def parseArgs(args):
parser = argparse.ArgumentParser(prog="Honey.py force", description=USAGE, \
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument("bam", metavar="BAM", type=str, \
help="Assembled Contigs Bam")
parser.add_argument("bed", metavar="BED", type=str, \
help="Bed of locations to force SV Calls")
parser.add_argument("-s", "--sizebuffer", type=float, default=0.35, \
help=("Buffer of estimated sv size to "
"create match (%(default)s)"))
parser.add_argument("-d", "--maxDelta", type=int, default=500, \
help="Max distance between predicted and discovered variant (%(default)s)")
parser.add_argument("-f", "--fetchbuffer", type=int, default=1000, \
help="Buffer for fetching reads from .bam (%(default)s)")
#parser.add_argument("-o", "--overlapbuffer", type=float, default=0.50, \
#help="Percent overlap required from calls to tails (%(default)s)")
parser.add_argument("-q", "--minMapq", type=int, default=100, \
help="Minimum mapping quality of a read and it's tail to consider (%(default)s)")
parser.add_argument("-m", "--minErr", type=int, default=5, \
help="Minimum ins/del error size to consider (%(default)s)")
#parser.add_argument("-a", "--asm", action="store_true", \
#help="Input reads are high-quality contigs")
parser.add_argument("-p", "--bedPE", action="store_true", \
help="Input bed file is bedPE - only tails searching will be performed")
parser.add_argument("--debug", action="store_true", \
help="Verbose logging")
args = parser.parse_args(args)
setupLogging(args.debug)
return args
def parseArgs(argv):
parser = argparse.ArgumentParser(prog="Honey.py cpxres", description=USAGE, \
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument("tails", metavar="TAILS", type=str, \
help="Input hon.tals file")
parser.add_argument("-o", "--output", type=str, default=None, \
help="Output file (<tails>.cpx)")
parser.add_argument("-c", "--minBlock", type=int, default=500, \
help=("To prevent 'tiny' reference bocks, remove "
"those with a size less than (%(default)s)"))
parser.add_argument("-s", "--maxSpan", type=int, default=100000, \
help=("Max Span of a breakpoint to be considered"
" (%(default)s)"))
parser.add_argument("-l", "--maxOvl", type=int, default=10, \
help=("Max number of overlaps in a cluster"
" (%(default)s)"))
parser.add_argument("-r", "--maxRefBlocks", type=int, default=10,
help=("Max number of reference blocks to consider"
" (%(default)s)"))
parser.add_argument("--debug", action="store_true", \
help="Verbose logging")
args = parser.parse_args(argv)
setupLogging(args.debug)
if args.output is None:
args.output = args.tails + '.cpx'
return args
def parseArgs(args):
parser = argparse.ArgumentParser(prog="Honey.py force", description=USAGE, \
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument("bam", metavar="BAM", type=str, \
help="Assembled Contigs Bam")
parser.add_argument("bed", metavar="BED", type=str, \
help="Bed of locations to force SV Calls")
parser.add_argument("-s", "--sizebuffer", type=float, default=0.35, \
help=("Buffer of estimated sv size to "
"create match (%(default)s)"))
parser.add_argument("-d", "--maxDelta", type=int, default=500, \
help="Max distance between predicted and discovered variant (%(default)s)")
parser.add_argument("-f", "--fetchbuffer", type=int, default=1000, \
help="Buffer for fetching reads from .bam (%(default)s)")
#parser.add_argument("-o", "--overlapbuffer", type=float, default=0.50, \
#help="Percent overlap required from calls to tails (%(default)s)")
parser.add_argument("-q", "--minMapq", type=int, default=100, \
help="Minimum mapping quality of a read and it's tail to consider (%(default)s)")
parser.add_argument("-m", "--minErr", type=int, default=5, \
help="Minimum ins/del error size to consider (%(default)s)")
#parser.add_argument("-a", "--asm", action="store_true", \
#help="Input reads are high-quality contigs")
parser.add_argument("-p", "--bedPE", action="store_true", \
help="Input bed file is bedPE - only tails searching will be performed")
parser.add_argument("--debug", action="store_true", \
help="Verbose logging")
args = parser.parse_args(args)
setupLogging(args.debug)
return args
def parseArgs(argv):
parser = argparse.ArgumentParser(prog="Honey.py cpxres", description=USAGE, \
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument("tails", metavar="TAILS", type=str, \
help="Input hon.tals file")
parser.add_argument("-o", "--output", type=str, default=None, \
help="Output file (<tails>.cpx)")
parser.add_argument("-c", "--minBlock", type=int, default=500, \
help=("To prevent 'tiny' reference bocks, remove "
"those with a size less than (%(default)s)"))
parser.add_argument("-s", "--maxSpan", type=int, default=100000, \
help=("Max Span of a breakpoint to be considered"
" (%(default)s)"))
parser.add_argument("-l", "--maxOvl", type=int, default=10, \
help=("Max number of overlaps in a cluster"
" (%(default)s)"))
parser.add_argument("-r", "--maxRefBlocks", type=int, default=10,
help=("Max number of reference blocks to consider"
" (%(default)s)"))
parser.add_argument("--debug", action="store_true", \
help="Verbose logging")
args = parser.parse_args(argv)
setupLogging(args.debug)
if args.output is None:
args.output = args.tails + '.cpx'
return args
def test(argv):
numpy.seterr(all="ignore")
args = parseArgs(argv)
setupLogging(True) #keep debug on.. you're testing!
