def getSigHeights(sig_bed, bam_file, outfile):
''' Take a bedgraph of significant x-linked bases and return a begraph of heights '''
print iCLIP.__file__
bam = pysam.AlignmentFile(bam_file)
last_contig = None
intervals = []
outlist = []
for line in IOTools.openFile(sig_bed):
contig, start, end, pval = line.strip().split("\t")
if last_contig is None:
last_contig = contig
if contig != last_contig:
print last_contig
out = iCLIP.count_intervals(bam, intervals, last_contig)
out.index.name = "start"
out.name = "count"
out = out.reset_index()
out["contig"] = last_contig
outlist.append(out)
intervals = []
last_contig = contig
intervals.append((int(start), int(end)))
# output the final chrom
out = iCLIP.count_intervals(bam, intervals, last_contig)
out.index.name = "start"
out.name = "count"
out = out.reset_index()
out["contig"] = last_contig
outlist.append(out)
outframe = pandas.concat(outlist)
outframe["end"] = outframe["start"] + 1
outframe = outframe.loc[:, ["contig", "start", "end", "count"]]
outframe["start"] = outframe["start"].astype("int")
outframe["end"] = outframe["end"].astype("int")
outframe.to_csv(IOTools.openFile(outfile, "w"),
sep="\t",
index=False,
header=False)
def getSigHeights(sig_bed, bam_file, outfile):
''' Take a bedgraph of significant x-linked bases and return a begraph of heights '''
print iCLIP.__file__
bam = pysam.AlignmentFile(bam_file)
last_contig = None
intervals = []
outlist = []
for line in IOTools.openFile(sig_bed):
contig, start, end, pval = line.strip().split("\t")
if last_contig is None:
last_contig = contig
if contig != last_contig:
print last_contig
out = iCLIP.count_intervals(bam, intervals, last_contig)
out.index.name = "start"
out.name = "count"
out = out.reset_index()
out["contig"] = last_contig
outlist.append(out)
intervals = []
last_contig = contig
intervals.append((int(start), int(end)))
# output the final chrom
out = iCLIP.count_intervals(bam, intervals, last_contig)
out.index.name = "start"
out.name = "count"
out = out.reset_index()
out["contig"] = last_contig
outlist.append(out)
outframe = pandas.concat(outlist)
outframe["end"] = outframe["start"] + 1
outframe = outframe.loc[:,["contig", "start", "end", "count"]]
outframe["start"] = outframe["start"].astype("int")
outframe["end"] = outframe["end"].astype("int")
outframe.to_csv(IOTools.openFile(outfile, "w"), sep="\t", index=False, header=False)
def countTagsInClusters(bedfile, bamfile, outfile):
bam = pysam.AlignmentFile(bamfile)
outlines = []
for bed in Bed.iterator(IOTools.openFile(bedfile)):
interval = (bed.start, bed.end)
counts = iCLIP.count_intervals(bam, [interval], bed.contig).sum()
outlines.append(["%s:%i-%i" % (bed.contig, bed.start, bed.end), str(counts)])
IOTools.writeLines(outfile, outlines, header=["position","count"])
def countTagsInClusters(bedfile, bamfile, outfile):
bam = pysam.AlignmentFile(bamfile)
outlines = []
for bed in Bed.iterator(IOTools.openFile(bedfile)):
interval = (bed.start, bed.end)
counts = iCLIP.count_intervals(bam, [interval], bed.contig).sum()
outlines.append(
["%s:%i-%i" % (bed.contig, bed.start, bed.end),
str(counts)])
IOTools.writeLines(outfile, outlines, header=["position", "count"])
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__"])
parser.add_option("-m",
"--method",
dest="method",
type="choice",
choices=["ave_dist", "min_dist", "corr"],
default="min_dist",
help="Method for calcuating similarity between profiles")
parser.add_option("-s",
"--spread",
dest="spread",
type="int",
default=10,
help="Amount to spread each tag by")
parser.add_option("-k",
"--keep-dist",
dest="keep_dist",
action="store_true",
help="Keep the distribution of tag depths")
parser.add_option("-r",
"--rands",
dest="rands",
default=100,
help="Number of randomisations to use for calculating"
" mean and stdev of distance")
# add common options (-h/--help, ...) and parse command line
(options, args) = E.Start(parser, argv=argv)
profile1_file, profile2_file = args
profile1_file = pysam.AlignmentFile(profile1_file)
