def group(args):
"""
%prog group anchorfiles
Group the anchors into ortho-groups. Can input multiple anchor files.
"""
p = OptionParser(group.__doc__)
p.set_outfile()
opts, args = p.parse_args(args)
if len(args) < 1:
sys.exit(not p.print_help())
anchorfiles = args
groups = Grouper()
for anchorfile in anchorfiles:
ac = AnchorFile(anchorfile)
for a, b, idx in ac.iter_pairs():
groups.join(a, b)
logging.debug("Created {0} groups with {1} members.".\
format(len(groups), groups.num_members))
outfile = opts.outfile
fw = must_open(outfile, "w")
for g in groups:
print >> fw, ",".join(sorted(g))
fw.close()
return outfile
def fuse(args):
"""
%prog fuse *.bed *.anchors
Fuse gene orders based on anchors file.
"""
from jcvi.algorithms.graph import BiGraph
p = OptionParser(fuse.__doc__)
opts, args = p.parse_args(args)
if len(args) < 1:
sys.exit(not p.print_help())
bedfiles = [x for x in args if x.endswith(".bed")]
anchorfiles = [x for x in args if x.endswith(".anchors")]
# TODO: Use Markov clustering to sparsify the edges
families = Grouper()
for anchorfile in anchorfiles:
af = AnchorFile(anchorfile)
for a, b, block_id in af.iter_pairs():
families.join(a, b)
allowed = set(families.keys())
logging.debug("Total families: {}, Gene members: {}"
.format(len(families), len(allowed)))
# TODO: Use C++ implementation of BiGraph() when available
# For now just serialize this to the disk
G = BiGraph()
for bedfile in bedfiles:
bed = Bed(bedfile, include=allowed)
#add_bed_to_graph(G, bed, families)
print_edges(G, bed, families)
def fuse(args):
"""
%prog fuse *.bed *.anchors
Fuse gene orders based on anchors file.
"""
from jcvi.algorithms.graph import BiGraph
p = OptionParser(fuse.__doc__)
opts, args = p.parse_args(args)
if len(args) < 1:
sys.exit(not p.print_help())
bedfiles = [x for x in args if x.endswith(".bed")]
anchorfiles = [x for x in args if x.endswith(".anchors")]
# TODO: Use Markov clustering to sparsify the edges
families = Grouper()
for anchorfile in anchorfiles:
af = AnchorFile(anchorfile)
for a, b, block_id in af.iter_pairs():
families.join(a, b)
allowed = set(families.keys())
logging.debug("Total families: {}, Gene members: {}".format(
len(families), len(allowed)))
# TODO: Use C++ implementation of BiGraph() when available
# For now just serialize this to the disk
for bedfile in bedfiles:
bed = Bed(bedfile, include=allowed)
print_edges(bed, families)
def group(args):
"""
%prog group anchorfiles
Group the anchors into ortho-groups. Can input multiple anchor files.
"""
p = OptionParser(group.__doc__)
p.set_outfile()
opts, args = p.parse_args(args)
if len(args) < 1:
sys.exit(not p.print_help())
anchorfiles = args
groups = Grouper()
for anchorfile in anchorfiles:
ac = AnchorFile(anchorfile)
for a, b, idx in ac.iter_pairs():
groups.join(a, b)
logging.debug("Created {0} groups with {1} members.".\
format(len(groups), groups.num_members))
outfile = opts.outfile
fw = must_open(outfile, "w")
for g in groups:
print >> fw, ",".join(sorted(g))
fw.close()
return outfile
def bed(args):
"""
%prog bed anchorsfile
Convert ANCHORS file to BED format.
