def test_bam_coverage_filter_blacklist():
"""
Test --samFlagInclude --samFlagExclude --minMappingQuality --ignoreDuplicates and --blackListFileName
"""
outfile = '/tmp/test_file_filter.bg'
for fname in [BAMFILE_FILTER1, CRAMFILE_FILTER1]:
args = "--bam {} --normalizeUsing RPGC --effectiveGenomeSize 1400 -p 1 -o {} -of bedgraph --samFlagInclude 512 " \
"--samFlagExclude 256 --minMappingQuality 5 --ignoreDuplicates " \
"--blackListFileName {}".format(fname, outfile, BEDFILE_FILTER)
args = args.split()
bam_cov.main(args)
_foo = open(outfile, 'r')
resp = _foo.readlines()
_foo.close()
expected = ['3R\t0\t100\t0\n', '3R\t100\t150\t1.42338\n',
'3R\t150\t250\t4.88017\n', '3R\t250\t300\t3.05011\n',
'3R\t300\t400\t2.23675\n', '3R\t400\t450\t3.86347\n',
'3R\t450\t500\t4.06681\n', '3R\t500\t550\t2.03341\n',
'3R\t550\t600\t2.44009\n', '3R\t600\t650\t4.47349\n',
'3R\t650\t700\t3.45679\n', '3R\t700\t750\t3.66013\n',
'3R\t750\t800\t4.06681\n', '3R\t900\t950\t2.44009\n',
'3R\t950\t1000\t1.62672\n', '3R\t1000\t1050\t0.813362\n',
'3R\t1050\t1500\t0\n']
assert_equal(resp, expected)
unlink(outfile)
def test_bam_coverage_filter_blacklist():
"""
Test --samFlagInclude --samFlagExclude --minMappingQuality --ignoreDuplicates and --blackListFileName
"""
outfile = '/tmp/test_file_filter.bg'
args = "--bam {} --normalizeTo1x 1400 -p 1 -o {} -of bedgraph --samFlagInclude 512 " \
"--samFlagExclude 256 --minMappingQuality 5 --ignoreDuplicates " \
"--blackListFileName {}".format(BAMFILE_FILTER1, outfile, BEDFILE_FILTER)
args = args.split()
bam_cov.main(args)
_foo = open(outfile, 'r')
resp = _foo.readlines()
_foo.close()
expected = [
'3R\t0\t100\t0\n', '3R\t100\t150\t1.42338\n',
'3R\t150\t250\t4.88017\n', '3R\t250\t300\t3.05011\n',
'3R\t300\t400\t2.23675\n', '3R\t400\t450\t3.86347\n',
'3R\t450\t500\t4.06681\n', '3R\t500\t550\t2.03341\n',
'3R\t550\t600\t2.44009\n', '3R\t600\t650\t4.47349\n',
'3R\t650\t700\t3.45679\n', '3R\t700\t750\t3.66013\n',
'3R\t750\t800\t4.06681\n', '3R\t900\t950\t2.44009\n',
'3R\t950\t1000\t1.62672\n', '3R\t1000\t1050\t0.813362\n',
'3R\t1050\t1500\t0\n'
]
assert_equal(resp, expected)
unlink(outfile)
def test_bam_coverage_extend():
outfile = '/tmp/test_file.bg'
args = "-b {} -o {} --extendReads 100 --outFileFormat bedgraph".format(BAMFILE_B, outfile).split()
bam_cov.main(args)
resp = open(outfile, 'r').readlines()
assert resp == ['3R\t0\t150\t1.00\n', '3R\t150\t200\t3.0\n']
unlink(outfile)
def produce_bamCoverage(Type, bamFile, basenameNoExtension, NumberCpus,
binSize, blackListFileName, effectiveGenomeSize,
normalizeUsing):
outFileBW = basenameNoExtension + "_" + Type + "_.bw"
args_bamCoverage="-b {} -o {} --numberOfProcessors {} --binSize {} --blackListFileName {} --effectiveGenomeSize {} --normalizeUsing {} " \
"--outFileFormat bigwig".format(bamFile, outFileBW, NumberCpus, binSize, blackListFileName,effectiveGenomeSize,normalizeUsing).split()
bamCoverage.main(args_bamCoverage)
return outFileBW
def test_bam_coverage_skipnas():
outfile = '/tmp/test_file.bg'
args = "--bam {} -o {} --outFileFormat bedgraph --skipNAs".format(BAMFILE_B, outfile).split()
bam_cov.main(args)
resp = open(outfile, 'r').readlines()
expected = ['3R\t50\t150\t1.00\n', '3R\t150\t200\t2.0\n']
assert resp == expected, "{} != {}".format(resp, expected)
unlink(outfile)
def createBedGraphFile(bamFileSorted, cpus):
basenameNoExtension = os.path.splitext(os.path.basename(bamFileSorted))[0]
