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
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 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 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 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 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 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 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))
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:
qbed = subset_bed(qbed, qseqids)
sbed = subset_bed(sbed, sseqids)
image_name = op.splitext(anchorfile)[0] + "." + opts.format
dotplot_main(anchorfile,
qbed,
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:
qbed = subset_bed(qbed, qseqids)
sbed = subset_bed(sbed, sseqids)
image_name = op.splitext(anchorfile)[0] + "." + opts.format
dotplot_main(anchorfile, qbed, sbed, image_name, iopts,
vmin=opts.vmin, vmax=opts.vmax, is_self=is_self,