logging.critical(("Running HSpots.py directly implements testing mode. "
"If you're trying to run the full, actual program, use "
"Honey.py spots"))
bam = pysam.Samfile(args.bam)
reference = pysam.Fastafile(args.reference)
try:
if bam.header["HD"]["SO"] != "coordinate":
logging.warning(
"BAM is not sorted by coordinates! Performance may be slower")
except KeyError:
logging.warning(
"Assuming BAM is sorted by coordinate. Be sure this is correct")
logging.info("Running in test mode")
#do what you will.. from here
# This is what I need to start with
#spot = SpotResult(chrom="7", start=138402727, end=138402830, svtype="INS", size=113)
chrom = "3"
start, end = (195498264, 195498609)
start -= 200
end += 200
spot = SpotResult(chrom=chrom,
start=start,
end=end,
svtype="DEL",
size=100)
#fh = open("possible.bed")
#for line in fh.readlines():
#data = line.strip().split('\t')
#spot = SpotResult(chrom=data[0], start=int(data[8]), end = int(data[9]), \
#size=int(data[5]), svtype=data[4])
j = SpotCaller('group', spot.chrom, spot.start, spot.end, args)
if j.supportingReadsFilter(spot, bam, args):
consen = ConsensusCaller(spot, args)
consen(bam, reference, 'none')
for i in consen.newSpots:
i.tags["seqmade"] = True
print i
if len(consen.newSpots) == 0:
spot.tags["noseq"] = True
print str(spot)
else:
spot.tags["filtfail"] = True
print str(spot)
#done with test code
logging.info("Finished testing")
def __init__(self):
"""
Given a protocol fn, load it up so we are ready to run.
"""
self.parseArgs()
setupLogging(self.options.debug)
sys.stderr.write("""
Please Cite: English, Adam C., Stephen Richards, Yi Han, Min Wang,
Vanesa Vee, Jiaxin Qu, Xiang Qin, et al. "Mind the
Gap: Upgrading Genomes with Pacific Biosciences RS
Long-Read Sequencing Technology." PLoS ONE 7, no. 11
(November 21, 2012): e47768.
doi:10.1371/journal.pone.0047768.\n\n""")
self.parseProtocol()
def __init__(self):
"""
Given a protocol fn, load it up so we are ready to run.
"""
self.parseArgs()
setupLogging(self.options.debug)
sys.stderr.write("""
Please Cite: English, Adam C., Stephen Richards, Yi Han, Min Wang,
Vanesa Vee, Jiaxin Qu, Xiang Qin, et al. "Mind the
Gap: Upgrading Genomes with Pacific Biosciences RS
Long-Read Sequencing Technology." PLoS ONE 7, no. 11
(November 21, 2012): e47768.
