def main(argv=None): # IGNORE:C0111
'''Command line options.'''
if argv is None:
argv = sys.argv
else:
sys.argv.extend(argv)
program_name = os.path.basename(sys.argv[0])
program_version = "v%s" % __version__
program_build_date = str(__updated__)
program_version_message = '%%(prog)s %s (%s)' % (program_version,
program_build_date)
if __name__ == '__main__':
program_shortdesc = __import__('__main__').__doc__.split("\n")[1]
else:
program_shortdesc = __doc__.split("\n")[1]
#program_shortdesc = __import__('__main__').__doc__.split("\n")[1]
program_license = '''%s
Created by TGen North on %s.
Copyright 2015 TGen North. All rights reserved.
Available for academic and research use only under a license
from The Translational Genomics Research Institute (TGen)
that is free for non-commercial use.
Distributed on an "AS IS" basis without warranties
or conditions of any kind, either express or implied.
USAGE
''' % (program_shortdesc, str(__date__))
try:
# Setup argument parser
parser = argparse.ArgumentParser(
description=program_license,
formatter_class=argparse.RawDescriptionHelpFormatter)
required_group = parser.add_argument_group("required arguments")
required_group.add_argument("-n",
"--name",
required=True,
help="name for this run. [REQUIRED]")
required_group.add_argument(
"-j",
"--json",
required=True,
help="JSON file of assay descriptions. [REQUIRED]")
optional_group = parser.add_argument_group("optional arguments")
reads_bams_group = optional_group.add_mutually_exclusive_group()
reads_bams_group.add_argument(
"-r",
"--read-dir",
dest="rdir",
metavar="DIR",
help="directory of read files to analyze.")
reads_bams_group.add_argument(
"--bam-dir",
dest="bdir",
metavar="DIR",
help="directory of bam files to analyze.")
optional_group.add_argument(
"-o",
"--out-dir",
dest="odir",
metavar="DIR",
help="directory to write output files to. [default: `pwd`]")
optional_group.add_argument(
"-s",
"--submitter",
dest="job_manager",
default="PBS",
help=
"cluster job submitter to use (PBS, SLURM, SGE, none). [default: PBS]"
)
optional_group.add_argument(
"--submitter-args",
dest="sargs",
metavar="ARGS",
help=
"additional arguments to pass to the job submitter, enclosed in \"\"."
)
optional_group.add_argument(
"--smor",
action="store_true",
default=False,
help=
"perform SMOR analysis with overlapping reads. [default: False]")
trim_group = parser.add_argument_group("read trimming options")
on_off_group = trim_group.add_mutually_exclusive_group()
on_off_group.add_argument(
"--trim",
action="store_true",
default=True,
help="perform adapter trimming on reads. [default: True]")
on_off_group.add_argument("--no-trim",
dest="trim",
action="store_false",
help="do not perform adapter trimming.")
trim_group.add_argument(
"--adapter-sequences",
dest="adapters",
default="/scratch/dlemmer/ASAP/illumina_adapters_all.fasta",
help=
"location of the adapter sequence file to use for trimming. [default: /scratch/dlemmer/ASAP/illumina_adapters_all.fasta]"
)
trim_group.add_argument(
"-q",
"--qual",
nargs="?",
const="SLIDINGWINDOW:5:20",
help=
"perform quality trimming [default: False], optional parameter can be used to customize quality trimming parameters to trimmomatic. [default: SLIDINGWINDOW:5:20]"
)
trim_group.add_argument(
"-m",
"--minlen",
metavar="LEN",
default=80,
type=int,
help="minimum read length to keep after trimming. [default: 80]")
align_group = parser.add_argument_group("read mapping options")
align_group.add_argument(
"-a",
"--aligner",
default="bowtie2",
help=
"aligner to use for read mapping, supports bowtie2, novoalign, and bwa. [default: bowtie2]"
)
align_group.add_argument(
"--aligner-args",
dest="aargs",
metavar="ARGS",
default='',
help=
"additional arguments to pass to the aligner, enclosed in \"\".")