if profile2_file.endswith("bed") or profile2_file.endswith("bed.gz"):
profile2_file = Bed.readAndIndex(profile2_file, with_values=True)
profile2_counter = bed_counter
else:
profile2_file = pysam.AlignmentFile(profile2_file)
profile2_counter = iCLIP.count_intervals
if options.method == "min_dist":
distance_func = iCLIP.findMinDistance
elif options.method == "ave_dist":
distance_func = iCLIP.calcAverageDistance
else:
def distance_func(profile1, profile2):
return iCLIP.corr_profile(profile1,
profile2,
options.spread,
profile2_ready=True)
for exon in GTF.iterator(options.stdin):
if exon.feature != "exon":
continue
contig = exon.contig
strand = exon.strand
transcript_id = exon.transcript_id
start = exon.start
end = exon.end
profile1 = iCLIP.count_intervals(profile1_file, [(start, end)],
contig=contig,
strand=strand)
profile2 = profile2_counter(profile2_file, [(start, end)],
contig=contig,
strand=strand)
if profile1.sum() == 0 or profile2.sum() == 0:
z = "NA"
distance = "NA"
options.stdout.write(
"%(contig)s\t%(start)i\t%(end)i\t%(transcript_id)s\t%(strand)s\t%(distance)s\t%(z)s\n"
% locals())
continue
if options.method == "corr":
profile2 = iCLIP.spread(profile2, options.spread)
distance = distance_func(profile1, profile2)
rands = iCLIP.rand_apply(profile=profile1,
exon=exon,
n=options.rands,
func=distance_func,
keep_dist=options.keep_dist,
profile2=profile2)
z = (distance - rands.mean()) / rands.std()
options.stdout.write(
"%(contig)s\t%(start)i\t%(end)i\t%(transcript_id)s\t%(strand)s\t%(distance).3f\t%(z).2f\n"
% locals())
# 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__"])
parser.add_option("-f",
"--feature",
dest="feature",
type="choice",
choices=["gene", "transcript", "exon"],
default="transcript",
help="which feature to use: gene/transcript/exon")
parser.add_option("--unstranded-bw",
dest="unstranded_wig",
type="string",
help="BigWig with tag counts on both strands")
parser.add_option("--plus-bw",
dest="plus_wig",
type="string",
help="BigWig with tag counts from plus strand")
parser.add_option("--minus-bw",
dest="minus_wig",
type="string",
help="BigWig with tag counts from minus strand")
parser.add_option("--bed",
dest="bedfile",
type="string",
help="tabix indexed bed file with tag counts"),
parser.add_option("-c",
"--use-centre",
dest="centre",
action="store_true",
default=False,
help="Use centre of read rather than start")
# add common options (-h/--help, ...) and parse command line
(options, args) = E.Start(parser, argv=argv)
iterator = GTF.iterator(options.stdin)
if options.feature == "gene":
iterator = GTF.flat_gene_iterator(iterator)
elif options.feature == "transcript":
iterator = GTF.transcript_iterator(iterator)
elif options.feature == "exon":
def _exon_iterator(gff_iterator):
for exon in gff_iterator:
yield [exon]
iterator = _exon_iterator(iterator)
if options.unstranded_wig:
bamfile = iCLIP.make_getter(plus_wig=options.unstranded_wig)
elif options.plus_wig:
if not options.minus_wig:
raise ValueError(
"Please provide wigs for both strands or use --unstranded_wig")
bamfile = iCLIP.make_getter(plus_wig=options.plus_wig,
minus_wig=options.minus_wig)
elif options.bedfile:
bamfile = iCLIP.make_getter(bedfile=options.bedfile)
else:
bamfile = pysam.AlignmentFile(args[0])
outlines = []
for feature in iterator:
exons = GTF.asRanges(feature, "exon")
exon_counts = iCLIP.count_intervals(bamfile,
exons,
feature[0].contig,
feature[0].strand,
dtype="uint32",
use_centre=options.centre)
exon_counts = exon_counts.sum()
introns = Intervals.complement(exons)
intron_counts = iCLIP.count_intervals(bamfile,
introns,
feature[0].contig,
feature[0].strand,
dtype="uint32",
use_centre=options.centre)
intron_counts = intron_counts.sum()
if options.feature == "exon":
try:
exon_id = feature[0].exon_id
except AttributeError:
try:
exon_id = feature[0].exon_number
except AttributeError:
exon_id = "missing"
gene_id = feature[0].gene_id
transcript_id = feature[0].transcript_id
intron_counts = "NA"
else:
exon_id = "NA"
gene_id = feature[0].gene_id
