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 = E.ArgumentParser(description=__doc__)
parser.add_argument("--version", action='version', version="1.0")
parser.add_argument("-o", "--output-section", dest="output", type=str,
choices=("full", "name"),
help="output either ``full`` overlapping entries, only the ``name``s.")
parser.set_defaults(
output="full",
)
# add common options (-h/--help, ...) and parse command line
(args, unknown) = E.start(parser,
argv=argv,
unknowns=True)
if len(unknown) != 2:
raise ValueError("two arguments required")
if unknown[0] == "-":
infile1 = args.stdin
else:
infile1 = iotools.open_file(unknown[0], "r")
infile2 = iotools.open_file(unknown[1], "r")
idx = Bed.readAndIndex(infile2, with_values=True)
output = args.output
outfile = args.stdout
if output == "name":
outfile.write("name1\tname2\n")
outf = lambda x: x.fields[0]
else:
outf = str
for bed in Bed.iterator(infile1):
try:
overlaps = idx[bed.contig].find(bed.start, bed.end)
except (KeyError, IndexError):
# ignore missing contig and zero length intervals
continue
for o in overlaps:
outfile.write("\t".join((outf(bed), outf(o[2]))) + "\n")
E.stop()
def exportSequencesFromBedFile(infile, outfile, masker=None, mode="intervals"):
'''export sequences for intervals in :term:`bed`-formatted *infile*
to :term:`fasta` formatted *outfile*
'''
track = P.snip(infile, ".bed.gz")
fasta = IndexedFasta.IndexedFasta(
os.path.join(P.get_params()["genome_dir"],
P.get_params()["genome"]))
outs = iotools.open_file(outfile, "w")
ids, seqs = [], []
for bed in Bed.setName(Bed.iterator(iotools.open_file(infile))):
lcontig = fasta.getLength(bed.contig)
if mode == "intervals":
seqs.append(fasta.getSequence(bed.contig, "+", bed.start, bed.end))
ids.append("%s_%s %s:%i..%i" %
(track, bed.name, bed.contig, bed.start, bed.end))
elif mode == "leftright":
l = bed.end - bed.start
start, end = max(0, bed.start - l), bed.end - l
ids.append("%s_%s_l %s:%i..%i" %
(track, bed.name, bed.contig, start, end))
seqs.append(fasta.getSequence(bed.contig, "+", start, end))
start, end = bed.start + l, min(lcontig, bed.end + l)
ids.append("%s_%s_r %s:%i..%i" %
(track, bed.name, bed.contig, start, end))
seqs.append(fasta.getSequence(bed.contig, "+", start, end))
masked = maskSequences(seqs, masker)
outs.write("\n".join([">%s\n%s" % (x, y) for x, y in zip(ids, masked)]))
outs.close()
def buildQuicksectMask(bed_file):
'''return Quicksect object containing the regions specified
takes a bed file listing the regions to mask
'''
mask = IndexedGenome.Quicksect()
n_regions = 0
for bed in Bed.iterator(iotools.openFile(bed_file)):
# it is neccessary to extend the region to make an accurate mask
mask.add(bed.contig, (bed.start - 1), (bed.end + 1), 1)
n_regions += 1
E.info("Built Quicksect mask for %i regions" % n_regions)
return(mask)
def transcript2bed12(transcript):
new_entry = Bed.Bed()
start = min(entry.start for entry in transcript)
end = max(entry.end for entry in transcript)
try:
thickStart = min(entry.start for entry in transcript
if entry.feature == "CDS")
thickEnd = max(entry.end for entry in transcript
if entry.feature == "CDS")
except ValueError:
# if there is no CDS, then set first base of transcript as
# start
if transcript[0].strand == "-":
thickStart = end
thickEnd = end
else:
thickStart = start
thickEnd = start
exons = GTF.asRanges(transcript, "exon")
exon_starts = [es - start for (es, ee) in exons]
exon_lengths = [ee - es for (es, ee) in exons]
exon_count = len(exons)
new_entry.contig = transcript[0].contig
new_entry.start = start
new_entry.end = end
new_entry["strand"] = transcript[0].strand
new_entry["name"] = transcript[0].transcript_id
new_entry["thickStart"] = thickStart
new_entry["thickEnd"] = thickEnd
new_entry["blockCount"] = exon_count
new_entry["blockStarts"] = ",".join(map(str, exon_starts))
new_entry["blockSizes"] = ",".join(map(str, exon_lengths))
return new_entry
def __init__(self, filename, *args, **kwargs):
assert filename is not None,\
"please supply filename for CounterOverlap"
Counter.__init__(self, *args, **kwargs)
self.filename = filename
E.info("reading intervals from %s" % self.filename)
self.index = Bed.readAndIndex(iotools.open_file(self.filename, "r"),
per_track=True)
E.info("read intervals for %s tracks" % len(self.index))
self.tracks = list(self.index.keys())
self.headers = []
for track in self.tracks:
self.headers.extend(["%s_nover" % track, "%s_bases" % track])
def makeIntervalCorrelation(infiles, outfile, field, reference):
'''compute correlation of interval properties between sets
'''
dbhandle = sqlite3.connect(PARAMS["database_name"])
tracks, idx = [], []
for infile in infiles:
track = P.snip(infile, ".bed.gz")
tablename = "%s_intervals" % P.tablequote(track)
cc = dbhandle.cursor()
statement = "SELECT contig, start, end, %(field)s FROM %(tablename)s" % locals(
)
cc.execute(statement)
ix = IndexedGenome.IndexedGenome()
for contig, start, end, peakval in cc:
ix.add(contig, start, end, peakval)
idx.append(ix)
tracks.append(track)
outs = iotools.openFile(outfile, "w")
outs.write("contig\tstart\tend\tid\t" + "\t".join(tracks) + "\n")
for bed in Bed.iterator(infile=iotools.openFile(reference, "r")):
row = []
for ix in idx:
try:
intervals = list(ix.get(bed.contig, bed.start, bed.end))
except KeyError:
row.append("")
continue
if len(intervals) == 0:
peakval = ""
else:
peakval = str((max([x[2] for x in intervals])))
row.append(peakval)
outs.write(str(bed) + "\t" + "\t".join(row) + "\n")
outs.close()
def _count(self, filename, idx):
'''count filename against idx.'''
overlapping_genes = set()
genes = set()
# iterate over exons
infile = iotools.open_file(filename, "r")
it = Bed.bed_iterator(infile)
nexons, nexons_overlapping = 0, 0
nbases, nbases_overlapping = 0, 0
for this in it:
nexons += 1
nbases += this.end - this.start
try:
intervals = list(idx[this.contig].find(max(0, this.start),
this.end))
except KeyError:
continue
except Exception as msg:
raise Exception("error while processing %s, msg=%s" %
(filename, msg))
if len(intervals) == 0:
continue
nexons_overlapping += 1
start, end = this.start, this.end
counts = numpy.zeros(end - start, numpy.int)
for other_start, other_end, other_value in intervals:
for x in range(
max(start, other_start) - start,
min(end, other_end) - start):
counts[x] += 1
nbases_overlapping += sum([1 for x in counts if x > 0])
infile.close()
return nexons, nexons_overlapping, nbases, nbases_overlapping
def getExonLocations(filename):
'''return a list of exon locations as Bed entries
from a file contain a one ensembl gene ID per line
'''
fh = iotools.openFile(filename, "r")
ensembl_ids = []
for line in fh:
ensembl_ids.append(line.strip())
fh.close()
dbhandle = sqlite3.connect(PARAMS["annotations_database"])
cc = dbhandle.cursor()
gene_ids = []
n_ids = 0
for ID in ensembl_ids:
gene_ids.append('gene_id="%s"' % ID)
n_ids += 1
statement = "select contig,start,end from geneset_cds_gtf where " + \
" OR ".join(gene_ids)
cc.execute(statement)
region_list = []
n_regions = 0
for result in cc:
b = Bed.Bed()
b.contig, b.start, b.end = result
region_list.append(b)
n_regions += 1
cc.close()
E.info("Retrieved exon locations for %i genes. Got %i regions" %
(n_ids, n_regions))
return(region_list)
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 = E.ArgumentParser(description=__doc__)
parser.add_argument("--version", action='version', version="1.0")
parser.add_argument("--bed-file",
dest="infiles",
type=str,
metavar="bed",
help="supply list of bed files",
action="append")
parser.set_defaults(infiles=[])
# add common options (-h/--help, ...) and parse command line
(args, unknown) = E.start(parser, argv=argv, unknowns=True)
args.infiles.extend(unknown)
if len(args.infiles) == 0:
raise ValueError('please provide at least 1 bed file')
E.info("concatenating bed files")
# concatenate the list of files
tmp = tempfile.NamedTemporaryFile(delete=False, mode="w")
tmp_merge = tempfile.NamedTemporaryFile(delete=False, mode="w")
infs = args.infiles
for inf in infs:
for bed in Bed.iterator(iotools.open_file(inf)):
tmp.write("%s\n" % bed)
tmp.close()
E.info("merging bed entries")
# merge the bed entries in the file
name = tmp.name
tmp_bed = pybedtools.BedTool(name)
tmp_bed.sort().merge().saveas(tmp_merge.name)
tmp_merge.close()
E.info("indexing bed entries")
# index the bed entries
merged = IndexedGenome.Simple()
for bed in Bed.iterator(iotools.open_file(tmp_merge.name)):
merged.add(bed.contig, bed.start, bed.end)
counts = collections.defaultdict(int)
# list of samples
samples = args.infiles
E.info("counting no. samples overlapping each interval")
for sample in samples:
found = set()
for bed in Bed.iterator(iotools.open_file(sample)):
if merged.contains(bed.contig, bed.start, bed.end):
key = [bed.contig] + \
[x for x in merged.get(bed.contig, bed.start, bed.end)]
key = (key[0], key[1][0], key[1][1])
if key in found:
continue
found.add(key)
# tuple of interval description as key - (contig, start, end)
counts[key] += 1
# open outfile
args.stdout.write("contig\tstart\tend\tcount\n")
E.info("outputting result")
for interval, count in sorted(counts.items()):
args.stdout.write("\t".join(map(str, interval)) + "\t" + str(count) +
"\n")
# write footer and output benchmark information.
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("-b",
"--bin-size",
dest="bin_size",
type="string",
help="bin size.")