doi:10.1371/journal.pone.0047768.\n\n""")
self.parseProtocol()
def parseArgs(self):
parser = OptionParser()
parser.add_option("-i", "--inputDir", default=None,\
help="Input directory to find chunks.m4 [DEFAULT=pwd]")
parser.add_option("-j", "--json", action="store_true",\
help="Output table in JSON format instead of lined [DEFAULT=False]")
parser.add_option("-o", "--output", default=None,\
help="Output file name [DEFAULT=stdout]")
parser.add_option("-t", "--tailMax", type="int", default=-1, \
help=("Use PBJelly's Support module to remove discordant "
"alignments with greater than specified tail length "
"[DEFAULT=off]"))
parser.add_option("-l", "--lengthMin", type="int", default=0, \
help="Ignore reads (query or target) less than specified length [DEFAULT=off]")
parser.add_option("-b", "--bestn", type="int", default=sys.maxint, \
help=("Report only the top bestn alignment scores for a query"
" [DEFAULT=all]"))
parser.add_option("-e", "--extends", action="store_true", \
help="Only report alignments that extend query [DEFAULT=False]")
parser.add_option("-m", "--maxEntries", type="int", default=10000, \
help="Max number of alignments to hold in memory from each file [DEFAULT=10000]")
parser.add_option("--debug", action="store_true",\
help="Verbose logging")
opts, args = parser.parse_args()
setupLogging(opts.debug)
if opts.inputDir is not None:
self.inputDir = opts.inputDir
else:
self.inputDir = os.getcwd()
if not os.path.exists(self.inputDir):
parser.error("Input directory (%s) does not exist" % inputDir)
self.outputJson = opts.json
if opts.output is not None:
self.output = open(opts.output,'w')
else:
self.output = sys.stdout
#Filter params
self.tailMax = opts.tailMax
self.lengthMin = opts.lengthMin
self.bestn = opts.bestn
self.extends = opts.extends
self.maxEntries = opts.maxEntries
self.debug = opts.debug
def parseArgs(self):
parser = OptionParser()
parser.add_option("-i", "--inputDir", default=None,\
help="Input directory to find chunks.m4 [DEFAULT=pwd]")
parser.add_option("-j", "--json", action="store_true",\
help="Output table in JSON format instead of lined [DEFAULT=False]")
parser.add_option("-o", "--output", default=None,\
help="Output file name [DEFAULT=stdout]")
parser.add_option("-t", "--tailMax", type="int", default=-1, \
help=("Use PBJelly's Support module to remove discordant "
"alignments with greater than specified tail length "
"[DEFAULT=off]"))
parser.add_option("-l", "--lengthMin", type="int", default=0, \
help="Ignore reads (query or target) less than specified length [DEFAULT=off]")
parser.add_option("-b", "--bestn", type="int", default=sys.maxint, \
help=("Report only the top bestn alignment scores for a query"
" [DEFAULT=all]"))
parser.add_option("-e", "--extends", action="store_true", \
help="Only report alignments that extend query [DEFAULT=False]")
parser.add_option("-m", "--maxEntries", type="int", default=10000, \
help="Max number of alignments to hold in memory from each file [DEFAULT=10000]")
parser.add_option("--debug", action="store_true",\
help="Verbose logging")
opts, args = parser.parse_args()
setupLogging(opts.debug)
if opts.inputDir is not None:
self.inputDir = opts.inputDir
else:
self.inputDir = os.getcwd()
if not os.path.exists(self.inputDir):
parser.error("Input directory (%s) does not exist" % inputDir)
self.outputJson = opts.json
if opts.output is not None:
self.output = open(opts.output, 'w')
else:
self.output = sys.stdout
#Filter params
self.tailMax = opts.tailMax
self.lengthMin = opts.lengthMin
self.bestn = opts.bestn
self.extends = opts.extends
self.maxEntries = opts.maxEntries
self.debug = opts.debug
def test(argv):
numpy.seterr(all="ignore")
args = parseArgs(argv)
setupLogging(True)#keep debug on.. you're testing!
logging.critical(("Running HSpots.py directly implements testing mode. "
"If you're trying to run the full, actual program, use "
"Honey.py spots"))
bam = pysam.Samfile(args.bam)
reference = pysam.Fastafile(args.reference)
try:
if bam.header["HD"]["SO"] != "coordinate":
logging.warning("BAM is not sorted by coordinates! Performance may be slower")
except KeyError:
logging.warning("Assuming BAM is sorted by coordinate. Be sure this is correct")
logging.info("Running in test mode")
#do what you will.. from here
# This is what I need to start with
#spot = SpotResult(chrom="7", start=138402727, end=138402830, svtype="INS", size=113)
chrom="3"
start,end = (195498264, 195498609)
start -=200
end +=200
spot = SpotResult(chrom=chrom, start=start, end=end, svtype="DEL", size=100)
#fh = open("possible.bed")
#for line in fh.readlines():
#data = line.strip().split('\t')
#spot = SpotResult(chrom=data[0], start=int(data[8]), end = int(data[9]), \
#size=int(data[5]), svtype=data[4])
j = SpotCaller('group', spot.chrom, spot.start, spot.end, args)
if j.supportingReadsFilter(spot, bam, args):
consen = ConsensusCaller(spot, args)
consen(bam, reference, 'none')
for i in consen.newSpots:
i.tags["seqmade"] = True
print i
if len(consen.newSpots) == 0:
spot.tags["noseq"] = True
print str(spot)
else:
spot.tags["filtfail"] = True
print str(spot)
#done with test code
logging.info("Finished testing")
def test(argv):
numpy.seterr(all="ignore")
args = parseArgs(argv)
setupLogging(True) #keep debug on.. you're testing!
