def bisect(args):
"""
%prog bisect acc accession.fasta
determine the version of the accession, based on a fasta file.
This proceeds by a sequential search from xxxx.1 to the latest record.
"""
p = OptionParser(bisect.__doc__)
p.set_email()
opts, args = p.parse_args(args)
if len(args) != 2:
sys.exit(not p.print_help())
acc, fastafile = args
arec = get_first_rec(fastafile)
valid = None
for i in range(1, 100):
term = "%s.%d" % (acc, i)
try:
query = list(batch_entrez([term], email=opts.email))
except AssertionError as e:
logging.debug("no records found for %s. terminating." % term)
return
id, term, handle = query[0]
brec = SeqIO.parse(handle, "fasta").next()
match = print_first_difference(arec,
brec,
ignore_case=True,
ignore_N=True,
rc=True)
if match:
valid = term
break
if valid:
print
print green("%s matches the sequence in `%s`" % (valid, fastafile))
def bisect(args):
"""
%prog bisect acc accession.fasta
determine the version of the accession by querying entrez, based on a fasta file.
This proceeds by a sequential search from xxxx.1 to the latest record.
"""
p = OptionParser(bisect.__doc__)
p.set_email()
opts, args = p.parse_args(args)
if len(args) != 2:
sys.exit(not p.print_help())
acc, fastafile = args
arec = get_first_rec(fastafile)
valid = None
for i in range(1, 100):
term = "%s.%d" % (acc, i)
try:
query = list(batch_entrez([term], email=opts.email))
except AssertionError as e:
logging.debug("no records found for %s. terminating." % term)
return
id, term, handle = query[0]
brec = SeqIO.parse(handle, "fasta").next()
match = print_first_difference(arec, brec, ignore_case=True,
ignore_N=True, rc=True)
if match:
valid = term
break
if valid:
print
print green("%s matches the sequence in `%s`" % (valid, fastafile))
def asciiplot(x, y, digit=1, width=50, title=None, char="="):
"""
Print out a horizontal plot using ASCII chars.
width is the textwidth (height) of the plot.
"""
ax = np.array(x)
ay = np.array(y)
if title:
print >> sys.stderr, dark(title)
az = ay * width / ay.max()
tx = [asciiaxis(x, digit=digit) for x in ax]
rjust = max([len(x) for x in tx]) + 1
for x, y, z in zip(tx, ay, az):
x = x.rjust(rjust)
y = y or ""
z = green(char * z)
print >> sys.stderr, "{0} |{1} {2}".format(x, z, y)
def asciiplot(x, y, digit=1, width=50, title=None, char="="):
"""
Print out a horizontal plot using ASCII chars.
width is the textwidth (height) of the plot.
"""
ax = np.array(x)
ay = np.array(y)
if title:
print(dark(title), file=sys.stderr)
az = ay * width // ay.max()
tx = [asciiaxis(x, digit=digit) for x in ax]
rjust = max([len(x) for x in tx]) + 1
for x, y, z in zip(tx, ay, az):
x = x.rjust(rjust)
y = y or ""
z = green(char * z)
print("{0} |{1} {2}".format(x, z, y), file=sys.stderr)
def overlap(args):
"""
%prog overlap best.contains iid
Visualize overlaps for a given fragment. Must be run in 4-unitigger. All
overlaps for iid were retrieved, excluding the ones matching best.contains.
"""
from jcvi.apps.console import green
p = OptionParser(overlap.__doc__)
p.add_option("--maxerr", default=2, type="int", help="Maximum error rate")
p.add_option("--canvas", default=100, type="int", help="Canvas size")
opts, args = p.parse_args(args)
if len(args) != 2:
sys.exit(not p.print_help())
bestcontains, iid = args
canvas = opts.canvas
bestcontainscache = bestcontains + ".cache"
if need_update(bestcontains, bestcontainscache):
fp = open(bestcontains)
fw = open(bestcontainscache, "w")
exclude = set()
for row in fp:
if row[0] == "#":
continue
j = int(row.split()[0])
exclude.add(j)
cPickle.dump(exclude, fw)
fw.close()
exclude = cPickle.load(open(bestcontainscache))
logging.debug("A total of {0} reads to exclude".format(len(exclude)))
cmd = "overlapStore -d ../asm.ovlStore -b {0} -e {0}".format(iid)
cmd += " -E {0}".format(opts.maxerr)
frags = []
for row in popen(cmd):
r = OverlapLine(row)
if r.bid in exclude:
continue
frags.append(r)
# Also include to query fragment
frags.append(OverlapLine("{0} {0} N 0 0 0 0".format(iid)))
frags.sort(key=lambda x: x.ahang)
# Determine size of the query fragment
cmd = "gatekeeper -b {0} -e {0}".format(iid)
cmd += " -tabular -dumpfragments ../asm.gkpStore"
fp = popen(cmd)
row = fp.next()
size = int(fp.next().split()[-1])
# Determine size of canvas
xmin = min(x.ahang for x in frags)
xmax = max(x.bhang for x in frags)
