def buildBAMforPeakCalling(infiles, outfile, dedup, mask):
''' Make a BAM file suitable for peak calling.
Infiles are merged and unmapped reads removed.
If specificied duplicate reads are removed.
This method use Picard.
If a mask is specified, reads falling within
the mask are filtered out.
This uses bedtools.
The mask is a quicksect object containing
the regions from which reads are to be excluded.
'''
# open the infiles, if more than one merge and sort first using samtools.
samfiles = []
num_reads = 0
nfiles = 0
statement = []
tmpfile = P.getTempFilename(".")
if len(infiles) > 1 and isinstance(infiles, str) == 0:
# assume: samtools merge output is sorted
# assume: sam files are sorted already
statement.append('''samtools merge @OUT@ %s''' % (infiles.join(" ")))
statement.append('''samtools sort @IN@ @OUT@''')
if dedup:
statement.append('''MarkDuplicates
INPUT=@IN@
ASSUME_SORTED=true
REMOVE_DUPLICATES=true
QUIET=true
OUTPUT=@OUT@
METRICS_FILE=%(outfile)s.picardmetrics
VALIDATION_STRINGENCY=SILENT
> %(outfile)s.picardlog ''')
if mask:
statement.append(
'''intersectBed -abam @IN@ -b %(mask)s -wa -v > @OUT@''')
statement.append('''mv @IN@ %(outfile)s''')
statement.append('''samtools index %(outfile)s''')
statement = P.joinStatements(statement, infiles)
P.run()
def buildBAMforPeakCalling(infiles, outfile, dedup, mask):
''' Make a BAM file suitable for peak calling.
Infiles are merged and unmapped reads removed.
If specificied duplicate reads are removed.
This method use Picard.
If a mask is specified, reads falling within
the mask are filtered out.
This uses bedtools.
The mask is a quicksect object containing
the regions from which reads are to be excluded.
'''
# open the infiles, if more than one merge and sort first using samtools.
samfiles = []
num_reads = 0
nfiles = 0
statement = []
tmpfile = P.getTempFilename(".")
if len(infiles) > 1 and isinstance(infiles, str) == 0:
# assume: samtools merge output is sorted
# assume: sam files are sorted already
statement.append('''samtools merge @OUT@ %s''' % (infiles.join(" ")))
statement.append('''samtools sort @IN@ @OUT@''')
if dedup:
statement.append('''MarkDuplicates
INPUT=@IN@
ASSUME_SORTED=true
REMOVE_DUPLICATES=true
QUIET=true
OUTPUT=@OUT@
METRICS_FILE=%(outfile)s.picardmetrics
VALIDATION_STRINGENCY=SILENT
> %(outfile)s.picardlog ''')
if mask:
statement.append(
'''intersectBed -abam @IN@ -b %(mask)s -wa -v > @OUT@''')
statement.append('''mv @IN@ %(outfile)s''')
statement.append('''samtools index %(outfile)s''')
statement = P.joinStatements(statement, infiles)
P.run()
def filterBamfiles(infile, sentinel):
"""
Pre-process bamfiles prior to peak calling.
i) sort bamfiles
ii) remove unmapped readswith bam2bam.py
iii) remove non-uniquely mapping reads with bam2bam.py (optional)
iv) remove duplicates with Picards MarkDuplicates (optional)
v) remove reads from masked regions with bedtools intersect (optional)
vi) index
"""
# create tempfile for Picard's MarkDuplicates
picard_tmp = P.getTempDir(PARAMS["scratchdir"])
outfile = P.snip(sentinel, ".sentinel") + ".bam"
# ensure bamfile is sorted,
statement = [
"samtools sort @IN@ -o @[email protected]",
]
# remove unmapped reads
statement.append("cgat bam2bam"
" --method=filter --filter-method=mapped"
" --log=%(outfile)s.log"
" < @[email protected]"
" > @OUT@")
# remove non-uniquely mapping reads, if requested
if PARAMS["filter_remove_non_unique"]:
statement.append("cgat bam2bam"
" --method=filter --filter-method=unique"
" --log=%(outfile)s.log"
" < @IN@"
" > @OUT@")
# remove duplicates, if requested
if PARAMS["filter_remove_duplicates"]:
statement.append("MarkDuplicates"
" INPUT=@IN@"
" ASSUME_SORTED=true"
" REMOVE_DUPLICATES=true"
" QUIET=false"
" OUTPUT=@OUT@"
" METRICS_FILE=/dev/null"
" VALIDATION_STRINGENCY=SILENT"
" TMP_DIR=%(picard_tmp)s"
" 2> %(outfile)s.log")
# mask regions, if intervals supplied
if PARAMS["filter_mask_intervals"]:
mask = PARAMS["filter_mask_intervals"]
statement.append("bedtools intersect"
" -abam @IN@"
" -b %(mask)s"
" -wa"
" -v"
" > @OUT@")
statement.append("mv @IN@ %(outfile)s")
statement.append("samtools index %(outfile)s")
job_memory = "5G"
statement = P.joinStatements(statement, infile)
P.run()
P.touch(sentinel)
shutil.rmtree(picard_tmp)
def filterBamfiles(infile, sentinel):
"""
Pre-process bamfiles prior to peak calling.
i) sort bamfiles
ii) remove unmapped readswith bam2bam.py
iii) remove non-uniquely mapping reads with bam2bam.py (optional)
iv) remove duplicates with Picards MarkDuplicates (optional)
v) remove reads from masked regions with bedtools intersect (optional)
vi) index
"""
# create tempfile for Picard's MarkDuplicates
picard_tmp = picard_tmp = P.getTempDir(PARAMS["scratchdir"])
outfile = P.snip(sentinel, ".sentinel") + ".bam"
# ensure bamfile is sorted,
statement = ["samtools sort @IN@ @OUT@", ]
# remove unmapped reads
statement.append("python %(scriptsdir)s/bam2bam.py"
" --method=filter --filter-method=mapped"
" --log=%(outfile)s.log"
" < @[email protected]"
" > @OUT@")
# remove non-uniquely mapping reads, if requested
if PARAMS["filter_remove_non_unique"]:
statement.append("python %(scriptsdir)s/bam2bam.py"
" --method=filter --filter-method=unique"
" --log=%(outfile)s.log"
" < @IN@"
" > @OUT@")
# remove duplicates, if requested
if PARAMS["filter_remove_duplicates"]:
statement.append("MarkDuplicates"
" INPUT=@IN@"
" ASSUME_SORTED=true"
" REMOVE_DUPLICATES=true"
" QUIET=false"
" OUTPUT=@OUT@"
" METRICS_FILE=/dev/null"
" VALIDATION_STRINGENCY=SILENT"
" TMP_DIR=%(picard_tmp)s"
" 2> %(outfile)s.log")
# mask regions, if intervals supplied
if PARAMS["filter_mask_intervals"]:
mask = PARAMS["filter_mask_intervals"]
statement.append("bedtools intersect"
" -abam @IN@"
" -b %(mask)s"
" -wa"
" -v"
" > @OUT@")
statement.append("mv @IN@ %(outfile)s")
statement.append("samtools index %(outfile)s")
job_options = "-l mem_free=10G"
statement = P.joinStatements(statement, infile)
P.run()
P.touch(sentinel)
shutil.rmtree(picard_tmp)
