def stats(args):
"""
%prog stats infile.gff
Collect gene statistics based on gff file. There are some terminology issues
here and so normally we call "gene" are actually mRNA, and sometimes "exon"
are actually CDS, but they are configurable.
Thee numbers are written to text file in four separate folders,
corresponding to the four metrics:
Exon length, Intron length, Gene length, Exon count
With data written to disk then you can run %prog histogram
"""
p = OptionParser(stats.__doc__)
p.add_option("--gene", default="mRNA",
help="The gene type [default: %default]")
p.add_option("--exon", default="CDS",
help="The exon type [default: %default]")
opts, args = p.parse_args(args)
if len(args) != 1:
sys.exit(not p.print_help())
gff_file, = args
g = make_index(gff_file)
exon_lengths = []
intron_lengths = []
gene_lengths = []
exon_counts = []
for feat in g.features_of_type(opts.gene):
exons = []
for c in g.children(feat.id, 1):
if c.featuretype != opts.exon:
continue
exons.append((c.chrom, c.start, c.stop))
introns = range_interleave(exons)
feat_exon_lengths = [(stop - start + 1) for (chrom, start, stop) in exons]
feat_intron_lengths = [(stop - start + 1) for (chrom, start, stop) in introns]
exon_lengths += feat_exon_lengths
intron_lengths += feat_intron_lengths
gene_lengths.append(sum(feat_exon_lengths))
exon_counts.append(len(feat_exon_lengths))
a = SummaryStats(exon_lengths)
b = SummaryStats(intron_lengths)
c = SummaryStats(gene_lengths)
d = SummaryStats(exon_counts)
for x, title in zip((a, b, c, d), metrics):
x.title = title
print(x, file=sys.stderr)
prefix = gff_file.split(".")[0]
for x in (a, b, c, d):
dirname = x.title
mkdir(dirname)
txtfile = op.join(dirname, prefix + ".txt")
x.tofile(txtfile)
def summary(args):
"""
%prog summary gffile fastafile
Print summary stats, including:
- Gene/Exon/Intron
- Number
- Average size (bp)
- Median size (bp)
- Total length (Mb)
- % of genome
- % GC
"""
p = OptionParser(summary.__doc__)
opts, args = p.parse_args(args)
if len(args) != 2:
sys.exit(not p.print_help())
gff_file, ref = args
s = Fasta(ref)
g = make_index(gff_file)
geneseqs, exonseqs, intronseqs = [], [], [] # Calc % GC
for f in g.features_of_type("gene"):
fid = f.id
fseq = s.sequence({'chr': f.chrom, 'start': f.start, 'stop': f.stop})
geneseqs.append(fseq)
exons = set((c.chrom, c.start, c.stop) for c in g.children(fid, 2) \
if c.featuretype == "exon")
exons = list(exons)
for chrom, start, stop in exons:
fseq = s.sequence({'chr': chrom, 'start': start, 'stop': stop})
exonseqs.append(fseq)
introns = range_interleave(exons)
for chrom, start, stop in introns:
fseq = s.sequence({'chr': chrom, 'start': start, 'stop': stop})
intronseqs.append(fseq)
r = {} # Report
for t, tseqs in zip(("Gene", "Exon", "Intron"),
(geneseqs, exonseqs, intronseqs)):
tsizes = [len(x) for x in tseqs]
tsummary = SummaryStats(tsizes, dtype="int")
r[t, "Number"] = tsummary.size
r[t, "Average size (bp)"] = tsummary.mean
r[t, "Median size (bp)"] = tsummary.median
r[t, "Total length (Mb)"] = human_size(tsummary.sum,