logging.critical(("Running HSpots.py directly implements testing mode. "
"If you're trying to run the full, actual program, use "
"Honey.py spots"))
bam = pysam.Samfile(args.bam)
reference = pysam.Fastafile(args.reference)
try:
if bam.header["HD"]["SO"] != "coordinate":
logging.warning(
"BAM is not sorted by coordinates! Performance may be slower")
except KeyError:
logging.warning(
"Assuming BAM is sorted by coordinate. Be sure this is correct")
logging.info("Running in test mode")
#do what you will.. from here
#spot = SpotResult(chrom='11', start=2215290, end=2215798, svtype="DEL", size=208)
#spot = SpotResult(chrom='22', start=45964261, end=45965596, svtype="DEL", size=-1)
# This is what I need to start with
#spot = SpotResult(chrom="22", start=45963975, end=45964532, svtype="DEL", size=57)
fh = open("honeymissing.bed")
for line in fh.readlines():
data = line.strip().split('\t')
spot = SpotResult(chrom=data[0], start=int(data[1]), end = int(data[2]), \
size=int(data[3].split('=')[-1]), svtype="DEL")
j = SpotCaller('group', spot.chrom, spot.start, spot.end, args)
if j.supportingReadsFilter(spot, bam, args):
consen = ConsensusCaller(spot, args)
consen(bam, reference, 'none')
for i in consen.newSpots:
i.tags["seqmade"] = True
print i
if len(consen.newSpots) == 0:
spot.tags["noseq"] = True
print str(spot)
else:
spot.tags["filtfail"] = True
print str(spot)
#done with test code
logging.info("Finished testing")
def _parseOptions( self ):
parser = OptionParser( usage=USAGE )
parser.add_option("--debug", action="store_true", help="Increases verbosity of logging" )
parser.add_option("--nproc", type="int", help="Number of processes to use." )
parser.add_option("-o", "--outName", type="string", help="Name of the output fasta and qual files (Don't include the extension)", default="out")
parser.add_option("--fqOut", action="store_true", help="Create a .fastq output file")
parser.add_option("--rename", type="string", help="Gives the ouput contigs more descriptive names")
parser.add_option("--minSubreads", type="int", help="Minimum number of subreads required to attempt assembly")
parser.add_option("--workDir", type="string", help="Directory to build the bank an everything in.")
parser.add_option("--workTmp", type="string", help="Work in a temporary directory")
parser.add_option("--threshold", type="int", help="Threshold when determining overlaps")
parser.add_option("--transmax", type="int", help="Max links of transitivity")
parser.add_option("-e", type="str", help="Alignment Error% e.g. 0.15 = 15%")
parser.set_defaults(debug=False, nproc=1, outName="out", rename=None, minSubreads=2, \
filtering=False, workTmp=None, threshold=800, transmax=1, e="0.15")
self.options, args = parser.parse_args(sys.argv)
setupLogging(self.options.debug)
logging.warning("This program doesn't work with SMRTAnalysis v2.1 and on")
logging.info("Reading Input Reads")
if len(args) == 2:
self.fastqFile = args[1]
if not self.fastqFile.endswith(".fastq"):
parser.error("Expected a Fastq File or Fasta/Qual")
self.fastqSeq = FastqFile(self.fastqFile)
elif len(args) == 3:
fasta = args[1]
qual = args[2]
if not fasta.endswith(".fasta"):
parser.error("Expected First Argument To End With .fasta")
if not qual.endswith(".qual"):
parser.error("Expected Second Argument To End With .qual")
self.fastqSeq = mergeFastaQual(fasta, qual)
self.fastaFile = fasta
self.qualFile = qual
else:
parser.error("Expected <input.fastq> or <input.fasta> <input.qual> Arguments!")
self.options.outName = os.path.abspath(self.options.outName)
if self.options.workTmp is not None:
self.options.workDir = tempfile.mkdtemp(dir=self.options.workTmp)
if self.options.workDir is not None:
os.chdir(self.options.workDir)
def test(argv):
numpy.seterr(all="ignore")
args = parseArgs(argv)
setupLogging(True)#keep debug on.. you're testing!