align_group.add_argument(
"-d",
"--depth",
default=100,
type=int,
help=
"minimum read depth required to consider a position covered. [default: 100]"
)
align_group.add_argument(
"-b",
"--breadth",
default=0.8,
type=float,
help=
"minimum breadth of coverage required to consider an amplicon as present. [default: 0.8]"
)
align_group.add_argument(
"-p",
"--proportion",
default=0.1,
type=float,
help=
"minimum proportion required to call a SNP at a given position. [default: 0.1]"
)
align_group.add_argument(
"-i",
"--identity",
dest="percid",
default=0,
type=float,
help=
"minimum percent identity required to align a read to a reference amplicon sequence. [default: 0]"
)
parser.add_argument("-V",
"--version",
action="version",
version=program_version_message)
# Process arguments
args = parser.parse_args()
run_name = args.name
json_fp = dispatcher.expandPath(args.json)
read_dir = args.rdir
bam_dir = args.bdir
out_dir = args.odir
trim = args.trim
qual = args.qual
minlen = args.minlen
aligner = args.aligner
aligner_args = args.aargs
depth = args.depth
breadth = args.breadth
proportion = args.proportion
percid = args.percid
adapters = dispatcher.expandPath(args.adapters)
dispatcher.job_manager = args.job_manager.upper()
dispatcher.job_manager_args = args.sargs
smor = args.smor
if not out_dir:
out_dir = os.getcwd()
if not (read_dir or bam_dir):
read_dir = os.getcwd()
out_dir = dispatcher.expandPath(out_dir)
if read_dir:
read_dir = dispatcher.expandPath(read_dir)
if bam_dir:
bam_dir = dispatcher.expandPath(bam_dir)
if os.path.exists(out_dir):
response = input(
"\nOutput folder %s already exists!\nFiles in it may be overwritten!\nShould we continue anyway [N]? "
% out_dir)
if not re.match('^[Yy]', response):
print("Operation cancelled!")
quit()
else:
os.makedirs(out_dir)
logfile = os.path.join(out_dir, "asap.log")
logging.basicConfig(level=logging.DEBUG,
format='%(asctime)s %(levelname)-8s %(message)s',
datefmt='%m/%d/%Y %H:%M:%S',
filename=logfile,
filemode='w')
logging.info(
"Combining reads in %s and JSON file: %s for run: %s. Trim=%s Qual=%s"
% (read_dir, json_fp, run_name, trim, qual))
assay_list = assayInfo.parseJSON(json_fp)
bam_list = []
output_files = []
final_jobs = []
xml_dir = os.path.join(out_dir, "xml")
if not os.path.exists(xml_dir):
os.makedirs(xml_dir)
if bam_dir:
bam_list = dispatcher.findBams(bam_dir)
if read_dir:
reference = assayInfo.generateReference(assay_list)
ref_fasta = os.path.join(out_dir, "reference.fasta")
reference.write(ref_fasta, 'fasta')
index_job = dispatcher.indexFasta(ref_fasta, aligner)
read_list = dispatcher.findReads(read_dir)
for read in read_list:
if (not read.reads):
#TODO: write out appropriate xml for samples with empty read files so they show up in results
continue
if trim:
trimmed_reads = dispatcher.trimAdapters(*read,
outdir=out_dir,
adapters=adapters,
quality=qual,
minlen=minlen)
(bam_file, job_id) = dispatcher.alignReadsToReference(
trimmed_reads.sample,
trimmed_reads.reads,
ref_fasta,
out_dir,
jobid=trimmed_reads.jobid,
aligner=aligner,
args=aligner_args)
else:
(bam_file, job_id) = dispatcher.alignReadsToReference(
read.sample,
read.reads,
ref_fasta,
out_dir,
jobid=index_job,
aligner=aligner,
args=aligner_args)
bam_list.append((read.sample, bam_file, job_id))
for sample, bam, job in bam_list:
(xml_file, job_id) = dispatcher.processBam(sample, json_fp, bam,
xml_dir, job, depth,
breadth, proportion,
percid, smor)
output_files.append(xml_file)
final_jobs.append(job_id)
(final_output,
job) = dispatcher.combineOutputFiles(run_name, xml_dir, out_dir,
final_jobs)
print(
"All jobs are submitted, the final job id is: %s. Output will be in %s when ready."