"""
from collections import defaultdict
from jcvi.compara.synteny import AnchorFile, check_beds
from jcvi.formats.bed import Bed
from jcvi.formats.base import get_number
p = OptionParser(bed.__doc__)
p.add_option("--switch", default=False, action="store_true",
help="Switch reference and aligned map elements")
p.add_option("--scale", type="float",
help="Scale the aligned map distance by factor")
p.set_beds()
p.set_outfile()
opts, args = p.parse_args(args)
if len(args) != 1:
sys.exit(not p.print_help())
anchorsfile, = args
switch = opts.switch
scale = opts.scale
ac = AnchorFile(anchorsfile)
pairs = defaultdict(list)
for a, b, block_id in ac.iter_pairs():
pairs[a].append(b)
qbed, sbed, qorder, sorder, is_self = check_beds(anchorsfile, p, opts)
bd = Bed()
for q in qbed:
qseqid, qstart, qend, qaccn = q.seqid, q.start, q.end, q.accn
if qaccn not in pairs:
continue
for s in pairs[qaccn]:
si, s = sorder[s]
sseqid, sstart, send, saccn = s.seqid, s.start, s.end, s.accn
if switch:
qseqid, sseqid = sseqid, qseqid
qstart, sstart = sstart, qstart
qend, send = send, qend
qaccn, saccn = saccn, qaccn
if scale:
sstart /= scale
try:
newsseqid = get_number(sseqid)
except ValueError:
raise ValueError, "`{0}` is on `{1}` with no number to extract".\
format(saccn, sseqid)
bedline = "\t".join(str(x) for x in (qseqid, qstart - 1, qend,
"{0}:{1}".format(newsseqid, sstart)))
bd.add(bedline)
bd.print_to_file(filename=opts.outfile, sorted=True)
def bed(args):
"""
%prog bed anchorsfile
Convert ANCHORS file to BED format.
"""
from collections import defaultdict
from jcvi.compara.synteny import AnchorFile, check_beds
from jcvi.formats.bed import Bed, BedLine
from jcvi.formats.base import get_number
p = OptionParser(bed.__doc__)
p.add_option("--switch",
default=False,
action="store_true",
help="Switch reference and aligned map elements")
p.add_option("--scale",
type="float",
help="Scale the aligned map distance by factor")
p.set_beds()
p.set_outfile()
opts, args = p.parse_args(args)
if len(args) != 1:
sys.exit(not p.print_help())
anchorsfile, = args
switch = opts.switch
scale = opts.scale
ac = AnchorFile(anchorsfile)
pairs = defaultdict(list)
for a, b, block_id in ac.iter_pairs():
pairs[a].append(b)
qbed, sbed, qorder, sorder, is_self = check_beds(anchorsfile, p, opts)
bd = Bed()
for q in qbed:
qseqid, qstart, qend, qaccn = q.seqid, q.start, q.end, q.accn
if qaccn not in pairs:
continue
for s in pairs[qaccn]:
si, s = sorder[s]
sseqid, sstart, send, saccn = s.seqid, s.start, s.end, s.accn
if switch:
qseqid, sseqid = sseqid, qseqid
qstart, sstart = sstart, qstart
qend, send = send, qend
qaccn, saccn = saccn, qaccn
if scale:
sstart /= scale
bedline = "\t".join(
str(x) for x in (qseqid, qstart - 1, qend,
"{0}:{1}".format(get_number(sseqid), sstart)))
bd.append(BedLine(bedline))
bd.print_to_file(filename=opts.outfile, sorted=True)
def from_block_orientation(cls,
anchorfile,
qbed,
sbed,
forward_color="#e7298a",
reverse_color="#3690c0"):
"""Generate a palette which contains mapping from block_id (1-based) to colors.
Args:
anchorfile (str): Path to the .anchors file
qbed (BedFile): Query BED
sbed (BedFile): Subject BED
forward_color (str, optional): Color of forward block. Defaults to "#e7298a".
reverse_color (str, optional): Color of reverse block. Defaults to "#3690c0".
"""
ac = AnchorFile(anchorfile)
blocks = ac.blocks
palette = {}
qorder = qbed.order
sorder = sbed.order
for i, block in enumerate(blocks):
block_id = i + 1
a, b, _ = zip(*block)
a = [qorder[x] for x in a]
b = [sorder[x] for x in b]
ia, _ = zip(*a)
ib, _ = zip(*b)
orientation = get_orientation(ia, ib)
palette[
block_id] = reverse_color if orientation == "-" else forward_color
return cls(palettedict=palette)
def pairs(args):
"""
%prog pairs anchorsfile prefix
Convert anchorsfile to pairsfile.