logging.critical(("Running HSpots.py directly implements testing mode. "
"If you're trying to run the full, actual program, use "
"Honey.py spots"))
bam = pysam.Samfile(args.bam)
reference = pysam.Fastafile(args.reference)
try:
if bam.header["HD"]["SO"] != "coordinate":
logging.warning("BAM is not sorted by coordinates! Performance may be slower")
except KeyError:
logging.warning("Assuming BAM is sorted by coordinate. Be sure this is correct")
logging.info("Running in test mode")
#do what you will.. from here
#spot = SpotResult(chrom='11', start=2215290, end=2215798, svtype="DEL", size=208)
#spot = SpotResult(chrom='22', start=45964261, end=45965596, svtype="DEL", size=-1)
# This is what I need to start with
#spot = SpotResult(chrom="22", start=45963975, end=45964532, svtype="DEL", size=57)
fh = open("honeymissing.bed")
for line in fh.readlines():
data = line.strip().split('\t')
spot = SpotResult(chrom=data[0], start=int(data[1]), end = int(data[2]), \
size=int(data[3].split('=')[-1]), svtype="DEL")
j = SpotCaller('group', spot.chrom, spot.start, spot.end, args)
if j.supportingReadsFilter(spot, bam, args):
consen = ConsensusCaller(spot, args)
consen(bam, reference, 'none')
for i in consen.newSpots:
i.tags["seqmade"] = True
print i
if len(consen.newSpots) == 0:
spot.tags["noseq"] = True
print str(spot)
else:
spot.tags["filtfail"] = True
print str(spot)
#done with test code
logging.info("Finished testing")
def _parseOptions(self):
parser = OptionParser(usage=USAGE)
parser.add_option("--debug",
action="store_true",
help="Increases verbosity of logging")
parser.add_option("--nproc",
type="int",
help="Number of processes to use.")
parser.add_option(
"-o",
"--outName",
type="string",
help=
"Name of the output fasta and qual files (Don't include the extension)",
default="out")
parser.add_option("--fqOut",
action="store_true",
help="Create a .fastq output file")
parser.add_option(
"--rename",
type="string",
help="Gives the ouput contigs more descriptive names")
parser.add_option(
"--minSubreads",
type="int",
help="Minimum number of subreads required to attempt assembly")
parser.add_option("--workDir",
type="string",
help="Directory to build the bank an everything in.")
parser.add_option("--workTmp",
type="string",
help="Work in a temporary directory")
parser.add_option("--threshold",
type="int",
help="Threshold when determining overlaps")
parser.add_option("--transmax",
type="int",
help="Max links of transitivity")
parser.add_option("-e",
type="str",
help="Alignment Error% e.g. 0.15 = 15%")
parser.set_defaults(debug=False, nproc=1, outName="out", rename=None, minSubreads=2, \
filtering=False, workTmp=None, threshold=800, transmax=1, e="0.15")
self.options, args = parser.parse_args(sys.argv)
setupLogging(self.options.debug)
logging.warning(
"This program doesn't work with SMRTAnalysis v2.1 and on")
logging.info("Reading Input Reads")
if len(args) == 2:
self.fastqFile = args[1]
if not self.fastqFile.endswith(".fastq"):
parser.error("Expected a Fastq File or Fasta/Qual")
self.fastqSeq = FastqFile(self.fastqFile)
elif len(args) == 3:
fasta = args[1]
qual = args[2]
if not fasta.endswith(".fasta"):
parser.error("Expected First Argument To End With .fasta")
if not qual.endswith(".qual"):
parser.error("Expected Second Argument To End With .qual")
self.fastqSeq = mergeFastaQual(fasta, qual)
self.fastaFile = fasta
self.qualFile = qual
else:
parser.error(
"Expected <input.fastq> or <input.fasta> <input.qual> Arguments!"
)
self.options.outName = os.path.abspath(self.options.outName)
if self.options.workTmp is not None:
self.options.workDir = tempfile.mkdtemp(dir=self.options.workTmp)
if self.options.workDir is not None:
os.chdir(self.options.workDir)
def __init__(self):
self.parseOpts()
#setupLogging(self.debug)
setupLogging(True)
def parseArgs(argv, established=False):
parser = argparse.ArgumentParser(prog="Honey.py spots", description=USAGE, \
formatter_class=argparse.RawDescriptionHelpFormatter)
ioGroup = parser.add_argument_group("I/O Arguments")
ioGroup.add_argument("bam", metavar="BAM", type=str, \
help="BAM containing mapped reads")
ioGroup.add_argument("--hon", metavar="HON.H5", type=str, default=None, \
help="HON.h5 containing Error data. Skips ErrorCouting.")