% (job, final_output))
return 0
except KeyboardInterrupt:
### handle keyboard interrupt ###
return 0
except Exception as e:
if DEBUG or TESTRUN:
raise (e)
indent = len(program_name) * " "
sys.stderr.write(program_name + ": " + repr(e) + "\n")
sys.stderr.write(indent + " for help use --help")
return 2
def main(argv=None): # IGNORE:C0111
'''Command line options.'''
if argv is None:
argv = sys.argv
else:
sys.argv.extend(argv)
program_name = os.path.basename(sys.argv[0])
program_version = "v%s" % __version__
program_build_date = str(__updated__)
program_version_message = '%%(prog)s %s (%s)' % (program_version, program_build_date)
if __name__ == '__main__':
program_shortdesc = __import__('__main__').__doc__.split("\n")[1]
else:
program_shortdesc = __doc__.split("\n")[1]
#program_shortdesc = __import__('__main__').__doc__.split("\n")[1]
program_license = '''%s
Created by TGen North on %s.
Copyright 2015 TGen North. All rights reserved.
Available for academic and research use only under a license
from The Translational Genomics Research Institute (TGen)
that is free for non-commercial use.
Distributed on an "AS IS" basis without warranties
or conditions of any kind, either express or implied.
USAGE
''' % (program_shortdesc, str(__date__))
try:
# Setup argument parser
parser = argparse.ArgumentParser(description=program_license, formatter_class=argparse.RawDescriptionHelpFormatter)
required_group = parser.add_argument_group("required arguments")
required_group.add_argument("-j", "--json", metavar="FILE", required=True, help="JSON file of assay descriptions. [REQUIRED]")
required_group.add_argument("-b", "--bam", metavar="FILE", required=True, help="BAM file to analyze. [REQUIRED]")
#required_group.add_argument("-r", "--ref", metavar="FILE", required=True, help="reference fasta file, should already be indexed. [REQUIRED]")
#parser.add_argument("-o", "--out-dir", dest="odir", metavar="DIR", help="directory to write output files to. [default: `pwd`]")
required_group.add_argument("-o", "--out", metavar="FILE", required=True, help="XML file to write output to. [REQUIRED]")
#parser.add_argument("-n", "--name", help="sample name, if not provided it will be derived from BAM file")
parser.add_argument("-d", "--depth", default=100, type=int, help="minimum read depth required to consider a position covered. [default: 100]")
parser.add_argument("--breadth", default=0.8, type=float, help="minimum breadth of coverage required to consider an amplicon as present. [default: 0.8]")
parser.add_argument("-p", "--proportion", default=0.1, type=float, help="minimum proportion required to call a SNP at a given position. [default: 0.1]")
parser.add_argument("-V", "--version", action="version", version=program_version_message)
# Process arguments
args = parser.parse_args()
json_fp = args.json
bam_fp = args.bam
out_fp = args.out
depth = args.depth
breadth = args.breadth
proportion = args.proportion
#ref_fp = args.ref
#out_dir = args.odir
#if not out_dir:
# out_dir = os.getcwd()
#out_dir = dispatcher.expandPath(out_dir)
#if not os.path.exists(out_dir):
# os.makedirs(out_dir)
assay_list = assayInfo.parseJSON(json_fp)
samdata = pysam.AlignmentFile(bam_fp, "rb")
#reference = pysam.FastaFile(ref_fp)
sample_dict = {}
if 'RG' in samdata.header :
sample_dict['name'] = samdata.header['RG'][0]['ID']
else:
sample_dict['name'] = os.path.splitext(os.path.basename(bam_fp))[0]
sample_dict['mapped_reads'] = str(samdata.mapped)
sample_dict['unmapped_reads'] = str(samdata.unmapped)
sample_dict['unassigned_reads'] = str(samdata.nocoordinate)
sample_node = ElementTree.Element("sample", sample_dict)
#out_fp = os.path.join(out_dir, sample_dict['name']+".xml")
for assay in assay_list:
assay_dict = {}
assay_dict['name'] = assay.name