"""
p = OptionParser(pairs.__doc__)
opts, args = p.parse_args(args)
if len(args) != 2:
sys.exit(not p.print_help())
anchorfile, prefix = args
outfile = prefix + ".pairs"
fw = open(outfile, "w")
af = AnchorFile(anchorfile)
blocks = af.blocks
pad = len(str(len(blocks)))
npairs = 0
for i, block in enumerate(blocks):
block_id = "{0}{1:0{2}d}".format(prefix, i + 1, pad)
lines = []
for q, s, score in block:
npairs += 1
score = score.replace("L", "")
lines.append("\t".join((q, s, score, block_id)))
print("\n".join(sorted(lines)), file=fw)
fw.close()
logging.debug("A total of {0} pairs written to `{1}`.".format(
npairs, outfile))
def filter_exclude(blast_list, exclude=None):
""" Filter gene pairs from an excluded list
Args:
blast_list (List[BlastLine]): List of BlastLines
exclude (str, optional): Path to the excluded anchors file. Defaults to None.
"""
from jcvi.compara.synteny import AnchorFile
excluded_pairs = set()
ac = AnchorFile(exclude)
for a, b, block in ac.iter_pairs():
excluded_pairs.add((a, b))
excluded_pairs.add((b, a))
for b in blast_list:
if (b.query, b.subject) in excluded_pairs:
continue
yield b
def anchor2tsv(args):
anchors = AnchorFile(args.fi)
blocks = anchors.blocks
i = 1
fmt = "b%%0%dd" % ndigit(len(blocks))
print("\t".join('bid gid1 gid2 score'.split()))
for block in blocks:
bid = fmt % i
for line in block:
a, b, score = line
print("\t".join((bid, a, b, score)))
i += 1
def fuse(args):
"""
%prog fuse *.bed *.anchors
Fuse gene orders based on anchors file.
"""
p = OptionParser(fuse.__doc__)
opts, args = p.parse_args(args)
if len(args) < 1:
sys.exit(not p.print_help())
bedfiles = [x for x in args if x.endswith(".bed")]
anchorfiles = [x for x in args if x.endswith(".anchors")]
aligned_genes = Grouper()
for anchorfile in anchorfiles:
af = AnchorFile(anchorfile)
for a, b, block_id in af.iter_pairs():
aligned_genes.join(a, b)
print list(aligned_genes)
logging.debug("Total aligned genes: {}".format(len(aligned_genes)))
def read_clusters(qa_file, qorder, sorder):
af = AnchorFile(qa_file)
blocks = af.blocks
clusters = []
for block in blocks:
cluster = []
for a, b, score in block:
ia, oa = qorder[a]
ib, ob = sorder[b]
ca, cb = oa.seqid, ob.seqid
cluster.append(((ca, ia), (cb, ib), score))
clusters.append(cluster)
return clusters
def zipbed(args):
"""
%prog zipbed species.bed collinear.anchors
Build ancestral contig from collinear blocks. For example, to build pre-rho
order, use `zipbed rice.bed rice.rice.1x1.collinear.anchors`. The algorithms
proceeds by interleaving the genes together.
"""
p = OptionParser(zipbed.__doc__)
p.add_option("--prefix",
default="b",
help="Prefix for the new seqid [default: %default]")
opts, args = p.parse_args(args)
if len(args) != 2:
sys.exit(not p.print_help())
bedfile, anchorfile = args
prefix = opts.prefix
bed = Bed(bedfile)
order = bed.order
newbedfile = prefix + ".bed"
fw = open(newbedfile, "w")
af = AnchorFile(anchorfile)
blocks = af.blocks
pad = len(str(len(blocks)))
for i, block in enumerate(blocks):
block_id = "{0}{1:0{2}d}".format(prefix, i + 1, pad)
pairs = []
for q, s, score in block:
qi, q = order[q]
si, s = order[s]
pairs.append((qi, si))
newbed = list(interleave_pairs(pairs))
for i, b in enumerate(newbed):
accn = bed[b].accn
print("\t".join(str(x) for x in (block_id, i, i + 1, accn)),
file=fw)
logging.debug("Reconstructed bedfile written to `{0}`.".format(newbedfile))
def collinear(args):
"""
%prog collinear a.b.anchors
Reduce synteny blocks to strictly collinear, use dynamic programming in a
procedure similar to DAGchainer.