ioGroup.add_argument("-r", "--region", type=str, default=None,\
help="Only call spots in region.bed")
ioGroup.add_argument("--chrom", type=str, default=None, \
help="Only call spots on specified chromosomes (comma-separated) (%(default)s)")
ioGroup.add_argument("-n", "--nproc", type=int, default=1, \
help="Number of processors to use (only for consensus) (%(default)s)")
ioGroup.add_argument("-o", "--output", type=str, default=None, \
help="Basename for output (BAM.hon)")
ioGroup.add_argument("--readFile", action="store_true", \
help="Create a file with what reads support what events (%(default)s)")
pGroup = parser.add_argument_group(
"Spot-Calling Threshold/Filtering Arguments")
pGroup.add_argument("-b", "--binsize", type=int, default=100, \
help="binsize for window averaging (%(default)s)")
pGroup.add_argument("-e",
"--threshold",
type=float,
default=3,
help="Minimum Spot Threshold (%(default)s)")
pGroup.add_argument("-c", "--minCoverage", type=int, default=2, \
help="Minimum coverage of a region (%(default)s)")
pGroup.add_argument("-C", "--maxCoverage", type=int, default=BIGINT, \
help="Maximum coverage of a region (%(default)s)")
pGroup.add_argument("-q", "--minMapQ", type=int, default=1, \
help="Minimum map quality of reads considered (%(default)s)")
pGroup.add_argument(
"-m",
"--minIndelErr",
type=int,
default=5,
help="Minimum size of an indel error to be counted (%(default)s)")
pGroup.add_argument("-i", "--minIndelSize", type=int, default=50, \
help="Minimum indel SV size (%(default)s)")
pGroup.add_argument("-E", "--minErrReads", type=int, default=3, \
help="Minimum number of reads with indel (%(default)s)")
pGroup.add_argument("--spanMax", type=int, default=2000, \
help="Maximum Size of spot to be called (%(default)s)")
#pGroup.add_argument("-I", "--minIndelPct", type=float, default=0.20, \
#help="Minimum pct of reads with indel (max(%(default)s*cov,minErrReads)")
aGroup = parser.add_argument_group("Consensus Arguments")
aGroup.add_argument("--noConsensus", action="store_true", \
help="Turn off consensus calling, just report spots (False)")
aGroup.add_argument("--buffer", default=1000, type=int, \
help="Buffer around SV to assemble (%(default)s)")
aGroup.add_argument("--reference", default=None, type=str, \
help="Sample reference. Required with consensus calling (None)")
aGroup.add_argument("--polish", type=str, default="pbdagcon", choices=["pbdagcon", "pbbanana", "None"], \
help="Method for polishing consensus. (%(default)s)")
aGroup.add_argument("--blasr", default="blasr", \
help="Path to blasr if it's not in the env")
#aGroup.add_argument("--contig", default="store_false", \
#help="Report the full contig sequences and QVs in INFO (False)")
parser.add_argument("--debug", action="store_true", \
help="Verbose logging")
args = parser.parse_args(argv)
setupLogging(args.debug)
if args.maxCoverage > BIGINT:
logging.error("Max Coverge must be less than %d" % (BIGINT))
exit(0)
#check bam is bamfile
if args.output is None:
#args.output = args.bam.filename[:-4]+".hon"
if args.hon is not None:
args.output = args.hon.rstrip(".h5")
else:
args.output = args.bam[:-4] + ".hon"
if not args.noConsensus:
if args.reference is None:
logging.error("Reference is required with consensus calling")
exit(0)
#Check is fastafile
if args.chrom is not None:
args.chrom = args.chrom.split(',')
return args
def __init__(self):
self.parseArgs()
setupLogging(self.opts.debug)
def parseArgs(argv, established=False):
parser = argparse.ArgumentParser(prog="Honey.py spots", description=USAGE, \
formatter_class=argparse.RawDescriptionHelpFormatter)
ioGroup = parser.add_argument_group("I/O Arguments")
ioGroup.add_argument("bam", metavar="BAM", type=str, \
help="BAM containing mapped reads")
ioGroup.add_argument("--hon", metavar="HON.H5", type=str, default=None, \
help="HON.h5 containing Error data. Skips ErrorCouting.")