assay_dict['type'] = assay.assay_type
assay_node = ElementTree.SubElement(sample_node, "assay", assay_dict)
ref_name = assay.name
reverse_comp = assay.target.reverse_comp
for amplicon in assay.target.amplicons:
ref_name = assay.name + "_%s" % amplicon.variant_name if amplicon.variant_name else assay.name
amplicon_dict = {}
amplicon_dict['reads'] = str(samdata.count(ref_name))
if amplicon.variant_name:
amplicon_dict['variant'] = amplicon.variant_name
amplicon_node = ElementTree.SubElement(assay_node, "amplicon", amplicon_dict)
if samdata.count(ref_name) == 0:
significance_node = ElementTree.SubElement(amplicon_node, "significance", {"flag":"no coverage"})
#Check for indeterminate resistances
resistances = set()
if amplicon.significance and amplicon.significance.resistance:
resistances.add(amplicon.significance.resistance)
for snp in amplicon.SNPs:
if snp.significance.resistance:
resistances.add(snp.significance.resistance)
for roi in amplicon.ROIs:
if roi.significance.resistance:
resistances.add(roi.significance.resistance)
if resistances:
significance_node.set("resistance", ",".join(resistances))
else:
if amplicon.significance or samdata.count(ref_name) < depth:
significance_node = ElementTree.SubElement(amplicon_node, "significance")
if amplicon.significance:
significance_node.text = amplicon.significance.message
if amplicon.significance.resistance:
significance_node.set("resistance", amplicon.significance.resistance)
if samdata.count(ref_name) < depth:
significance_node.set("flag", "low coverage")
#Check for indeterminate resistances
resistances = set()
if amplicon.significance and amplicon.significance.resistance:
resistances.add(amplicon.significance.resistance)
for snp in amplicon.SNPs:
if snp.significance.resistance:
resistances.add(snp.significance.resistance)
for roi in amplicon.ROIs:
if roi.significance.resistance:
resistances.add(roi.significance.resistance)
if resistances:
significance_node.set("resistance", ",".join(resistances))
pileup = samdata.pileup(ref_name, max_depth=1000000)
amplicon_data = _process_pileup(pileup, amplicon, depth, proportion)
if float(amplicon_data['breadth']) < breadth*100:
significance_node = amplicon_node.find("significance")
if significance_node is None:
significance_node = ElementTree.SubElement(amplicon_node, "significance")
if not significance_node.get("flag"):
significance_node.set("flag", "insufficient breadth of coverage")
for snp in amplicon_data['SNPs']:
_add_snp_node(amplicon_node, snp)
# This would be helpful, but count_coverage is broken in python3
#print(samdata.count_coverage(ref_name, snp.position-1, snp.position))
del amplicon_data['SNPs']
_write_parameters(amplicon_node, amplicon_data)
for roi in amplicon.ROIs:
roi_dict = _process_roi(roi, samdata, ref_name, reverse_comp)
_add_roi_node(amplicon_node, roi, roi_dict, depth, proportion)
samdata.close()
_write_xml(sample_node, out_fp)
return 0
except KeyboardInterrupt:
### handle keyboard interrupt ###
return 0
except Exception as e:
if DEBUG or TESTRUN:
raise(e)
indent = len(program_name) * " "
sys.stderr.write(program_name + ": " + repr(e) + "\n")
sys.stderr.write(indent + " for help use --help")
return 2
def main(argv=None): # IGNORE:C0111
'''Command line options.'''
if argv is None:
argv = sys.argv
else:
sys.argv.extend(argv)
program_name = os.path.basename(sys.argv[0])
program_version = "v%s" % __version__
program_build_date = str(__updated__)
program_version_message = '%%(prog)s %s (%s)' % (program_version,
program_build_date)
if __name__ == '__main__':
program_shortdesc = __import__('__main__').__doc__.split("\n")[1]
else:
program_shortdesc = __doc__.split("\n")[1]
#program_shortdesc = __import__('__main__').__doc__.split("\n")[1]
program_license = '''%s
Created by TGen North on %s.