precision=0,
target="Mb")
r[t, "% of genome"] = percentage(tsummary.sum,
s.totalsize,
precision=0,
mode=-1)
r[t, "% GC"] = gc(tseqs)
print >> sys.stderr, tabulate(r)
def summary(args):
"""
%prog summary gffile fastafile
Print summary stats, including:
- Gene/Exon/Intron
- Number
- Average size (bp)
- Median size (bp)
- Total length (Mb)
- % of genome
- % GC
"""
p = OptionParser(summary.__doc__)
opts, args = p.parse_args(args)
if len(args) != 2:
sys.exit(not p.print_help())
gff_file, ref = args
s = Fasta(ref)
g = make_index(gff_file)
geneseqs, exonseqs, intronseqs = [], [], [] # Calc % GC
for f in g.features_of_type("gene"):
fid = f.id
fseq = s.sequence({'chr': f.chrom, 'start': f.start, 'stop': f.stop})
geneseqs.append(fseq)
exons = set((c.chrom, c.start, c.stop) for c in g.children(fid, 2) \
if c.featuretype == "exon")
exons = list(exons)
for chrom, start, stop in exons:
fseq = s.sequence({'chr': chrom, 'start': start, 'stop': stop})
exonseqs.append(fseq)
introns = range_interleave(exons)
for chrom, start, stop in introns:
fseq = s.sequence({'chr': chrom, 'start': start, 'stop': stop})
intronseqs.append(fseq)
r = {} # Report
for t, tseqs in zip(("Gene", "Exon", "Intron"), (geneseqs, exonseqs, intronseqs)):
tsizes = [len(x) for x in tseqs]
tsummary = SummaryStats(tsizes, dtype="int")
r[t, "Number"] = tsummary.size
r[t, "Average size (bp)"] = tsummary.mean
r[t, "Median size (bp)"] = tsummary.median
r[t, "Total length (Mb)"] = human_size(tsummary.sum, precision=0, target="Mb")
r[t, "% of genome"] = percentage(tsummary.sum, s.totalsize, precision=0, mode=-1)
r[t, "% GC"] = gc(tseqs)
print(tabulate(r), file=sys.stderr)
def swap(args):
"""
%prog swap agpfile
Swap objects and components. Will add gap lines. This is often used in
conjuction with formats.chain.fromagp() to convert between different
coordinate systems.
"""
from itertools import izip_longest
from jcvi.utils.range import range_interleave
p = OptionParser(swap.__doc__)
opts, args = p.parse_args(args)
if len(args) != 1:
sys.exit(not p.print_help())
agpfile, = args
agp = AGP(agpfile)
agp.sort(key=lambda x: (x.component_id, x.component_beg))
newagpfile = agpfile.rsplit(".", 1)[0] + ".swapped.agp"
fw = open(newagpfile, "w")
for cid, aa in groupby(agp, key=(lambda x: x.component_id)):
aa = list(aa)
aranges = [(x.component_id, x.component_beg, x.component_end) \
for x in aa]
gaps = range_interleave(aranges)
for a, g in izip_longest(aa, gaps):
a.object, a.component_id = a.component_id, a.object
a.component_beg = a.object_beg
a.component_end = a.object_end
print >> fw, a
if not g:
continue
aline = [cid, 0, 0, 0]
gseq, ga, gb = g
cspan = gb - ga + 1
aline += ["N", cspan, "fragment", "yes"]
print >> fw, "\t".join(str(x) for x in aline)
fw.close()
# Reindex
idxagpfile = reindex([newagpfile])
shutil.move(idxagpfile, newagpfile)
return newagpfile
def swap(args):
"""
%prog swap agpfile
Swap objects and components. Will add gap lines. This is often used in
conjuction with formats.chain.fromagp() to convert between different
coordinate systems.
