本文整理汇总了Python中CGAT.Bed.merge方法的典型用法代码示例。如果您正苦于以下问题：Python Bed.merge方法的具体用法？Python Bed.merge怎么用？Python Bed.merge使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类CGAT.Bed的用法示例。
在下文中一共展示了Bed.merge方法的2个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: main
# 需要导入模块: from CGAT import Bed [as 别名]
# 或者: from CGAT.Bed import merge [as 别名]
def main( argv = None ):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if argv == None: argv = sys.argv
parser = E.OptionParser( version = "%prog version: $Id: bed2annotator2tsv.py 2885 2010-04-07 08:46:50Z andreas $",
usage = globals()["__doc__"])
parser.add_option( "-g", "--genome-file", dest="genome_file", type="string",
help="filename with genome." )
parser.add_option( "-f", "--features", dest="features", type="string",
help="feature to collect [default=None]." )
parser.add_option( "-i", "--files", dest="files", action="append",
help="use multiple annotations [default=None]." )
parser.add_option( "-a", "--annotations", dest="annotations", type="string",
help="aggregate name for annotations if only single file is provided from STDIN [default=None]." )
parser.add_option( "--input-filename-map", dest="input_filename_map", type="string",
help="filename with a map of gene_ids to categories [default=None]." )
parser.add_option( "-l", "--max-length", dest="max_length", type="string",
help="maximum segment length [default=None]." )
parser.add_option( "-m", "--merge", dest="merge", action="store_true",
help="merge overlapping bed segments [default=%default]." )
parser.add_option( "-s", "--section", dest="section", type="choice",
choices=("segments", "annotations", "workspace" ),
help="annotator section [default=None]." )
parser.add_option( "--subset", dest="subsets", type="string", action="append",
help="add filenames to delimit subsets within the gff files. The syntax is filename.gff,label,filename.ids [default=None]." )
parser.set_defaults(
genome_file = None,
feature = None,
remove_random = True,
section = "segments",
annotations = "annotations",
max_length = 100000,
files = [],
subsets = [],
input_filename_map = None,
merge = False,
)
(options, args) = E.Start( parser )
options.files += args
if len(options.files) == 0: options.files.append("-")
options.files = list( itertools.chain( *[ re.split( "[,; ]+", x) for x in options.files ] ) )
if options.subsets:
subsets = collections.defaultdict( list )
for s in options.subsets:
filename_gff,label,filename_ids = s.split( "," )
subsets[filename_gff].append( (label,filename_ids) )
options.subsets = subsets
if options.genome_file:
fasta = IndexedFasta.IndexedFasta( options.genome_file )
else:
fasta = None
if options.section == "segments":
prefix = "##Segs"
elif options.section == "annotations":
prefix = "##Id"
elif options.section == "workspace":
prefix = "##Work"
else:
raise ValueError("unknown section %s" % options.section)
if options.max_length:
max_length = options.max_length
else:
max_length = 0
ninput, ntracks, ncontigs, nsegments, ndiscarded = 0, 0, 0, 0, 0
if options.section in ("annotations"):
contigs = set()
it = itertools.groupby( Bed.iterator( options.stdin ), key=lambda x: x.track["name"])
map_track2segments = {}
for track, beds in it:
ntracks += 1
map_track2segments[track] = []
first_segment = nsegments
beds = list(beds)
if options.merge: beds = Bed.merge( beds )
#.........这里部分代码省略.........
示例2: in
# 需要导入模块: from CGAT import Bed [as 别名]
# 或者: from CGAT.Bed import merge [as 别名]
ninput, ntracks, ncontigs, nsegments, ndiscarded = 0, 0, 0, 0, 0
if options.section in ("annotations"):
contigs = set()
it = itertools.groupby( Bed.iterator( options.stdin ), key=lambda x: x.track["name"])
map_track2segments = {}
for track, beds in it:
ntracks += 1
map_track2segments[track] = []
first_segment = nsegments
beds = list(beds)
if options.merge: beds = Bed.merge( beds )
for bed in beds:
contig, start, end = bed.contig, bed.start, bed.end
if options.remove_random and "random" in contig: continue
if max_length > 0 and end - start > max_length:
ndiscarded += 1
continue
contigs.add(contig)
map_track2segments[track].append( nsegments )
options.stdout.write( "%s\t%i\t%s\t(%i,%i)\n" % (prefix, nsegments, contig, start, end ) )
nsegments += 1