def parse_args( args=sys.argv[1:] ):
import argparse
from ngs_mapper import config
conf_parser, args, config, configfile = config.get_config_argparse(args)
defaults = config['roche_sync']
parser = argparse.ArgumentParser(
description='Sync roche run directories into the NGSData data structure',
parents=[conf_parser]
)
parser.add_argument(
'runpath',
help='Path to the Roche run directory(/path/to/R_something)'
)
parser.add_argument(
'--ngsdata',
default=defaults['ngsdata']['default'],
help=defaults['ngsdata']['help']
)
import pkg_resources
default = defaults['midparse']['default']
if default is None:
default = pkg_resources.resource_filename(__name__, 'MidParse.conf')
parser.add_argument(
'--midparse',
default=default,
help=defaults['midparse']['help']
)
return parser.parse_args( args )
def parse_args(args=sys.argv[1:]):
from ngs_mapper import config
conf_parser, args, config, configfile = config.get_config_argparse(args)
defaults = config['tagreads']
parser = argparse.ArgumentParser(
description=
'''Adds Sanger, MiSeq, 454 and IonTorrent read groups to a bam file.
Will tag all reads in the alignment for each of the platforms based on the read name''',
parents=[conf_parser])
parser.add_argument(dest='bamfiles',
nargs='+',
help='Bamfile to add read groups to for platforms')
parser.add_argument('-SM',
dest='SM',
default=defaults['SM']['default'],
help=defaults['SM']['help'])
parser.add_argument('-CN',
dest='CN',
default=defaults['CN']['default'],
help=defaults['CN']['help'])
return parser.parse_args(args)
def parse_args(args=sys.argv[1:]):
import argparse
from ngs_mapper import config
conf_parser, args, config, configfile = config.get_config_argparse(args)
defaults = config['roche_sync']
parser = argparse.ArgumentParser(
description=
'Sync roche run directories into the NGSData data structure',
parents=[conf_parser])
parser.add_argument(
'runpath',
help='Path to the Roche run directory(/path/to/R_something)')
parser.add_argument('--ngsdata',
default=defaults['ngsdata']['default'],
help=defaults['ngsdata']['help'])
import pkg_resources
default = defaults['midparse']['default']
if default is None:
default = pkg_resources.resource_filename(__name__, 'MidParse.conf')
parser.add_argument('--midparse',
default=default,
help=defaults['midparse']['help'])
return parser.parse_args(args)
def parse_args( args=sys.argv[1:] ):
import argparse
from ngs_mapper import config
conf_parser, args, config, configfile = config.get_config_argparse(args)
defaults = config['sanger_sync']
parser = argparse.ArgumentParser(
description='Syncs Sanger Run_ directories into the NGSData structure',
parents=[conf_parser]
)
parser.add_argument(
'--ngsdata',
dest='ngsdata',
default=defaults['ngsdata']['default'],
help=defaults['ngsdata']['help']
)
parser.add_argument(
'runpath',
help='Path to Sanger Run_3130xl directory'
)
return parser.parse_args( args )
def parse_args( args=sys.argv[1:] ):
from ngs_mapper import config
conf_parser, args, config, configfile = config.get_config_argparse(args)
defaults = config['tagreads']
parser = argparse.ArgumentParser(
description='''Adds Sanger, MiSeq, 454 and IonTorrent read groups to a bam file.