ioGroup.add_argument("-r", "--region", type=str, default=None,\
help="Only call spots in region.bed")
ioGroup.add_argument("--chrom", type=str, default=None, \
help="Only call spots on specified chromosomes (comma-separated) (%(default)s)")
ioGroup.add_argument("-n", "--nproc", type=int, default=1, \
help="Number of processors to use (only for consensus) (%(default)s)")
ioGroup.add_argument("-o", "--output", type=str, default=None, \
help="Basename for output (BAM.hon)")
ioGroup.add_argument("--readFile", action="store_true", \
help="Create a file with what reads support what events (%(default)s)")
pGroup = parser.add_argument_group("Spot-Calling Threshold/Filtering Arguments")
pGroup.add_argument("-b", "--binsize", type=int, default=50, \
help="Binsize for window averaging (%(default)s)")
pGroup.add_argument("-e", "--threshold", type=float, default=3,
help="Minimum Spot Threshold (%(default)s)")
pGroup.add_argument("-c", "--minCoverage", type=int, default=2, \
help="Minimum coverage of a region (%(default)s)")
pGroup.add_argument("-C", "--maxCoverage", type=int, default=BIGINT, \
help="Maximum coverage of a region (%(default)s)")
pGroup.add_argument("-q", "--minMapQ", type=int, default=1, \
help="Minimum map quality of reads considered (%(default)s)")
pGroup.add_argument("-m", "--minIndelErr", type=int, default=5,
help="Minimum size of an indel error to be counted (%(default)s)")
pGroup.add_argument("-i", "--minIndelSize", type=int, default=50, \
help="Minimum indel SV size (%(default)s)")
pGroup.add_argument("-E", "--minErrReads", type=int, default=3, \
help="Minimum number of reads with indel (%(default)s)")
pGroup.add_argument("--spanMax", type=int, default=3000, \
help="Maximum Size of spot to be called (%(default)s)")
#pGroup.add_argument("-I", "--minIndelPct", type=float, default=0.20, \
#help="Minimum pct of reads with indel (max(%(default)s*cov,minErrReads)")
aGroup = parser.add_argument_group("Consensus Arguments")
aGroup.add_argument("--consensus", type=str, default="pbdagcon", choices=["pbdagcon", "pbbanana", "None"], \
help="Method for polishing consensus. (%(default)s)")
aGroup.add_argument("--buffer", default=1000, type=int, \
help="Buffer around SV to consense (%(default)s)")
aGroup.add_argument("--reference", default=None, type=str, \
help="Sample reference. Required with consensus calling (None)")
aGroup.add_argument("--reportContig", action="store_true", \
help="Report the contig created that called the spot")
#aGroup.add_argument("--blasr", default="blasr", \
#help="Path to blasr if it's not in the env")
#aGroup.add_argument("--contig", default="store_false", \
#help="Report the full contig sequences and QVs in INFO (False)")
parser.add_argument("--debug", action="store_true", \
help="Verbose logging")
args = parser.parse_args(argv)
setupLogging(args.debug)
if args.maxCoverage > BIGINT:
logging.error("Max Coverge must be less than %d" % (BIGINT))
exit(0)
#check bam is bamfile
if args.output is None:
#args.output = args.bam.filename[:-4]+".hon"
if args.hon is not None:
args.output = args.hon.rstrip(".h5")
else:
args.output = args.bam[:-4]+".hon"
if args.consensus != "None":
if args.reference is None:
logging.error("Reference is required with consensus calling")
exit(0)
#Check is fastafile
if args.chrom is not None:
args.chrom = args.chrom.split(',')
return args
def parseArgs(argv):
parser = argparse.ArgumentParser(description=USAGE, \
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument("putative", metavar="BED", type=str, \
help="Bed of regions to assemble")
parser.add_argument("-b", "--bam", type=str, nargs="*", \
help="Input Bam (NonTrim)")
parser.add_argument("-p", "--pacBam", type=str, nargs="*", \
help="PacBio Bam")
parser.add_argument("-a", "--assembler", type=str, default='phrap', choices=["phrap", "minia", "spades"],
help="Assembly program to use (%(default)s)")
parser.add_argument("-B", "--buffer", type=int, default=1000, \
help="Amount of buffer sequence around the variant to use (%(default)s)")
parser.add_argument("-n", "--nproc", type=int, default=1, \
help="Number of processors to use (%(default)s)")
parser.add_argument("-o", "--output", default="asm.fastq",\
help="Where to write the resultant assemblies (%(default)s)")
parser.add_argument("-r", "--reference", default=None, \
help="Reference to map to (optional if --noRemap)")
parser.add_argument("--noRemap", action="store_false", \
help="Do not remap assembly")
parser.add_argument("--noSplitMap", action="store_false", \
help="Do not map tails from remapped assembly (off if --noRemap)")
parser.add_argument("--timeout", type=int, default=30, \
help="Timeout assembly after N minutes (%(default)s)")
parser.add_argument("--maxspan", type=int, default=100000, \
help="Maximum Span of SV to attempt assembling (%(default)s)")
parser.add_argument("--maxreads", type=int, default=500, \
help="Maximum number of Illumina reads used to attempt assembling (%(default)s)")
