def _cap_enzymes_between_alleles(allele1, allele2, reference, start, end,
all_enzymes=False):
'''It looks in the enzymes that differenciate the given alleles.
It returns a set.
'''
start += 1
# we have to build the two sequences
if all_enzymes:
restriction_batch = CommOnly
else:
restriction_batch = RestrictionBatch(COMMON_ENZYMES)
sseq = reference.seq
post_seq_start = start - 100 if start - 100 > 0 else 0
prev_seq = sseq[post_seq_start: start - 1]
post_seq = sseq[end: end + 100]
seq1 = prev_seq + allele1 + post_seq
seq2 = prev_seq + allele2 + post_seq
anal1 = Analysis(restriction_batch, seq1, linear=True)
enzymes1 = set(anal1.with_sites().keys())
anal1 = Analysis(restriction_batch, seq2, linear=True)
enzymes2 = set(anal1.with_sites().keys())
enzymes = set(enzymes1).symmetric_difference(set(enzymes2))
return enzymes
def fragment(args):
"""
%prog fragment fastafile enzyme
Cut the fastafile using the specified enzyme, and grab upstream and
downstream nucleotide sequence along with the cut site. In this case, the
sequences extracted are:
|- PstI
============|===========
(-------)
Sometimes we need to limit the size of the restriction fragments, for
example the GBS protocol does not allow fragments larger than 800bp.
|-PstI |- PstI |- PstI
~~~====|=============|==========~~~~~~~===|============
(---) (---)
In this case, the second fragment is longer than 800bp, therefore the two
ends are NOT extracted, as in the first fragment.
"""
p = OptionParser(fragment.__doc__)
p.add_option(
"--flank",
default=150,
type="int",
help="Extract flanking bases of the cut sites",
)
p.add_option(
"--full",
default=False,
action="store_true",
help="The full extraction mode",
)
opts, args = p.parse_args(args)
if len(args) != 2:
sys.exit(not p.print_help())
fastafile, enzyme = args
flank = opts.flank
assert flank > 0
extract = extract_full if opts.full else extract_ends
tag = "full" if opts.full else "ends"
assert enzyme in set(str(x) for x in AllEnzymes)
fragfastafile = fastafile.split(".")[0] + ".{0}.flank{1}.{2}.fasta".format(
enzyme, flank, tag
)
enzyme = [x for x in AllEnzymes if str(x) == enzyme][0]
f = Fasta(fastafile, lazy=True)
fw = open(fragfastafile, "w")
for name, rec in f.iteritems_ordered():
a = Analysis([enzyme], rec.seq)
sites = a.full()[enzyme]
extract(rec, sites, flank, fw)
logging.debug("Fragments written to `{0}`.".format(fragfastafile))
def fragment(args):
"""
%prog fragment fastafile enzyme
Cut the fastafile using the specified enzyme, and grab upstream and
downstream nucleotide sequence along with the cut site. In this case, the
sequences extracted are:
|- PstI
============|===========
(-------)
Sometimes we need to limit the size of the restriction fragments, for
example the GBS protocol does not allow fragments larger than 800bp.
|-PstI |- PstI |- PstI
~~~====|=============|==========~~~~~~~===|============
(---) (---)
In this case, the second fragment is longer than 800bp, therefore the two
ends are NOT extracted, as in the first fragment.
"""
p = OptionParser(fragment.__doc__)
p.add_option("--flank", default=150, type="int",
help="Extract flanking bases of the cut sites [default: %default]")
p.add_option("--full", default=False, action="store_true",
help="The full extraction mode [default: %default]")
opts, args = p.parse_args(args)
if len(args) != 2:
sys.exit(not p.print_help())
fastafile, enzyme = args
flank = opts.flank
assert flank > 0
extract = extract_full if opts.full else extract_ends
tag = "full" if opts.full else "ends"
assert enzyme in set(str(x) for x in AllEnzymes)
fragfastafile = fastafile.split(".")[0] + \
".{0}.flank{1}.{2}.fasta".format(enzyme, flank, tag)
enzyme = [x for x in AllEnzymes if str(x) == enzyme][0]
f = Fasta(fastafile, lazy=True)
fw = open(fragfastafile, "w")
for name, rec in f.iteritems_ordered():
a = Analysis([enzyme], rec.seq)
sites = a.full()[enzyme]
extract(rec, sites, flank, fw)
logging.debug("Fragments written to `{0}`.".format(fragfastafile))