inputNameBAM = os.path.abspath(bamFileSorted)
outNameBW = basenameNoExtension + ".bedgraph"
args_bamCoverage = "-b {} -o {} --numberOfProcessors {} --binSize 1 " \
"--outFileFormat bedgraph".format(inputNameBAM, outNameBW, cpus).split()
bamCoverage.main(args_bamCoverage)
return basenameNoExtension + ".bedgraph"
def test_bam_coverage_extend():
outfile = '/tmp/test_file.bg'
args = "-b {} -o {} --extendReads 100 --outFileFormat bedgraph".format(BAMFILE_B, outfile).split()
bam_cov.main(args)
_foo = open(outfile, 'r')
resp = _foo.readlines()
_foo.close()
expected = ['3R\t0\t150\t1\n', '3R\t150\t200\t3\n']
assert_equal(resp, expected)
unlink(outfile)
def test_bam_coverage_filtering():
outfile = '/tmp/test_file.bg'
args = "--bam {} -o {} --outFileFormat bedgraph --ignoreDuplicates --verbose".format(BAMFILE_B, outfile).split()
bam_cov.main(args)
_foo = open(outfile, 'r')
resp = _foo.readlines()
_foo.close()
expected = ['3R\t0\t50\t0\n', '3R\t50\t200\t1\n']
assert_equal(resp, expected)
unlink(outfile)
def test_bam_coverage_extend():
outfile = '/tmp/test_file.bg'
args = "-b {} -o {} --extendReads 100 --outFileFormat bedgraph".format(
BAMFILE_B, outfile).split()
bam_cov.main(args)
_foo = open(outfile, 'r')
resp = _foo.readlines()
_foo.close()
expected = ['3R\t0\t150\t1\n', '3R\t150\t200\t3\n']
assert_equal(resp, expected)
unlink(outfile)
def test_bam_coverage_extend_and_normalizeto1x():
outfile = '/tmp/test_file.bg'
args = "-b {} -o {} --normalizeTo1x 200 --extendReads 100 " \
"--outFileFormat bedgraph".format(BAMFILE_B, outfile).split()
bam_cov.main(args)
resp = open(outfile, 'r').readlines()
# the scale factor should be 0.5, thus the result is similar to
# that of the previous test divided by 0.5
expected = ['3R\t0\t150\t0.50\n', '3R\t150\t200\t1.5\n']
assert resp == expected, "{} != {}".format(resp, expected)
unlink(outfile)
def test_bam_coverage_arguments():
"""
Test minimal command line args for bamCoverage
"""
outfile = '/tmp/test_file.bg'
args = "--bam {} -o {} --outFileFormat bedgraph".format(BAMFILE_B, outfile).split()
bam_cov.main(args)
resp = open(outfile, 'r').readlines()
expected = ['3R\t0\t50\t0.00\n', '3R\t50\t150\t1.00\n', '3R\t150\t200\t2.0\n']
assert resp == expected, "{} != {}".format(resp, expected)
unlink(outfile)
def test_bam_coverage_skipnas():
outfile = '/tmp/test_file.bg'
for fname in [BAMFILE_B, CRAMFILE_B]:
args = "--bam {} -o {} --outFileFormat bedgraph --skipNAs".format(fname, outfile).split()
bam_cov.main(args)
_foo = open(outfile, 'r')
resp = _foo.readlines()
_foo.close()
expected = ['3R\t50\t150\t1\n', '3R\t150\t200\t2\n']
assert_equal(resp, expected)
unlink(outfile)
def test_bam_coverage_skipnas():
outfile = '/tmp/test_file.bg'
args = "--bam {} -o {} --outFileFormat bedgraph --skipNAs".format(
BAMFILE_B, outfile).split()
bam_cov.main(args)
_foo = open(outfile, 'r')
resp = _foo.readlines()
_foo.close()
expected = ['3R\t50\t150\t1\n', '3R\t150\t200\t2\n']
assert_equal(resp, expected)
unlink(outfile)
def test_bam_coverage_filtering():
outfile = '/tmp/test_file.bg'
for fname in [BAMFILE_B, CRAMFILE_B]:
args = "--bam {} -o {} --outFileFormat bedgraph --ignoreDuplicates --verbose".format(
fname, outfile).split()
bam_cov.main(args)
_foo = open(outfile, 'r')
resp = _foo.readlines()
_foo.close()
expected = ['3R\t0\t50\t0\n', '3R\t50\t200\t1\n']
assert_equal(resp, expected)
unlink(outfile)
def test_bam_coverage_arguments():
"""