transcript_id = feature[0].transcript_id
intron_counts = float(intron_counts)
outlines.append([
gene_id, transcript_id, exon_id,
str(float(exon_counts)),
str(intron_counts)
])
options.stdout.write("\t".join([
"gene_id", "transcript_id", "exon_id", "exon_count", "intron_count"
]) + "\n")
outlines = ["\t".join(outline) for outline in outlines]
outlines = "\n".join(outlines)
options.stdout.write(outlines + "\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
# setup command line parser
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option("-m","--method", dest="method", type="choice",
choices=["ave_dist","min_dist","corr"],
default="min_dist",
help="Method for calcuating similarity between profiles")
parser.add_option("-s", "--spread", dest="spread", type="int",
default=10,
help="Amount to spread each tag by")
parser.add_option("-k", "--keep-dist", dest="keep_dist",
action="store_true",
help="Keep the distribution of tag depths")
parser.add_option("-r", "--rands", dest="rands",
default=100,
help="Number of randomisations to use for calculating"
" mean and stdev of distance")
# add common options (-h/--help, ...) and parse command line
(options, args) = E.Start(parser, argv=argv)
profile1_file, profile2_file = args
profile1_file = pysam.AlignmentFile(profile1_file)
if profile2_file.endswith("bed") or profile2_file.endswith("bed.gz"):
profile2_file = Bed.readAndIndex(profile2_file, with_values=True)
profile2_counter = bed_counter
else:
profile2_file = pysam.AlignmentFile(profile2_file)
profile2_counter = iCLIP.count_intervals
if options.method=="min_dist":
distance_func = iCLIP.findMinDistance
elif options.method=="ave_dist":
distance_func = iCLIP.calcAverageDistance
else:
def distance_func(profile1,profile2):
return iCLIP.corr_profile(profile1,profile2, options.spread, profile2_ready=True)
for exon in GTF.iterator(options.stdin):
if exon.feature != "exon":
continue
contig = exon.contig
strand = exon.strand
transcript_id = exon.transcript_id
start = exon.start
end = exon.end
profile1 = iCLIP.count_intervals(profile1_file,
[(start, end)],
contig=contig,
strand=strand)
profile2 = profile2_counter(profile2_file,
[(start, end)],
contig=contig,
strand=strand)
if profile1.sum() == 0 or profile2.sum() == 0:
z = "NA"
distance = "NA"
options.stdout.write(
"%(contig)s\t%(start)i\t%(end)i\t%(transcript_id)s\t%(strand)s\t%(distance)s\t%(z)s\n" % locals())
continue
if options.method=="corr":
profile2 = iCLIP.spread(profile2, options.spread)
distance = distance_func(profile1, profile2)
rands = iCLIP.rand_apply(profile=profile1,
exon=exon,
n=options.rands,
func=distance_func,
keep_dist=options.keep_dist,
profile2=profile2)
z = (distance - rands.mean())/rands.std()
options.stdout.write(
"%(contig)s\t%(start)i\t%(end)i\t%(transcript_id)s\t%(strand)s\t%(distance).3f\t%(z).2f\n" % locals())
# 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__"])
grouping_choices = ["exons",
"utrs",
"all"]
parser.add_option("-g", "--grouping", dest="grouping", type="choice",
choices=grouping_choices,
help="How to group transcript regions choices are [%s]"
% ",".join(grouping_choices))
parser.add_option("-p", "--pipeout", dest="pipeout", action="store_true",
help="Output continuously to the pipe rather than in a"
"chunk at the end")
parser.add_option("-d", "--dtype", dest="dtype", type="string",
default="int32",
help="Numpy dtype for storing counts")
parser.add_option("-w", "--window-size", dest="window_size",
type="int", default=15,
help="Size of window either size of crosslinked base to"
"consider")
parser.add_option("-f", "--fdr", dest="fdr", action="store_true",
default=False,
help="perform BH fdr correction on p-values, implies not"
"--pipeout")
parser.add_option("-o", "--output-windows", dest="output_windows",
action="store_true",
default=False,
help="Output consolidated windows isntead of bases")
parser.add_option("-b", "--output-both", type="string", dest="output_both",
default=None,
help="Output both bases bedGraph (stdout) and windows"
"bed12 (specified file).")