Copyright 2015 TGen North. All rights reserved.
Available for academic and research use only under a license
from The Translational Genomics Research Institute (TGen)
that is free for non-commercial use.
Distributed on an "AS IS" basis without warranties
or conditions of any kind, either express or implied.
USAGE
''' % (program_shortdesc, str(__date__))
try:
# Setup argument parser
parser = argparse.ArgumentParser(
description=program_license,
formatter_class=argparse.RawDescriptionHelpFormatter)
required_group = parser.add_argument_group("required arguments")
required_group.add_argument(
"-j",
"--json",
metavar="FILE",
required=True,
help="JSON file of assay descriptions. [REQUIRED]")
required_group.add_argument("-b",
"--bam",
metavar="FILE",
required=True,
help="BAM file to analyze. [REQUIRED]")
#required_group.add_argument("-r", "--ref", metavar="FILE", required=True, help="reference fasta file, should already be indexed. [REQUIRED]")
#parser.add_argument("-o", "--out-dir", dest="odir", metavar="DIR", help="directory to write output files to. [default: `pwd`]")
required_group.add_argument(
"-o",
"--out",
metavar="FILE",
required=True,
help="XML file to write output to. [REQUIRED]")
#parser.add_argument("-n", "--name", help="sample name, if not provided it will be derived from BAM file")
parser.add_argument(
"-d",
"--depth",
default=100,
type=int,
help=
"minimum read depth required to consider a position covered. [default: 100]"
)
parser.add_argument(
"--breadth",
default=0.8,
type=float,
help=
"minimum breadth of coverage required to consider an amplicon as present. [default: 0.8]"
)
parser.add_argument(
"-p",
"--proportion",
default=0.1,
type=float,
help=
"minimum proportion required to call a SNP at a given position. [default: 0.1]"
)
parser.add_argument(
"-i",
"--identity",
dest="percid",
default=0,
type=float,
help=
"minimum percent identity required to align a read to a reference amplicon sequence. [default: 0]"
)
parser.add_argument(
"-s",
"--smor",
action="store_true",
default=False,
help=
"perform SMOR analysis with overlapping reads. [default: False]")
parser.add_argument("-V",
"--version",
action="version",
version=program_version_message)
# Process arguments
args = parser.parse_args()
json_fp = args.json
bam_fp = args.bam
out_fp = args.out
depth = args.depth
breadth = args.breadth
proportion = args.proportion
percid = args.percid
smor = args.smor
#ref_fp = args.ref
#out_dir = args.odir
#if not out_dir:
# out_dir = os.getcwd()
#out_dir = dispatcher.expandPath(out_dir)
#if not os.path.exists(out_dir):
# os.makedirs(out_dir)
assay_list = assayInfo.parseJSON(json_fp)
samdata = pysam.AlignmentFile(bam_fp, "rb")
#reference = pysam.FastaFile(ref_fp)
sample_dict = {}
if 'RG' in samdata.header:
sample_dict['name'] = samdata.header['RG'][0]['ID']
else:
sample_dict['name'] = os.path.splitext(os.path.basename(bam_fp))[0]
sample_dict['mapped_reads'] = str(samdata.mapped)
sample_dict['unmapped_reads'] = str(samdata.unmapped)
sample_dict['unassigned_reads'] = str(samdata.nocoordinate)
sample_dict['depth_filter'] = str(depth)
sample_dict['proportion_filter'] = str(proportion)
sample_dict['breadth_filter'] = str(breadth)
if percid:
sample_dict['identity_filter'] = str(percid)
sample_dict['json_file'] = json_fp
sample_dict['bam_file'] = bam_fp
sample_node = ElementTree.Element("sample", sample_dict)
#out_fp = os.path.join(out_dir, sample_dict['name']+".xml")
for assay in assay_list:
assay_dict = {}
assay_dict['name'] = assay.name
assay_dict['type'] = assay.assay_type
assay_dict['function'] = assay.target.function
assay_dict['gene'] = assay.target.gene_name or ""
assay_node = ElementTree.SubElement(sample_node, "assay",
assay_dict)