parser.add_option("--min-value",
dest="min_value",
type="float",
help="minimum value for histogram.")
parser.add_option("--max-value",
dest="max_value",
type="float",
help="maximum value for histogram.")
parser.add_option("--no-empty-bins",
dest="no_empty_bins",
action="store_true",
help="do not display empty bins.")
parser.add_option("--with-empty-bins",
dest="no_empty_bins",
action="store_false",
help="display empty bins.")
parser.add_option(
"--ignore-out-of-range",
dest="ignore_out_of_range",
action="store_true",
help="ignore values that are out of range (as opposed to truncating "
"them to range border.")
parser.add_option("--missing-value",
dest="missing_value",
type="string",
help="entry for missing values [%default].")
parser.add_option("--use-dynamic-bins",
dest="dynamic_bins",
action="store_true",
help="each value constitutes its own bin.")
parser.add_option("--format",
dest="format",
type="choice",
choices=("gff", "gtf", "bed"),
help="input file format [%default].")
parser.add_option("--method",
dest="methods",
type="choice",
action="append",
choices=("all", "hist", "stats", "overlaps", "values"),
help="methods to apply [%default].")
parser.add_option("--output-section",
dest="output_section",
type="choice",
choices=("all", "size", "distance"),
help="data to compute [%default].")
parser.set_defaults(
no_empty_bins=True,
bin_size=None,
dynamic_bins=False,
ignore_out_of_range=False,
min_value=None,
max_value=None,
nonull=None,
missing_value="na",
output_filename_pattern="%s",
methods=[],
output_section="all",
format="gff",
)
(options, args) = E.start(parser, add_output_options=True)
if "all" in options.methods:
options.methods = ("hist", "stats", "overlaps")
if not options.output_filename_pattern:
options.output_filename_pattern = "%s"
if len(options.methods) == 0:
raise ValueError(
"please provide counting method using --method option")
if options.format in ("gff", "gtf"):
gffs = GTF.iterator(options.stdin)
elif options.format == "bed":
gffs = Bed.iterator(options.stdin)
values_between = []
values_within = []
values_overlaps = []
if "overlaps" in options.methods:
if not options.output_filename_pattern:
options.output_filename_pattern = "%s"
outfile_overlaps = E.open_output_file("overlaps")
else:
outfile_overlaps = None
last = None
ninput, noverlaps = 0, 0
for this in gffs:
ninput += 1
values_within.append(this.end - this.start)
if last and last.contig == this.contig:
if this.start < last.end:
noverlaps += 1
if outfile_overlaps:
outfile_overlaps.write("%s\t%s\n" % (str(last), str(this)))
values_overlaps.append(
min(this.end, last.end) - max(last.start, this.start))
if this.end > last.end:
last = this
continue
else:
values_between.append(this.start - last.end)
# if this.start - last.end < 10:
# print str(last)
# print str(this)
# print "=="
values_overlaps.append(0)
last = this
if "hist" in options.methods:
outfile = E.open_output_file("hist")
h_within = Histogram.Calculate(
values_within,
no_empty_bins=options.no_empty_bins,
increment=options.bin_size,
min_value=options.min_value,
max_value=options.max_value,
dynamic_bins=options.dynamic_bins,
ignore_out_of_range=options.ignore_out_of_range)
h_between = Histogram.Calculate(
values_between,
no_empty_bins=options.no_empty_bins,
increment=options.bin_size,
min_value=options.min_value,
max_value=options.max_value,
dynamic_bins=options.dynamic_bins,
ignore_out_of_range=options.ignore_out_of_range)
if "all" == options.output_section:
outfile.write("residues\tsize\tdistance\n")
combined_histogram = Histogram.Combine(
[h_within, h_between], missing_value=options.missing_value)
Histogram.Write(outfile, combined_histogram, nonull=options.nonull)
elif options.output_section == "size":
outfile.write("residues\tsize\n")
Histogram.Write(outfile, h_within, nonull=options.nonull)
elif options.output_section == "distance":
outfile.write("residues\tdistance\n")
Histogram.Write(outfile, h_between, nonull=options.nonull)
outfile.close()
if "stats" in options.methods:
outfile = E.open_output_file("stats")
outfile.write("data\t%s\n" % Stats.Summary().getHeader())
if options.output_section in ("size", "all"):
outfile.write("size\t%s\n" % str(Stats.Summary(values_within)))
if options.output_section in ("distance", "all"):
outfile.write("distance\t%s\n" %
str(Stats.Summary(values_between)))
outfile.close()
if "values" in options.methods:
outfile = E.open_output_file("distances")
outfile.write("distance\n%s\n" % "\n".join(map(str, values_between)))
outfile.close()
outfile = E.open_output_file("sizes")
outfile.write("size\n%s\n" % "\n".join(map(str, values_within)))
outfile.close()
outfile = E.open_output_file("overlaps")
outfile.write("overlap\n%s\n" % "\n".join(map(str, values_overlaps)))
outfile.close()
E.info("ninput=%i, ndistance=%i, nsize=%i, noverlap=%i" %
(ninput, len(values_between), len(values_within), noverlaps))
E.stop()
def main(argv=sys.argv):
parser = E.ArgumentParser(description=__doc__)
parser.add_argument("-a",
"--as-gtf",
dest="as_gtf",
action="store_true",
help="output as gtf.")
parser.add_argument(
"-f",
"--id-format",
dest="id_format",
type=str,
help="format for numeric identifier if --as-gtf is set and "
"no name in bed file .")
parser.set_defaults(as_gtf=False, id_format="%08i", test=None)
(args) = E.start(parser, add_pipe_options=True)
as_gtf = args.as_gtf
id_format = args.id_format
if as_gtf:
gff = GTF.Entry()
else:
gff = GTF.Entry()
gff.source = "bed"
gff.feature = "exon"
ninput, noutput, nskipped = 0, 0, 0
id = 0
for bed in Bed.iterator(args.stdin):
ninput += 1
gff.contig = bed.contig
gff.start = bed.start
gff.end = bed.end
if bed.fields and len(bed.fields) >= 3:
gff.strand = bed.fields[2]
else:
gff.strand = "."
if bed.fields and len(bed.fields) >= 2:
gff.score = bed.fields[1]
if as_gtf:
if bed.fields:
gff.gene_id = bed.fields[0]
gff.transcript_id = bed.fields[0]
else:
id += 1
gff.gene_id = id_format % id
gff.transcript_id = id_format % id
else:
if bed.fields:
gff.source = bed.fields[0]
args.stdout.write(str(gff) + "\n")
noutput += 1
E.info("ninput=%i, noutput=%i, nskipped=%i" % (ninput, noutput, nskipped))
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.ArgumentParser(description=__doc__)
parser.add_argument("-g",
"--genome-file",
dest="genome_file",
type=str,
help="filename with genome.")
parser.add_argument("-f",
"--features",
dest="features",
type=str,
help="feature to collect.")
parser.add_argument("-i",
"--files",
dest="files",
action="append",
help="use multiple annotations.")
parser.add_argument(
"-a",
"--annotations",
dest="annotations",
type=str,
help=
"aggregate name for annotations if only single file is provided from STDIN."
)
parser.add_argument("--map-tsv-file",
dest="input_filename_map",
type=str,
help="filename with a map of gene_ids to categories.")
parser.add_argument("-l",
"--max-length",
dest="max_length",
type=str,
help="maximum segment length.")
parser.add_argument("-m",
"--merge-overlapping",
dest="merge",
action="store_true",
help="merge overlapping bed segments.")
parser.add_argument("-s",
"--section",
dest="section",
type=str,
choices=("segments", "annotations", "workspace"),
help="annotator section.")
parser.add_argument(
"--subset",
dest="subsets",
type=str,
action="append",
help=
"add filenames to delimit subsets within the gff files. The syntax is filename.gff,label,filename.ids."