parser.add_option("-t", "--threshold", dest="threshold", type="float",
default=0.05,
help="p-value threshold under which to merge windows")
parser.add_option("-c", "--centre", dest="centre", action="store_true",
default=False,
help="Use centre of read rather than -1 base when no"
"mutaiton is present")
# add common options (-h/--help, ...) and parse command line
(options, args) = E.Start(parser, argv=argv)
# Standard in contains the transcripts
gffs = GTF.gene_iterator(GTF.iterator(options.stdin))
# bam file is the first positional arguement
bamfile = iCLIP.make_getter(bamfile=args[0], centre=options.centre)
if options.output_both:
outfile_bases = options.stdout
outfile_windows = IOTools.openFile(options.output_both, "w")
elif options.output_windows:
outfile_bases = None
outfile_windows = options.stdout
else:
outfile_bases = options.stdout
outfile_windows = None
if options.fdr and options.pipeout:
E.warning("--fdr implies not --pipeout, instant output disabled")
options.pipeout = False
if options.pipeout:
output = InstantOutput(outfile_bases=outfile_bases,
outfile_windows=outfile_windows,
window_size=options.window_size,
threshold=options.threshold)
else:
output = DeferredOutput(outfile_bases=outfile_bases,
outfile_windows=outfile_windows,
correct=options.fdr,
window_size=options.window_size,
threshold=options.threshold)
E.info("Counting accross transcripts ...")
max_end = 0
for gene in gffs:
if options.grouping == "all":
gene = GTF.merged_gene_iterator(gene)
transcript_ps = {}
for transcript in gene:
# E.debug("Transcript is %s" % transcript[0].transcript_id)
coords_converter = iCLIP.TranscriptCoordInterconverter(transcript)
exons = GTF.asRanges(transcript, "exon")
counts = iCLIP.count_intervals(bamfile,
exons,
strand=transcript[0].strand,
contig=transcript[0].contig,
dtype=options.dtype)
counts.index = coords_converter.genome2transcript(counts.index.values)
counts = counts.sort_index()
cds = GTF.asRanges(transcript, "CDS")
if options.grouping == "utrs" and len(cds) > 0:
cds_interval = (cds[0][0], cds[-1][1])
cds_interval = coords_converter.genome2transcript(cds_interval)
cds_interval.sort()
cds_length = cds_interval[1] - cds_interval[0]
p_intervals = [(0, cds_interval[0]),
(cds_interval[0], cds_length),
(cds_interval[1], coords_converter.length - cds_interval[1])]
else: # do not group by cds or there is no cds
p_intervals = [(0, coords_converter.length)]
p_values = [calculateProbabilities(counts, options.window_size,
length=length, start=start)
for start, length in p_intervals
if length > 0]
if len(p_values) > 1:
p_values = pd.concat(p_values)
else:
p_values = p_values[0]
p_values.index = coords_converter.transcript2genome(p_values.index.values)
intron_intervals = GTF.toIntronIntervals(transcript)
if len(intron_intervals) > 0:
intron_coords = iCLIP.TranscriptCoordInterconverter(transcript,
introns=True)
intron_counts = iCLIP.count_intervals(bamfile,
intron_intervals,
strand=transcript[0].strand,
contig=transcript[0].contig,
dtype=options.dtype)
intron_counts.index = intron_coords.genome2transcript(
intron_counts.index.values)
intron_counts = intron_counts.sort_index()
intron_pvalues = calculateProbabilities(intron_counts,
options.window_size,
intron_coords.length)
intron_pvalues.index = intron_coords.transcript2genome(
intron_pvalues.index.values)
p_values = p_values.append(intron_pvalues)
transcript_ps[transcript[0].transcript_id] = p_values
transcript_df = pd.DataFrame(transcript_ps)
transcript_df.index.rename("position", inplace=True)
transcript_df["contig"] = gene[0][0].contig
transcript_df["strand"] = gene[0][0].strand
transcript_df["gene_id"] = gene[0][0].gene_id
transcript_df.set_index("contig", append=True, inplace=True)
transcript_df.set_index("strand", append=True, inplace=True)
transcript_df.set_index("gene_id", append=True, inplace=True)
gene_ps = transcript_df.mean(1)
gene_ps = gene_ps.reorder_levels(["gene_id", "contig",