"""
p = OptionParser(collinear.__doc__)
p.set_beds()
opts, args = p.parse_args(args)
if len(args) != 1:
sys.exit(not p.print_help())
(anchorfile, ) = args
qbed, sbed, qorder, sorder, is_self = check_beds(anchorfile, p, opts)
af = AnchorFile(anchorfile)
newanchorfile = anchorfile.rsplit(".", 1)[0] + ".collinear.anchors"
fw = open(newanchorfile, "w")
blocks = af.blocks
for block in blocks:
print("#" * 3, file=fw)
iblock = []
for q, s, score in block:
qi, q = qorder[q]
si, s = sorder[s]
score = get_number(score)
iblock.append([qi, si, score])
block = get_collinear(iblock)
for q, s, score in block:
q = qbed[q].accn
s = sbed[s].accn
print("\t".join((q, s, str(score))), file=fw)
fw.close()
def mergechrom(args):
"""
%prog mergechrom a.b.anchors
merge synteny blocks on the same chromosome
"""
p = OptionParser(mergechrom.__doc__)
p.set_beds()
opts, args = p.parse_args(args)
if len(args) != 1:
sys.exit(not p.print_help())
anchorfile, = args
qbed, sbed, qorder, sorder, is_self = check_beds(anchorfile, p, opts)
af = AnchorFile(anchorfile)
newanchorfile = anchorfile.rsplit(".", 1)[0] + ".mergechrom.anchors"
fw = open(newanchorfile, "w")
qchrom_dic = dict((b.accn, b.seqid) for b in qbed)
schrom_dic = dict((b.accn, b.seqid) for b in sbed)
block_dic = dict()
blocks = af.blocks
for (i, block) in enumerate(blocks):
q, s, score = block[0]
qchrom, schrom = qchrom_dic[q], schrom_dic[s]
k = "%s_%s" % (qchrom, schrom)
if k not in block_dic: block_dic[k] = []
block_dic[k].append(i)
for (k, idxs) in block_dic.items():
print("#" * 3, file=fw)
for i in idxs:
for q, s, score in blocks[i]:
print("\t".join((q, s, str(score))), file=fw)
fw.close()
print("%d blocks merged to %d" % (len(blocks), len(block_dic.keys())))
def read_clusters(qa_file, qorder, sorder):
"""Read in the clusters from anchors file
Args:
qa_file (str): Path to input file
qorder (dict): Dictionary to find position of feature in query
sorder (dict): Dictionary to find position of feature in subject
Returns:
List: List of matches and scores
"""
af = AnchorFile(qa_file)
blocks = af.blocks
clusters = []
for block in blocks:
cluster = []
for a, b, score in block:
ia, oa = qorder[a]
ib, ob = sorder[b]
ca, cb = oa.seqid, ob.seqid
cluster.append(((ca, ia), (cb, ib), score))
clusters.append(cluster)
return clusters
def dotplot_main(args):
p = OptionParser(__doc__)
p.set_beds()
p.add_option("--synteny", default=False, action="store_true",
help="Run a fast synteny scan and display blocks [default: %default]")
p.add_option("--cmaptext", help="Draw colormap box on the bottom-left corner")
p.add_option("--vmin", dest="vmin", type="float", default=0,
help="Minimum value in the colormap [default: %default]")
p.add_option("--vmax", dest="vmax", type="float", default=2,
help="Maximum value in the colormap [default: %default]")
p.add_option("--genomenames", type="string", default=None,
help="genome names for labeling axes in the form of qname_sname, " \
"eg. \"Vitis vinifera_Oryza sativa\"")
p.add_option("--nmax", dest="sample_number", type="int", default=10000,
help="Maximum number of data points to plot [default: %default]")
p.add_option("--minfont", type="int", default=4,
help="Do not render labels with size smaller than")
p.add_option("--colormap",
help="Two column file, block id to color mapping [default: %default]")
p.add_option("--nosort", default=False, action="store_true",
help="Do not sort the seqids along the axes")
p.add_option("--nosep", default=False, action="store_true",
help="Do not add contig lines")
p.add_option("--nostdpf", default=False, action="store_true",
help="Do not standardize contig names")
p.add_option("--skipempty", default=False, action="store_true",