ref_name = assay.name
reverse_comp = assay.target.reverse_comp
for amplicon in assay.target.amplicons:
temp_file = None
ref_name = assay.name + "_%s" % amplicon.variant_name if amplicon.variant_name else assay.name
amplicon_dict = {}
if percid:
(temp_file, discarded_reads) = _verify_percent_identity(
samdata, ref_name, amplicon, percid)
samdata = pysam.AlignmentFile(temp_file, "rb")
amplicon_dict['discarded_reads'] = str(discarded_reads)
elif samdata.closed:
samdata = pysam.AlignmentFile(bam_fp, "rb")
amplicon_dict['reads'] = str(samdata.count(ref_name))
if amplicon.variant_name:
amplicon_dict['variant'] = amplicon.variant_name
amplicon_node = ElementTree.SubElement(assay_node, "amplicon",
amplicon_dict)
if samdata.count(ref_name) == 0:
significance_node = ElementTree.SubElement(
amplicon_node, "significance", {"flag": "no coverage"})
#Check for indeterminate resistances
resistances = set()
if amplicon.significance and amplicon.significance.resistance:
resistances.add(amplicon.significance.resistance)
for snp in amplicon.SNPs:
if snp.significance.resistance:
resistances.add(snp.significance.resistance)
for roi in amplicon.ROIs:
if roi.significance.resistance:
resistances.add(roi.significance.resistance)
if resistances:
significance_node.set("resistance",
",".join(resistances))
else:
if amplicon.significance or samdata.count(
ref_name) < depth:
significance_node = ElementTree.SubElement(
amplicon_node, "significance")
if amplicon.significance:
significance_node.text = amplicon.significance.message
if amplicon.significance.resistance:
significance_node.set(
"resistance",
amplicon.significance.resistance)
if samdata.count(ref_name) < depth:
significance_node.set("flag", "low coverage")
#Check for indeterminate resistances
resistances = set()
if amplicon.significance and amplicon.significance.resistance:
resistances.add(
amplicon.significance.resistance)
for snp in amplicon.SNPs:
if snp.significance.resistance:
resistances.add(
snp.significance.resistance)
for roi in amplicon.ROIs:
if roi.significance.resistance:
resistances.add(
roi.significance.resistance)
if resistances:
significance_node.set("resistance",
",".join(resistances))
pileup = samdata.pileup(ref_name, max_depth=1000000)
if smor:
amplicon_data = _process_pileup_SMOR(
pileup, amplicon, depth, proportion)
else:
amplicon_data = _process_pileup(
pileup, amplicon, depth, proportion)
if float(amplicon_data['breadth']) < breadth * 100:
significance_node = amplicon_node.find("significance")
if significance_node is None:
significance_node = ElementTree.SubElement(
amplicon_node, "significance")
if not significance_node.get("flag"):
significance_node.set(
"flag", "insufficient breadth of coverage")
for snp in amplicon_data['SNPs']:
_add_snp_node(amplicon_node, snp)
# This would be helpful, but count_coverage is broken in python3
#print(samdata.count_coverage(ref_name, snp.position-1, snp.position))
del amplicon_data['SNPs']
_write_parameters(amplicon_node, amplicon_data)
for roi in amplicon.ROIs:
if smor:
roi_dict = _process_roi_SMOR(
roi, samdata, ref_name, reverse_comp)
else:
roi_dict = _process_roi(roi, samdata, ref_name,
reverse_comp)
_add_roi_node(amplicon_node, roi, roi_dict, depth,
proportion)
if temp_file:
samdata.close()
os.remove(temp_file)
os.remove(temp_file + ".bai")
if samdata.is_open():
samdata.close()
_write_xml(sample_node, out_fp)
return 0
except KeyboardInterrupt:
### handle keyboard interrupt ###
return 0
except Exception as e:
if DEBUG or TESTRUN:
raise (e)
indent = len(program_name) * " "
sys.stderr.write(program_name + ": " + repr(e) + "\n")
sys.stderr.write(indent + " for help use --help")
return 2
def main(argv=None): # IGNORE:C0111
'''Command line options.'''
