def get_argument_parser():
parser = argparse.ArgumentParser(usage="%(prog)s [options] <index> "
"<mate1.fq> <mate2.fq> <output_dir>")
# required options
parser.add_argument("index_dir",
default=None,
help="Location of chimerascan index directory")
parser.add_argument("read1",
default=None,
help="Path to read1 FASTQ file")
parser.add_argument("read2",
default=None,
help="Path to read2 FASTQ file")
parser.add_argument("output_dir",
default=None,
help="Location of output files")
# standard options
parser.add_argument('--version',
action='version',
version='%s' % __version__)
parser.add_argument("--config-file",
dest="config_file",
help="Load parameters from a XML file "
"generated during a previous run ",
default=None)
parser.add_argument("-v",
"--verbose",
dest="verbose",
action="store_true",
default=False,
help="enable verbose logging output "
"[default=%(default)s]")
parser.add_argument("-p",
"--processors",
dest="num_processors",
type=int,
default=DEFAULT_NUM_PROCESSORS,
help="Number of processor cores to allocate to "
"chimerascan [default=%(default)s]")
parser.add_argument("--keep-tmp",
dest="keep_tmp",
action="store_true",
default=DEFAULT_KEEP_TMP,
help="DO NOT delete intermediate files after "
"run [default=%(default)s]")
parser.add_argument("--rm-tmp",
dest="keep_tmp",
action="store_false",
help="Delete intermediate files after run "
"[default=%s]" % str(not DEFAULT_KEEP_TMP))
parser.add_argument("--quals",
dest="quals",
choices=FASTQ_QUAL_FORMATS,
default=DEFAULT_FASTQ_QUAL_FORMAT,
metavar="FMT",
help="FASTQ quality score format "
"[default=%(default)s]")
parser.add_argument('--library-type',
dest="library_type",
choices=LibraryTypes.choices(),
default=DEFAULT_LIBRARY_TYPE,
help="Library type [default=%(default)s]")
parser.add_argument("--isize-mean",
dest="isize_mean",
type=int,
default=DEFAULT_ISIZE_MEAN,
metavar="N",
help="Mean insert size to sample from when "
"insert size distribution cannot be determined "
"empirically [default=%(default)s]")
parser.add_argument("--isize-stdev",
dest="isize_stdev",
type=float,
default=DEFAULT_ISIZE_STDEV,
metavar="N",
help="Insert size standard deviation to sample "
"from when insert size distribution cannot be "
"determined empirically [default=%(default)s]")
parser.add_argument("--trim5",
type=int,
dest="trim5",
default=DEFAULT_TRIM5,
metavar="N",
help="Trim N bases from 5' end of read")
parser.add_argument("--trim3",
type=int,
dest="trim3",
default=DEFAULT_TRIM3,
metavar="N",
help="Trim N bases from 3' end of read")
parser.add_argument("--min-fragment-length",
type=int,
dest="min_fragment_length",
default=config.DEFAULT_MIN_FRAG_LENGTH,
help="Smallest expected fragment length "
"[default=%(default)s]")
parser.add_argument("--max-fragment-length",
type=int,
dest="max_fragment_length",
default=config.DEFAULT_MAX_FRAG_LENGTH,
help="Largest expected fragment length (reads "
"less than this fragment length are assumed to "
"be unspliced and contiguous) "
"[default=%(default)s]")
parser.add_argument("--segment-length",
type=int,
dest="segment_length",
default=DEFAULT_SEGMENT_LENGTH,
metavar="N",
help="Override size of soft-clipped read "
"segments during discordant alignment phase "
"(determined empirically by default)")
parser.add_argument("--multihits",
type=int,
dest="max_multihits",
default=config.DEFAULT_MAX_MULTIHITS,
metavar="N",
help="Maximum alignments allowed for each "
"discordant read")
parser.add_argument("--local-multihits",
type=int,
dest="local_multihits",
default=config.DEFAULT_LOCAL_MULTIHITS,
metavar="N",
help="Maximum alignments allowed for each "
"discordant read")
parser.add_argument("--local-anchor-length",
type=int,
dest="local_anchor_length",
default=config.DEFAULT_LOCAL_ANCHOR_LENGTH,
metavar="N",
help="Number of bases that read must span "
"on each side of a chimera to be considered "
"a valid breakpoint read")
# filtering options
group = parser.add_argument_group('Filtering options')
group.add_argument("--filter-num-frags",
type=float,
default=config.DEFAULT_FILTER_FRAGS,
dest="filter_num_frags",
metavar="N",
help="Filter chimeras with less than N "
"aligned fragments [default=%(default)s]")
group.add_argument("--filter-allele-fraction",
type=float,
default=config.DEFAULT_FILTER_ALLELE_FRACTION,
dest="filter_allele_fraction",
metavar="X",
help="Filter chimeras with expression less than "
"the specified fraction of the total expression "
"level [default=%(default)s")
group.add_argument("--mask-biotypes-file",
default="",
dest="mask_biotypes_file",
help="File containing list of gene biotypes "
"to ignore (ex. pseudogenes, rRNA)")
group.add_argument("--mask-rnames-file",
default="",
dest="mask_rnames_file",
help="File containing list of reference names "
"to ignore (ex. MT or chrM)")
# filtering options
return parser