"strand", "position"])
output.write(gene_ps, gene)
output.close()
# 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__"])
grouping_choices = ["exons", "utrs", "all"]
parser.add_option("-g",
"--grouping",
dest="grouping",
type="choice",
choices=grouping_choices,
help="How to group transcript regions choices are [%s]" %
",".join(grouping_choices))
parser.add_option("-p",
"--pipeout",
dest="pipeout",
action="store_true",
help="Output continuously to the pipe rather than in a"
"chunk at the end")
parser.add_option("-d",
"--dtype",
dest="dtype",
type="string",
default="int32",
help="Numpy dtype for storing counts")
parser.add_option("-w",
"--window-size",
dest="window_size",
type="int",
default=15,
help="Size of window either size of crosslinked base to"
"consider")
parser.add_option("-f",
"--fdr",
dest="fdr",
action="store_true",
default=False,
help="perform BH fdr correction on p-values, implies not"
"--pipeout")
parser.add_option("-o",
"--output-windows",
dest="output_windows",
action="store_true",
default=False,
help="Output consolidated windows isntead of bases")
parser.add_option("-b",
"--output-both",
type="string",
dest="output_both",
default=None,
help="Output both bases bedGraph (stdout) and windows"
"bed12 (specified file).")
parser.add_option("-t",
"--threshold",
dest="threshold",
type="float",
default=0.05,
help="p-value threshold under which to merge windows")
parser.add_option("-c",
"--centre",
dest="centre",
action="store_true",
default=False,
help="Use centre of read rather than -1 base when no"
"mutaiton is present")
# add common options (-h/--help, ...) and parse command line
(options, args) = E.Start(parser, argv=argv)
# Standard in contains the transcripts
gffs = GTF.gene_iterator(GTF.iterator(options.stdin))
# bam file is the first positional arguement
bamfile = iCLIP.make_getter(bamfile=args[0], centre=options.centre)
if options.output_both:
outfile_bases = options.stdout
outfile_windows = IOTools.openFile(options.output_both, "w")
elif options.output_windows:
outfile_bases = None
outfile_windows = options.stdout
else:
outfile_bases = options.stdout
outfile_windows = None
if options.fdr and options.pipeout:
E.warning("--fdr implies not --pipeout, instant output disabled")
options.pipeout = False
if options.pipeout:
output = InstantOutput(outfile_bases=outfile_bases,
outfile_windows=outfile_windows,
window_size=options.window_size,
threshold=options.threshold)
else:
output = DeferredOutput(outfile_bases=outfile_bases,
outfile_windows=outfile_windows,
correct=options.fdr,
window_size=options.window_size,
threshold=options.threshold)
E.info("Counting accross transcripts ...")
max_end = 0
for gene in gffs:
if options.grouping == "all":
gene = GTF.merged_gene_iterator(gene)
transcript_ps = {}
for transcript in gene:
# E.debug("Transcript is %s" % transcript[0].transcript_id)
coords_converter = iCLIP.TranscriptCoordInterconverter(transcript)
exons = GTF.asRanges(transcript, "exon")
counts = iCLIP.count_intervals(bamfile,
exons,
strand=transcript[0].strand,
contig=transcript[0].contig,
dtype=options.dtype)
counts.index = coords_converter.genome2transcript(
counts.index.values)
counts = counts.sort_index()
cds = GTF.asRanges(transcript, "CDS")
if options.grouping == "utrs" and len(cds) > 0:
cds_interval = (cds[0][0], cds[-1][1])
cds_interval = coords_converter.genome2transcript(cds_interval)
cds_interval.sort()
cds_length = cds_interval[1] - cds_interval[0]
p_intervals = [(0, cds_interval[0]),
(cds_interval[0], cds_length),
(cds_interval[1],
coords_converter.length - cds_interval[1])]
else: # do not group by cds or there is no cds
p_intervals = [(0, coords_converter.length)]
p_values = [
calculateProbabilities(counts,
options.window_size,
length=length,
start=start)
for start, length in p_intervals if length > 0
]
if len(p_values) > 1:
p_values = pd.concat(p_values)
else:
