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 = next(SeqIO.parse(handle, "fasta"))
match = print_first_difference(arec,
brec,
ignore_case=True,
ignore_N=True,
rc=True)
if match:
valid = term
break
if valid:
printf()
printf("[green]{} matches the sequence in `{}`".format(
valid, fastafile))
def entrez(args):
"""
%prog entrez <filename|term>
`filename` contains a list of terms to search. Or just one term. If the
results are small in size, e.g. "--format=acc", use "--batchsize=100" to speed
the download.
"""
p = OptionParser(entrez.__doc__)
allowed_databases = {
"fasta": ["genome", "nuccore", "nucgss", "protein", "nucest"],
"asn.1": ["genome", "nuccore", "nucgss", "protein", "gene"],
"xml": ["genome", "nuccore", "nucgss", "nucest", "gene"],
"gb": ["genome", "nuccore", "nucgss"],
"est": ["nucest"],
"gss": ["nucgss"],
"acc": ["nuccore"],
}
valid_formats = tuple(allowed_databases.keys())
valid_databases = ("genome", "nuccore", "nucest", "nucgss", "protein", "gene")
p.add_option(
"--noversion",
dest="noversion",
default=False,
action="store_true",
help="Remove trailing accession versions",
)
p.add_option(
"--format",
default="fasta",
choices=valid_formats,
help="download format",
)
p.add_option(
"--database",
default="nuccore",
choices=valid_databases,
help="search database",
)
p.add_option(
"--retmax",
default=1000000,
type="int",
help="how many results to return",
)
p.add_option(
"--skipcheck",
default=False,
action="store_true",
help="turn off prompt to check file existence",
)
p.add_option(
"--batchsize",
default=500,
type="int",
help="download the results in batch for speed-up",
)
p.set_outdir(outdir=None)
p.add_option("--outprefix", default="out", help="output file name prefix")
p.set_email()
opts, args = p.parse_args(args)
if len(args) != 1:
sys.exit(p.print_help())
(filename,) = args
if op.exists(filename):
pf = filename.rsplit(".", 1)[0]
list_of_terms = [row.strip() for row in open(filename)]
if opts.noversion:
list_of_terms = [x.rsplit(".", 1)[0] for x in list_of_terms]
else:
pf = filename
# the filename is the search term
list_of_terms = [filename.strip()]
fmt = opts.format
database = opts.database
batchsize = opts.batchsize
assert (
database in allowed_databases[fmt]
), "For output format '{0}', allowed databases are: {1}".format(
fmt, allowed_databases[fmt]
)
assert batchsize >= 1, "batchsize must >= 1"
if " " in pf:
pf = opts.outprefix
outfile = "{0}.{1}".format(pf, fmt)
outdir = opts.outdir
if outdir:
mkdir(outdir)
# If noprompt, will not check file existence
if not outdir:
fw = must_open(outfile, "w", checkexists=True, skipcheck=opts.skipcheck)
if fw is None:
return
seen = set()
totalsize = 0
for id, size, term, handle in batch_entrez(
list_of_terms,
retmax=opts.retmax,
rettype=fmt,
db=database,
batchsize=batchsize,
email=opts.email,
):
if outdir:
outfile = urljoin(outdir, "{0}.{1}".format(term, fmt))
fw = must_open(outfile, "w", checkexists=True, skipcheck=opts.skipcheck)
if fw is None:
continue
rec = handle.read()
if id in seen:
logging.error("Duplicate key ({0}) found".format(rec))
continue
totalsize += size
print(rec, file=fw)
print(file=fw)
seen.add(id)
if seen:
printf(
"A total of {0} {1} records downloaded.".format(totalsize, fmt.upper()),
)
return outfile
stats.register("min", min)
eaSimpleConverge(pop,
toolbox,
0.7,
0.2,
ngen,
stats=stats,
halloffame=hof,
callback=callback)
tour = hof[0]
if cpus > 1:
pool.terminate()
return tour, tour.fitness
if __name__ == "__main__":
POINTS, SCF = 200, 20
scaffolds = make_data(POINTS, SCF)
# Demo case: scramble of the list
guess = list(range(SCF))
guess[5:15] = guess[5:15][::-1]
guess[7:18] = guess[7:18][::-1]
printf(guess)
toolbox = GA_setup(guess)
toolbox.register("evaluate", colinear_evaluate, scaffolds=scaffolds)
tour, tour.fitness = GA_run(toolbox, cpus=8)
printf(tour, tour.fitness)
def eaSimpleConverge(
population,
toolbox,
cxpb,
mutpb,
ngen,
stats=None,
halloffame=None,
callback=None,
verbose=True,
):
"""This algorithm reproduce the simplest evolutionary algorithm as
presented in chapter 7 of [Back2000]_.
Modified to allow checking if there is no change for ngen, as a simple
rule for convergence. Interface is similar to eaSimple(). However, in
eaSimple, ngen is total number of iterations; in eaSimpleConverge, we
terminate only when the best is NOT updated for ngen iterations.
"""
# Evaluate the individuals with an invalid fitness
invalid_ind = [ind for ind in population if not ind.fitness.valid]
fitnesses = toolbox.map(toolbox.evaluate, invalid_ind)
for ind, fit in zip(invalid_ind, fitnesses):
ind.fitness.values = fit
if halloffame is not None:
halloffame.update(population)
record = stats.compile(population) if stats else {}
# Begin the generational process
gen = 1
best = (0, )
while True:
# Select the next generation individuals
offspring = toolbox.select(population, len(population))
# Vary the pool of individuals
offspring = varAnd(offspring, toolbox, cxpb, mutpb)
# Evaluate the individuals with an invalid fitness
invalid_ind = [ind for ind in offspring if not ind.fitness.valid]
fitnesses = toolbox.map(toolbox.evaluate, invalid_ind)
for ind, fit in zip(invalid_ind, fitnesses):
ind.fitness.values = fit
# Update the hall of fame with the generated individuals
if halloffame is not None:
halloffame.update(offspring)
if callback is not None:
callback(halloffame[0], gen)
# Replace the current population by the offspring
population[:] = offspring
# Append the current generation statistics to the logbook
record = stats.compile(population) if stats else {}
current_best = record["max"]
if gen % 20 == 0 and verbose:
printf(
"Current iteration {0}: max_score={1}".format(
gen, current_best), )
if current_best > best:
best = current_best
updated = gen
gen += 1
if gen - updated > ngen:
break
return population
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.
"""
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
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]{}".format(t)
c = canvas - a - b
printf(
"{}{}{}{} ({})".format(" " * a, t, " " * c,
str(f.bid).rjust(10), f.erate_adj), )
