from gtfIO import GTFReader, GTFWriter
from optparse import OptionParser
parser = OptionParser()
parser.add_option("--input",
dest="input",
help="A gtf file containing the RepeatMasked gtf annotation")
parser.add_option("--minlen", dest="minleng", help="minimum length")
parser.add_option("--output", dest="output", help="A gtf output file")
parser.add_option("--maxdiv",
dest="maxdiv",
help="minimum length",
default=99999999999999999)
(options, args) = parser.parse_args()
minleng = int(options.minleng)
w = GTFWriter(options.output)
for e in GTFReader(options.input):
leng = (e.end - e.start) + 1
if (leng >= minleng):
if (e.score < float(options.maxdiv)):
w.write(e)
w.close()
from gtfIO import GTFReader,GTFWriter;
import sys
import random
from optparse import OptionParser, OptionGroup
import collections
parser = OptionParser()
parser.add_option("--input",dest="input",help="A gtf file containing the RepeatMasked gtf annotation")
parser.add_option("--min-leng",dest="minleng",help="minimum length")
parser.add_option("--output",dest="output",help="A gtf output file")
(options, args) = parser.parse_args()
minleng=int(options.minleng)
w=GTFWriter(options.output)
for e in GTFReader(options.input):
leng=(e.end-e.start)+1
if(leng>=minleng):
w.write(e)
w.close()
active=chrlist.pop(0)
while(True):
tested=[]
activeUnmodified=True
while(len(chrlist)>0):
totest=chrlist.pop(0)
#if(comparecount%100000==0):
# print "Finished {0} comparision; len chrlist {1}".format(comparecount,len(chrlist))
comparecount+=1
testdist,narrowdist=get_distance(active,totest)
if(testdist < maxdist):
active = mergeNucmer(active,totest,testdist)
activeUnmodified=False
else:
tested.append(totest)
chrlist=tested
if activeUnmodified:
break
chrentries.append(active)
print "Finished {0} with {1} fragments".format(chr,len(chrentries))
finallist.extend(chrentries)
refgtf=get_refgtflist(finallist)
querygtf=get_querygtflist(finallist)
GTFWriter.write_all(options.outputref,refgtf) # (cls,file,gtfentries):
GTFWriter.write_all(options.outputquery,querygtf)
if(options.outputdist):
print_distances(options.outputdist,finallist)
while (len(chrlist) > 0):
active = chrlist.pop(0)
while (True):
tested = []
activeUnmodified = True
while (len(chrlist) > 0):
totest = chrlist.pop(0)
#if(comparecount%100000==0):
# print "Finished {0} comparision; len chrlist {1}".format(comparecount,len(chrlist))
comparecount += 1
testdist, narrowdist = get_distance(active, totest)
if (testdist < maxdist):
active = mergeNucmer(active, totest, testdist)
activeUnmodified = False
else:
tested.append(totest)
chrlist = tested
if activeUnmodified:
break
chrentries.append(active)
print "Finished {0} with {1} fragments".format(chr, len(chrentries))
finallist.extend(chrentries)
refgtf = get_refgtflist(finallist)
querygtf = get_querygtflist(finallist)
GTFWriter.write_all(options.outputref, refgtf) # (cls,file,gtfentries):
GTFWriter.write_all(options.outputquery, querygtf)
if (options.outputdist):
print_distances(options.outputdist, finallist)
help="A gtf file containing the reference annotation")
parser.add_option(
"--totest",
dest="totest",
help="A gtf file containing the annotation that should be tested")
parser.add_option(
"--output",
dest="output",
help=
"The output file containing novel TE insertions not in the reference genome"
)
(options, args) = parser.parse_args()
# chromosomes with incomplete reference annotation: 2L, 2R, 3L
# fine: 3R, X, 4
rawref = GTFReader.readall(options.reference)
rawtotest = GTFReader.readall(options.totest)
chref = convert_chrhash(rawref)
chtotest = convert_chrhash(rawtotest)
ofh = GTFWriter(options.output)
for chr in ["X", "2L", "2R", "3L", "3R", "4"]:
cref = chref[chr]
ctotest = chtotest[chr]
ne = novelentries(cref, ctotest)
for n in ne:
ofh.write(n)
ofh.close()
parser = OptionParser()
parser.add_option("--reference",dest="reference",help="A gtf file containing the reference annotation")
parser.add_option("--totest",dest="totest",help="A gtf file containing the annotation that should be tested")
parser.add_option("--output",dest="output",help="The output file containing novel TE insertions not in the reference genome")
(options, args) = parser.parse_args()
# chromosomes with incomplete reference annotation: 2L, 2R, 3L
# fine: 3R, X, 4
rawref=GTFReader.readall(options.reference)
rawtotest=GTFReader.readall(options.totest)
chref=convert_chrhash(rawref)
chtotest=convert_chrhash(rawtotest)
ofh=GTFWriter(options.output)
for chr in ["X","2L","2R","3L","3R","4"]:
cref=chref[chr]
ctotest=chtotest[chr]
ne=novelentries(cref,ctotest)
for n in ne:
ofh.write(n)
ofh.close()