def test_fastq_bam(self):
myInputDir = util.file.get_test_input_path(self)
# Define file names
inFastq1 = os.path.join(myInputDir, 'in1.fastq')
inFastq2 = os.path.join(myInputDir, 'in2.fastq')
inHeader = os.path.join(myInputDir, 'inHeader.txt')
expected1_7Sam = os.path.join(myInputDir, 'expected.java1_7.sam')
expected1_8Sam = os.path.join(myInputDir, 'expected.java1_8.sam')
expected1_8Sam_v15 = os.path.join(myInputDir, 'expected.java1_8_v1.5.sam')
expectedFastq1 = os.path.join(myInputDir, 'expected.fastq1')
outBamCmd = util.file.mkstempfname('.bam')
outBamTxt = util.file.mkstempfname('.bam')
outSam = util.file.mkstempfname('.sam')
outFastq1 = util.file.mkstempfname('.fastq')
outFastq2 = util.file.mkstempfname('.fastq')
outHeader = util.file.mkstempfname('.txt')
outHeaderFix = util.file.mkstempfname('.fix.txt')
# in1.fastq, in2.fastq -> out.bam; header params from command-line
parser = read_utils.parser_fastq_to_bam(argparse.ArgumentParser())
args = parser.parse_args([inFastq1,
inFastq2,
outBamCmd,
'--sampleName',
'FreeSample',
'--JVMmemory',
'1g',
'--picardOptions',
'LIBRARY_NAME=Alexandria',
'PLATFORM=9.75',
'SEQUENCING_CENTER=KareemAbdul-Jabbar',])
args.func_main(args)
# Note for developers: if you're fixing the tests to handle non-bugs
# (ie our testing here is too brittle), let's just replace a lot of this
# in the future with code that just reads the header, sorts it, and
# tests for equality of sorted values in the RG line (and stricter
# equality in the non-header lines). This is kind of hacky.
# samtools view for out.sam and compare to expected
samtools = tools.samtools.SamtoolsTool()
samtools.view(['-h'], outBamCmd, outSam)
# picard.sam.FastqToSam outputs header fields in different order for
# java version 1.8 vs 1.7/1.6, so compare both
self.assertTrue(filecmp.cmp(outSam,
expected1_7Sam,
shallow=False) or filecmp.cmp(outSam,
expected1_8Sam,
shallow=False) or
filecmp.cmp(outSam,
expected1_8Sam_v15,
shallow=False))
# in1.fastq, in2.fastq, inHeader.txt -> out.bam; header from txt
parser = read_utils.parser_fastq_to_bam(argparse.ArgumentParser())
args = parser.parse_args([inFastq1, inFastq2, outBamTxt, '--header', inHeader])
args.func_main(args)
def test_fastq_bam(self):
myInputDir = util.file.get_test_input_path(self)
# Define file names
inFastq1 = os.path.join(myInputDir, 'in1.fastq')
inFastq2 = os.path.join(myInputDir, 'in2.fastq')
inHeader = os.path.join(myInputDir, 'inHeader.txt')
expected1_7Sam = os.path.join(myInputDir, 'expected.java1_7.sam')
expected1_8Sam = os.path.join(myInputDir, 'expected.java1_8.sam')
expected1_8Sam_v15 = os.path.join(myInputDir, 'expected.java1_8_v1.5.sam')
expectedFastq1 = os.path.join(myInputDir, 'expected.fastq1')
outBamCmd = util.file.mkstempfname('.bam')
outBamTxt = util.file.mkstempfname('.bam')
outSam = util.file.mkstempfname('.sam')
outFastq1 = util.file.mkstempfname('.fastq')
outFastq2 = util.file.mkstempfname('.fastq')
outHeader = util.file.mkstempfname('.txt')
outHeaderFix = util.file.mkstempfname('.fix.txt')
# in1.fastq, in2.fastq -> out.bam; header params from command-line
parser = read_utils.parser_fastq_to_bam(argparse.ArgumentParser())
args = parser.parse_args([inFastq1,
inFastq2,
outBamCmd,
'--sampleName',
'FreeSample',
'--JVMmemory',
'1g',
'--picardOptions',
'LIBRARY_NAME=Alexandria',
'PLATFORM=9.75',
'SEQUENCING_CENTER=KareemAbdul-Jabbar',])
args.func_main(args)