"""
from itertools import izip_longest
from jcvi.utils.range import range_interleave
p = OptionParser(swap.__doc__)
opts, args = p.parse_args(args)
if len(args) != 1:
sys.exit(not p.print_help())
agpfile, = args
agp = AGP(agpfile)
agp.sort(key=lambda x: (x.component_id, x.component_beg))
newagpfile = agpfile.rsplit(".", 1)[0] + ".swapped.agp"
fw = open(newagpfile, "w")
for cid, aa in groupby(agp, key=(lambda x: x.component_id)):
aa = list(aa)
aranges = [(x.component_id, x.component_beg, x.component_end) \
for x in aa]
gaps = range_interleave(aranges)
for a, g in izip_longest(aa, gaps):
a.object, a.component_id = a.component_id, a.object
a.component_beg = a.object_beg
a.component_end = a.object_end
print >> fw, a
if not g:
continue
aline = [cid, 0, 0, 0]
gseq, ga, gb = g
cspan = gb - ga + 1
aline += ["N", cspan, "fragment", "yes"]
print >> fw, "\t".join(str(x) for x in aline)
fw.close()
# Reindex
idxagpfile = reindex([newagpfile])
shutil.move(idxagpfile, newagpfile)
return newagpfile
def breakpoint(args):
"""
%prog breakpoint blastfile bedfile
Identify breakpoints where collinearity ends. `blastfile` contains mapping
from markers (query) to scaffolds (subject). `bedfile` contains marker
locations in the related species.
"""
from jcvi.formats.blast import bed
from jcvi.utils.range import range_interleave
p = OptionParser(breakpoint.__doc__)
p.add_option("--xdist",
type="int",
default=20,
help="xdist (in related genome) cutoff [default: %default]")
p.add_option("--ydist",
type="int",
default=200000,
help="ydist (in current genome) cutoff [default: %default]")
p.add_option("-n",
type="int",
default=5,
help="number of markers in a block [default: %default]")
opts, args = p.parse_args(args)
if len(args) != 2:
sys.exit(not p.print_help())
blastfile, bedfile = args
order = Bed(bedfile).order
blastbedfile = bed([blastfile])
bbed = Bed(blastbedfile)
key = lambda x: x[1]
for scaffold, bs in bbed.sub_beds():
blocks = get_blocks(scaffold,
bs,
order,
xdist=opts.xdist,
ydist=opts.ydist,
N=opts.n)
sblocks = []
for block in blocks:
xx, yy = zip(*block)
sblocks.append((scaffold, min(yy), max(yy)))
iblocks = range_interleave(sblocks)
for ib in iblocks:
ch, start, end = ib
print "{0}\t{1}\t{2}".format(ch, start - 1, end)
def breakpoint(args):
"""
%prog breakpoint blastfile bedfile
Identify breakpoints where collinearity ends. `blastfile` contains mapping
from markers (query) to scaffolds (subject). `bedfile` contains marker
locations in the related species.
"""
from jcvi.formats.blast import bed
from jcvi.utils.range import range_interleave
p = OptionParser(breakpoint.__doc__)
p.add_option("--xdist", type="int", default=20,
help="xdist (in related genome) cutoff [default: %default]")
p.add_option("--ydist", type="int", default=200000,
help="ydist (in current genome) cutoff [default: %default]")
p.add_option("-n", type="int", default=5,
help="number of markers in a block [default: %default]")
opts, args = p.parse_args(args)
if len(args) != 2:
sys.exit(not p.print_help())
blastfile, bedfile = args
order = Bed(bedfile).order
blastbedfile = bed([blastfile])
bbed = Bed(blastbedfile)
key = lambda x: x[1]
for scaffold, bs in bbed.sub_beds():
blocks = get_blocks(scaffold, bs, order,
xdist=opts.xdist, ydist=opts.ydist, N=opts.n)