p_values = p_values[0]
p_values.index = coords_converter.transcript2genome(
p_values.index.values)
intron_intervals = GTF.toIntronIntervals(transcript)
if len(intron_intervals) > 0:
intron_coords = iCLIP.TranscriptCoordInterconverter(
transcript, introns=True)
intron_counts = iCLIP.count_intervals(
bamfile,
intron_intervals,
strand=transcript[0].strand,
contig=transcript[0].contig,
dtype=options.dtype)
intron_counts.index = intron_coords.genome2transcript(
intron_counts.index.values)
intron_counts = intron_counts.sort_index()
intron_pvalues = calculateProbabilities(
intron_counts, options.window_size, intron_coords.length)
intron_pvalues.index = intron_coords.transcript2genome(
intron_pvalues.index.values)
p_values = p_values.append(intron_pvalues)
transcript_ps[transcript[0].transcript_id] = p_values
transcript_df = pd.DataFrame(transcript_ps)
transcript_df.index.rename("position", inplace=True)
transcript_df["contig"] = gene[0][0].contig
transcript_df["strand"] = gene[0][0].strand
transcript_df["gene_id"] = gene[0][0].gene_id
transcript_df.set_index("contig", append=True, inplace=True)
transcript_df.set_index("strand", append=True, inplace=True)
transcript_df.set_index("gene_id", append=True, inplace=True)
gene_ps = transcript_df.mean(1)
gene_ps = gene_ps.reorder_levels(
["gene_id", "contig", "strand", "position"])
output.write(gene_ps, gene)
output.close()
# 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__"])
parser.add_option("-f", "--feature", dest="feature", type="choice",
choices=["gene", "transcript", "exon"],
default="transcript",
help="which feature to use: gene/transcript/exon")
parser.add_option("--unstranded-bw", dest="unstranded_wig", type="string",
help="BigWig with tag counts on both strands")
parser.add_option("--plus-bw", dest="plus_wig", type="string",
help="BigWig with tag counts from plus strand")
parser.add_option("--minus-bw", dest="minus_wig", type="string",
help="BigWig with tag counts from minus strand")
parser.add_option("--bed", dest="bedfile", type="string",
help="tabix indexed bed file with tag counts"),
parser.add_option("-c", "--use-centre", dest="centre", action="store_true",
default=False,
help="Use centre of read rather than start")
# add common options (-h/--help, ...) and parse command line
(options, args) = E.Start(parser, argv=argv)
iterator = GTF.iterator(options.stdin)
if options.feature == "gene":
iterator = GTF.flat_gene_iterator(iterator)
elif options.feature == "transcript":
iterator = GTF.transcript_iterator(iterator)
elif options.feature == "exon":
def _exon_iterator(gff_iterator):
for exon in gff_iterator:
yield [exon]
iterator = _exon_iterator(iterator)
if options.unstranded_wig:
bamfile = iCLIP.make_getter(plus_wig=options.unstranded_wig)
elif options.plus_wig:
if not options.minus_wig:
raise ValueError(
"Please provide wigs for both strands or use --unstranded_wig")
bamfile = iCLIP.make_getter(plus_wig=options.plus_wig,
minus_wig=options.minus_wig)
elif options.bedfile:
bamfile = iCLIP.make_getter(bedfile=options.bedfile)
else:
bamfile = pysam.AlignmentFile(args[0])
outlines = []
for feature in iterator:
exons = GTF.asRanges(feature, "exon")
exon_counts = iCLIP.count_intervals(bamfile,
exons,
feature[0].contig,
feature[0].strand,
dtype="uint32",
use_centre=options.centre)
exon_counts = exon_counts.sum()
introns = Intervals.complement(exons)
intron_counts = iCLIP.count_intervals(bamfile,
introns,
feature[0].contig,
feature[0].strand,
dtype="uint32",
use_centre=options.centre)
intron_counts = intron_counts.sum()
if options.feature == "exon":
try:
exon_id = feature[0].exon_id
except AttributeError:
try:
exon_id = feature[0].exon_number
except AttributeError:
exon_id = "missing"
gene_id = feature[0].gene_id
transcript_id = feature[0].transcript_id
intron_counts = "NA"
else:
exon_id = "NA"
gene_id = feature[0].gene_id
transcript_id = feature[0].transcript_id
