quit now.\n".format(args.normalizeUsing))
# Get mapping statistics
bam1, mapped1, unmapped1, stats1 = bamHandler.openBam(args.bamfile1, returnStats=True, nThreads=args.numberOfProcessors)
bam1.close()
bam2, mapped2, unmapped2, stats2 = bamHandler.openBam(args.bamfile2, returnStats=True, nThreads=args.numberOfProcessors)
bam2.close()
scale_factors = get_scale_factors(args, [stats1, stats2], [mapped1, mapped2])
if scale_factors is None:
# check whether one of the depth norm methods are selected
if args.normalizeUsing is not None:
args.scaleFactor = 1.0
# if a normalization is required then compute the scale factors
args.bam = args.bamfile1
scale_factor_bam1 = get_scale_factor(args, stats1)
args.bam = args.bamfile2
scale_factor_bam2 = get_scale_factor(args, stats2)
scale_factors = [scale_factor_bam1, scale_factor_bam2]
else:
scale_factors = [1, 1]
if args.verbose:
print("Individual scale factors are {0}".format(scale_factors))
# the getRatio function is called and receives
# the func_args per each tile that is considered
FUNC = getRatio
func_args = {'valueType': args.operation,
'scaleFactors': scale_factors,
'pseudocount': args.pseudocount
}
wr = writeBedGraph.WriteBedGraph([args.bamfile1, args.bamfile2], args.binSize, 0,
stepSize=args.binSize,
region=args.region,
numberOfProcessors=args.numberOfProcessors,
extendReads=args.extendReads,
blackListFileName=args.blackListFileName,
minMappingQuality=args.minMappingQuality,
ignoreDuplicates=args.ignoreDuplicates,
center_read=args.centerReads,
zerosToNans=args.skipNonCoveredRegions,
skipZeroOverZero=args.skipZeroOverZero,
samFlag_include=args.samFlagInclude,
samFlag_exclude=args.samFlagExclude,
minFragmentLength=args.minFragmentLength,
maxFragmentLength=args.maxFragmentLength,
chrsToSkip=args.ignoreForNormalization,
verbose=args.verbose
)
wr.run(FUNC, func_args, args.outFileName, blackListFileName=args.blackListFileName, format=args.outFileFormat, smoothLength=args.smoothLength)