sblocks = []
for block in blocks:
xx, yy = zip(*block)
sblocks.append((scaffold, min(yy), max(yy)))
iblocks = range_interleave(sblocks)
for ib in iblocks:
ch, start, end = ib
print "{0}\t{1}\t{2}".format(ch, start - 1, end)
def shuffle_twobeds(afbed, bfbed, bbfasta, prefix=None):
# Shuffle the two bedfiles together
sz = Sizes(bbfasta)
sizes = sz.mapping
shuffled = "shuffled.bed"
border = bfbed.order
all = []
afbed.sort(key=afbed.nullkey)
totalids = len(sizes)
pad = int(math.log10(totalids)) + 1
cj = 0
seen = set()
accn = lambda x: "{0}{1:0{2}d}".format(prefix, x, pad)
for seqid, aa in afbed.sub_beds():
cj += 1
abeds, bbeds, beds = [], [], []
size = sizes[seqid]
ranges = [(x.seqid, x.start, x.end) for x in aa]
cranges = range_interleave(ranges, sizes={seqid: size}, empty=True)
for crange in cranges:
if crange:
seqid, start, end = crange
bedline = "\t".join(str(x) for x in (seqid, start - 1, end))
abeds.append(BedLine(bedline))
else:
abeds.append(None)
for a in aa:
gapid = a.accn
bi, b = border[gapid]
if a.strand == "-":
b.extra[1] = b.strand = "-" if b.strand == "+" else "+"
bbeds.append(b)
n_abeds = len(abeds)
n_bbeds = len(bbeds)
assert n_abeds - n_bbeds == 1, "abeds: {0}, bbeds: {1}".format(n_abeds, n_bbeds)
beds = [x for x in roundrobin(abeds, bbeds) if x]
if prefix:
for b in beds:
b.accn = accn(cj)
all.extend(beds)
seen.add(seqid)
# Singletons
for seqid, size in sz.iter_sizes():
if seqid in seen:
continue
bedline = "\t".join(str(x) for x in (seqid, 0, size, accn(cj)))
b = BedLine(bedline)
cj += 1
if prefix:
b.accn = accn(cj)
all.append(b)
shuffledbed = Bed()
shuffledbed.extend(all)
shuffledbed.print_to_file(shuffled)
return shuffledbed
def shuffle_twobeds(afbed, bfbed, bbfasta, prefix=None):
# Shuffle the two bedfiles together
sz = Sizes(bbfasta)
sizes = sz.mapping
shuffled = "shuffled.bed"
border = bfbed.order
all = []
afbed.sort(key=afbed.nullkey)
totalids = len(sizes)
pad = int(math.log10(totalids)) + 1
cj = 0
seen = set()
accn = lambda x: "{0}{1:0{2}d}".format(prefix, x, pad)
for seqid, aa in afbed.sub_beds():
cj += 1
abeds, bbeds, beds = [], [], []
size = sizes[seqid]
ranges = [(x.seqid, x.start, x.end) for x in aa]
cranges = range_interleave(ranges, sizes={seqid: size}, empty=True)
for crange in cranges:
if crange:
seqid, start, end = crange
bedline = "\t".join(str(x) for x in (seqid, start - 1, end))
abeds.append(BedLine(bedline))
else:
abeds.append(None)
for a in aa:
gapid = a.accn
bi, b = border[gapid]
if a.strand == '-':
b.extra[1] = b.strand = ('-' if b.strand == '+' else '+')
bbeds.append(b)
n_abeds = len(abeds)
n_bbeds = len(bbeds)
assert n_abeds - n_bbeds == 1, \
"abeds: {0}, bbeds: {1}".format(n_abeds, n_bbeds)
beds = [x for x in roundrobin(abeds, bbeds) if x]
if prefix:
for b in beds:
b.accn = accn(cj)
all.extend(beds)
seen.add(seqid)
# Singletons
for seqid, size in sz.iter_sizes():
if seqid in seen:
continue
bedline = "\t".join(str(x) for x in (seqid, 0, size, accn(cj)))
b = BedLine(bedline)
cj += 1
if prefix:
b.accn = accn(cj)
all.append(b)
shuffledbed = Bed()
shuffledbed.extend(all)
shuffledbed.print_to_file(shuffled)
return shuffledbed
def deletion(args):
"""
%prog deletion [mac.mic.bam|mac.mic.bed] mic.gaps.bed
Find IES based on mapping MAC reads to MIC genome.