Will tag all reads in the alignment for each of the platforms based on the read name''',
parents=[conf_parser]
)
parser.add_argument(
dest='bamfiles',
nargs='+',
help='Bamfile to add read groups to for platforms'
)
parser.add_argument(
'-SM',
dest='SM',
default=defaults['SM']['default'],
help=defaults['SM']['help']
)
parser.add_argument(
'-CN',
dest='CN',
default=defaults['CN']['default'],
help=defaults['CN']['help']
)
return parser.parse_args( args )
def parse_args(args=sys.argv[1:]):
import argparse
from ngs_mapper import config
conf_parser, args, config, configfile = config.get_config_argparse(args)
defaults = config['sanger_sync']
parser = argparse.ArgumentParser(
description='Syncs Sanger Run_ directories into the NGSData structure',
parents=[conf_parser])
parser.add_argument('--ngsdata',
dest='ngsdata',
default=defaults['ngsdata']['default'],
help=defaults['ngsdata']['help'])
parser.add_argument('runpath', help='Path to Sanger Run_3130xl directory')
return parser.parse_args(args)
def parse_args():
conf_parser, args, cfg, configfile = config.get_config_argparse(sys.argv[1:])
defaults = cfg['ion_sync']
parser = argparse.ArgumentParser(
description='Sync roche run directories into the NGSData data structure',
parents=[conf_parser]
)
parser.add_argument(
'rundir',
help='Path to IonTorrent or IonProton run which contains' \
' an ion_params_00.json file and a ' \
' plugin_out/downloads directory with fastq files'
)
parser.add_argument(
'--ngsdata',
default=defaults['ngsdata']['default'],
help=defaults['ngsdata']['help']
)
parser.add_argument(
'--print-samplemapping',
dest='print_samplemapping',
default=False,
action='store_true',
help='Just print the sample mapping for the run and quit'
)
parser.add_argument(
'--min-fastq-size',
dest='min_fastq_size',
type=int,
default=defaults['min_fastq_size']['default'],
help=defaults['min_fastq_size']['help']
)
return parser.parse_args(args)
def parse_args( args=sys.argv[1:] ):
from ngs_mapper import config
conf_parser, args, config, configfile = config.get_config_argparse(args)
defaults = config['miseq_sync']
parser = argparse.ArgumentParser(
description='Sync MiSeq run into the NGSData structure',
parents=[conf_parser]
)
parser.add_argument(
'runpath',
help='Path to the run to be synced(/path/to/YYMMDD_)'
)
parser.add_argument(
'--ngsdata',
default=defaults['ngsdata']['default'],
help=defaults['ngsdata']['help']
)
return parser.parse_args( args )
def parse_args(args=sys.argv[1:]):
conf_parser, args, _config, configfile = config.get_config_argparse(args)
parser = argparse.ArgumentParser(
description='Runs a single sample through the pipeline',
parents=[conf_parser])
parser.add_argument(dest='readsdir',
help='Directory that contains reads to be mapped')
parser.add_argument(dest='reference',
help='The path to the reference to map to')
parser.add_argument(
dest='prefix',
help=
'The prefix to put before every output file generated. Probably the samplename'
)
parser.add_argument(
'-trim_qual',
dest='trim_qual',
default=_config['trim_reads']['q']['default'],
help=_config['trim_reads']['q']['help'],
)
parser.add_argument(
'-head_crop',
dest='head_crop',
default=_config['trim_reads']['headcrop']['default'],
help=_config['trim_reads']['headcrop']['help'],
)
parser.add_argument('--primer-file',
dest='primer_file',
default=_config['trim_reads']['primerfile']['default'],
help=_config['trim_reads']['primerfile']['help'])
parser.add_argument('--primer-seed',
dest='primer_seed',
default=_config['trim_reads']['primerseed']['default'],
help=_config['trim_reads']['primerseed']['help'])
parser.add_argument(
'--palindrome-clip',
dest='palindrom_clip',
default=_config['trim_reads']['palindromeclip']['default'],
help=_config['trim_reads']['palindromeclip']['help'])
parser.add_argument('--simple-clip',
dest='simple_clip',
default=_config['trim_reads']['simpleclip']['default'],
help=_config['trim_reads']['simpleclip']['help'])
minth_default = 0.8
parser.add_argument(
'-minth',
dest='minth',
default=_config['base_caller']['minth']['default'],
help=_config['base_caller']['minth']['help'],
)
parser.add_argument(
'--CN',
dest='CN',
default=_config['tagreads']['CN']['default'],
help=_config['tagreads']['CN']['help'],
)
parser.add_argument(
'--index-min',
dest='index_min',
default=_config['ngs_filter']['indexQualityMin']['default'],
help=_config['ngs_filter']['indexQualityMin']['help'],
)
parser.add_argument(
'--drop-ns',
dest='drop_ns',
action='store_true',
default=_config['ngs_filter']['dropNs']['default'],
help=_config['ngs_filter']['dropNs']['help'],
)
parser.add_argument(
'--platforms',
dest='platforms',
default=_config['ngs_filter']['platforms']['default'],
help=_config['ngs_filter']['platforms']['help'],
)
default_outdir = os.getcwd()
parser.add_argument(
'-od',
'--outdir',
dest='outdir',
default=default_outdir,
help='The output directory for all files to be put[Default: {0}]'.