help="Skip seqids that do not have matches")
p.add_option("--title", help="Title of the dot plot")
p.set_outfile(outfile=None)
opts, args, iopts = p.set_image_options(args, figsize="8x8",
style="dark", dpi=90, cmap="copper")
if len(args) != 1:
sys.exit(not p.print_help())
palette = opts.colormap
if palette:
palette = Palette(palette)
anchorfile, = args
cmaptext = opts.cmaptext
if anchorfile.endswith(".ks"):
from jcvi.apps.ks import KsFile
logging.debug("Anchors contain Ks values")
cmaptext = cmaptext or "*Ks* values"
anchorksfile = anchorfile + ".anchors"
if need_update(anchorfile, anchorksfile):
ksfile = KsFile(anchorfile)
ksfile.print_to_anchors(anchorksfile)
anchorfile = anchorksfile
qbed, sbed, qorder, sorder, is_self = check_beds(anchorfile, p, opts,
sorted=(not opts.nosort))
if opts.skipempty:
ac = AnchorFile(anchorfile)
if is_self:
qseqids = sseqids = set()
else:
qseqids, sseqids = set(), set()
for pair in ac.iter_pairs():
q, s = pair[:2]
qi, q = qorder[q]
si, s = sorder[s]
qseqids.add(q.seqid)
sseqids.add(s.seqid)
if is_self:
qbed = sbed = subset_bed(qbed, qseqids)
else:
qbed = subset_bed(qbed, qseqids)
sbed = subset_bed(sbed, sseqids)
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1]) # the whole canvas
ax = fig.add_axes([.1, .1, .8, .8]) # the dot plot
dotplot(anchorfile, qbed, sbed, fig, root, ax,
vmin=opts.vmin, vmax=opts.vmax, is_self=is_self,
synteny=opts.synteny, cmap_text=opts.cmaptext, cmap=iopts.cmap,
genomenames=opts.genomenames, sample_number=opts.sample_number,
minfont=opts.minfont, palette=palette, sep=(not opts.nosep),
title=opts.title, stdpf=(not opts.nostdpf))
image_name = opts.outfile or \
(op.splitext(anchorfile)[0] + "." + opts.format)
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
fig.clear()
def omgprepare(args):
"""
%prog omgprepare ploidy anchorsfile blastfile
Prepare to run Sankoff's OMG algorithm to get orthologs.
"""
from jcvi.formats.blast import cscore
from jcvi.formats.base import DictFile
p = OptionParser(omgprepare.__doc__)
p.add_option("--norbh",
action="store_true",
help="Disable RBH hits [default: %default]")
p.add_option("--pctid",
default=0,
type="int",
help="Percent id cutoff for RBH hits [default: %default]")
p.add_option("--cscore",
default=90,
type="int",
help="C-score cutoff for RBH hits [default: %default]")
p.set_stripnames()
p.set_beds()
opts, args = p.parse_args(args)
if len(args) != 3:
sys.exit(not p.print_help())
ploidy, anchorfile, blastfile = args
norbh = opts.norbh
pctid = opts.pctid
cs = opts.cscore
qbed, sbed, qorder, sorder, is_self = check_beds(anchorfile, p, opts)
fp = open(ploidy)
genomeidx = dict((x.split()[0], i) for i, x in enumerate(fp))
fp.close()
ploidy = DictFile(ploidy)
geneinfo(qbed, qorder, genomeidx, ploidy)
geneinfo(sbed, sorder, genomeidx, ploidy)
pf = blastfile.rsplit(".", 1)[0]
cscorefile = pf + ".cscore"
cscore([blastfile, "-o", cscorefile, "--cutoff=0", "--pct"])
ac = AnchorFile(anchorfile)
pairs = set((a, b) for a, b, i in ac.iter_pairs())
logging.debug("Imported {0} pairs from `{1}`.".format(
len(pairs), anchorfile))
weightsfile = pf + ".weights"
fp = open(cscorefile)
fw = open(weightsfile, "w")
npairs = 0
for row in fp:
a, b, c, pct = row.split()
c, pct = float(c), float(pct)
c = int(c * 100)
if (a, b) not in pairs:
if norbh:
continue
if c < cs:
continue
if pct < pctid:
continue
c /= 10 # This severely penalizes RBH against synteny
print >> fw, "\t".join((a, b, str(c)))
npairs += 1
fw.close()
logging.debug("Write {0} pairs to `{1}`.".format(npairs, weightsfile))
def omgprepare(args):
"""
%prog omgprepare ploidy anchorsfile blastfile
Prepare to run Sankoff's OMG algorithm to get orthologs.