def get_argument_parser():
parser = argparse.ArgumentParser(usage="%(prog)s [options] <index> "
"<mate1.fq> <mate2.fq> <output_dir>")
# required options
parser.add_argument("index_dir", default=None,
help="Location of chimerascan index directory")
parser.add_argument("read1", default=None,
help="Path to read1 FASTQ file")
parser.add_argument("read2", default=None,
help="Path to read2 FASTQ file")
parser.add_argument("output_dir", default=None,
help="Location of output files")
# standard options
parser.add_argument('--version', action='version',
version='%s' % __version__)
parser.add_argument("--config-file", dest="config_file",
help="Load parameters from a XML file "
"generated during a previous run ",
default=None)
parser.add_argument("-v", "--verbose", dest="verbose",
action="store_true", default=False,
help="enable verbose logging output "
"[default=%(default)s]")
parser.add_argument("-p", "--processors", dest="num_processors",
type=int, default=DEFAULT_NUM_PROCESSORS,
help="Number of processor cores to allocate to "
"chimerascan [default=%(default)s]")
parser.add_argument("--keep-tmp", dest="keep_tmp",
action="store_true",
default=DEFAULT_KEEP_TMP,
help="DO NOT delete intermediate files after "
"run [default=%(default)s]")
parser.add_argument("--rm-tmp", dest="keep_tmp",
action="store_false",
help="Delete intermediate files after run "
"[default=%s]" % str(not DEFAULT_KEEP_TMP))
parser.add_argument("--quals", dest="quals",
choices=FASTQ_QUAL_FORMATS,
default=DEFAULT_FASTQ_QUAL_FORMAT, metavar="FMT",
help="FASTQ quality score format "
"[default=%(default)s]")
parser.add_argument('--library-type', dest="library_type",
choices=LibraryTypes.choices(),
default=DEFAULT_LIBRARY_TYPE,
help="Library type [default=%(default)s]")
parser.add_argument("--isize-mean", dest="isize_mean", type=int,
default=DEFAULT_ISIZE_MEAN, metavar="N",
help="Mean insert size to sample from when "
"insert size distribution cannot be determined "
"empirically [default=%(default)s]")
parser.add_argument("--isize-stdev", dest="isize_stdev", type=float,
default=DEFAULT_ISIZE_STDEV, metavar="N",
help="Insert size standard deviation to sample "
"from when insert size distribution cannot be "
"determined empirically [default=%(default)s]")
parser.add_argument("--trim5", type=int, dest="trim5",
default=DEFAULT_TRIM5, metavar="N",
help="Trim N bases from 5' end of read")
parser.add_argument("--trim3", type=int, dest="trim3",
default=DEFAULT_TRIM3, metavar="N",
help="Trim N bases from 3' end of read")
parser.add_argument("--min-fragment-length", type=int,
dest="min_fragment_length",
default=config.DEFAULT_MIN_FRAG_LENGTH,
help="Smallest expected fragment length "
"[default=%(default)s]")
parser.add_argument("--max-fragment-length", type=int,
dest="max_fragment_length",
default=config.DEFAULT_MAX_FRAG_LENGTH,
help="Largest expected fragment length (reads "
"less than this fragment length are assumed to "
"be unspliced and contiguous) "
"[default=%(default)s]")
parser.add_argument("--segment-length", type=int,
dest="segment_length",
default=DEFAULT_SEGMENT_LENGTH,
metavar="N",
help="Override size of soft-clipped read "
"segments during discordant alignment phase "
"(determined empirically by default)")
parser.add_argument("--multihits", type=int,
dest="max_multihits",
default=config.DEFAULT_MAX_MULTIHITS,
metavar="N",
help="Maximum alignments allowed for each "
"discordant read")
parser.add_argument("--local-multihits", type=int,
dest="local_multihits",
default=config.DEFAULT_LOCAL_MULTIHITS,
metavar="N",
help="Maximum alignments allowed for each "
"discordant read")
parser.add_argument("--local-anchor-length", type=int,
dest="local_anchor_length",
default=config.DEFAULT_LOCAL_ANCHOR_LENGTH,
metavar="N",
help="Number of bases that read must span "
"on each side of a chimera to be considered "
"a valid breakpoint read")
# filtering options
group = parser.add_argument_group('Filtering options')
group.add_argument("--filter-num-frags", type=float,
default=config.DEFAULT_FILTER_FRAGS,
dest="filter_num_frags", metavar="N",
help="Filter chimeras with less than N "
"aligned fragments [default=%(default)s]")
group.add_argument("--filter-allele-fraction", type=float,
default=config.DEFAULT_FILTER_ALLELE_FRACTION,
dest="filter_allele_fraction", metavar="X",
help="Filter chimeras with expression less than "
"the specified fraction of the total expression "
"level [default=%(default)s")
group.add_argument("--mask-biotypes-file", default="",
dest="mask_biotypes_file",
help="File containing list of gene biotypes "
"to ignore (ex. pseudogenes, rRNA)")
group.add_argument("--mask-rnames-file", default="",
dest="mask_rnames_file",
help="File containing list of reference names "
"to ignore (ex. MT or chrM)")
# filtering options
return parser