format(default_outdir))
args, rest = parser.parse_known_args(args)
args.config = configfile
# Parse qsub args if found
if rest and rest[0].startswith('--qsub'):
qsub_parser = argparse.ArgumentParser(add_help=False)
qsub_parser.add_argument('--qsub-help',
default=False,
action='store_true')
qsub_parser.add_argument(
'--qsub_l',
default='nodes=1:ppn=1',
)
qsub_parser.add_argument('--qsub_M', default=None)
qsub_args = qsub_parser.parse_args(rest)
if qsub_args.qsub_help:
qsub_parser.print_help()
sys.exit(1)
rest = qsub_args
return args, rest
def parse_args( args=sys.argv[1:] ):
'''
Uses argparse to parse arguments
@params args - List of command line arguments to parse
@returns Namespace object with parsed args in it(Same as ArgumentParser.parse_args)
'''
import argparse
from ngs_mapper import config
conf_parser, args, config, configfile = config.get_config_argparse(args)
defaults = config['run_bwa_on_samplename']
parser = argparse.ArgumentParser(
description='Runs the bwa mem argument on a given set of reads and references for the given platform\'s reads',
epilog='You should consider this script an autonomous bwa operation. That is, it will select the reads for ' \
'the platforms you select and it will pull those reads onto the current host. It will ' \
'compile references if they are multiple ones in a directory you select onto the local computer. Then it ' \
'will map any mated reads against to those refs and also map the nonpaired reads against that ref in a separate ' \
'call. Then when both are finished it will convert to bam/sort/index/merge/reindex the results. It attempts all of ' \
'this inside of the /dev/shm filesystem which should be very fast. If /dev/shm cannot be used then /tmp will be used. '\
'If you want the temporary files that are created to stay then you can use the --keep-temp argument',
parents=[conf_parser]
)
parser.add_argument(
dest='reads',
help='Location to a directory containing fastq read files'
)
parser.add_argument(
dest='reference',
help='Location of the reference to map to. Should be a fasta file or directory of fasta files that will be compiled together.'
)
parser.add_argument(
'--platforms',
dest='platforms',
nargs='+',
choices=defaults['platforms']['choices'],
default=defaults['platforms']['default'],
help=defaults['platforms']['help']
)
parser.add_argument(
'-o',
'--output',
dest='output',
default=defaults['output']['default'],
help=defaults['output']['default']
)
parser.add_argument(
'--keep-temp',
dest='keep_temp',
action='store_true',
default=defaults['keep_temp']['default'],
help=defaults['keep_temp']['help']
)
parser.add_argument(
'-t',
dest='threads',
default=defaults['threads']['default'],
type=int,
help=defaults['threads']['help']
)
return parser.parse_args( args )
def parse_args(args=sys.argv[1:]):
from ngs_mapper import config
conf_parser, args, config, configfile = config.get_config_argparse(args)
defaults = config['base_caller']
parser = argparse.ArgumentParser(
description = 'Generates a VCF that has called bases in it which follow ' \
'the WRAIR VDB SOP for calling bases',
epilog = '''WRAIR VDB Base Calling SOP:
Depth < 10:
All bases with base quality < 25 get set to N
Then the base is called on the percentage(See below)
Depth > 10:
All bases with base quality < 25 get removed
Then the base is called on the percentage(See below)
Calling on Percentage:
Any base with >= 80% majority is called
- or -
N is called if the depth was < 10 and N is > 20%
- or -
The specific IUPAC ambiguious base is called for all bases over
20%
- or -
The majority base is called
''',
parents=[conf_parser]
)
parser.add_argument(
dest='bamfile',
help='The bam file to generate the vcf for'
)
parser.add_argument(
dest='reffile',
help='The reference file(has to have an fai index already built)'
)
parser.add_argument(
dest='vcf_output_file',
help='Where to save the vcf'
)
parser.add_argument(
'-r',