if argv is None:
argv = sys.argv
else:
sys.argv.extend(argv)
program_name = os.path.basename(sys.argv[0])
program_version = "v%s" % __version__
program_build_date = str(__updated__)
program_version_message = '%%(prog)s %s (%s)' % (program_version, program_build_date)
if __name__ == '__main__':
program_shortdesc = __import__('__main__').__doc__.split("\n")[1]
else:
program_shortdesc = __doc__.split("\n")[1]
#program_shortdesc = __import__('__main__').__doc__.split("\n")[1]
program_license = '''%s
Created by TGen North on %s.
Copyright 2015 TGen North. All rights reserved.
Available for academic and research use only under a license
from The Translational Genomics Research Institute (TGen)
that is free for non-commercial use.
Distributed on an "AS IS" basis without warranties
or conditions of any kind, either express or implied.
USAGE
''' % (program_shortdesc, str(__date__))
try:
# Setup argument parser
parser = argparse.ArgumentParser(description=program_license, formatter_class=argparse.RawDescriptionHelpFormatter)
required_group = parser.add_argument_group("required arguments")
required_group.add_argument("-n", "--name", required=True, help="name for this run. [REQUIRED]")
required_group.add_argument("-j", "--json", required=True, help="JSON file of assay descriptions. [REQUIRED]")
optional_group = parser.add_argument_group("optional arguments")
reads_bams_group = optional_group.add_mutually_exclusive_group()
reads_bams_group.add_argument("-r", "--read-dir", dest="rdir", metavar="DIR", help="directory of read files to analyze.")
reads_bams_group.add_argument("-b", "--bam-dir", dest="bdir", metavar="DIR", help="directory of bam files to analyze.")
optional_group.add_argument("-o", "--out-dir", dest="odir", metavar="DIR", help="directory to write output files to. [default: `pwd`]")
trim_group = parser.add_argument_group("read trimming options")
on_off_group = trim_group.add_mutually_exclusive_group()
on_off_group.add_argument("--trim", action="store_true", default=True, help="perform adapter trimming on reads. [default: True]")
on_off_group.add_argument("--no-trim", dest="trim", action="store_false", help="do not perform adapter trimming.")
trim_group.add_argument("-s", "--adapter-sequences", dest="adapters", default="/scratch/dlemmer/ASAP/illumina_adapters_all.fasta", help="location of the adapter sequence file to use for trimming. [default: /scratch/dlemmer/ASAP/illumina_adapters_all.fasta]")
trim_group.add_argument("-q", "--qual", nargs="?", const="SLIDINGWINDOW:5:20", help="perform quality trimming [default: False], optional parameter can be used to customize quality trimming parameters to trimmomatic. [default: SLIDINGWINDOW:5:20]")
trim_group.add_argument("-m", "--minlen", metavar="LEN", default=80, type=int, help="minimum read length to keep after trimming. [default: 80]")
align_group = parser.add_argument_group("read mapping options")
align_group.add_argument("-a", "--aligner", default="bowtie2", help="aligner to use for read mapping, supports bowtie2, novoalign, and bwa. [default: bowtie2]")
align_group.add_argument("--aligner-args", dest="aargs", metavar="ARGS", default='', help="additional arguments to pass to the aligner, enclosed in \"\".")