intron_counts = float(intron_counts)
outlines.append([gene_id,
transcript_id,
exon_id,
str(float(exon_counts)),
str(intron_counts)])
options.stdout.write("\t".join(["gene_id",
"transcript_id",
"exon_id",
"exon_count",
"intron_count"])+"\n")
outlines = ["\t".join(outline) for outline in outlines]
outlines = "\n".join(outlines)
options.stdout.write(outlines + "\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
# setup command line parser
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option("-f",
"--feature",
dest="feature",
type="choice",
choices=["gene", "transcript", "exon"],
default="transcript",
help="supply help")
# add common options (-h/--help, ...) and parse command line
(options, args) = E.Start(parser, argv=argv)
iterator = GTF.iterator(options.stdin)
if options.feature == "gene":
iterator = GTF.flat_gene_iterator(iterator)
elif options.feature == "transcript":
iterator = GTF.transcript_iterator(iterator)
elif options.feature == "exon":
def _exon_iterator(gff_iterator):
for exon in gff_iterator:
yield [exon]
iterator = _exon_iterator(iterator)
bamfile = pysam.AlignmentFile(args[0])
outlines = []
for feature in iterator:
exons = GTF.asRanges(feature, "exon")
exon_counts = iCLIP.count_intervals(bamfile,
exons,
feature[0].contig,
feature[0].strand,
dtype="uint32")
exon_counts = exon_counts.sum()
introns = Intervals.complement(exons)
intron_counts = iCLIP.count_intervals(bamfile,
introns,
feature[0].contig,
feature[0].strand,
dtype="uint32")
intron_counts = intron_counts.sum()
if options.feature == "exon":
exon_id = feature[0].exon_id
gene_id = feature[0].gene_id
transcript_id = feature[0].transcript_id
intron_counts = "NA"
else:
exon_id = "NA"
gene_id = feature[0].gene_id
transcript_id = feature[0].transcript_id
outlines.append([
gene_id, transcript_id, exon_id,
str(exon_counts),
str(intron_counts)
])
options.stdout.write("\t".join([
"gene_id", "transcript_id", "exon_id", "exon_count", "intron_count"
]) + "\n")
outlines = ["\t".join(outline) for outline in outlines]
outlines = "\n".join(outlines)
options.stdout.write(outlines + "\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
# setup command line parser
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option("-f", "--feature", dest="feature", type="choice",
choices=["gene", "transcript", "exon"],
default="transcript",
help="supply help")
# add common options (-h/--help, ...) and parse command line
(options, args) = E.Start(parser, argv=argv)
iterator = GTF.iterator(options.stdin)
if options.feature == "gene":
iterator = GTF.flat_gene_iterator(iterator)
elif options.feature == "transcript":
iterator = GTF.transcript_iterator(iterator)
elif options.feature == "exon":
def _exon_iterator(gff_iterator):
for exon in gff_iterator:
yield [exon]
iterator = _exon_iterator(iterator)
bamfile = pysam.AlignmentFile(args[0])
outlines = []
for feature in iterator:
exons = GTF.asRanges(feature, "exon")
exon_counts = iCLIP.count_intervals(bamfile,
exons,
feature[0].contig,
feature[0].strand,
dtype="uint32")
exon_counts = exon_counts.sum()
introns = Intervals.complement(exons)
intron_counts = iCLIP.count_intervals(bamfile,
introns,
feature[0].contig,
feature[0].strand,
dtype="uint32")
intron_counts = intron_counts.sum()
if options.feature == "exon":
try:
exon_id = feature[0].exon_id
except AttributeError:
exon_id = "missing"
gene_id = feature[0].gene_id
transcript_id = feature[0].transcript_id
intron_counts = "NA"
else:
exon_id = "NA"
gene_id = feature[0].gene_id
transcript_id = feature[0].transcript_id
outlines.append([gene_id,
transcript_id,
exon_id,
str(exon_counts),
str(intron_counts)])
options.stdout.write("\t".join(["gene_id",
"transcript_id",
"exon_id",
"exon_count",
"intron_count"])+"\n")
outlines = ["\t".join(outline) for outline in outlines]
outlines = "\n".join(outlines)
options.stdout.write(outlines + "\n")
# write footer and output benchmark information.
E.Stop()