'--regionstr',
dest='regionstr',
default=defaults['regionstr']['default'],
help=defaults['regionstr']['help']
)
parser.add_argument(
'-minbq',
dest='minbq',
default=defaults['minbq']['default'],
type=int,
help=defaults['minbq']['help']
)
parser.add_argument(
'-maxd',
dest='maxd',
default=defaults['maxd']['default'],
type=int,
help=defaults['maxd']['help']
)
parser.add_argument(
'-mind',
dest='mind',
default=defaults['mind']['default'],
type=int,
help=defaults['mind']['help']
)
parser.add_argument(
'-minth',
dest='minth',
default=defaults['minth']['default'],
type=float,
help=defaults['minth']['help']
)
parser.add_argument(
'-biasth',
dest='biasth',
default=defaults['biasth']['default'],
type=float,
help=defaults['biasth']['help']
)
parser.add_argument(
'-bias',
dest='bias',
default=defaults['bias']['default'],
type=int,
help=defaults['bias']['help']
)
parser.add_argument(
'--threads',
default=defaults['threads']['default'],
type=int,
help=defaults['threads']['help']
)
args = parser.parse_args(args)
if args.vcf_output_file is None:
args.vcf_output_file = args.bamfile + '.vcf'
return args
def parse_args( args=sys.argv[1:] ):
from ngs_mapper import config
conf_parser, args, config, configfile = config.get_config_argparse(args)
defaults = config['trim_reads']
parser = argparse.ArgumentParser(
parents=[conf_parser],
description='Trims reads'
)
parser.add_argument(
dest='readsdir',
help='Read or directory of read files'
)
parser.add_argument(
'-q',
dest='q',
default=defaults['q']['default'],
help=defaults['q']['help']
)
parser.add_argument(
'--head-crop',
dest='headcrop',
default=defaults['headcrop']['default'],
help=defaults['headcrop']['help']
)
parser.add_argument(
'-o',
dest='outputdir',
default=defaults['outputdir']['default'],
help=defaults['outputdir']['help']
)
parser.add_argument(
'--platforms',
dest='platforms',
choices=defaults['platforms']['choices'],
default=defaults['platforms']['default'],
help=defaults['platforms']['help']
)
parser.add_argument(
'--primer-file',
dest='primer_file',
default=defaults['primerfile']['default'],
help=defaults['primerfile']['help']
)
parser.add_argument(
'--primer-seed',
dest='primer_seed',
default=defaults['primerseed']['default'],
help=defaults['primerseed']['help']
)
parser.add_argument(
'--palindrome-clip',
dest='palindrom_clip',
default=defaults['palindromeclip']['default'],
help=defaults['palindromeclip']['help']
)
parser.add_argument(
'--simple-clip',
dest='simple_clip',
default=defaults['simpleclip']['default'],
help=defaults['simpleclip']['help']
)
return parser.parse_args( args )
def parse_args( args=sys.argv[1:] ):
conf_parser, args, _config, configfile = config.get_config_argparse(args)
parser = argparse.ArgumentParser(
description='Runs a single sample through the pipeline',
parents=[conf_parser]
)
parser.add_argument(
dest='readsdir',
help='Directory that contains reads to be mapped'
)
parser.add_argument(
dest='reference',
help='The path to the reference to map to'
)
parser.add_argument(
dest='prefix',
help='The prefix to put before every output file generated. Probably the samplename'
)
parser.add_argument(
'-trim_qual',
dest='trim_qual',
default=_config['trim_reads']['q']['default'],
help=_config['trim_reads']['q']['help'],
)
parser.add_argument(
'-head_crop',
dest='head_crop',
default=_config['trim_reads']['headcrop']['default'],
help=_config['trim_reads']['headcrop']['help'],
)
parser.add_argument(
'--primer-file',
dest='primer_file',
default=_config['trim_reads']['primerfile']['default'],
help=_config['trim_reads']['primerfile']['help']
)
parser.add_argument(
'--primer-seed',
dest='primer_seed',
default=_config['trim_reads']['primerseed']['default'],
help=_config['trim_reads']['primerseed']['help']
)
parser.add_argument(
'--palindrome-clip',
dest='palindrom_clip',
default=_config['trim_reads']['palindromeclip']['default'],
help=_config['trim_reads']['palindromeclip']['help']