parser.add_argument("--temp", type=str, default=tempfile.gettempdir(),
help="Where to save temporary files")
parser.add_argument("--start", type=int, default=0,
help="Index of the first variant to begin assembling. (%(default)s)")
parser.add_argument("--stride", type=int, default=1,
help="Assemble one every N reads (%(default)s)")
parser.add_argument("--debug", action="store_true",\
help="Verbose Logging")
#parser.add_argument("--insertsize", type=int, default=None, \
#help=("Celera - insert size for PE Illumina reads (auto_detect)"))
#parser.add_argument("--insertstd", type=float, default=None, \
#help=("Celera - insert std for PE Illumina reads (auto_detect)"))
args = parser.parse_args(argv)
setupLogging(args.debug)
# Parameter checks
if args.bam is None and args.pacBam is None:
logging.error("Expected at least one BAM argument")
exit(1)
if not args.output.endswith(".fastq"):
logging.error("Output needs to end with .fastq")
exit(1)
if not os.path.exists(args.putative):
logging.error("Input {inp} does not exist".format(inp=args.putative))
exit(1)
if args.noRemap and args.reference == None:
logging.error("Cannot remap without --reference")
exit(1)
if args.reference and not os.path.exists(args.reference):
logging.error("Reference {ref} does not exist".format(ref=args.reference))
exit(1)
if args.bam is None:
args.bam = []
if args.insertsize is None and args.bam is not None:
j = pysam.Samfile(args.bam[0])
mu,std = insertDist(j)
j.close()
args.insertsize = mu
args.insertstd = std if args.insertstd is None else args.insertstd
if args.pacBam is None:
args.pacBam = []
return args
def __init__(self):
self.parseOpts()
#setupLogging(self.debug)
setupLogging(True)
def parseArgs(argv):
parser = argparse.ArgumentParser(description=USAGE, \
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument("putative", metavar="BED", type=str, \
help="Bed of regions to assemble")
parser.add_argument("-b", "--bam", type=str, nargs="*", \
help="Input Bam (NonTrim)")
parser.add_argument("-p", "--pacBam", type=str, nargs="*", \
help="PacBio Bam")
parser.add_argument("-a",
"--assembler",
type=str,
default='phrap',
choices=["phrap", "minia", "spades"],
help="Assembly program to use (%(default)s)")
parser.add_argument("-B", "--buffer", type=int, default=1000, \
help="Amount of buffer sequence around the variant to use (%(default)s)")
parser.add_argument("-n", "--nproc", type=int, default=1, \
help="Number of processors to use (%(default)s)")
parser.add_argument("-o", "--output", default="asm.fastq",\
help="Where to write the resultant assemblies (%(default)s)")
parser.add_argument("-r", "--reference", default=None, \
help="Reference to map to (optional if --noRemap)")
parser.add_argument("--noRemap", action="store_false", \
help="Do not remap assembly")
parser.add_argument("--noSplitMap", action="store_false", \
help="Do not map tails from remapped assembly (off if --noRemap)")
parser.add_argument("--timeout", type=int, default=30, \
help="Timeout assembly after N minutes (%(default)s)")
parser.add_argument("--maxspan", type=int, default=100000, \
help="Maximum Span of SV to attempt assembling (%(default)s)")
parser.add_argument("--maxreads", type=int, default=2500, \
help="Maximum number of Illumina reads used to attempt assembling (%(default)s)")
parser.add_argument("--temp",
type=str,
default=tempfile.gettempdir(),
help="Where to save temporary files")
parser.add_argument(
"--start",
type=int,
default=0,
help="Index of the first variant to begin assembling. (%(default)s)")
parser.add_argument("--stride",
type=int,
default=1,
help="Assemble one every N reads (%(default)s)")
parser.add_argument("--debug", action="store_true",\
help="Verbose Logging")
#parser.add_argument("--insertsize", type=int, default=None, \
#help=("Celera - insert size for PE Illumina reads (auto_detect)"))
#parser.add_argument("--insertstd", type=float, default=None, \
#help=("Celera - insert std for PE Illumina reads (auto_detect)"))
args = parser.parse_args(argv)
setupLogging(args.debug)
# Parameter checks
if args.bam is None and args.pacBam is None:
logging.error("Expected at least one BAM argument")
exit(1)
if not args.output.endswith(".fastq"):
logging.error("Output needs to end with .fastq")
exit(1)
if not os.path.exists(args.putative):
logging.error("Input {inp} does not exist".format(inp=args.putative))
exit(1)
if args.noRemap and args.reference == None:
logging.error("Cannot remap without --reference")
exit(1)
if args.reference and not os.path.exists(args.reference):
logging.error(
"Reference {ref} does not exist".format(ref=args.reference))
exit(1)
if args.bam is None:
args.bam = []
#if args.insertsize is None and args.bam is not None:
#j = pysam.Samfile(args.bam[0])
#mu,std = insertDist(j)
#j.close()
#args.insertsize = mu
#args.insertstd = std if args.insertstd is None else args.insertstd
if args.pacBam is None:
args.pacBam = []
return args
def __init__(self):
self.parseArgs()
setupLogging(self.opts.debug)