)
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,
)
(args, unknown) = E.start(parser, unknowns=True)
args.files += unknown
if len(args.files) == 0:
args.files.append("-")
args.files = list(
itertools.chain(*[re.split("[,; ]+", x) for x in args.files]))
if args.subsets:
subsets = collections.defaultdict(list)
for s in args.subsets:
filename_gff, label, filename_ids = s.split(",")
subsets[filename_gff].append((label, filename_ids))
args.subsets = subsets
if args.genome_file:
fasta = IndexedFasta.IndexedFasta(args.genome_file)
else:
fasta = None
if args.section == "segments":
prefix = "##Segs"
elif args.section == "annotations":
prefix = "##Id"
elif args.section == "workspace":
prefix = "##Work"
else:
raise ValueError("unknown section %s" % args.section)
if args.max_length:
max_length = args.max_length
else:
max_length = 0
ninput, ntracks, ncontigs, nsegments, ndiscarded = 0, 0, 0, 0, 0
if args.section in ("annotations"):
contigs = set()
it = itertools.groupby(Bed.iterator(args.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 args.merge:
beds = Bed.merge(beds)
for bed in beds:
contig, start, end = bed.contig, bed.start, bed.end
if args.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)
args.stdout.write("%s\t%i\t%s\t(%i,%i)\n" %
(prefix, nsegments, contig, start, end))
nsegments += 1
args.stdout.write("##Ann\t%s\t%s\n" % (track, "\t".join(
["%i" % x for x in range(first_segment, nsegments)])))
E.info("track %s: annotated with %i segments" %
(track, nsegments - first_segment))
ncontigs = len(contigs)
E.info(
"ninput=%i, ntracks=%i, ncontigs=%i, nsegments=%i, ndiscarded=%i" %
(ninput, ntracks, ncontigs, nsegments, ndiscarded))
E.stop()
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 = E.ArgumentParser(description=__doc__)
parser.add_argument("--version", action='version', version="1.0")
parser.add_argument("-m",
"--min-overlap",
dest="min_overlap",
type=float,
help="minimum overlap ")
parser.add_argument("-a",
"--bam-file",
dest="filename_bam",
metavar="bam",
type=str,
help="bam-file to use (required) ")
parser.add_argument("-b",
"--bed-file",
dest="filename_bed",
metavar="bed",
type=str,
help="bed-file to use (required) ")
parser.add_argument(
"-s",
"--sort-bed",
dest="sort_bed",
action="store_true",
help="sort the bed file by chromosomal location before "
"processing. ")
parser.add_argument(
"--assume-sorted",
dest="sort_bed",
action="store_false",
help="assume that the bed-file is sorted by chromosomal location. ")
parser.add_argument(
"--split-intervals",
dest="split_intervals",
action="store_true",
help="treat split BAM intervals, for example spliced intervals, "
"as separate intervals. Note that a single alignment might be "
"counted several times as a result. ")
parser.set_defaults(
min_overlap=0.5,
filename_bam=None,
filename_bed=None,
sort_bed=True,
split_intervals=False,
)
# add common options (-h/--help, ...) and parse command line
(args, unknown) = E.start(parser, argv=argv, unknowns=True)
filename_bam = args.filename_bam
filename_bed = args.filename_bed
if filename_bam is None and filename_bed is None:
if len(unknown) != 2:
raise ValueError(
"please supply a bam and a bed file or two bed-files.")
filename_bam, filename_bed = unknown
if filename_bed is None:
raise ValueError("please supply a bed file to compare to.")
if filename_bam is None:
raise ValueError("please supply a bam file to compare with.")
E.info("intersecting the two files")
min_overlap = args.min_overlap
args.stdout.write("category\talignments\n")
# get number of columns of reference bed file
for bed in Bed.iterator(iotools.open_file(filename_bed)):
ncolumns_bed = bed.columns
break
E.info("assuming %s is bed%i format" % (filename_bed, ncolumns_bed))
if ncolumns_bed < 4:
raise ValueError("please supply a name attribute in the bed file")
# get information about
if filename_bam.endswith(".bam"):
format = "-abam"
samfile = pysam.AlignmentFile(filename_bam, "rb")
total = samfile.mapped
# latest bedtools uses bed12 format when bam is input
ncolumns_bam = 12
# count per read
sort_key = lambda x: x.name
else:
format = "-a"
total = iotools.get_num_lines(filename_bam)
# get bed format
ncolumns_bam = 0
for bed in Bed.iterator(iotools.open_file(filename_bam)):
ncolumns_bam = bed.columns
break
if ncolumns_bam > 0:
E.info("assuming %s is bed%i fomat" % (filename_bam, ncolumns_bam))
if ncolumns_bam == 3:
# count per interval
sort_key = lambda x: (x.contig, x.start, x.end)
else:
# count per interval category
sort_key = lambda x: x.name
# use fields for bam/bed file (regions to count with)
data_fields = [
"contig", "start", "end", "name", "score", "strand", "thickstart",
"thickend", "rgb", "blockcount", "blockstarts", "blockends"
][:ncolumns_bam]
# add fields for second bed (regions to count in)
data_fields.extend([
"contig2", "start2", "end2", "name2", "score2", "strand2",
"thickstart2", "thickend2", "rgb2", "blockcount2", "blockstarts2",
"blockends2"
][:ncolumns_bed])
# add bases overlap
data_fields.append("bases_overlap")
data = collections.namedtuple("data", data_fields)
args.stdout.write("total\t%i\n" % total)
if total == 0:
E.warn("no data in %s" % filename_bam)
return
# SNS: sorting optional, off by default
if args.sort_bed:
bedcmd = "<( gunzip < %s | sort -k1,1 -k2,2n)" % filename_bed
else:
bedcmd = filename_bed
if args.split_intervals:
split = "-split"
else:
split = ""
# IMS: newer versions of intersectBed have a very high memory
# requirement unless passed sorted bed files.
statement = """bedtools intersect %(format)s %(filename_bam)s
-b %(bedcmd)s
%(split)s
-sorted -bed -wo -f %(min_overlap)f""" % locals()
E.info("starting counting process: %s" % statement)
proc = E.run(statement, return_popen=True, stdout=subprocess.PIPE)
E.info("counting")
counts_per_alignment = collections.defaultdict(int)
take_columns = len(data._fields)
def iterate(infile):
for line in infile:
if not line.strip():
continue
yield data._make(line[:-1].split()[:take_columns])
for read, overlaps in itertools.groupby(iterate(
iotools.force_str(proc.stdout)),
key=sort_key):
annotations = [x.name2 for x in overlaps]
for anno in annotations:
counts_per_alignment[anno] += 1
for key, counts in sorted(counts_per_alignment.items()):
args.stdout.write("%s\t%i\n" % (key, counts))
# write footer and output benchmark information.
E.stop()
def loadIntervals(infile, outfile):
'''load intervals from :term:`bed` formatted files into
the database.
If a :term:`bam` file is associated with a :term:`bed`
file, re-evaluate the intervals by counting reads within
the interval. In contrast to the initial pipeline, the
genome is not binned.
nprobes: number of reads in interval
peakcenter: position with maximum number of reads in interval
avgval: average coverage within interval
'''
tmpfile = P.get_temp_file(".")
headers = ("avgval", "disttostart",
"genelist", "length",
"peakcenter", "peakval",
"position", "interval_id",
"npeaks", "nprobes",
"contig", "start", "end", "score", "strand")
tmpfile.write("\t".join(headers) + "\n")
(avgval, contig, disttostart, end, genelist,
length, peakcenter, peakval, position,
start, interval_id, npeaks, nprobes) = \
0, "", 0, 0, "", 0, 0, 0, 0, 0, 0, 0, 0
track = Sample(filename=P.snip(infile, ".bed.gz"))
bamfiles, offsets = getAssociatedBAMFiles(track)
if bamfiles:
E.info("%s: associated bamfiles = %s" % (track, bamfiles))
else:
E.info("%s: no bamfiles associated" % (track))
# open all bamfiles
samfiles = [pysam.Samfile(fn, "rb") for fn in bamfiles]
c = E.Counter()
# count tags
for bed in Bed.iterator(IOTools.open_file(infile, "r")):
c.input += 1
if "name" not in bed:
bed.name = c.input
try:
strand = bed["strand"]
except IndexError:
strand = "."