)
parser.add_argument(
'--simple-clip',
dest='simple_clip',
default=_config['trim_reads']['simpleclip']['default'],
help=_config['trim_reads']['simpleclip']['help']
)
minth_default=0.8
parser.add_argument(
'-minth',
dest='minth',
default=_config['base_caller']['minth']['default'],
help=_config['base_caller']['minth']['help'],
)
parser.add_argument(
'--CN',
dest='CN',
default=_config['tagreads']['CN']['default'],
help=_config['tagreads']['CN']['help'],
)
parser.add_argument(
'--index-min',
dest='index_min',
default=_config['ngs_filter']['indexQualityMin']['default'],
help=_config['ngs_filter']['indexQualityMin']['help'],
)
parser.add_argument(
'--drop-ns',
dest='drop_ns',
action='store_true',
default=_config['ngs_filter']['dropNs']['default'],
help=_config['ngs_filter']['dropNs']['help'],
)
parser.add_argument(
'--platforms',
dest='platforms',
default=_config['ngs_filter']['platforms']['default'],
help=_config['ngs_filter']['platforms']['help'],
)
default_outdir = os.getcwd()
parser.add_argument(
'-od',
'--outdir',
dest='outdir',
default=default_outdir,
help='The output directory for all files to be put[Default: {0}]'.format(default_outdir)
)
args, rest = parser.parse_known_args(args)
args.config = configfile
# Parse qsub args if found
if rest and rest[0].startswith('--qsub'):
qsub_parser = argparse.ArgumentParser(add_help=False)
qsub_parser.add_argument(
'--qsub-help',
default=False,
action='store_true'
)
qsub_parser.add_argument(
'--qsub_l',
default='nodes=1:ppn=1',
)
qsub_parser.add_argument(
'--qsub_M',
default=None
)
qsub_args = qsub_parser.parse_args(rest)
if qsub_args.qsub_help:
qsub_parser.print_help()
sys.exit(1)
rest = qsub_args
return args, rest
def parse_args(args=sys.argv[1:]):
'''
Uses argparse to parse arguments
@params args - List of command line arguments to parse
@returns Namespace object with parsed args in it(Same as ArgumentParser.parse_args)
'''
import argparse
from ngs_mapper import config
conf_parser, args, config, configfile = config.get_config_argparse(args)
defaults = config['run_bwa_on_samplename']
parser = argparse.ArgumentParser(
description='Runs the bwa mem argument on a given set of reads and references for the given platform\'s reads',
epilog='You should consider this script an autonomous bwa operation. That is, it will select the reads for ' \
'the platforms you select and it will pull those reads onto the current host. It will ' \
'compile references if they are multiple ones in a directory you select onto the local computer. Then it ' \
'will map any mated reads against to those refs and also map the nonpaired reads against that ref in a separate ' \
'call. Then when both are finished it will convert to bam/sort/index/merge/reindex the results. It attempts all of ' \
'this inside of the /dev/shm filesystem which should be very fast. If /dev/shm cannot be used then /tmp will be used. '\
'If you want the temporary files that are created to stay then you can use the --keep-temp argument',
parents=[conf_parser]
)
parser.add_argument(
dest='reads',
help='Location to a directory containing fastq read files')
parser.add_argument(
dest='reference',
help=
'Location of the reference to map to. Should be a fasta file or directory of fasta files that will be compiled together.'
)
parser.add_argument('--platforms',
dest='platforms',
nargs='+',
choices=defaults['platforms']['choices'],
default=defaults['platforms']['default'],
help=defaults['platforms']['help'])
parser.add_argument('-o',
'--output',
dest='output',
default=defaults['output']['default'],
help=defaults['output']['default'])
parser.add_argument('--keep-temp',
dest='keep_temp',
action='store_true',
default=defaults['keep_temp']['default'],
help=defaults['keep_temp']['help'])
parser.add_argument('-t',
dest='threads',
default=defaults['threads']['default'],
type=int,
help=defaults['threads']['help'])
return parser.parse_args(args)