def deeptools_bamCoverage(self):
func_args = {'scaleFactor': 1.0}
from deeptools import bamCoverage
from deeptools import writeBedGraph
wr = writeBedGraph.WriteBedGraph(
[self.treat_bam, self.control_bam],
binLength=self.binSize,
stepSize=self.binSize,
region=None,
blackListFileName=None,
numberOfProcessors=self.numberOfProcessors,
extendReads=False,
minMappingQuality=None,
ignoreDuplicates=True,
center_read=False,
zerosToNans=False,
samFlag_include=None,
samFlag_exclude=None,
minFragmentLength=0,
maxFragmentLength=0,
verbose=True,
)
wr.run(
writeBedGraph.scaleCoverage,
func_args,
self.outFileName,
blackListFileName=None,
)
def setUp(self):
"""
The distribution of reads between the two bam files is as follows.
They cover 200 bp::
0 100 200
|------------------------------------------------------------|
A ==============>
<==============
B <============== ==============>
==============>
==============>
"""
self.root = ROOT
self.bamFile1 = self.root + "testA.bam"
self.bamFile2 = self.root + "testB.bam"
self.bamFile_PE = self.root + "test_paired2.bam"
self.chrom = '3R'
self.step_size = 50
self.bin_length = 50
self.func_args = {'scaleFactor': 1.0}
self.c = wr.WriteBedGraph([self.bamFile1],
binLength=self.bin_length,
stepSize=self.step_size)
def test_writeBedGraph_worker_ignore_duplicates(self):
self.c = wr.WriteBedGraph([self.bamFile2],
binLength=self.bin_length,
stepSize=self.step_size,
ignoreDuplicates=True)
self.c.zerosToNans = True
tempFile = self.c.writeBedGraph_worker('3R', 0, 200, scaleCoverage,
self.func_args)
res = open(tempFile, 'r').readlines()
assert_equal(res, ['3R\t50\t200\t1.0\n'])
os.remove(tempFile)
def main(args=None):
"""
The algorithm is composed of two parts.
1. Using the SES or read counts method, appropriate scaling
factors are determined to account for sequencing depth differences.
2. The genome is transversed, scaling the BAM files, and computing
the log ratio/ratio/difference for bins of fixed width
given by the user.
"""
args = process_args(args)
scale_factors = get_scale_factors(args)
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.ratio,
'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,
samFlag_include=args.samFlagInclude,
samFlag_exclude=args.samFlagExclude,
minFragmentLength=args.minFragmentLength,
maxFragmentLength=args.maxFragmentLength,
verbose=args.verbose)
wr.run(FUNC,
func_args,
args.outFileName,
blackListFileName=args.blackListFileName,
format=args.outFileFormat,
smoothLength=args.smoothLength)
def setUp(self):
"""
As above, but for CRAM files
"""
self.root = ROOT
self.bamFile1 = self.root + "testA.cram"
self.bamFile2 = self.root + "testB.cram"
self.bamFile_PE = self.root + "test_paired2.cram"
self.chrom = '3R'
self.step_size = 50
self.bin_length = 50
self.func_args = {'scaleFactor': 1.0}
self.c = wr.WriteBedGraph([self.bamFile1],
binLength=self.bin_length,
stepSize=self.step_size)
def deeptools_bamCompare(self):
print("++++++++++++++++++++++++++++++++++++++++++++++++++++++++")
print(self.name)
from deeptools import writeBedGraph
from deeptools.SES_scaleFactor import estimateScaleFactor
from deeptools import parserCommon
from deeptools import bamHandler
from deeptools import getRatio
from deeptools.getScaleFactor import get_num_kept_reads
debug = 0
FUNC = getRatio.getRatio
#log2,ratio,subtract,add,mean,reciprocal_ratio,first,second
func_args = {
'valueType': "ratio",
'scaleFactors': [1, 1],
'pseudocount': 1
}
from deeptools import writeBedGraph
wr = writeBedGraph.WriteBedGraph(
[self.treat_bam, self.control_bam],
self.binSize,
0,
stepSize=self.binSize,
region=None,
numberOfProcessors=self.numberOfProcessors,
extendReads=False,
blackListFileName=None,
minMappingQuality=None,
ignoreDuplicates=False,
center_read=False,
zerosToNans=False,
samFlag_include=None,
samFlag_exclude=None,
minFragmentLength=0,
maxFragmentLength=0,
verbose=True,
)
wr.run(FUNC, func_args, self.outFileName)
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:
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,
args.bamIndex,
return_lengths=False,
numberOfProcessors=args.numberOfProcessors,
verbose=args.verbose)
if frag_len_dict is None:
exit(
"*Error*: For the --MNAse function a paired end library is required. "
)
wr = CenterFragment(
[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,
verbose=args.verbose,
)
else:
wr = writeBedGraph.WriteBedGraph(
[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,
verbose=args.verbose,
)
wr.run(writeBedGraph.scaleCoverage,
func_args,
args.outFileName,
format=args.outFileFormat,
smooth_length=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)