"""
from jcvi.formats.blast import cscore
from jcvi.formats.base import DictFile
p = OptionParser(omgprepare.__doc__)
p.add_option("--norbh", action="store_true",
help="Disable RBH hits [default: %default]")
p.add_option("--pctid", default=0, type="int",
help="Percent id cutoff for RBH hits [default: %default]")
p.add_option("--cscore", default=90, type="int",
help="C-score cutoff for RBH hits [default: %default]")
p.set_stripnames()
p.set_beds()
opts, args = p.parse_args(args)
if len(args) != 3:
sys.exit(not p.print_help())
ploidy, anchorfile, blastfile = args
norbh = opts.norbh
pctid = opts.pctid
cs = opts.cscore
qbed, sbed, qorder, sorder, is_self = check_beds(anchorfile, p, opts)
fp = open(ploidy)
genomeidx = dict((x.split()[0], i) for i, x in enumerate(fp))
fp.close()
ploidy = DictFile(ploidy)
geneinfo(qbed, qorder, genomeidx, ploidy)
geneinfo(sbed, sorder, genomeidx, ploidy)
pf = blastfile.rsplit(".", 1)[0]
cscorefile = pf + ".cscore"
cscore([blastfile, "-o", cscorefile, "--cutoff=0", "--pct"])
ac = AnchorFile(anchorfile)
pairs = set((a, b) for a, b, i in ac.iter_pairs())
logging.debug("Imported {0} pairs from `{1}`.".format(len(pairs), anchorfile))
weightsfile = pf + ".weights"
fp = open(cscorefile)
fw = open(weightsfile, "w")
npairs = 0
for row in fp:
a, b, c, pct = row.split()
c, pct = float(c), float(pct)
c = int(c * 100)
if (a, b) not in pairs:
if norbh:
continue
if c < cs:
continue
if pct < pctid:
continue
c /= 10 # This severely penalizes RBH against synteny
print >> fw, "\t".join((a, b, str(c)))
npairs += 1
fw.close()
logging.debug("Write {0} pairs to `{1}`.".format(npairs, weightsfile))
def cluster(args):
"""
%prog cluster blastfile anchorfile --qbed qbedfile --sbed sbedfile
Cluster the segments and form PAD. This is the method described in Tang et
al. (2010) PNAS paper. The anchorfile defines a list of synteny blocks,
based on which the genome on one or both axis can be chopped up into pieces
and clustered.