# The fifth field of a bed file can be used to supply a
# score. Our iterator returns the optional fields as a "fields
# array". The first of these is the interval name, and the
# second the score. The score may be more is better or less is
# better.
if len(bed.fields) > 1:
value = bed.fields[1]
if value != "":
score = value
else:
score = 1
else:
score = 1
if samfiles:
npeaks, peakcenter, length, avgval, peakval, nprobes = \
PipelinePeakcalling.countPeaks(
bed.contig,
bed.start,
bed.end,
samfiles,
offsets)
if nprobes == 0:
c.skipped_reads += 1
else:
# deal with bed12
bed_intervals = bed.toIntervals()
length = sum([e - s for s, e in bed_intervals])
mid_point = length / 2
for s, e in bed_intervals:
peakcenter = s + mid_point
if peakcenter >= e:
mid_point = peakcenter - e
else:
break
npeaks, avgval, peakval, nprobes = \
(1,
1,
1,
1)
c.output += 1
tmpfile.write("\t".join(map(
str,
(avgval, disttostart, genelist, length,
peakcenter, peakval, position, bed.name,
npeaks, nprobes,
bed.contig, bed.start, bed.end, score, strand))) + "\n")
if c.output == 0:
E.warn("%s - no aggregate intervals")
tmpfile.close()
P.load(tmpfile.name,
outfile,
tablename=os.path.basename("%s_intervals" % track.asTable()),
options="--allow-empty-file "
"--add-index=interval_id")
os.unlink(tmpfile.name)
E.info("%s\n" % str(c))
from cgatcore import expriment as E
parser = E.OptionParser(version="%prog version: $1.0$",
usage=globals()["__doc__"])
parser.add_option("-g", "--genome", dest="genome",
help="index fasta genome sequence")
parser.add_option("-O", "--per-utron-out", dest="outfile",
help="File name for output file that will contain one row"
"per entry in the input")
options, args = E.start(parser, sys.argv)
genome = IndexedFasta.IndexedFasta(options["genome"])
bedfile = Bed.iterator(options.stdin)
splice_site_dict = dict()
outfile = iotools.open_file(options["outfile"], "w")
outfile.write("\t".join("transcript_id",
"strand",
"ss5",
"ss3",
"contig",
"splice_site_start",
"splice_site_end",
"utron_size"))
for utron in bedfile:
ss5_sequence = genome.getSequence(utron.contig, "+", utron.start, utron.start+2)
ss3_sequence = genome.getSequence(utron.contig, "+", utron.end-2, utron.end)
if utron.strand == "+":
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 = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option(
"-g", "--gtf-file", dest="filename_gtf", type="string",
help="filename with gene models in gtf format [%default]")
parser.add_option(
"-m", "--filename-mismapped", dest="filename_mismapped", type="string",
help="output bam file for mismapped reads [%default]")
parser.add_option(
"-j", "--junctions-bed-file", dest="filename_junctions", type="string",
help="bam file with reads mapped across junctions [%default]")
parser.add_option(
"-r", "--filename-regions", dest="filename_regions", type="string",
help="filename with regions to remove in bed format [%default]")
parser.add_option(
"-t", "--transcripts-gtf-file", dest="filename_transcriptome",
type="string",
help="bam file with reads mapped against transcripts [%default]")
parser.add_option(
"-p", "--map-tsv-file", dest="filename_map", type="string",
help="filename mapping transcript numbers (used by "
"--filename-transciptome) to transcript names "
"(used by --filename-gtf) [%default]")
parser.add_option(
"-s", "--filename-stats", dest="filename_stats", type="string",
help="filename to output stats to [%default]")
parser.add_option(
"-o", "--colour",
dest="colour_mismatches", action="store_true",
help="mismatches will use colour differences (CM tag) [%default]")
parser.add_option(
"-i", "--ignore-mismatches",
dest="ignore_mismatches", action="store_true",
help="ignore mismatches [%default]")
parser.add_option(
"-c", "--remove-contigs", dest="remove_contigs", type="string",
help="','-separated list of contigs to remove [%default]")
parser.add_option(
"-f", "--force-output", dest="force", action="store_true",
help="force overwriting of existing files [%default]")
parser.add_option("-u", "--unique", dest="unique", action="store_true",
help="remove reads not matching uniquely [%default]")
parser.add_option("--output-sam", dest="output_sam", action="store_true",
help="output in sam format [%default]")
parser.set_defaults(
filename_gtf=None,
filename_mismapped=None,
filename_junctions=None,
filename_transcriptome=None,
filename_map=None,
remove_contigs=None,
force=False,
unique=False,
colour_mismatches=False,
ignore_mismatches=False,
output_sam=False,
filename_table=None,
)
# add common options (-h/--help, ...) and parse command line
(options, args) = E.start(parser, argv=argv)
if len(args) != 1:
raise ValueError("please supply one bam file")
bamfile_genome = args[0]
genome_samfile = pysam.AlignmentFile(bamfile_genome, "rb")
if options.remove_contigs:
options.remove_contigs = options.remove_contigs.split(",")
if options.filename_map:
E.info("reading map")
id_map = iotools.read_map(
iotools.open_file(options.filename_map), has_header=True)
id_map = dict([(y, x) for x, y in id_map.items()])
else:
id_map = None
transcripts = {}
if options.filename_gtf:
E.info("indexing geneset")
mapped, missed = 0, 0
for gtf in GTF.transcript_iterator(
GTF.iterator(iotools.open_file(options.filename_gtf))):
gtf.sort(key=lambda x: x.start)
transcript_id = gtf[0].transcript_id
if id_map:
try:
transcript_id = id_map[transcript_id]
mapped += 1
except KeyError:
missed += 1
continue
transcripts[transcript_id] = gtf
E.info("read %i transcripts from geneset (%i mapped, %i missed)" %
(len(transcripts), mapped, missed))
regions_to_remove = None
if options.filename_regions:
E.info("indexing regions")
regions_to_remove = IndexedGenome.Simple()
for bed in Bed.iterator(iotools.open_file(options.filename_regions)):
regions_to_remove.add(bed.contig, bed.start, bed.end)
E.info("read %i regions" % len(regions_to_remove))
if options.filename_transcriptome:
transcripts_samfile = pysam.AlignmentFile(options.filename_transcriptome,
"rb")
else:
transcripts_samfile = None
if options.output_sam:
output_samfile = pysam.AlignmentFile("-", "wh", template=genome_samfile)
else:
output_samfile = pysam.AlignmentFile("-", "wb", template=genome_samfile)
if options.filename_mismapped:
if not options.force and os.path.exists(options.filename_mismapped):
raise IOError("output file %s already exists" %
options.filename_mismapped)
output_mismapped = pysam.AlignmentFile(options.filename_mismapped,
"wb",
template=genome_samfile)
else:
output_mismapped = None
if options.filename_junctions:
junctions_samfile = pysam.AlignmentFile(options.filename_junctions,
"rb")
else:
junctions_samfile = None
c = bams2bam_filter(genome_samfile,
output_samfile,
output_mismapped,
transcripts_samfile,
junctions_samfile,
transcripts,
regions=regions_to_remove,
unique=options.unique,
remove_contigs=options.remove_contigs,
colour_mismatches=options.colour_mismatches,
ignore_mismatches=options.ignore_mismatches,
ignore_transcripts=transcripts_samfile is None,
ignore_junctions=junctions_samfile is None)
if options.filename_stats:
outf = iotools.open_file(options.filename_stats, "w")
outf.write("category\tcounts\n%s\n" % c.asTable())
outf.close()
if options.filename_transcriptome:
transcripts_samfile.close()
genome_samfile.close()
output_samfile.close()
if output_mismapped:
output_mismapped.close()
# write footer and output benchmark information.
E.stop()
def buildIndex(self, filename):
return Bed.readAndIndex(iotools.open_file(filename, "r"))
def __init__(self, filename):
self.mIndices = Bed.readAndIndex(iotools.open_file(filename, "r"),
per_track=True)
def main(argv=None):
if argv is None:
argv = sys.argv
parser = E.ArgumentParser(description=__doc__)
parser.add_argument("-g",
"--genome-file",
dest="genome_file",
type=str,
help="filename with genome.")
parser.add_argument(
"-b",
"--bam-file",
dest="bam_files",
type=str,
help="filename with read mapping information. Multiple files can be "
"submitted in a comma-separated list.")
parser.add_argument(
"--control-bam-file",
dest="control_bam_files",
type=str,
help="filename with read mapping information for input/control. "
"Multiple files can be submitted in a comma-separated list ")
parser.add_argument("--filename-format",
dest="filename_format",
type=str,
choices=("bed", "gff", "gtf"),
help="format of secondary stream.")
parser.add_argument("-c",
"--counter",
dest="counters",
type=str,
action="append",
choices=("length", "overlap", "peaks",
"composition-na", "composition-cpg",
"classifier-chipseq", "motif"),
help="select counters to apply.")
parser.add_argument("--motif-sequence",
dest="motif_sequence",
type=str,
help="specify a sequence to search for")
parser.add_argument(
"-o",
"--offset",
dest="offsets",
type=int,
action="append",
help="tag offsets for tag counting - supply as many as there "
"are bam-files")
parser.add_argument(
"--control-offset",
dest="control_offsets",
type=int,
action="append",
help="control tag offsets for tag counting - supply as many as "
"there are bam-files.")
parser.add_argument(
"-a",
"--output-all-fields",
dest="all_fields",
action="store_true",
help="output all fields in original bed file, by default only "
"the first 4 are output.")