"""
p = OptionParser(deletion.__doc__)
p.add_option("--mindepth",
default=3,
type="int",
help="Minimum depth to call a deletion")
p.add_option("--minspan",
default=30,
type="int",
help="Minimum span to call a deletion")
p.add_option("--split",
default=False,
action="store_true",
help="Break at cigar N into separate parts")
p.set_tmpdir()
opts, args = p.parse_args(args)
if len(args) != 2:
sys.exit(not p.print_help())
bedfile, gapsbedfile = args
if bedfile.endswith(".bam"):
bamfile = bedfile
bedfile = bamfile.replace(".sorted.", ".").replace(".bam", ".bed")
if need_update(bamfile, bedfile):
cmd = "bamToBed -i {0}".format(bamfile)
if opts.split:
cmd += " -split"
cmd += " | cut -f1-4"
sh(cmd, outfile=bedfile)
sort_tmpdir = "--tmpdir={0}".format(opts.tmpdir)
if bedfile.endswith(".sorted.bed"):
pf = bedfile.rsplit(".", 2)[0]
sortedbedfile = bedfile
else:
pf = bedfile.rsplit(".", 1)[0]
sortedbedfile = pf + ".sorted.bed"
if need_update(bedfile, sortedbedfile):
sort([bedfile, "-u", "--accn", sort_tmpdir])
# Find reads that contain multiple matches
ibedfile = pf + ".d.bed"
if need_update(sortedbedfile, ibedfile):
bed = Bed(sortedbedfile, sorted=False)
fw = open(ibedfile, "w")
logging.debug("Write deletions to `{0}`.".format(ibedfile))
for accn, bb in groupby(bed, key=lambda x: x.accn):
bb = list(bb)
branges = [(x.seqid, x.start, x.end) for x in bb]
iranges = range_interleave(branges)
for seqid, start, end in iranges:
if end - start + 1 < opts.minspan:
continue
print("\t".join(str(x) for x in \
(seqid, start - 1, end, accn + '-d')), file=fw)
fw.close()
# Uniqify the insertions and count occurrences
countbedfile = pf + ".uniq.bed"
if need_update(ibedfile, countbedfile):
bed = Bed(ibedfile)
fw = open(countbedfile, "w")
logging.debug("Write counts to `{0}`.".format(countbedfile))
registry = Counter((x.seqid, x.start, x.end) for x in bed)
ies_id = 1
for (seqid, start, end), count in registry.items():
ies_name = "{0:05d}-r{1}".format(ies_id, count)
if count < opts.mindepth:
continue
print("\t".join(str(x) for x in \
(seqid, start - 1, end, ies_name)), file=fw)
ies_id += 1
fw.close()
sort([countbedfile, "-i", sort_tmpdir])
# Remove deletions that contain some read depth
depthbedfile = pf + ".depth.bed"
if need_update((sortedbedfile, countbedfile), depthbedfile):
depth([
sortedbedfile, countbedfile, "--outfile={0}".format(depthbedfile)
])
validbedfile = pf + ".valid.bed"
if need_update(depthbedfile, validbedfile):
fw = open(validbedfile, "w")
logging.debug("Filter valid deletions to `{0}`.".format(validbedfile))
bed = Bed(depthbedfile)
all_scores = [float(b.score) for b in bed]
lb, ub = outlier_cutoff(all_scores)
logging.debug(
"Bounds for depths: LB={0:.2f} (ignored) UB={1:.2f}".format(
lb, ub))
for b in bed:
if float(b.score) > ub:
continue
print(b, file=fw)
fw.close()
# Remove deletions that contain sequencing gaps on its flanks
selectedbedfile = pf + ".selected.bed"
if need_update(validbedfile, selectedbedfile):
flanksbedfile = pf + ".flanks.bed"
fw = open(flanksbedfile, "w")
bed = Bed(validbedfile)
flank = 100
logging.debug("Write deletion flanks to `{0}`.".format(flanksbedfile))
for b in bed:
start, end = b.start, b.end
b.start, b.end = start, min(start + flank - 1, end)
print(b, file=fw)
b.start, b.end = max(start, end - flank + 1), end
print(b, file=fw)
fw.close()
intersectidsfile = pf + ".intersect.ids"
cmd = "intersectBed -a {0} -b {1}".format(flanksbedfile, gapsbedfile)
cmd += " | cut -f4 | sort -u"
sh(cmd, outfile=intersectidsfile)
some([
validbedfile, intersectidsfile, "-v",
"--outfile={0}".format(selectedbedfile)
])
# Find best-scoring non-overlapping set
iesbedfile = pf + ".ies.bed"
if need_update(selectedbedfile, iesbedfile):
bed = Bed(selectedbedfile)
fw = open(iesbedfile, "w")
logging.debug("Write IES to `{0}`.".format(iesbedfile))
branges = [Range(x.seqid, x.start, x.end, int(x.accn.rsplit("r")[-1]), i) \
for i, x in enumerate(bed)]
iranges, iscore = range_chain(branges)
logging.debug("Best chain score: {0} ({1} IES)".\
format(iscore, len(iranges)))
ies_id = 1
for seqid, start, end, score, id in iranges:
ies_name = "IES-{0:05d}-r{1}".format(ies_id, score)
span = end - start + 1
print("\t".join(str(x) for x in \
(seqid, start - 1, end, ies_name, span)), file=fw)
ies_id += 1
fw.close()
def install(args):
"""
%prog install patchers.bed patchers.fasta backbone.fasta alt.fasta
Install patches into backbone, using sequences from alternative assembly.
