def find_synteny_region(query, sbed, data, window, cutoff, colinear=False):
"""
Get all synteny blocks for a query, algorithm is single linkage
anchors are a window centered on query
Two categories of syntenic regions depending on what query is:
(Syntelog): syntenic region is denoted by the syntelog
(Gray gene): syntenic region is marked by the closest flanker
"""
regions = []
ysorted = sorted(data, key=lambda x: x[1])
g = Grouper()
a, b = tee(ysorted)
next(b, None)
for ia, ib in zip(a, b):
pos1, pos2 = ia[1], ib[1]
if pos2 - pos1 < window and sbed[pos1].seqid == sbed[pos2].seqid:
g.join(ia, ib)
for group in sorted(g):
(qflanker, syntelog), (far_flanker, far_syntelog), flanked = \
get_flanker(group, query)
# run a mini-dagchainer here, take the direction that gives us most anchors
if colinear:
y_indexed_group = [(y, i) for i, (x, y) in enumerate(group)]
lis = longest_increasing_subsequence(y_indexed_group)
lds = longest_decreasing_subsequence(y_indexed_group)
if len(lis) >= len(lds):
track = lis
orientation = "+"
else:
track = lds
orientation = "-"
group = [group[i] for (y, i) in track]
xpos, ypos = zip(*group)
score = min(len(set(xpos)), len(set(ypos)))
if qflanker == query:
gray = "S"
else:
gray = "G" if not flanked else "F"
score -= 1 # slight penalty for not finding syntelog
if score < cutoff:
continue
# y-boundary of the block
left, right = group[0][1], group[-1][1]
# this characterizes a syntenic region (left, right).
# syntelog is -1 if it's a gray gene
syn_region = (syntelog, far_syntelog, left, right, gray, orientation,
score)
regions.append(syn_region)
return sorted(regions, key=lambda x: -x[-1]) # decreasing synteny score
def find_synteny_region(query, sbed, data, window, cutoff, colinear=False):
"""
Get all synteny blocks for a query, algorithm is single linkage
anchors are a window centered on query
Two categories of syntenic regions depending on what query is:
(Syntelog): syntenic region is denoted by the syntelog
(Gray gene): syntenic region is marked by the closest flanker
"""
regions = []
ysorted = sorted(data, key=lambda x: x[1])
g = Grouper()
a, b = tee(ysorted)
next(b, None)
for ia, ib in izip(a, b):
pos1, pos2 = ia[1], ib[1]
if pos2 - pos1 < window and sbed[pos1].seqid == sbed[pos2].seqid:
g.join(ia, ib)
for group in sorted(g):
(qflanker, syntelog), (far_flanker, far_syntelog), flanked = \
get_flanker(group, query)
# run a mini-dagchainer here, take the direction that gives us most anchors
if colinear:
y_indexed_group = [(y, i) for i, (x, y) in enumerate(group)]
lis = longest_increasing_subsequence(y_indexed_group)
lds = longest_decreasing_subsequence(y_indexed_group)
if len(lis) >= len(lds):
track = lis
orientation = "+"
else:
track = lds
orientation = "-"
group = [group[i] for (y, i) in track]
xpos, ypos = zip(*group)
score = min(len(set(xpos)), len(set(ypos)))
if qflanker == query:
gray = "S"
else:
gray = "G" if not flanked else "F"
score -= 1 # slight penalty for not finding syntelog
if score < cutoff:
continue
# y-boundary of the block
left, right = group[0][1], group[-1][1]
# this characterizes a syntenic region (left, right).
# syntelog is -1 if it's a gray gene
syn_region = (syntelog, far_syntelog, left,
right, gray, orientation, score)
regions.append(syn_region)
return sorted(regions, key=lambda x: -x[-1]) # decreasing synteny score
def main(arg):
fp = open(arg)
N = int(fp.readline().strip())
a = [int(x) for x in fp.readline().split()]
assert N == len(a)
lis = longest_increasing_subsequence(a)
lds = longest_decreasing_subsequence(a)
print " ".join(str(x) for x in lis)
print " ".join(str(x) for x in lds)
def renumber(args):
"""
%prog renumber Mt35.consolidated.bed > tagged.bed
Renumber genes for annotation updates.