parser.add_argument(
"--output-bed-headers",
dest="bed_headers",
type=str,
help="supply ',' separated list of headers for bed component ")
parser.add_argument(
"-f",
"--gff-file",
dest="filename_gff",
type=str,
action="append",
metavar='bed',
help="filename with extra gff files. The order is important")
parser.add_argument(
"--has-header",
dest="has_header",
action="store_true",
help="bed file with headers. Headers and first columns are "
"preserved ")
parser.set_defaults(genome_file=None,
counters=[],
bam_files=None,
offsets=[],
control_bam_files=None,
control_offsets=[],
all_fields=False,
filename_format=None,
bed_headers=None,
filename_gff=[],
has_header=False,
motif_sequence=None)
(args) = E.start(parser)
if args.bed_headers is not None:
bed_headers = [x.strip() for x in args.bed_headers.split(",")]
if len(bed_headers) < 3:
raise ValueError("a bed file needs at least three columns")
else:
bed_headers = None
if args.has_header:
while 1:
line = args.stdin.readline()
if not line:
E.warn("empty bed file with no header")
E.stop()
return
if not line.startswith("#"):
break
bed_headers = line[:-1].split("\t")
if "motif" in args.counters and not args.motif_sequence:
raise ValueError("if using motif must specify a motif-sequence")
# get files
if args.genome_file:
fasta = IndexedFasta.IndexedFasta(args.genome_file)
else:
fasta = None
if args.bam_files:
bam_files = []
for bamfile in args.bam_files.split(","):
bam_files.append(pysam.AlignmentFile(bamfile, "rb"))
else:
bam_files = None
if args.control_bam_files:
control_bam_files = []
for bamfile in args.control_bam_files.split(","):
control_bam_files.append(pysam.AlignmentFile(bamfile, "rb"))
else:
control_bam_files = None
counters = []
for c in args.counters:
if c == "length":
counters.append(CounterLength(fasta=fasta, options=args))
elif c == "overlap":
counters.append(
CounterOverlap(filename=args.filename_gff[0],
fasta=fasta,
options=args))
del args.filename_gff[0]
elif c == "peaks":
counters.append(
CounterPeaks(bam_files,
args.offsets,
control_bam_files,
args.control_offsets,
options=args))
elif c == "composition-na":
counters.append(
CounterCompositionNucleotides(fasta=fasta, options=args))
elif c == "composition-cpg":
counters.append(CounterCompositionCpG(fasta=fasta, options=args))
elif c == "classifier-chipseq":
counters.append(
ClassifierChIPSeq(filename_gff=args.filename_gff,
fasta=fasta,
options=args,
prefix=None))
del args.filename_gff[0]
elif c == "motif":
counters.append(
CounterMotif(fasta=fasta, motif=args.motif_sequence))
extra_fields = None
for bed in Bed.iterator(args.stdin):
if extra_fields is None:
# output explicitely given headers
if bed_headers:
if len(bed_headers) > bed.columns:
raise ValueError(
"insufficient columns (%i, expected %i) in %s" %
(bed.columns, len(bed_headers), str(bed)))
else:
bed_headers = Bed.Headers[:bed.columns]
args.stdout.write("\t".join(bed_headers))
args.stdout.write("\t" +
"\t".join([x.getHeader()
for x in counters]) + "\n")
extra_fields = list(range(len(bed_headers) - 3))
for counter in counters:
counter.update(bed)
if args.all_fields:
args.stdout.write(str(bed))
else:
args.stdout.write("\t".join(
[bed.contig, str(bed.start),
str(bed.end)] + [bed.fields[x] for x in extra_fields]))
for counter in counters:
args.stdout.write("\t%s" % str(counter))
args.stdout.write("\n")
E.stop()
def loadIntervalsFromBed(bedfile, track, outfile,
bamfiles, offsets):
'''load intervals from :term:`bed` formatted files into database.
Re-evaluate the intervals by counting reads within
the interval. In contrast to the initial pipeline, the
genome is not binned. In particular, the meaning of the
columns in the table changes to:
nProbes: number of reads in interval
PeakCenter: position with maximum number of reads in interval
AvgVal: average coverage within interval
'''
tmpfile = P.getTempFile(".")
headers = ("AvgVal", "DisttoStart", "GeneList", "Length", "PeakCenter", "PeakVal", "Position",
"interval_id", "nCpGs", "nGenes", "nPeaks", "nProbes", "nPromoters", "contig", "start", "end")
tmpfile.write("\t".join(headers) + "\n")
avgval, contig, disttostart, end, genelist, length, peakcenter, peakval, position, start, interval_id, ncpgs, ngenes, npeaks, nprobes, npromoters = \
0, "", 0, 0, "", 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
mlength = int(PARAMS["calling_merge_min_interval_length"])
c = E.Counter()
# count tags
for bed in Bed.iterator(iotools.openFile(infile, "r")):
c.input += 1
if "name" not in bed:
bed.name = c.input
# remove very short intervals
if bed.end - bed.start < mlength:
c.skipped_length += 1
continue
if replicates:
npeaks, peakcenter, length, avgval, peakval, nprobes = \
PipelineChipseq.countPeaks(
bed.contig, bed.start, bed.end,
samfiles, offsets)
# nreads can be 0 if the intervals overlap only slightly
# and due to the binning, no reads are actually in the
# overlap region. However, most of these intervals should
# be small and have already be deleted via the
# merge_min_interval_length cutoff. do not output
# intervals without reads.
if nprobes == 0:
c.skipped_reads += 1
else:
npeaks, peakcenter, length, avgval, peakval, nprobes = (
1,
bed.start +
(bed.end - bed.start) // 2,
bed.end - bed.start,
1,
1,
1)
c.output += 1
tmpfile.write("\t".join(map(
str,
(avgval, disttostart, genelist, length,
peakcenter, peakval, position, bed.name,
ncpgs, ngenes, npeaks, nprobes, npromoters,
bed.contig, bed.start, bed.end))) + "\n")
if c.output == 0:
E.warn("%s - no intervals")
tmpfile.close()
tmpfilename = tmpfile.name
tablename = "%s_intervals" % track.asTable()
statement = '''
cgat csv2db %(csv2db_options)s
--allow-empty-file
--add-index=interval_id
--table=%(tablename)s
< %(tmpfilename)s
> %(outfile)s
'''
P.run()
os.unlink(tmpfile.name)
E.info("%s\n" % str(c))
def main(argv=sys.argv):
parser = E.ArgumentParser(description=__doc__)
# IMS: new method: extend intervals by set amount
parser.add_argument("-m",
"--method",
dest="methods",
type=str,
action="append",
choices=("merge", "filter-genome", "bins", "block",
"sanitize-genome", "shift", "extend",
"filter-names", "rename-chr"),
help="method to apply")
parser.add_argument("--num-bins",
dest="num_bins",
type=int,
help="number of bins into which to merge (used for "
"method `bins)")
parser.add_argument("--bin-edges",
dest="bin_edges",
type=str,
help="bin_edges for binning method")
parser.add_argument(
"--binning-method",
dest="binning_method",
type=str,
choices=("equal-bases", "equal-intervals", "equal-range"),
help="method used for binning (used for method `bins` if no "
"bin_edges is given)")
parser.add_argument(
"--merge-distance",
dest="merge_distance",
type=int,
help="distance in bases over which to merge that are not "
"directly adjacent")
parser.add_argument(
"--merge-min-intervals",
dest="merge_min_intervals",
type=int,
help="only output merged intervals that are build from at least "
"x intervals")
parser.add_argument("--merge-by-name",
dest="merge_by_name",
action="store_true",
help="only merge intervals with the same name")
parser.add_argument(
"--merge-and-resolve-blocks",
dest="resolve_blocks",
action="store_true",
help="When merging bed12 entrys, should blocks be resolved?")
parser.add_argument("--merge-stranded",
dest="stranded",
action="store_true",
help="Only merge intervals on the same strand")
parser.add_argument(
"--remove-inconsistent-names",
dest="remove_inconsistent_names",
action="store_true",
help="when merging, do not output intervals where the names of "
"overlapping intervals do not match")
parser.add_argument("--offset",
dest="offset",
type=int,
help="offset for shifting intervals")
parser.add_argument("-g",
"--genome-file",
dest="genome_file",
type=str,
help="filename with genome.")
parser.add_argument("-b",
"--bam-file",
dest="bam_file",
type=str,
help="bam-formatted filename with genome.")
parser.add_argument("--filter-names-file",
dest="names",
type=str,
help="list of names to keep. One per line")
parser.add_argument(
"--rename-chr-file",
dest="rename_chr_file",
type=str,
help="mapping table between old and new chromosome names."
"TAB separated 2-column file.")
parser.set_defaults(methods=[],
merge_distance=0,
binning_method="equal-bases",
merge_by_name=False,
genome_file=None,
rename_chr_file=None,
bam_file=None,
num_bins=5,
merge_min_intervals=1,
bin_edges=None,
offset=10000,
test=None,
extend_distance=1000,
remove_inconsistent_names=False,
resolve_blocks=False)
(args) = E.start(parser, add_pipe_options=True)
contigs = None
chr_map = None
# Why provide full indexed genome, when a tsv of contig sizes would do?
if args.genome_file:
genome_fasta = IndexedFasta.IndexedFasta(args.genome_file)
contigs = genome_fasta.getContigSizes()
if args.bam_file:
samfile = pysam.AlignmentFile(args.bam_file)
contigs = dict(list(zip(samfile.references, samfile.lengths)))
if args.rename_chr_file:
chr_map = {}
with open(args.rename_chr_file, 'r') as filein:
reader = csv.reader(filein, delimiter='\t')
for row in reader:
if len(row) != 2:
raise ValueError(
"Mapping table must have exactly two columns")
chr_map[row[0]] = row[1]
if not len(chr_map.keys()) > 0:
raise ValueError("Empty mapping dictionnary")
processor = Bed.iterator(args.stdin)
for method in args.methods:
if method == "filter-genome":
if not contigs:
raise ValueError("please supply contig sizes")
processor = filterGenome(processor, contigs)
elif method == "sanitize-genome":
if not contigs:
raise ValueError("please supply contig sizes")
processor = sanitizeGenome(processor, contigs)
elif method == "merge":
processor = merge(
processor,
args.merge_distance,
by_name=args.merge_by_name,
min_intervals=args.merge_min_intervals,
remove_inconsistent=args.remove_inconsistent_names,
resolve_blocks=args.resolve_blocks,
stranded=args.stranded)
elif method == "bins":
if args.bin_edges:
bin_edges = list(map(float, args.bin_edges.split(",")))
# IMS: check bin edges are valid
if not (len(bin_edges) == args.num_bins + 1):
raise ValueError(
"Number of bin edge must be one more than "
"number of bins")
else:
bin_edges = None
processor, bin_edges = Bed.binIntervals(processor,
num_bins=args.num_bins,
method=args.binning_method,
bin_edges=bin_edges)
E.info("# split bed: bin_edges=%s" % (str(bin_edges)))
elif method == "block":
processor = Bed.blocked_iterator(processor)
elif method == "shift":
# IMS: test that contig sizes are availible
if not contigs:
raise ValueError("please supply genome file")
processor = shiftIntervals(processor, contigs, offset=args.offset)
# IMS: new method: extend intervals by set amount
elif method == "extend":
if not contigs:
raise ValueError("please supply genome file")
processor = extendInterval(processor, contigs, args.offset)
elif method == "filter-names":
if not args.names:
raise ValueError("please supply list of names to filter")
names = [name.strip() for name in open(args.names)]
processor = filterNames(processor, names)
elif method == "rename-chr":
if not chr_map:
raise ValueError("please supply mapping file")
processor = renameChromosomes(processor, chr_map)
noutput = 0
for bed in processor:
args.stdout.write(str(bed) + "\n")
noutput += 1
E.info("noutput=%i" % (noutput))
E.stop()
def aggregateWindowsTagCounts(infiles, outfile, regex="(.*)\..*"):
'''aggregate output from several ``bedtools coverage`` results.