"""
from jcvi.utils.range import Range
p = OptionParser(cluster.__doc__)
p.set_beds()
p.add_option("--minsize", default=10, type="int",
help="Only segment using blocks >= size [default: %default]")
p.add_option("--path", default="~/scratch/bin",
help="Path to the CLUSTER 3.0 binary [default: %default]")
opts, args = p.parse_args(args)
if len(args) != 2:
sys.exit(not p.print_help())
blastfile, anchorfile = args
qbed, sbed, qorder, sorder, is_self = check_beds(blastfile, p, opts)
minsize = opts.minsize
ac = AnchorFile(anchorfile)
qranges, sranges = [], []
qextra = [x[1:] for x in qbed.get_breaks()]
sextra = [x[1:] for x in sbed.get_breaks()]
id = 0
for block in ac.iter_blocks(minsize=minsize):
q, s = zip(*block)[:2]
q = [qorder[x][0] for x in q]
s = [sorder[x][0] for x in s]
minq, maxq = min(q), max(q)
mins, maxs = min(s), max(s)
id += 1
qr = Range("0", minq, maxq, maxq - minq, id)
sr = Range("0", mins, maxs, maxs - mins, id)
qranges.append(qr)
sranges.append(sr)
qpads = list(get_segments(qranges, qextra))
spads = list(get_segments(sranges, sextra))
suffix = ".pad.bed"
qpf = opts.qbed.split(".")[0]
spf = opts.sbed.split(".")[0]
qpadfile = qpf + suffix
spadfile = spf + suffix
qnpads, qpadnames = write_PAD_bed(qpadfile, qpf, qpads, qbed)
snpads, spadnames = write_PAD_bed(spadfile, spf, spads, sbed)
qpadbed, spadbed = Bed(qpadfile), Bed(spadfile)
logmp = make_arrays(blastfile, qpadbed, spadbed, qpadnames, spadnames)
m, n = logmp.shape
matrixfile = ".".join((qpf, spf, "logmp.txt"))
fw = open(matrixfile, "w")
header = ["o"] + spadnames
print("\t".join(header), file=fw)
for i in xrange(m):
row = [qpadnames[i]] + ["{0:.1f}".format(x) for x in logmp[i, :]]
print("\t".join(row), file=fw)
fw.close()
# Run CLUSTER 3.0 (Pearson correlation, average linkage)
cmd = op.join(opts.path, "cluster")
cmd += " -g 2 -e 2 -m a -f {0}".format(matrixfile)
pf = matrixfile.rsplit(".", 1)[0]
cdtfile = pf + ".cdt"
if need_update(matrixfile, cdtfile):
sh(cmd)
help="Skip seqids that do not have matches")
opts, args, iopts = p.set_image_options(sys.argv[1:], figsize="8x8",
style="dark", dpi=90, cmap="copper")
if len(args) != 1:
sys.exit(not p.print_help())
palette = opts.colormap
if palette:
palette = Palette(palette)
anchorfile, = args
qbed, sbed, qorder, sorder, is_self = check_beds(anchorfile, p, opts)
if opts.skipempty:
ac = AnchorFile(anchorfile)
if is_self:
qseqids = sseqids = set()
else:
qseqids, sseqids = set(), set()
for pair in ac.iter_pairs():
q, s = pair[:2]
qi, q = qorder[q]
si, s = sorder[s]
qseqids.add(q.seqid)
sseqids.add(s.seqid)
if is_self:
qbed = sbed = subset_bed(qbed, qseqids)
else:
def ancestral(args):
"""
%prog ancestral vplanifoliaA.vplanifoliaA.anchors > vplanifoliaA_blocks.bed
Paint 14 chromosomes following alpha WGD.
"""
p = OptionParser(ancestral.__doc__)
p.set_beds()
opts, args = p.parse_args(args)
if len(args) != 1:
sys.exit(not p.print_help())
(anchorsfile, ) = args
qbed, sbed, qorder, sorder, is_self = check_beds(anchorsfile, p, opts)
# We focus on the following chromosome pairs
target_pairs = {
(1, 1),
(1, 6),
(1, 8),
(1, 13),
(2, 4),
(3, 12),
(3, 14),
(5, 6),
(5, 8),
(7, 9),
(7, 11),
(9, 10),
(10, 11),
}
def get_target(achr, bchr):
if "chr" not in achr and "chr" not in bchr:
return None
achr, bchr = get_number(achr), get_number(bchr)
if achr > bchr:
achr, bchr = bchr, achr
if (achr, bchr) in target_pairs:
return achr, bchr
return None
def build_bedline(astart, aend, target_pair):
# target_name = "{:02d}-{:02d}".format(*target_pair)
target_name = [
str(x) for x in target_pair if x in (1, 2, 3, 5, 7, 10)
][0]
return "\t".join(
str(x)
for x in (astart.seqid, astart.start, aend.end, target_name))
# Iterate through the blocks, store any regions that has hits to one of the
# target_pairs
ac = AnchorFile(anchorsfile)
blocks = ac.blocks
outbed = Bed()
for i, block in enumerate(blocks):
a, b, scores = zip(*block)
a = [qorder[x] for x in a]
b = [sorder[x] for x in b]
astart, aend = min(a)[1], max(a)[1]
bstart, bend = min(b)[1], max(b)[1]
# Now convert to BED lines with new accn
achr, bchr = astart.seqid, bstart.seqid
target = get_target(achr, bchr)
if target is None:
continue
outbed.add(build_bedline(astart, aend, target))
outbed.add(build_bedline(bstart, bend, target))
outbed.print_to_file(sorted=True)
def cluster(args):
"""
%prog cluster blastfile anchorfile --qbed qbedfile --sbed sbedfile
Cluster the segments and form PAD. This is the method described in Tang et
al. (2010) PNAS paper. The anchorfile defines a list of synteny blocks,
based on which the genome on one or both axis can be chopped up into pieces
and clustered.