# Note for developers: if you're fixing the tests to handle non-bugs
# (ie our testing here is too brittle), let's just replace a lot of this
# in the future with code that just reads the header, sorts it, and
# tests for equality of sorted values in the RG line (and stricter
# equality in the non-header lines). This is kind of hacky.
# samtools view for out.sam and compare to expected
samtools = tools.samtools.SamtoolsTool()
samtools.view(['-h'], outBamCmd, outSam)
# picard.sam.FastqToSam outputs header fields in different order for
# java version 1.8 vs 1.7/1.6, so compare both
self.assertTrue(filecmp.cmp(outSam,
expected1_7Sam,
shallow=False) or filecmp.cmp(outSam,
expected1_8Sam,
shallow=False) or
filecmp.cmp(outSam,
expected1_8Sam_v15,
shallow=False))
# in1.fastq, in2.fastq, inHeader.txt -> out.bam; header from txt
parser = read_utils.parser_fastq_to_bam(argparse.ArgumentParser())
args = parser.parse_args([inFastq1, inFastq2, outBamTxt, '--header', inHeader])
args.func_main(args)
def test_fastq_bam(self) :
myInputDir = util.file.get_test_input_path(self)
# Define file names
inFastq1 = os.path.join(myInputDir, 'in1.fastq')
inFastq2 = os.path.join(myInputDir, 'in2.fastq')
inHeader = os.path.join(myInputDir, 'inHeader.txt')
expected1_7Sam = os.path.join(myInputDir, 'expected.java1_7.sam')
expected1_8Sam = os.path.join(myInputDir, 'expected.java1_8.sam')
expectedFastq1 = os.path.join(myInputDir, 'expected.fastq1')
outBamCmd = util.file.mkstempfname('.bam')
outBamTxt = util.file.mkstempfname('.bam')
outSam = util.file.mkstempfname('.sam')
outFastq1 = util.file.mkstempfname('.fastq')
outFastq2 = util.file.mkstempfname('.fastq')
outHeader = util.file.mkstempfname('.txt')
# in1.fastq, in2.fastq -> out.bam; header params from command-line
parser = read_utils.parser_fastq_to_bam(argparse.ArgumentParser())
args = parser.parse_args([inFastq1, inFastq2, outBamCmd,
'--sampleName', 'FreeSample',
'--JVMmemory', '1g',
'--picardOptions',
'LIBRARY_NAME=Alexandria',
'PLATFORM=9.75',
'SEQUENCING_CENTER=KareemAbdul-Jabbar',
])
args.func_main(args)
# samtools view for out.sam and compare to expected
samtools = tools.samtools.SamtoolsTool()
samtools.view(['-h'], outBamCmd, outSam)
# picard.sam.FastqToSam outputs header fields in different order for
# java version 1.8 vs 1.7/1.6, so compare both
self.assertTrue(filecmp.cmp(outSam, expected1_7Sam, shallow=False) or
filecmp.cmp(outSam, expected1_8Sam, shallow=False))
# in1.fastq, in2.fastq, inHeader.txt -> out.bam; header from txt
parser = read_utils.parser_fastq_to_bam(argparse.ArgumentParser())
args = parser.parse_args([inFastq1, inFastq2, outBamTxt,
'--header', inHeader])
args.func_main(args)
# out.bam -> out1.fastq, out2.fastq, outHeader.txt; trim 1 base from 1
parser = read_utils.parser_bam_to_fastq(argparse.ArgumentParser())
args = parser.parse_args([outBamTxt, outFastq1, outFastq2,
'--outHeader', outHeader,
'--JVMmemory', '1g',
'--picardOptions', 'READ1_TRIM=1',
])
args.func_main(args)
# compare to out1.fastq, out2.fastq, outHeader.txt to in and expected
self.assertEqualContents(outFastq1, expectedFastq1) # 1 base trimmed
self.assertEqualContents(outFastq2, inFastq2)
self.assertEqualContents(outHeader, inHeader)
def test_fastq_bam(self) :
myInputDir = util.file.get_test_input_path(self)
# Define file names
inFastq1 = os.path.join(myInputDir, 'in1.fastq')
inFastq2 = os.path.join(myInputDir, 'in2.fastq')
inHeader = os.path.join(myInputDir, 'inHeader.txt')
expectedSam = os.path.join(myInputDir, 'expected.sam')
expectedFastq1 = os.path.join(myInputDir, 'expected.fastq1')
outBamCmd = util.file.mkstempfname('.bam')
outBamTxt = util.file.mkstempfname('.bam')