"""
from jcvi.algorithms.lis import longest_increasing_subsequence
from jcvi.utils.grouper import Grouper
p = OptionParser(renumber.__doc__)
p.set_annot_reformat_opts()
opts, args = p.parse_args(args)
if len(args) != 1:
sys.exit(not p.print_help())
bedfile, = args
pf = bedfile.rsplit(".", 1)[0]
abedfile = pf + ".a.bed"
bbedfile = pf + ".b.bed"
if need_update(bedfile, (abedfile, bbedfile)):
prepare(bedfile)
mbed = Bed(bbedfile)
g = Grouper()
for s in mbed:
accn = s.accn
g.join(*accn.split(";"))
bed = Bed(abedfile)
for chr, sbed in bed.sub_beds():
current_chr = chr_number(chr)
if not current_chr:
continue
ranks = []
gg = set()
for s in sbed:
accn = s.accn
achr, arank = atg_name(accn)
if achr != current_chr:
continue
ranks.append(arank)
gg.add(accn)
lranks = longest_increasing_subsequence(ranks)
print >> sys.stderr, current_chr, len(sbed), "==>", len(ranks), \
"==>", len(lranks)
granks = set(gene_name(current_chr, x, prefix=opts.prefix, \
pad0=opts.pad0, uc=opts.uc) for x in lranks) | \
set(gene_name(current_chr, x, prefix=opts.prefix, \
pad0=opts.pad0, sep="te", uc=opts.uc) for x in lranks)
tagstore = {}
for s in sbed:
achr, arank = atg_name(s.accn)
accn = s.accn
if accn in granks:
tag = (accn, FRAME)
elif accn in gg:
tag = (accn, RETAIN)
else:
tag = (".", NEW)
tagstore[accn] = tag
# Find cases where genes overlap
for s in sbed:
accn = s.accn
gaccn = g[accn]
tags = [((tagstore[x][-1] if x in tagstore else NEW), x)
for x in gaccn]
group = [(PRIORITY.index(tag), x) for tag, x in tags]
best = min(group)[-1]
if accn != best:
tag = (best, OVERLAP)
else:
tag = tagstore[accn]
print "\t".join((str(s), "|".join(tag)))
def renumber(args):
"""
%prog renumber Mt35.consolidated.bed > tagged.bed
Renumber genes for annotation updates.
"""
from jcvi.algorithms.lis import longest_increasing_subsequence
from jcvi.utils.grouper import Grouper
p = OptionParser(renumber.__doc__)
p.set_annot_reformat_opts()
opts, args = p.parse_args(args)
if len(args) != 1:
sys.exit(not p.print_help())
bedfile, = args
pf = bedfile.rsplit(".", 1)[0]
abedfile = pf + ".a.bed"
bbedfile = pf + ".b.bed"
if need_update(bedfile, (abedfile, bbedfile)):
prepare(bedfile)
mbed = Bed(bbedfile)
g = Grouper()
for s in mbed:
accn = s.accn
g.join(*accn.split(";"))
bed = Bed(abedfile)
for chr, sbed in bed.sub_beds():
current_chr = chr_number(chr)
if not current_chr:
continue
ranks = []
gg = set()
for s in sbed:
accn = s.accn
achr, arank = atg_name(accn)
if achr != current_chr:
continue
ranks.append(arank)
gg.add(accn)
lranks = longest_increasing_subsequence(ranks)
print >> sys.stderr, current_chr, len(sbed), "==>", len(ranks), \
"==>", len(lranks)
granks = set(gene_name(current_chr, x, prefix=opts.prefix, \
pad0=opts.pad0, uc=opts.uc) for x in lranks) | \
set(gene_name(current_chr, x, prefix=opts.prefix, \
pad0=opts.pad0, sep="te", uc=opts.uc) for x in lranks)
tagstore = {}
for s in sbed:
achr, arank = atg_name(s.accn)
accn = s.accn
if accn in granks:
tag = (accn, FRAME)
elif accn in gg:
tag = (accn, RETAIN)
else:
tag = (".", NEW)
tagstore[accn] = tag
# Find cases where genes overlap
for s in sbed:
accn = s.accn
gaccn = g[accn]
tags = [((tagstore[x][-1] if x in tagstore else NEW), x) for x in gaccn]
group = [(PRIORITY.index(tag), x) for tag, x in tags]
best = min(group)[-1]
if accn != best:
tag = (best, OVERLAP)
else:
tag = tagstore[accn]
print "\t".join((str(s), "|".join(tag)))
def test_longest_increasing_subsequence(input_array, expected):
from jcvi.algorithms.lis import longest_increasing_subsequence
assert longest_increasing_subsequence(input_array) == expected