"""
from jcvi.utils.range import Range
p = OptionParser(cluster.__doc__)
p.set_beds()
p.add_option(
"--minsize", default=10, type="int", help="Only segment using blocks >= size"
)
p.add_option(
"--path", default="~/scratch/bin", help="Path to the CLUSTER 3.0 binary"
)
opts, args = p.parse_args(args)
if len(args) != 2:
sys.exit(not p.print_help())
blastfile, anchorfile = args
qbed, sbed, qorder, sorder, is_self = check_beds(blastfile, p, opts)
minsize = opts.minsize
ac = AnchorFile(anchorfile)
qranges, sranges = [], []
qextra = [x[1:] for x in qbed.get_breaks()]
sextra = [x[1:] for x in sbed.get_breaks()]
id = 0
for block in ac.iter_blocks(minsize=minsize):
q, s = list(zip(*block))[:2]
q = [qorder[x][0] for x in q]
s = [sorder[x][0] for x in s]
minq, maxq = min(q), max(q)
mins, maxs = min(s), max(s)
id += 1
qr = Range("0", minq, maxq, maxq - minq, id)
sr = Range("0", mins, maxs, maxs - mins, id)
qranges.append(qr)
sranges.append(sr)
qpads = list(get_segments(qranges, qextra))
spads = list(get_segments(sranges, sextra))
suffix = ".pad.bed"
qpf = opts.qbed.split(".")[0]
spf = opts.sbed.split(".")[0]
qpadfile = qpf + suffix
spadfile = spf + suffix
qnpads, qpadnames = write_PAD_bed(qpadfile, qpf, qpads, qbed)
snpads, spadnames = write_PAD_bed(spadfile, spf, spads, sbed)
qpadbed, spadbed = Bed(qpadfile), Bed(spadfile)
logmp = make_arrays(blastfile, qpadbed, spadbed, qpadnames, spadnames)
m, n = logmp.shape
matrixfile = ".".join((qpf, spf, "logmp.txt"))
fw = open(matrixfile, "w")
header = ["o"] + spadnames
print("\t".join(header), file=fw)
for i in range(m):
row = [qpadnames[i]] + ["{0:.1f}".format(x) for x in logmp[i, :]]
print("\t".join(row), file=fw)
fw.close()
# Run CLUSTER 3.0 (Pearson correlation, average linkage)
cmd = op.join(opts.path, "cluster")
cmd += " -g 2 -e 2 -m a -f {0}".format(matrixfile)
pf = matrixfile.rsplit(".", 1)[0]
cdtfile = pf + ".cdt"
if need_update(matrixfile, cdtfile):
sh(cmd)
figsize="8x8",
style="dark",
dpi=90)
if len(args) != 1:
sys.exit(not p.print_help())
palette = opts.colormap
if palette:
palette = Palette(palette)
anchorfile, = args
qbed, sbed, qorder, sorder, is_self = check_beds(anchorfile, p, opts)
if opts.skipempty:
ac = AnchorFile(anchorfile)
if is_self:
qseqids = sseqids = set()
else:
qseqids, sseqids = set(), set()
for pair in ac.iter_pairs():
q, s = pair[:2]
qi, q = qorder[q]
si, s = sorder[s]
qseqids.add(q.seqid)
sseqids.add(s.seqid)
if is_self:
qbed = sbed = subset_bed(qbed, qseqids)
else: