def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if argv is None:
argv = sys.argv
parser = E.OptionParser(
version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option("--filter-query", dest="filename_filter_query",
type="string",
help="filename with intervals in the query "
"to filter (in gff format) [default=%default].")
parser.add_option("--filter-target", dest="filename_filter_target",
type="string",
help="filename with intervals in the target to "
"filter (in gff format) [default=%default].")
parser.add_option("-m", "--method", dest="methods", type="choice",
action="append",
choices=("map", "merge",
"add-sequence", "complement",
"select-query", "test",
"filter-keep", "filter-remove",
"rename-query",
"sanitize",
"filter-fasta",
"remove-overlapping-query",
"remove-overlapping-target"),
help="""action to perform [default=%default].""")
parser.add_option("--select", dest="select", type="choice",
choices=("most-nmatches", "least-nmatches",
"most-nmismatches", "least-nmismatches"),
help="entry to select [default=%default].")
parser.add_option("--header-names", dest="header", type="choice",
choices=("none", "table", "full"),
help="output psl header [default=%default].")
parser.add_option("--format", dest="format", type="choice",
choices=("gff", "gtf"),
help="format of intervals [default=%default].")
parser.add_option("--queries-tsv-file", dest="filename_queries",
type="string",
help="fasta filename with queries.")
parser.add_option("--target-psl-file", dest="filename_sbjcts",
type="string",
help="fasta filename with sbjct [default=%default].")
parser.add_option("--id-format", dest="id_format", type="string",
help="format of new identifiers for the rename "
"function [default=%default].")
parser.add_option("--unique", dest="unique", action="store_true",
help="in the rename function, make each match "
"unique [default=%default].")
parser.add_option("--output-filename-map", dest="output_filename_map",
type="string",
help="filename with map of old to new labels for "
"rename function [default=%default].")
parser.add_option("--complement-min-length", dest="complement_min_length",
type="int",
help="minimum length for complemented blocks "
"[default=%default].")
parser.add_option("--complement-border", dest="complement_border",
type="int",
help="number of residues to exclude before alignment "
"at either end [default=%default].")
parser.add_option("--complement-aligner", dest="complement_aligner",
type="choice",
choices=("clustal", "dba", "dialign", "dialign-lgs"),
help="aligner for complemented segments "
"[default=%default].")
parser.add_option("--threshold-merge-distance",
dest="threshold_merge_distance", type="int",
help="distance in nucleotides at which two adjacent "
"reads shall be merged even if they are not "
"overlapping [%default].")
parser.add_option("--test", dest="test", type="int",
help="for debugging purposes - stop after x "
"iterations [default=%default].")
parser.set_defaults(filename_filter_target=None,
filename_filter_query=None,
filename_queries=None,
filename_sbjcts=None,
threshold_merge_distance=0,
report_step=100000,
min_aligned=100,
methods=[],
format="gff",
select="most-nmatches",
id_format="%06i",
unique=False,
output_filename_map=None,
header=None,
test=None)
(options, args) = E.Start(parser, add_pipe_options=True)
if options.filename_queries:
query_fasta = IndexedFasta.IndexedFasta(options.filename_queries)
else:
query_fasta = None
if options.filename_sbjcts:
sbjct_fasta = IndexedFasta.IndexedFasta(options.filename_sbjcts)
else:
sbjct_fasta = None
if "add-sequence" in options.methods and \
(sbjct_fasta is None or query_fasta is None):
raise ValueError(
"please supply both indexed query and "
"target/genome sequence data.")
iterator = Blat.iterator(options.stdin)
if options.header is not None or options.header != "none":
if options.header == "table":
options.stdout.write("\t".join(Blat.FIELDS) + "\n")
elif options.header == "full":
options.stdout.write(Blat.HEADER + "\n")
for method in options.methods:
if "map" == method:
pslMap(options)
break
elif "filter-keep" == method:
pslFilter(options, keep=True)
break
elif "filter-remove" == method:
pslFilter(options, keep=False)
break
elif "merge" == method:
pslMerge(options)
break
elif "add-sequence" == method:
pslAddSequence(query_fasta, sbjct_fasta, options)
break
elif "complement" == method:
pslComplement(query_fasta, sbjct_fasta, options)
break
elif "select-query" == method:
pslSelectQuery(options)
break
elif "test" == method:
iterator = Blat.iterator_test(iterator, options.report_step)
elif "rename-query" == method:
iterator = iterator_rename_query(iterator, options)
elif "sanitize" == method:
iterator = iterator_sanitize(
iterator, query_fasta, sbjct_fasta, options)
elif "filter-fasta" == method:
iterator = iterator_filter_fasta(
iterator, query_fasta, sbjct_fasta, options)
elif "remove-overlapping-query" == method:
iterator = iterator_filter_overlapping_query(iterator, options)
elif "remove-overlapping-target" == method:
iterator = iterator_filter_overlapping_target(iterator, options)
for psl in iterator:
options.stdout.write("%s\n" % str(psl))
E.Stop()
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if argv is None:
argv = sys.argv
parser = E.OptionParser(
version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option("--filter-query", dest="filename_filter_query",
type="string",
help="filename with intervals in the query "
"to filter (in gff format) [default=%default].")
parser.add_option("--filter-target", dest="filename_filter_target",
type="string",
help="filename with intervals in the target to "
"filter (in gff format) [default=%default].")
parser.add_option("-m", "--method", dest="methods", type="choice",
action="append",
choices=("map", "merge",
"add-sequence", "complement",
"select-query", "test",
"filter-keep", "filter-remove",
"rename-query",
"sanitize",
"filter-fasta",
"remove-overlapping-query",
"remove-overlapping-target"),
help="""action to perform [default=%default].""")
parser.add_option("--select", dest="select", type="choice",
choices=("most-nmatches", "least-nmatches",
"most-nmismatches", "least-nmismatches"),
help="entry to select [default=%default].")
parser.add_option("--header-names", dest="header", type="choice",
choices=("none", "table", "full"),
help="output psl header [default=%default].")
parser.add_option("--format", dest="format", type="choice",
choices=("gff", "gtf"),
help="format of intervals [default=%default].")
parser.add_option("--queries-tsv-file", dest="filename_queries",
type="string",
help="fasta filename with queries.")
parser.add_option("--target-psl-file", dest="filename_sbjcts",
type="string",
help="fasta filename with sbjct [default=%default].")
parser.add_option("--id-format", dest="id_format", type="string",
help="format of new identifiers for the rename "
"function [default=%default].")
parser.add_option("--unique", dest="unique", action="store_true",
help="in the rename function, make each match "
"unique [default=%default].")
parser.add_option("--output-filename-map", dest="output_filename_map",
type="string",
help="filename with map of old to new labels for "
"rename function [default=%default].")
parser.add_option("--complement-min-length", dest="complement_min_length",
type="int",
help="minimum length for complemented blocks "
"[default=%default].")
parser.add_option("--complement-border", dest="complement_border",
type="int",
help="number of residues to exclude before alignment "
"at either end [default=%default].")
parser.add_option("--complement-aligner", dest="complement_aligner",
type="choice",
choices=("clustal", "dba", "dialign", "dialign-lgs"),
help="aligner for complemented segments "
"[default=%default].")
parser.add_option("--threshold-merge-distance",
dest="threshold_merge_distance", type="int",
help="distance in nucleotides at which two adjacent "
"reads shall be merged even if they are not "
"overlapping [%default].")
parser.add_option("--test", dest="test", type="int",
help="for debugging purposes - stop after x "
"iterations [default=%default].")
parser.set_defaults(filename_filter_target=None,
filename_filter_query=None,
filename_queries=None,
filename_sbjcts=None,
threshold_merge_distance=0,
report_step=100000,
min_aligned=100,
methods=[],
format="gff",
select="most-nmatches",
id_format="%06i",
unique=False,
output_filename_map=None,
header=None,
test=None)
(options, args) = E.start(parser, add_pipe_options=True)
if options.filename_queries:
query_fasta = IndexedFasta.IndexedFasta(options.filename_queries)
else:
query_fasta = None
if options.filename_sbjcts:
sbjct_fasta = IndexedFasta.IndexedFasta(options.filename_sbjcts)
else:
sbjct_fasta = None
if "add-sequence" in options.methods and \
(sbjct_fasta is None or query_fasta is None):
raise ValueError(
"please supply both indexed query and "
"target/genome sequence data.")
iterator = Blat.iterator(options.stdin)
if options.header is not None or options.header != "none":
if options.header == "table":
options.stdout.write("\t".join(Blat.FIELDS) + "\n")
elif options.header == "full":
options.stdout.write(Blat.HEADER + "\n")
for method in options.methods:
if "map" == method:
pslMap(options)
break
elif "filter-keep" == method:
pslFilter(options, keep=True)
break
elif "filter-remove" == method:
pslFilter(options, keep=False)
break
elif "merge" == method:
pslMerge(options)
break
elif "add-sequence" == method:
pslAddSequence(query_fasta, sbjct_fasta, options)
break
elif "complement" == method:
pslComplement(query_fasta, sbjct_fasta, options)
break
elif "select-query" == method:
pslSelectQuery(options)
break
elif "test" == method:
iterator = Blat.iterator_test(iterator, options.report_step)
elif "rename-query" == method:
iterator = iterator_rename_query(iterator, options)
elif "sanitize" == method:
iterator = iterator_sanitize(
iterator, query_fasta, sbjct_fasta, options)
elif "filter-fasta" == method:
iterator = iterator_filter_fasta(
iterator, query_fasta, sbjct_fasta, options)
elif "remove-overlapping-query" == method:
iterator = iterator_filter_overlapping_query(iterator, options)
elif "remove-overlapping-target" == method:
iterator = iterator_filter_overlapping_target(iterator, options)
for psl in iterator:
options.stdout.write("%s\n" % str(psl))
E.stop()
pslFilter( options, keep = False )
break
elif "merge" == method:
pslMerge( options )
break
elif "add-sequence" == method:
pslAddSequence( query_fasta, sbjct_fasta, options )
break
elif "complement" == method:
pslComplement( query_fasta, sbjct_fasta, options )
break
elif "select-query" == method:
pslSelectQuery( options )
break
elif "test" == method:
iterator = Blat.iterator_test( iterator, options.report_step )
elif "rename-query" == method:
iterator = iterator_rename_query( iterator, options )
elif "sanitize" == method:
iterator = iterator_sanitize( iterator, query_fasta, sbjct_fasta, options )
elif "filter-fasta" == method:
iterator = iterator_filter_fasta( iterator, query_fasta, sbjct_fasta, options )
elif "remove-overlapping-query" == method:
iterator = iterator_filter_overlapping_query( iterator, options )
elif "remove-overlapping-target" == method:
iterator = iterator_filter_overlapping_target( iterator, options )
for psl in iterator:
options.stdout.write( "%s\n" % str( psl ) )
E.Stop()