align_group.add_argument("-d", "--depth", default=100, type=int, help="minimum read depth required to consider a position covered. [default: 100]")
align_group.add_argument("--breadth", default=0.8, type=float, help="minimum breadth of coverage required to consider an amplicon as present. [default: 0.8]")
align_group.add_argument("-p", "--proportion", default=0.1, type=float, help="minimum proportion required to call a SNP at a given position. [default: 0.1]")
parser.add_argument("-V", "--version", action="version", version=program_version_message)
# Process arguments
args = parser.parse_args()
run_name = args.name
json_fp = dispatcher.expandPath(args.json)
read_dir = args.rdir
bam_dir = args.bdir
out_dir = args.odir
trim = args.trim
qual = args.qual
minlen = args.minlen
aligner = args.aligner
aligner_args = args.aargs
depth = args.depth
breadth = args.breadth
proportion = args.proportion
adapters = dispatcher.expandPath(args.adapters)
if not out_dir:
out_dir = os.getcwd()
if not (read_dir or bam_dir):
read_dir = os.getcwd()
out_dir = dispatcher.expandPath(out_dir)
if read_dir:
read_dir = dispatcher.expandPath(read_dir)
if bam_dir:
bam_dir = dispatcher.expandPath(bam_dir)
if os.path.exists(out_dir):
response = input(
"\nOutput folder %s already exists!\nFiles in it may be overwritten!\nShould we continue anyway [N]? " % out_dir)
if not re.match('^[Yy]', response):
print("Operation cancelled!")
quit()
else:
os.makedirs(out_dir)
logfile = os.path.join(out_dir, "asap.log")
logging.basicConfig(level=logging.DEBUG,
format='%(asctime)s %(levelname)-8s %(message)s',
datefmt='%m/%d/%Y %H:%M:%S',
filename=logfile,
filemode='w')
logging.info("Combining reads in %s and JSON file: %s for run: %s. Trim=%s Qual=%s" % (read_dir, json_fp, run_name, trim, qual))
assay_list = assayInfo.parseJSON(json_fp)
bam_list = []
output_files = []
final_jobs = []
xml_dir = os.path.join(out_dir, "xml")
if not os.path.exists(xml_dir):
os.makedirs(xml_dir)
if bam_dir:
bam_list = dispatcher.findBams(bam_dir)
if read_dir:
reference = assayInfo.generateReference(assay_list)
ref_fasta = os.path.join(out_dir, "reference.fasta")
reference.write(ref_fasta, 'fasta')
index_job = dispatcher.indexFasta(ref_fasta, aligner)
read_list = dispatcher.findReads(read_dir)
for read in read_list:
if (not read.reads):
#TODO: write out appropriate xml for samples with empty read files so they show up in results
continue
if trim:
trimmed_reads = dispatcher.trimAdapters(*read, outdir=out_dir, adapters=adapters, quality=qual, minlen=minlen)
(bam_file, job_id) = dispatcher.alignReadsToReference(trimmed_reads.sample, trimmed_reads.reads, ref_fasta, out_dir, jobid=trimmed_reads.jobid, aligner=aligner, args=aligner_args)
else:
(bam_file, job_id) = dispatcher.alignReadsToReference(read.sample, read.reads, ref_fasta, out_dir, jobid=index_job, aligner=aligner, args=aligner_args)
bam_list.append((read.sample, bam_file, job_id))
for sample, bam, job in bam_list:
(xml_file, job_id) = dispatcher.processBam(sample, json_fp, bam, xml_dir, job, depth, breadth, proportion)
output_files.append(xml_file)
final_jobs.append(job_id)
(final_output, job) = dispatcher.combineOutputFiles(run_name, xml_dir, out_dir, final_jobs)
print("All jobs are submitted, the final job id is: %s. Output will be in %s when ready." % (job, final_output))
return 0
except KeyboardInterrupt:
### handle keyboard interrupt ###
return 0
except Exception as e:
if DEBUG or TESTRUN:
raise(e)
indent = len(program_name) * " "
sys.stderr.write(program_name + ": " + repr(e) + "\n")
sys.stderr.write(indent + " for help use --help")
return 2