outSam = util.file.mkstempfname('.sam')
outFastq1 = util.file.mkstempfname('.fastq')
outFastq2 = util.file.mkstempfname('.fastq')
outHeader = util.file.mkstempfname('.txt')
# in1.fastq, in2.fastq -> out.bam; header params from command-line
parser = read_utils.parser_fastq_to_bam()
args = parser.parse_args([inFastq1, inFastq2, outBamCmd,
'--sampleName', 'FreeSample',
'--JVMmemory', '1g',
'--picardOptions',
'LIBRARY_NAME=Alexandria',
'PLATFORM=9.75',
'SEQUENCING_CENTER=KareemAbdul-Jabbar',
])
read_utils.main_fastq_to_bam(args)
# samtools view for out.sam and compare to expected
samtools = tools.samtools.SamtoolsTool()
samtools.execute('view', ['-h', outBamCmd], stdout=outSam)
self.assertEqualContents(outSam, expectedSam)
# in1.fastq, in2.fastq, inHeader.txt -> out.bam; header from txt
parser = read_utils.parser_fastq_to_bam()
args = parser.parse_args([inFastq1, inFastq2, outBamTxt,
'--header', inHeader])
read_utils.main_fastq_to_bam(args)
# out.bam -> out1.fastq, out2.fastq, outHeader.txt; trim 1 base from 1
parser = read_utils.parser_bam_to_fastq()
args = parser.parse_args([outBamTxt, outFastq1, outFastq2,
'--outHeader', outHeader,
'--JVMmemory', '1g',
'--picardOptions', 'READ1_TRIM=1',
])
read_utils.main_bam_to_fastq(args)
# compare to out1.fastq, out2.fastq, outHeader.txt to in and expected
self.assertEqualContents(outFastq1, expectedFastq1) # 1 base trimmed
self.assertEqualContents(outFastq2, inFastq2)
self.assertEqualContents(outHeader, inHeader)
def test_fastq_bam(self):
myInputDir = util.file.get_test_input_path(self)
# Define file names
inFastq1 = os.path.join(myInputDir, 'in1.fastq')
inFastq2 = os.path.join(myInputDir, 'in2.fastq')
inHeader = os.path.join(myInputDir, 'inHeader.txt')
expected1_7Sam = os.path.join(myInputDir, 'expected.java1_7.sam')
expected1_8Sam = os.path.join(myInputDir, 'expected.java1_8.sam')
expected1_8Sam_v15 = os.path.join(myInputDir,
'expected.java1_8_v1.5.sam')
expectedFastq1 = os.path.join(myInputDir, 'expected.fastq1')
outBamCmd = util.file.mkstempfname('.bam')
outBamTxt = util.file.mkstempfname('.bam')
outSam = util.file.mkstempfname('.sam')
outFastq1 = util.file.mkstempfname('.fastq')
outFastq2 = util.file.mkstempfname('.fastq')
outHeader = util.file.mkstempfname('.txt')
outHeaderFix = util.file.mkstempfname('.fix.txt')
# in1.fastq, in2.fastq -> out.bam; header params from command-line
parser = read_utils.parser_fastq_to_bam(argparse.ArgumentParser())
args = parser.parse_args([
inFastq1,
inFastq2,
outBamCmd,
'--sampleName',
'FreeSample',
'--JVMmemory',
'1g',
'--picardOptions',
'LIBRARY_NAME=Alexandria',
'PLATFORM=9.75',
'SEQUENCING_CENTER=KareemAbdul-Jabbar',
])
args.func_main(args)
alternate_expected_vals = {"VN": ["1.4", "1.5", "1.6", "1.7"]}
self.assertEqualSamHeaders(
outBamCmd,
expected1_7Sam,
other_allowed_values=alternate_expected_vals)
assert_equal_bam_reads(self, outBamCmd, expected1_7Sam)
parser = read_utils.parser_fastq_to_bam(argparse.ArgumentParser())
args = parser.parse_args(
[inFastq1, inFastq2, outBamTxt, '--header', inHeader])
args.func_main(args)
def test_deplete_blastn_bam(self):
tempDir = tempfile.mkdtemp()
myInputDir = util.file.get_test_input_path(self)
# Make blast databases
makeblastdbPath = tools.blast.MakeblastdbTool().install_and_get_path()
dbnames = ['humanChr1Subset.fa', 'humanChr9Subset.fa']
refDbs = []
for dbname in dbnames:
refDb = os.path.join(tempDir, dbname)
os.symlink(os.path.join(myInputDir, dbname), refDb)
refDbs.append(refDb)
subprocess.check_call([makeblastdbPath, '-dbtype', 'nucl', '-in', refDb])
# convert the input fastq's to a bam
inFastq1 = os.path.join(myInputDir, "in1.fastq")