The patches sequences are generated via jcvi.assembly.patch.fill().
The output is a bedfile that can be converted to AGP using
jcvi.formats.agp.frombed().
"""
from jcvi.apps.base import blast
from jcvi.formats.blast import BlastSlow
from jcvi.formats.fasta import SeqIO
from jcvi.utils.iter import roundrobin
p = OptionParser(install.__doc__)
p.add_option(
"--rclip",
default=1,
type="int",
help="Pair ID is derived from rstrip N chars [default: %default]")
p.add_option(
"--maxsize",
default=1000000,
type="int",
help="Maximum size of patchers to be replaced [default: %default]")
p.add_option("--prefix",
help="Prefix of the new object [default: %default]")
p.add_option(
"--strict",
default=False,
action="store_true",
help="Only update if replacement has no gaps [default: %default]")
opts, args = p.parse_args(args)
if len(args) != 4:
sys.exit(not p.print_help())
pbed, pfasta, bbfasta, altfasta = args
Max = opts.maxsize # Max DNA size to replace gap
rclip = opts.rclip
prefix = opts.prefix
blastfile = blast([altfasta, pfasta, "--wordsize=100", "--pctid=99"])
order = Bed(pbed).order
beforebed, afterbed = "before.bed", "after.bed"
fwa = open(beforebed, "w")
fwb = open(afterbed, "w")
key1 = lambda x: x.query
key2 = lambda x: x.query[:-rclip] if rclip else key1
data = BlastSlow(blastfile)
for pe, lines in groupby(data, key=key2):
lines = list(lines)
if len(lines) != 2:
continue
a, b = lines
aquery, bquery = a.query, b.query
asubject, bsubject = a.subject, b.subject
if asubject != bsubject:
continue
astrand, bstrand = a.orientation, b.orientation
assert aquery[-1] == 'L' and bquery[-1] == 'R', str((aquery, bquery))
ai, ax = order[aquery]
bi, bx = order[bquery]
qstart, qstop = ax.start + a.qstart - 1, bx.start + b.qstop - 1
if astrand == '+' and bstrand == '+':
sstart, sstop = a.sstart, b.sstop
elif astrand == '-' and bstrand == '-':
sstart, sstop = b.sstart, a.sstop
else:
continue
if sstart > sstop:
continue
if sstop > sstart + Max:
continue
name = aquery[:-1] + "LR"
print >> fwa, "\t".join(str(x) for x in \
(ax.seqid, qstart - 1, qstop, name, 1000, "+"))
print >> fwb, "\t".join(str(x) for x in \
(asubject, sstart - 1, sstop, name, 1000, astrand))
fwa.close()
fwb.close()
beforefasta = fastaFromBed(beforebed, bbfasta, name=True, stranded=True)
afterfasta = fastaFromBed(afterbed, altfasta, name=True, stranded=True)
# Exclude the replacements that contain more Ns than before
ah = SeqIO.parse(beforefasta, "fasta")
bh = SeqIO.parse(afterfasta, "fasta")
count_Ns = lambda x: x.seq.count('n') + x.seq.count('N')
exclude = set()
for arec, brec in zip(ah, bh):
an = count_Ns(arec)
bn = count_Ns(brec)
if opts.strict:
if bn == 0:
continue
elif bn < an:
continue
id = arec.id
exclude.add(id)
logging.debug("Ignore {0} updates because of decreasing quality."\
.format(len(exclude)))
abed = Bed(beforebed, sorted=False)
bbed = Bed(afterbed, sorted=False)
abed = [x for x in abed if x.accn not in exclude]
bbed = [x for x in bbed if x.accn not in exclude]
abedfile = "before.filtered.bed"
bbedfile = "after.filtered.bed"
afbed = Bed()
afbed.extend(abed)
bfbed = Bed()
bfbed.extend(bbed)
afbed.print_to_file(abedfile)
bfbed.print_to_file(bbedfile)
# Shuffle the two bedfiles together
sz = Sizes(bbfasta)
sizes = sz.mapping
shuffled = "shuffled.bed"
border = bfbed.order
all = []
afbed.sort(key=afbed.nullkey)
totalids = len(sizes)
import math
pad = int(math.log10(totalids)) + 1
cj = 0
seen = set()
accn = lambda x: "{0}{1:0{2}d}".format(prefix, x, pad)
for seqid, aa in afbed.sub_beds():
cj += 1
abeds, bbeds, beds = [], [], []
size = sizes[seqid]
ranges = [(x.seqid, x.start, x.end) for x in aa]
cranges = range_interleave(ranges, sizes={seqid: size})
for seqid, start, end in cranges:
bedline = "\t".join(str(x) for x in (seqid, start - 1, end))
abeds.append(BedLine(bedline))
for a in aa:
gapid = a.accn
bi, b = border[gapid]
bbeds.append(b)
a = abeds[0] if abeds else []
assert abs(len(abeds) - len(bbeds)) <= 1
if (not a) or a.start > 1:
abeds, bbeds = bbeds, abeds
beds = list(roundrobin(abeds, bbeds))
if prefix:
for b in beds:
b.accn = accn(cj)
all.extend(beds)
seen.add(seqid)
# Singletons
for seqid, size in sz.iter_sizes():
if seqid in seen:
continue
bedline = "\t".join(str(x) for x in (seqid, 0, size, accn(cj)))
b = BedLine(bedline)
cj += 1
if prefix:
b.accn = accn(cj)
all.append(b)
shuffledbed = Bed()
shuffledbed.extend(all)
shuffledbed.print_to_file(shuffled)
def deletion(args):
"""
%prog deletion [mac.mic.bam|mac.mic.bed] mic.gaps.bed
Find IES based on mapping MAC reads to MIC genome.
"""
p = OptionParser(deletion.__doc__)
p.add_option("--mindepth", default=3, type="int",
help="Minimum depth to call a deletion")
p.add_option("--minspan", default=30, type="int",
help="Minimum span to call a deletion")
p.add_option("--split", default=False, action="store_true",
help="Break at cigar N into separate parts")
p.set_tmpdir()
opts, args = p.parse_args(args)
if len(args) != 2:
sys.exit(not p.print_help())
bedfile, gapsbedfile = args
if bedfile.endswith(".bam"):
bamfile = bedfile
bedfile = bamfile.replace(".sorted.", ".").replace(".bam", ".bed")
if need_update(bamfile, bedfile):
cmd = "bamToBed -i {0}".format(bamfile)
if opts.split:
cmd += " -split"
cmd += " | cut -f1-4"
sh(cmd, outfile=bedfile)
sort_tmpdir = "--tmpdir={0}".format(opts.tmpdir)
if bedfile.endswith(".sorted.bed"):
pf = bedfile.rsplit(".", 2)[0]
sortedbedfile = bedfile
else:
pf = bedfile.rsplit(".", 1)[0]
sortedbedfile = pf + ".sorted.bed"
if need_update(bedfile, sortedbedfile):
sort([bedfile, "-u", "--accn", sort_tmpdir])
# Find reads that contain multiple matches
ibedfile = pf + ".d.bed"
if need_update(sortedbedfile, ibedfile):
bed = Bed(sortedbedfile, sorted=False)
fw = open(ibedfile, "w")
logging.debug("Write deletions to `{0}`.".format(ibedfile))
for accn, bb in groupby(bed, key=lambda x: x.accn):
bb = list(bb)
branges = [(x.seqid, x.start, x.end) for x in bb]
iranges = range_interleave(branges)
for seqid, start, end in iranges:
if end - start + 1 < opts.minspan:
continue
print >> fw, "\t".join(str(x) for x in \
(seqid, start - 1, end, accn + '-d'))
fw.close()
# Uniqify the insertions and count occurrences
countbedfile = pf + ".uniq.bed"
if need_update(ibedfile, countbedfile):
bed = Bed(ibedfile)
fw = open(countbedfile, "w")
logging.debug("Write counts to `{0}`.".format(countbedfile))
registry = Counter((x.seqid, x.start, x.end) for x in bed)
ies_id = 1
for (seqid, start, end), count in registry.items():
ies_name = "{0:05d}-r{1}".format(ies_id, count)
if count < opts.mindepth:
continue
print >> fw, "\t".join(str(x) for x in \
(seqid, start - 1, end, ies_name))
ies_id += 1
fw.close()
sort([countbedfile, "-i", sort_tmpdir])
# Remove deletions that contain some read depth
depthbedfile = pf + ".depth.bed"
if need_update((sortedbedfile, countbedfile), depthbedfile):
depth([sortedbedfile, countbedfile, "--outfile={0}".format(depthbedfile)])
validbedfile = pf + ".valid.bed"
if need_update(depthbedfile, validbedfile):
fw = open(validbedfile, "w")
logging.debug("Filter valid deletions to `{0}`.".format(validbedfile))
bed = Bed(depthbedfile)
all_scores = [float(b.score) for b in bed]
lb, ub = outlier_cutoff(all_scores)
logging.debug("Bounds for depths: LB={0:.2f} (ignored) UB={1:.2f}".format(lb, ub))
for b in bed:
if float(b.score) > ub:
continue
print >> fw, b
fw.close()
# Remove deletions that contain sequencing gaps on its flanks
selectedbedfile = pf + ".selected.bed"
if need_update(validbedfile, selectedbedfile):
flanksbedfile = pf + ".flanks.bed"
fw = open(flanksbedfile, "w")
bed = Bed(validbedfile)
flank = 100
logging.debug("Write deletion flanks to `{0}`.".format(flanksbedfile))
for b in bed:
start, end = b.start, b.end
b.start, b.end = start, min(start + flank - 1, end)
print >> fw, b
b.start, b.end = max(start, end - flank + 1), end
print >> fw, b
fw.close()
intersectidsfile = pf + ".intersect.ids"
cmd = "intersectBed -a {0} -b {1}".format(flanksbedfile, gapsbedfile)
cmd += " | cut -f4 | sort -u"
sh(cmd, outfile=intersectidsfile)
some([validbedfile, intersectidsfile, "-v",
"--outfile={0}".format(selectedbedfile)])
# Find best-scoring non-overlapping set
iesbedfile = pf + ".ies.bed"
if need_update(selectedbedfile, iesbedfile):
bed = Bed(selectedbedfile)
fw = open(iesbedfile, "w")
logging.debug("Write IES to `{0}`.".format(iesbedfile))
branges = [Range(x.seqid, x.start, x.end, int(x.accn.rsplit("r")[-1]), i) \
for i, x in enumerate(bed)]
iranges, iscore = range_chain(branges)
logging.debug("Best chain score: {0} ({1} IES)".\
format(iscore, len(iranges)))
ies_id = 1
for seqid, start, end, score, id in iranges:
ies_name = "IES-{0:05d}-r{1}".format(ies_id, score)
span = end - start + 1
print >> fw, "\t".join(str(x) for x in \
(seqid, start - 1, end, ies_name, span))
ies_id += 1
fw.close()
def test_range_interleave(ranges, sizes, expected):
from jcvi.utils.range import range_interleave
assert range_interleave(ranges, sizes) == expected