Test minimal command line args for bamCoverage
"""
outfile = '/tmp/test_file.bg'
args = "--bam {} -o {} --outFileFormat bedgraph".format(BAMFILE_B, outfile).split()
bam_cov.main(args)
_foo = open(outfile, 'r')
resp = _foo.readlines()
_foo.close()
expected = ['3R\t0\t50\t0\n', '3R\t50\t150\t1\n', '3R\t150\t200\t2\n']
assert_equal(resp, expected)
unlink(outfile)
def test_bam_coverage_offset20_minus4():
"""
Test -bs 1 --Offset 20 -4
"""
outfile = '/tmp/test_offset.bw'
args = "--Offset 20 -4 -b {} -p 1 -bs 1 -o {}".format(BAMFILE_A, outfile)
args = args.split()
bam_cov.main(args)
try:
# python 3 only
filecmp.clear_cache()
except:
pass
assert(filecmp.cmp(outfile, "{}testA_offset20_-4.bw".format(ROOT)) is True)
unlink(outfile)
def test_bam_coverage_extend_and_normalizeUsingRPGC():
outfile = '/tmp/test_file.bg'
for fname in [BAMFILE_B, CRAMFILE_B]:
args = "-b {} -o {} --normalizeUsing RPGC --effectiveGenomeSize 200 --extendReads 100 " \
"--outFileFormat bedgraph".format(fname, outfile).split()
bam_cov.main(args)
_foo = open(outfile, 'r')
resp = _foo.readlines()
_foo.close()
# the scale factor should be 0.5, thus the result is similar to
# that of the previous test divided by 0.5
expected = ['3R\t0\t150\t0.5\n', '3R\t150\t200\t1.5\n']
assert_equal(resp, expected)
unlink(outfile)
def test_bam_coverage_offset_minus1():
"""
Test -bs 1 --Offset -1
"""
outfile = '/tmp/test_offset.bw'
args = "--Offset -1 -b {} -p 1 -bs 1 -o {}".format(BAMFILE_A, outfile)
args = args.split()
bam_cov.main(args)
try:
# python 3 only
filecmp.clear_cache()
except:
pass
assert (filecmp.cmp(outfile, "{}testA_offset-1.bw".format(ROOT)) is True)
unlink(outfile)
def test_bam_coverage_arguments():
"""
Test minimal command line args for bamCoverage
"""
outfile = '/tmp/test_file.bg'
args = "--bam {} -o {} --outFileFormat bedgraph".format(
BAMFILE_B, outfile).split()
bam_cov.main(args)
_foo = open(outfile, 'r')
resp = _foo.readlines()
_foo.close()
expected = ['3R\t0\t50\t0\n', '3R\t50\t150\t1\n', '3R\t150\t200\t2\n']
assert_equal(resp, expected)
unlink(outfile)
def test_bam_coverage_extend_and_normalizeUsingRPGC():
outfile = '/tmp/test_file.bg'
for fname in [BAMFILE_B, CRAMFILE_B]:
args = "-b {} -o {} --normalizeUsing RPGC --effectiveGenomeSize 200 --extendReads 100 " \
"--outFileFormat bedgraph".format(fname, outfile).split()
bam_cov.main(args)
_foo = open(outfile, 'r')
resp = _foo.readlines()
_foo.close()
# the scale factor should be 0.5, thus the result is similar to
# that of the previous test divided by 0.5
expected = ['3R\t0\t150\t0.5\n', '3R\t150\t200\t1.5\n']
assert_equal(resp, expected)
unlink(outfile)
def test_bam_coverage_offset_minus1():
"""
Test -bs 1 --Offset -1
"""
outfile = '/tmp/test_offset.bw'
for fname in [BAMFILE_A, CRAMFILE_A]:
args = "--Offset -1 -b {} -p 1 -bs 1 -o {}".format(fname, outfile)
args = args.split()
bam_cov.main(args)
try:
# python 3 only
filecmp.clear_cache()
except:
pass
assert(filecmp.cmp(outfile, "{}testA_offset-1.bw".format(ROOT)) is True)
unlink(outfile)
def test_bam_coverage_offset20_minus4():
"""
Test -bs 1 --Offset 20 -4
"""
outfile = '/tmp/test_offset.bw'
for fname in [BAMFILE_A, CRAMFILE_A]:
args = "--Offset 20 -4 -b {} -p 1 -bs 1 -o {}".format(fname, outfile)
args = args.split()
bam_cov.main(args)
try:
# python 3 only
filecmp.clear_cache()
except:
pass
assert (filecmp.cmp(outfile, "{}testA_offset20_-4.bw".format(ROOT)) is
True)
unlink(outfile)