xsize = -xmin + size + xmax
ratio = xsize / canvas
fw = sys.stdout
for f in frags:
fsize = -f.ahang + size + f.bhang
a = (f.ahang - xmin) / ratio
b = fsize / ratio
t = "-" * b
if f.orientation == "N":
t = t[:-1] + ">"
else:
t = "<" + t[1:]
if f.ahang == 0 and f.bhang == 0:
t = green(t)
c = canvas - a - b
fw.write(" " * a)
fw.write(t)
fw.write(" " * c)
print >> fw, "{0} ({1})".format(str(f.bid).rjust(10), f.erate_adj)
from jcvi.formats.base import LineFile, must_open
from jcvi.formats.bed import Bed
from jcvi.formats.sizes import Sizes
from jcvi.formats.blast import Blast
from jcvi.graphics.base import normalize_axes, plt, savefig
from jcvi.graphics.dotplot import dotplot
from jcvi.utils.cbook import gene_name, human_size
from jcvi.utils.natsort import natsorted
# Map orientations to ints
FF = {'+': 1, '-': -1, '?': 1}
RR = {'+': -1, '-': 1, '?': -1}
LB = 18 # Lower bound for golden_array()
UB = 29 # Upper bound for golden_array()
BB = UB - LB + 1 # Span for golden_array()
ACCEPT = green("ACCEPT")
REJECT = red("REJECT")
BINSIZE = 50000
class ContigOrderingLine(object):
'''Stores one line in the ContigOrdering file
'''
def __init__(self, line, sep="|"):
args = line.split()
self.contig_id = args[0]
self.contig_name = args[1].split(sep)[0]
contig_rc = args[2]
assert contig_rc in ('0', '1')
self.strand = '+' if contig_rc == '0' else '-'
self.orientation_score = args[3]
def overlap(args):
"""
%prog overlap best.contains iid
Visualize overlaps for a given fragment. Must be run in 4-unitigger. All
overlaps for iid were retrieved, excluding the ones matching best.contains.
"""
from jcvi.apps.console import green
p = OptionParser(overlap.__doc__)
p.add_option("--maxerr", default=2, type="int", help="Maximum error rate")
p.add_option("--canvas", default=100, type="int", help="Canvas size")
opts, args = p.parse_args(args)
if len(args) != 2:
sys.exit(not p.print_help())
bestcontains, iid = args
canvas = opts.canvas
bestcontainscache = bestcontains + ".cache"
if need_update(bestcontains, bestcontainscache):
fp = open(bestcontains)
fw = open(bestcontainscache, "w")
exclude = set()
for row in fp:
if row[0] == '#':
continue
j = int(row.split()[0])
exclude.add(j)
dump(exclude, fw)
fw.close()
exclude = load(open(bestcontainscache))
logging.debug("A total of {0} reads to exclude".format(len(exclude)))
cmd = "overlapStore -d ../asm.ovlStore -b {0} -e {0}".format(iid)
cmd += " -E {0}".format(opts.maxerr)
frags = []
for row in popen(cmd):
r = OverlapLine(row)
if r.bid in exclude:
continue
frags.append(r)
# Also include to query fragment
frags.append(OverlapLine("{0} {0} N 0 0 0 0".format(iid)))
frags.sort(key=lambda x: x.ahang)
# Determine size of the query fragment
cmd = "gatekeeper -b {0} -e {0}".format(iid)
cmd += " -tabular -dumpfragments ../asm.gkpStore"
fp = popen(cmd)
row = next(fp)
size = int(fp.next().split()[-1])
# Determine size of canvas
xmin = min(x.ahang for x in frags)
xmax = max(x.bhang for x in frags)
xsize = -xmin + size + xmax
ratio = xsize / canvas
fw = sys.stdout
for f in frags:
fsize = -f.ahang + size + f.bhang
a = (f.ahang - xmin) / ratio
b = fsize / ratio
t = '-' * b
if f.orientation == 'N':
t = t[:-1] + '>'
else:
t = '<' + t[1:]
if f.ahang == 0 and f.bhang == 0:
t = green(t)
c = canvas - a - b
fw.write(' ' * a)
fw.write(t)
fw.write(' ' * c)
print("{0} ({1})".format(str(f.bid).rjust(10), f.erate_adj), file=fw)
from jcvi.formats.bed import Bed
from jcvi.formats.sizes import Sizes
from jcvi.formats.blast import Blast
from jcvi.graphics.base import normalize_axes, plt, savefig
from jcvi.graphics.dotplot import dotplot
from jcvi.utils.cbook import gene_name, human_size
from jcvi.utils.natsort import natsorted
# Map orientations to ints
FF = {'+': 1, '-': -1, '?': 1}
RR = {'+': -1, '-': 1, '?': -1}
LB = 18 # Lower bound for golden_array()
UB = 29 # Upper bound for golden_array()
BB = UB - LB + 1 # Span for golden_array()
ACCEPT = green("ACCEPT")
REJECT = red("REJECT")
BINSIZE = 50000
class ContigOrderingLine(object):
'''Stores one line in the ContigOrdering file
'''
def __init__(self, line, sep="|"):
args = line.split()
self.contig_id = args[0]
self.contig_name = args[1].split(sep)[0]
contig_rc = args[2]
assert contig_rc in ('0', '1')
self.strand = '+' if contig_rc == '0' else '-'
self.orientation_score = args[3]