inFastq2 = os.path.join(myInputDir, "in2.fastq")
inBam = os.path.join(tempDir, 'in.bam')
parser = read_utils.parser_fastq_to_bam(argparse.ArgumentParser())
args = parser.parse_args([inFastq1,
inFastq2,
inBam,
'--sampleName',
'FreeSample',
'--JVMmemory',
'1g',
'--picardOptions',
'LIBRARY_NAME=Alexandria',
'PLATFORM=9.75',
'SEQUENCING_CENTER=KareemAbdul-Jabbar',])
args.func_main(args)
# Run deplete_blastn_bam
outBam = os.path.join(tempDir, 'out.bam')
args = taxon_filter.parser_deplete_blastn_bam(argparse.ArgumentParser()).parse_args(
[inBam, refDbs[0], refDbs[1], outBam, "--chunkSize", "1"])
args.func_main(args)
# samtools view for out.sam and compare to expected
outSam = os.path.join(tempDir, 'out.sam')
samtools = tools.samtools.SamtoolsTool()
samtools.view(['-h'], outBam, outSam)
with open(outSam, "r") as outSamFile:
for line in outSamFile.readlines():
print(line)
# the header field ordering may be different with Java 1.8
self.assertTrue(filecmp.cmp(outSam,
os.path.join(myInputDir, 'expected.sam'),
shallow=False) or
filecmp.cmp(outSam,
os.path.join(myInputDir, 'expected_1_8.sam'),
shallow=False) or
filecmp.cmp(outSam,
os.path.join(myInputDir, 'expected_alt_v1.5.sam'),
shallow=False) or
filecmp.cmp(outSam,
os.path.join(myInputDir, 'expected_1_8_v1.5.sam'),
shallow=False))
def test_fastq_bam(self):
myInputDir = util.file.get_test_input_path(self)
# Define file names
inFastq1 = os.path.join(myInputDir, 'in1.fastq')
inFastq2 = os.path.join(myInputDir, 'in2.fastq')
inHeader = os.path.join(myInputDir, 'inHeader.txt')
expected1_7Sam = os.path.join(myInputDir, 'expected.java1_7.sam')
expected1_8Sam = os.path.join(myInputDir, 'expected.java1_8.sam')
expected1_8Sam_v15 = os.path.join(myInputDir,
'expected.java1_8_v1.5.sam')
expectedFastq1 = os.path.join(myInputDir, 'expected.fastq1')
outBamCmd = util.file.mkstempfname('.bam')
outBamTxt = util.file.mkstempfname('.bam')
outSam = util.file.mkstempfname('.sam')
outFastq1 = util.file.mkstempfname('.fastq')
outFastq2 = util.file.mkstempfname('.fastq')
outHeader = util.file.mkstempfname('.txt')
# in1.fastq, in2.fastq -> out.bam; header params from command-line
parser = read_utils.parser_fastq_to_bam(argparse.ArgumentParser())
args = parser.parse_args([
inFastq1,
inFastq2,
outBamCmd,
'--sampleName',
'FreeSample',
'--JVMmemory',
'1g',
'--picardOptions',
'LIBRARY_NAME=Alexandria',
'PLATFORM=9.75',
'SEQUENCING_CENTER=KareemAbdul-Jabbar',
])
args.func_main(args)
# samtools view for out.sam and compare to expected
samtools = tools.samtools.SamtoolsTool()
samtools.view(['-h'], outBamCmd, outSam)
# picard.sam.FastqToSam outputs header fields in different order for
# java version 1.8 vs 1.7/1.6, so compare both
self.assertTrue(
filecmp.cmp(outSam, expected1_7Sam, shallow=False)
or filecmp.cmp(outSam, expected1_8Sam, shallow=False)
or filecmp.cmp(outSam, expected1_8Sam_v15, shallow=False))
# in1.fastq, in2.fastq, inHeader.txt -> out.bam; header from txt
parser = read_utils.parser_fastq_to_bam(argparse.ArgumentParser())
args = parser.parse_args(
[inFastq1, inFastq2, outBamTxt, '--header', inHeader])
args.func_main(args)
# out.bam -> out1.fastq, out2.fastq, outHeader.txt; trim 1 base from 1
parser = read_utils.parser_bam_to_fastq(argparse.ArgumentParser())
args = parser.parse_args([
outBamTxt,
outFastq1,
outFastq2,
'--outHeader',
outHeader,
'--JVMmemory',
'1g',
'--picardOptions',
'READ1_TRIM=1',
])
args.func_main(args)
# compare to out1.fastq, out2.fastq, outHeader.txt to in and expected
self.assertEqualContents(outFastq1, expectedFastq1) # 1 base trimmed
self.assertEqualContents(outFastq2, inFastq2)
self.assertEqualContents(outHeader, inHeader)