``bedtools coverage`` outputs the following columns for a bed4
file::
1 Contig
2 Start
3 Stop
4 Name
5 The number of features in A that overlapped (by at least one
base pair) the B interval.
6 The number of bases in B that had non-zero coverage from features in A.
7 The length of the entry in B.
8 The fraction of bases in B that had non-zero coverage from
features in A.
This method autodetects the number of columns in the :term:`infiles`
and selects:
* bed4: use column 5
* bed6: use column 7
* bed12: use column 13
Arguments
---------
infiles : list
Input filenames with the output from ``bedtools coverage``
outfile : string
Output filename in :term:`tsv` format.
regex : string
Regular expression used to extract the track name from the
filename. The default removes any suffix.
'''
# get bed format
bed_columns = Bed.getNumColumns(infiles[0])
# +1 as awk is 1-based
column = bed_columns - 4 + 1
src = " ".join([
"""<( zcat %s |
awk '{printf("%%s:%%i-%%i\\t%%i\\n", $1,$2,$3,$%s );}')""" %
(x, column) for x in infiles
])
tmpfile = P.get_temp_filename(".")
statement = '''paste %(src)s > %(tmpfile)s'''
P.run(statement)
# build track names
tracks = [
re.search(regex, os.path.basename(x)).groups()[0] for x in infiles
]
outf = iotools.open_file(outfile, "w")
outf.write("interval_id\t%s\n" % "\t".join(tracks))
# filter for uniqueness - keys with the same value as the
# previous line will be ignored.
last_gene = None
c = E.Counter()
for line in open(tmpfile, "r"):
c.input += 1
data = line[:-1].split("\t")
genes = list(set([data[x] for x in range(0, len(data), 2)]))
values = [int(data[x]) for x in range(1, len(data), 2)]
assert len(genes) == 1, \
"paste command failed, wrong number of genes per line: '%s'" % line
if genes[0] == last_gene:
c.duplicates += 1
continue
c.output += 1
outf.write("%s\t%s\n" % (genes[0], "\t".join(map(str, values))))
last_gene = genes[0]
outf.close()
os.unlink(tmpfile)
E.info("aggregateWindowsTagCounts: %s" % c)
def main(argv=None):
if argv is None:
argv = sys.argv
parser = E.OptionParser(
version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option("-g", "--genome-file", dest="genome_file", type="string",
help="filename with genomic sequence to retrieve "
"sequences from.")
parser.add_option("-m", "--masker", dest="masker", type="choice",
choices=("dust", "dustmasker", "softmask", "none"),
help="apply masker to mask output sequences "
"[%default].")
parser.add_option("--output-mode", dest="output_mode", type="choice",
choices=("intervals", "leftright", "segments"),
help="what to output. "
"'intervals' generates a single sequence for "
"each bed interval. 'leftright' generates two "
"sequences, one in each direction, for each bed "
"interval. 'segments' can be used to output "
"sequence from bed12 files so that sequence only covers "
"the segements [%default]")
parser.add_option("--min-sequence-length", dest="min_length", type="int",
help="require a minimum sequence length [%default]")
parser.add_option("--max-sequence-length", dest="max_length", type="int",
help="require a maximum sequence length [%default]")
parser.add_option(
"--extend-at", dest="extend_at", type="choice",
choices=("none", "3", "5", "both", "3only", "5only"),
help="extend at 3', 5' or both or no ends. If 3only or 5only "
"are set, only the added sequence is returned [default=%default]")
parser.add_option(
"--extend-by", dest="extend_by", type="int",
help="extend by # bases [default=%default]")
parser.add_option(
"--use-strand", dest="ignore_strand",
action="store_false",
help="use strand information and return reverse complement "
"on intervals located on the negative strand. "
"[default=%default]")
parser.set_defaults(
genome_file=None,
masker=None,
output_mode="intervals",
min_length=0,
max_length=0,
extend_at=None,
extend_by=100,
ignore_strand=True,
)
(options, args) = E.start(parser)
if options.genome_file:
fasta = IndexedFasta.IndexedFasta(options.genome_file)
contigs = fasta.getContigSizes()
fasta.setConverter(IndexedFasta.getConverter("zero-both-open"))
counter = E.Counter()
ids, seqs = [], []
E.info("collecting sequences")
for bed in Bed.setName(Bed.iterator(options.stdin)):
counter.input += 1
lcontig = fasta.getLength(bed.contig)
if options.ignore_strand:
strand = "+"
else:
strand = bed.strand
if options.output_mode == "segments" and bed.columns == 12:
ids.append("%s %s:%i..%i (%s) %s %s" %
(bed.name, bed.contig, bed.start, bed.end, strand,
bed["blockSizes"], bed["blockStarts"]))
seg_seqs = [fasta.getSequence(bed.contig, strand, start, end)
for start, end in bed.toIntervals()]
seqs.append("".join(seg_seqs))
elif (options.output_mode == "intervals" or
options.output_mode == "segments"):
ids.append("%s %s:%i..%i (%s)" %
(bed.name, bed.contig, bed.start, bed.end, strand))
seqs.append(
fasta.getSequence(bed.contig, strand, bed.start, bed.end))
elif options.output_mode == "leftright":
l = bed.end - bed.start
start, end = max(0, bed.start - l), bed.end - l
ids.append("%s_l %s:%i..%i (%s)" %
(bed.name, bed.contig, start, end, strand))
seqs.append(fasta.getSequence(bed.contig, strand, start, end))
start, end = bed.start + l, min(lcontig, bed.end + l)
ids.append("%s_r %s:%i..%i (%s)" %
(bed.name, bed.contig, start, end, strand))
seqs.append(fasta.getSequence(bed.contig, strand, start, end))
E.info("collected %i sequences" % len(seqs))
masked = Masker.maskSequences(seqs, options.masker)
options.stdout.write(
"\n".join([">%s\n%s" % (x, y) for x, y in zip(ids, masked)]) + "\n")
E.info("masked %i sequences" % len(seqs))
counter.output = len(seqs)
E.info("%s" % counter)
E.stop()
from cgat import Bed
from cgat import IndexedFasta
from cgatcore import iotools
from cgat import Genomics
# In[3]:
genome = IndexedFasta.IndexedFasta("/shared/sudlab1/General/mirror/genomes/plain/hg38.fasta")
# In[7]:
bedfile = Bed.iterator(iotools.open_file(sys.argv[1]))
splice_site_dict = dict()
outfile = iotools.open_file(sys.argv[2], "w")
for utron in bedfile:
ss5_sequence = genome.getSequence(utron.contig, "+", utron.start, utron.start+2)
ss3_sequence = genome.getSequence(utron.contig, "+", utron.end-2, utron.end)
if utron.strand == "+":
splice_site_dict[utron.name] = (ss5_sequence, ss3_sequence)
if ":" in utron.name:
transcript_id = utron.name.split(":")[0]
match_transcript_id = utron.name.split(":")[1]
outfile.write("%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\n" % (transcript_id, utron.strand, ss5_sequence, ss3_sequence, utron.contig, utron.start, utron.end, utron.end-utron.start))
else:
outfile.write("%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\n" % (utron.name, utron.strand, ss5_sequence, ss3_sequence, utron.contig, utron.start, utron.end, utron.end-utron.start))
def main(argv=sys.argv):
parser = E.ArgumentParser(description=__doc__)
parser.add_argument("--is-gtf",
dest="is_gtf",
action="store_true",
help="input file is in gtf format")
parser.add_argument("--set-name",
dest="name",
type=str,
help="field from the GFF/GTF file to use as the "
"name field in the BED file ",
choices=("gene_id", "transcript_id", "class", "family",
"feature", "source", "repName",
"gene_biotype"))
parser.add_argument("--track",
dest="track",
type=str,
choices=("feature", "source", None),
help="use feature/source field to define BED tracks ")
parser.add_argument(
"--bed12-from-transcripts",
dest="bed12",
action="store_true",
default=False,
help="Process GTF file into Bed12 entries, with blocks as exons"
"and thick/thin as coding/non-coding")
parser.set_defaults(track=None, name="gene_id", is_gtf=False)
(args) = E.start(parser, add_pipe_options=True)
ninput, noutput = 0, 0
iterator = GTF.iterator(args.stdin)
if args.bed12:
iterator = GTF.transcript_iterator(iterator)
if args.track:
all_input = list(iterator)
if args.track == "feature":
grouper = lambda x: x.feature
elif args.track == "source":
grouper = lambda x: x.source
all_input.sort(key=grouper)
bed = Bed.Bed()
for key, vals in itertools.groupby(all_input, grouper):
args.stdout.write("track name=%s\n" % key)
for gff in vals:
ninput += 1
if args.bed12:
bed = transcript2bed12(gff)
else:
bed.fromGTF(gff, name=args.name)
args.stdout.write(str(bed) + "\n")
noutput += 1
else:
bed = Bed.Bed()
for gff in iterator:
ninput += 1
if args.bed12:
bed = transcript2bed12(gff)
else:
bed.fromGTF(gff, name=args.name)
args.stdout.write(str(bed) + "\n")
noutput += 1
E.info("ninput=%i, noutput=%i" % (ninput, noutput))
E.stop()
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
parser = buildOptionParser(argv)
# add common options (-h/--help, ...) and parse command line
(options, args) = E.start(parser, argv=argv, add_output_options=True)
if len(args) != 2:
raise ValueError(
"please specify one bam- or wig-file and one bed file")
if options.control_files:
E.info("using control files: %s" % ",".join(options.control_files))
infile, bedfile = args
control_files = []
if options.format == "bigwig":
fg_file = pyBigWig.open(infile)
for control_file in options.control_files:
control_files.append(pyBigWig.open(control_file))
counter = bam2peakshape.CounterBigwig(
smooth_method=options.smooth_method)
elif options.format == "bam":
fg_file = pysam.AlignmentFile(infile, "rb")
for control_file in options.control_files:
control_files.append(pysam.AlignmentFile(control_file, "rb"))
counter = bam2peakshape.CounterBam(shift=options.shift,
smooth_method=options.smooth_method)
features_per_interval, bins = buildDensityMatrices(
Bed.iterator(iotools.open_file(bedfile)),
fg_file,
control_files,
counter,
window_size=options.window_size,
bin_size=options.bin_size,
strand_specific=options.strand_specific,
centring_method=options.centring_method,
use_interval=options.use_interval,
random_shift=options.random_shift,
smooth_method=options.smooth_method,
report_step=options.report_step)
if len(features_per_interval) == 0:
E.warn("no data - no output")
E.stop()
return
outputFeatureTable(options.stdout, features_per_interval, bins)
