def buildAlignmentSizes(infiles, outfile):
'''
use bed files to sum the total number of bases
that are aligned to the genomes
'''
outf = open(outfile, "w")
outf.write("genome\tsize\n")
for infile in infiles:
genome = P.snip(os.path.basename(infile), ".bed.gz")
c = 0
inf = iotools.openFile(infile)
for bed in Bed.iterator(inf):
c += bed.end - bed.start
outf.write("%s\t%s\n" % (genome, str(c)))
outf.close()
def buildAlignmentSizes(infiles, outfile):
'''
use bed files to sum the total number of bases
that are aligned to the genomes
'''
outf = open(outfile, "w")
outf.write("genome\tsize\n")
for infile in infiles:
genome = P.snip(os.path.basename(infile), ".bed.gz")
c = 0
inf = IOTools.openFile(infile)
for bed in Bed.iterator(inf):
c += bed.end - bed.start
outf.write("%s\t%s\n" % (genome, str(c)))
outf.close()
def getOverlappingRegionDict(bd1, bd2, debug=True):
''' Return a dictionary of overlapping regions within two dictionaries of Bed regions '''
retval = {}
for chrom, bedList1 in bd1.items():
bedList2 = bd2.get(chrom, [])
if bedList2 == []:
continue
if debug:
if not isNonContiguous(bedList1):
errAbort(
"Calculating overlapping regions must have non-contiguous input elements."
)
if not isNonContiguous(bedList2):
errAbort(
"Calculating overlapping regions must have non-contiguous input elements."
)
b1Len = len(bedList1)
b1Idx = 0
b2Len = len(bedList2)
b2Idx = 0
while (b1Idx < b1Len) and (b2Idx < b2Len):
b1Curr = bedList1[b1Idx]
b2Curr = bedList2[b2Idx]
assert b1Curr.chrom == b2Curr.chrom
maxStart = max(b1Curr.chromStart, b2Curr.chromStart)
minEnd = min(b1Curr.chromEnd, b2Curr.chromEnd)
if maxStart < minEnd:
retval[b1Curr.chrom] = retval.get(b1Curr.chrom, []) + [
Bed.Bed("%s\t%d\t%d" % (b1Curr.chrom, maxStart, minEnd))
]
if b1Curr.chromEnd < b2Curr.chromEnd:
b1Idx += 1
elif b1Curr.chromEnd > b2Curr.chromEnd:
b2Idx += 1
else:
b1Idx += 1
b2Idx += 1
return retval
def main( argv = None ):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if not argv: argv = sys.argv
# setup command line parser
parser = optparse.OptionParser( version = "%prog version: $Id: script_template.py 2871 2010-03-03 10:20:44Z andreas $",
usage = globals()["__doc__"] )
## add common options (-h/--help, ...) and parse command line
(options, args) = E.Start( parser, argv = argv )
coords_file=args[0]
bamfile=pysam.Samfile( args[1], 'rb' ) # bamfile
options.stdout.write( "gene_id\tcounts\tlength\n" )
iter = Bed.iterator( IOTools.openFile( coords_file ) )
for gene_id, exons in itertools.groupby( iter, lambda x: x.name ):
num_reads=0
anames=set([])
lgene = 0
for bed in exons:
lgene += bed.end - bed.start
for alignedread in bamfile.fetch(bed.contig, bed.start, bed.end):
anames.add((alignedread.qname, alignedread.is_read1))
num_reads = len(anames)
options.stdout.write( "\t".join( (gene_id,
str(num_reads),
str(lgene ) )) + "\n" )
## write footer and output benchmark information.
E.Stop()
def bedReadFromFile(fn, chromSizes=None):
''' Read a file of Bed regions into a list of Beds and return it '''
f = open(fn)
retval = [Bed.Bed(line, chromSizes=chromSizes) for line in f.readlines()]
f.close()
return retval
def main( argv = sys.argv ):
parser = optparse.OptionParser( version = "%prog version: $Id: bed2gff.py 2861 2010-02-23 17:36:32Z andreas $",
usage = globals()["__doc__"] )
parser.add_option("-a", "--as-gtf", dest="as_gtf", action="store_true",
help="output as gtf." )
parser.set_defaults( as_gtf = False,
id_format = "%08i",
test = None )
(options, args) = E.Start( parser, add_pipe_options = True )
as_gtf = options.as_gtf
id_format = options.id_format
if as_gtf:
gff = GTF.Entry()
else:
gff = GFF.Entry()
gff.source = "bed"
gff.feature = "exon"
ninput, noutput, nskipped = 0, 0, 0
id = 0
for bed in Bed.iterator( options.stdin ):
ninput += 1
gff.contig = bed.contig
gff.start = bed.start
gff.end = bed.end
if bed.mFields and len(bed.mFields) >= 3:
gff.strand = bed.mFields[2]
else:
gff.strand = "."
if bed.mFields and len(bed.mFields) >= 2:
gff.score = bed.mFields[1]
if as_gtf:
if bed.mFields:
gff.gene_id = bed.mFields[0]
gff.transcript_id = bed.mFields[0]
else:
id += 1
gff.gene_id = id_format % id
gff.transcript_id = id_format % id
else:
if bed.mFields:
gff.source = bed.mFields[0]
options.stdout.write( str(gff) + "\n" )
noutput += 1
E.info( "ninput=%i, noutput=%i, nskipped=%i" % (ninput, noutput, nskipped) )
E.Stop()