# apply normalization
# Note: does not normalize control?
# Needs reworking, currently it does not normalize across
# all samples nor does the work "sum" reflect the per million
# normalization.
if options.normalization == "sum":
E.info("starting sum normalization")
# get total counts across all intervals
norm = 0.0
for foreground, bed, controls, shifted in features_per_interval:
norm += sum(foreground.counts)
# per million
norm /= float(1000000)
E.info("sum/million normalization with %f" % norm)
# normalise
new_data = []
for foreground, bed, controls, shifted in features_per_interval:
foreground = foreground._replace(
counts=numpy.array(foreground.counts, dtype=numpy.float) /
norm)
new_controls = []
for control in controls:
new_controls.append(
control._replace(
counts=numpy.array(control.counts, dtype=numpy.float) /
norm))
if shifted:
shifted = shifted._replace(
counts=numpy.array(shifted.counts, dtype=numpy.float) /
norm)
new_data.append(
IntervalData._make((foreground, bed, new_controls, shifted)))
features_per_interval = new_data
else:
E.info("no normalization performed")
# center bins
out_bins = bins[:-1] + options.bin_size
# build tracks
def _toTrack(filename):
return os.path.splitext(os.path.basename(filename))[0]
outputMatrices(features_per_interval,
out_bins,
foreground_track=_toTrack(infile),
control_tracks=[_toTrack(x) for x in options.control_files],
shifted=options.random_shift,
sort_orders=options.sort_orders)
# write footer and output benchmark information.
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
# setup command line parser
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
# add common options (-h/--help, ...) and parse command line
(options, args) = E.start(parser, argv=argv)
bam = pysam.AlignmentFile(args[0])
outlines = list()
for junction in Bed.iterator(options.stdin):
reads = bam.fetch(junction.contig,
junction.start - 1,
junction.start + 1)
retained_reads = 0
spliced_reads = 0
incompatible = 0
reads = list(reads)
total = len(reads)
if len(reads) == 0:
continue
for read in reads:
if read.get_tag("NH") > 1:
continue
found = False
if 'N' not in read.cigarstring and \
read.pos < junction.start and \
read.aend > junction.start:
found = True
retained_reads += 1
continue
segments = read.get_blocks()
for i in range(len(segments) - 1):
if segments[i][0] < junction.start and\
segments[i][1] > junction.start:
found = True
retained_reads += 1
elif abs(segments[i][1] - junction.start) < 3 and\
abs(segments[i+1][0] - junction.end) < 3:
found = True
spliced_reads += 1
if not found and \
segments[-1][0] < junction.start and \
segments[-1][1] > junction.end:
retained_reads += 1
else:
incompatible += 1
if spliced_reads + retained_reads > 0:
psi = retained_reads/float(spliced_reads + retained_reads)
else:
psi = "NA"
options.stdout.write("\t".join(map(str, [junction.contig,
junction.start,
junction.end,
junction.name,
retained_reads,
spliced_reads,
incompatible,
total,
psi])) +
"\n")
# write footer and output benchmark information.
E.stop()
def annotateCpGIslands(infiles, outfile):
'''annotate transcript by absence/presence of CpG islands
'''
cpgfile, tssfile = infiles
cpg = Bed.readAndIndex(iotools.openFile(cpgfile))
extension_upstream = PARAMS["cpg_search_upstream"]
extension_downstream = PARAMS["cpg_search_downstream"]
c = E.Counter()
outf = iotools.openFile(outfile, "w")
outf.write(
"transcript_id\tstrand\tstart\tend\trelative_start\trelative_end\n")
for tss in Bed.iterator(iotools.openFile(tssfile)):
c.tss_total += 1
if tss.strand == "+":
start, end = tss.start - \
extension_upstream, tss.start + extension_downstream
else:
start, end = tss.end - \
extension_downstream, tss.end + extension_upstream
try:
matches = list(cpg[tss.contig].find(start, end))
except KeyError:
c.promotor_without_matches += 1
continue
if len(matches) == 0:
c.promotor_without_matches += 1
continue
c.promotor_output += 1
for match in matches:
c.matches_total += 1
genome_start, genome_end, x = match
l = genome_end - genome_start
# get relative location of match
if tss.strand == "+":
relative_start = genome_start - tss.start
else:
relative_start = tss.end - genome_end
relative_end = relative_start + l
outf.write("\t".join(
map(str, (tss.name, tss.strand, genome_start, genome_end,
relative_start, relative_end))) + "\n")
c.matches_output += 1
outf.close()
with iotools.openFile(outfile + ".summary", "w") as outf:
outf.write("category\tcounts\n")
outf.write(c.asTable() + "\n")
E.info(c)
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if argv is None:
argv = sys.argv
# setup command line parser
parser = E.OptionParser(version="%prog version: $1.0$",
usage=globals()["__doc__"])
parser.add_option("-r",
"--reffile",
dest="reffile",
type="string",
help="Supply reference gtf file name")
parser.add_option("-d",
"--class-file",
dest="classfile",
type="string",
help="Supply database name")
parser.add_option("-o",
"--outfile",
dest="outfile",
type="string",
help="Supply output bed file name")
parser.add_option("-u",
"--indivfile",
dest="indivfile",
type="string",
help="Supply output bed file name for individual utrons")
parser.add_option("-p",
"--partfile",
dest="partfile",
type="string",
help="Supply output bed file name for partnered utrons")
parser.add_option(
"-q",
"--indivpartfile",
dest="indivpartfile",
type="string",
help="Supply output bed file name for individual partnered utrons")
parser.add_option("-n",
"--novel-file",
dest="novelfile",
type="string",
help="Supply output bed file name for novel introns")
parser.add_option(
"--novel-transcript",
dest="novel_id",
type="string",
help="DEBUG: Output info for this transcript from the STDIN")
parser.add_option(
"--target-transcript",
dest="target_id",
type="string",
help="DEBUG: Output info for this transcript from ref-file")
# add common options (-h/--help, ...) and parse command line
(options, args) = E.start(parser, argv=argv)
outlines = []
individuals = []
partnered = []
individualpartnered = []
novel = []
db = pandas.read_csv(options.classfile, sep="\t")
# This keeps just one entry per-transcript - why?
#db = db.groupby("transcript_id").first()
db = db.set_index("transcript_id")
enshashtable = getGeneTable(options.reffile)
for novel_transcript in GTF.transcript_iterator(GTF.iterator(
options.stdin)):
# Why do it on a gene by gene basis rather than transcript by transcript basis?
transcript_id = novel_transcript[0].transcript_id
if transcript_id == options.novel_id:
output_novel = True
else:
output_novel = False
try:
geneid = db.loc[transcript_id].match_gene_id
except KeyError:
if output_novel:
E.debug("Transcript %s not in class table" % transcript_id)
continue
if pandas.isnull(geneid):
if output_novel:
E.debug("Transcript %s matches no gene in class table" %
transcript_id)
continue
ens_gene = enshashtable[geneid]
all_ref_introns = set()
novel_transcript_exons = GTF.asRanges(novel_transcript, "exon")
novel_transcript_introns = GTF.toIntronIntervals(novel_transcript)
for ref_transcript in ens_gene["models"].values():
ref_introns = GTF.toIntronIntervals(ref_transcript)
all_ref_introns.update(ref_introns)
#Identify comparison set
def _in_exon(position, exons):
return any(e[0] <= position <= e[1] for e in exons)
# check if this ever gets the wrong start_codon.
filtered_starts = [
s for s in ens_gene["start_codons"]
if _in_exon(s, novel_transcript_exons)
]
if len(filtered_starts) == 0:
if output_novel:
E.debug("No starts found for %s" % transcript_id)
continue
#if novel_transcript[0].strand == "-":
# selected_start = max(filtered_starts)
#else:
# selected_start = min(filtered_starts)
selected_models = list()
for startc in filtered_starts:
selected_models.extend(ens_gene["start_codons"][startc])
if output_novel:
E.debug("Transcripts with compatible starts are %s" %
selected_models)
for ref_transcript_id in selected_models:
if output_novel and ref_transcript_id == options.target_id:
output_ref = True
else:
output_ref = False
second = ens_gene["models"][ref_transcript_id]
ens_CDS = GTF.asRanges(second, "CDS")
if len(ens_CDS) == 0:
if output_ref:
E.debug("%s is not coding"
) # ensure only protein-coding transcripts
continue
ens_exons = GTF.asRanges(second, "exon")
first_introns = set(novel_transcript_introns)
second_introns = set(GTF.toIntronIntervals(second))
first_CDSintrons = [
intron for intron in first_introns
if (intron[0] > ens_CDS[0][0] and intron[1] < ens_CDS[-1][1])
]
second_CDSintrons = [
intron for intron in second_introns
if (intron[0] > ens_CDS[0][0] and intron[1] < ens_CDS[-1][1])
]
first_CDSintrons = set(first_CDSintrons)
second_CDSintrons = set(second_CDSintrons)
if not first_CDSintrons == second_CDSintrons:
if output_ref:
E.debug("CDS chains do not match. Chains are:")
first_CDSintrons = sorted(list(first_CDSintrons))
second_CDSintrons = sorted(list(second_CDSintrons))
output = "\n".join(
map(str, zip(first_CDSintrons, second_CDSintrons)))
E.debug(output)
continue # match CDS intron chain
firstUTRintrons = first_introns - first_CDSintrons
if len(firstUTRintrons) == 0:
if output_ref:
E.debug("No UTR introns")
continue
secondUTRintrons = second_introns - second_CDSintrons
found = False
for intron in first_introns:
if (intron[0] < ens_CDS[-1][1] and
intron[1] > ens_CDS[-1][1]) or \
(intron[0] < ens_CDS[0][0] and
intron[1] > ens_CDS[0][0]):
found = True
break # ensure pruned transcript doesn't have
# introns overlapping start or stop codons in ensembl
# transcript
if found:
if output_ref:
E.debug("Start or stop in intron")
continue
if second[0].strand == "+":
ens_stop = ens_CDS[-1][1]
UTR3introns = [
intron for intron in firstUTRintrons
if intron[0] >= ens_CDS[-1][1]
and intron[1] < ens_exons[-1][1]
]
secondUTR3introns = [
intron for intron in secondUTRintrons
if intron[0] >= ens_CDS[-1][1]
and intron[1] < ens_exons[-1][1]
]
else:
ens_stop = ens_CDS[0][0]
UTR3introns = [
intron for intron in firstUTRintrons if
intron[1] <= ens_CDS[0][0] and intron[0] > ens_exons[0][0]
]
secondUTR3introns = [
intron for intron in secondUTRintrons if
intron[1] <= ens_CDS[0][0] and intron[0] > ens_exons[0][0]
]
if len(UTR3introns) == 0:
if output_ref:
E.debug("No UTR introns")
continue
outbed = Bed.Bed()
outbed.fields = ['.', '.', '.', '.', '.', '.', '.', '.', '.']
outbed.fromIntervals(UTR3introns)
outbed.contig = novel_transcript[0].contig
outbed["name"] = novel_transcript[0].transcript_id
outbed["strand"] = novel_transcript[0].strand
outlines.append(outbed) # get output for each transcript
for item in UTR3introns:
outbed2 = Bed.Bed()
outbed2.fields = ['.', '.', '.', '.']
outbed2.fromIntervals([item])
outbed2.contig = novel_transcript[0].contig
outbed2['name'] = novel_transcript[0].transcript_id
outbed2["strand"] = novel_transcript[0].strand
outbed2["thickStart"] = ens_stop
individuals.append(outbed2) # get output for each intron
UTR3introns = set(UTR3introns)
secondUTR3introns = set(secondUTR3introns)
extraUTR3introns = list(UTR3introns - secondUTR3introns)
if output_ref and len(secondUTR3introns - UTR3introns) > 0:
E.debug("Following introns in UTR of %s but not %s" %
(options.target_id, options.novel_id))
E.debug(secondUTRintrons - UTR3introns)
# get only introns that are not in matched transcript
if len(extraUTR3introns) != 0 and len(secondUTR3introns -
UTR3introns) == 0:
outbed3 = Bed.Bed()
outbed3.fields = ['.'] * 9
outbed3.fromIntervals(extraUTR3introns)
outbed3.contig = novel_transcript[0].contig
outbed3["name"] = novel_transcript[
0].transcript_id + ":" + second[0].transcript_id
outbed3["strand"] = novel_transcript[0].strand
partnered.append(outbed3)
for item in extraUTR3introns:
outbed4 = Bed.Bed()
outbed4.fields = ['.', '.', '.', '.']
outbed4.fromIntervals([item])
outbed4.contig = novel_transcript[0].contig
outbed4["name"] = novel_transcript[
0].transcript_id + ":" + second[0].transcript_id
outbed4["strand"] = novel_transcript[0].strand
outbed4["thickStart"] = ens_stop
individualpartnered.append(outbed4)
if len(all_ref_introns) == 0:
ens_starts, ens_ends = [], []
else:
ens_starts, ens_ends = zip(*all_ref_introns)
novelEvents = [
i for i in UTR3introns
if i[0] not in ens_starts and i[1] not in ens_ends
]
for item in novelEvents:
outbed5 = Bed.Bed()
outbed5.fields = ['.'] * 4
outbed5.fromIntervals([item])
outbed5.contig = novel_transcript[0].contig
outbed5["name"] = novel_transcript[
0].transcript_id + ":" + second[0].transcript_id
outbed5["strand"] = novel_transcript[0].strand
outbed5["thickStart"] = ens_stop
novel.append(outbed5)
with IOTools.open_file(options.outfile, "w") as outf:
for line in outlines:
outf.write(str(line) + "\n")
if options.indivfile is not None:
with IOTools.open_file(options.indivfile, "w") as outf2:
for line in individuals:
outf2.write(str(line) + "\n")
if options.partfile is not None:
with IOTools.open_file(options.partfile, "w") as outf3:
for line in partnered:
outf3.write(str(line) + "\n")
if options.indivpartfile is not None:
with IOTools.open_file(options.indivpartfile, "w") as outf4:
for line in individualpartnered:
outf4.write(str(line) + "\n")
if options.novelfile is not None:
with IOTools.open_file(options.novelfile, "w") as outf5:
for line in novel:
outf5.write(str(line) + "\n")
# write footer and output benchmark information.
E.stop()
def main(argv=None):
if argv is None:
argv = sys.argv
parser = E.ArgumentParser(description=__doc__)
parser.add_argument(
"-g", "--genome-file", dest="genome_file", type=str,
help="filename with genome.")
parser.add_argument(
"-a", "--aggregate-by", dest="aggregate", type=str,
choices=("name", "contig", "track", "none"),
help="aggregate counts by feature.")
parser.add_argument(
"-p", "--add-percent", dest="add_percent", action="store_true",
help="add percentages.")
parser.set_defaults(
genome_file=None,
aggregate="none",
add_percent=False,
)
(args) = E.start(parser, argv)
# get files
if args.genome_file:
fasta = IndexedFasta.IndexedFasta(args.genome_file)
else:
if args.add_percent:
raise ValueError("--add-percent option requires --genome-file")
fasta = None
if args.add_percent and not args.aggregate == "contig":
raise NotImplementedError(
"--add-percent option requires --aggregate=contig")
counts = collections.defaultdict(Counter)
total = Counter()
output_totals = True
if args.aggregate == "track":
keyf = lambda x: x.track
elif args.aggregate == "name":
keyf = lambda x: x.name
elif args.aggregate == "contig":
keyf = lambda x: x.contig
else:
keyf = lambda x: "all"
output_totals = False
for bed in Bed.iterator(args.stdin):
counts[keyf(bed)].add(bed)
total.add(bed)
outf = args.stdout
key = "track"
if args.add_percent:
outf.write("%s\t%s\n" % (key, "\t".join(Counter.headers_percent)))
else:
outf.write("%s\t%s\n" % (key, "\t".join(Counter.headers)))
total_bases = 0
for key, count in sorted(counts.items()):
if args.add_percent:
total_bases += fasta.getLength(key)
count.setSize(fasta.getLength(key))
outf.write("%s\t%s\n" % (key, str(count)))
if output_totals:
if args.add_percent:
count.setSize(total_bases)
outf.write("%s\t%s\n" % ("total", str(total)))
E.stop()