comparison tools/seq_primer_clip/seq_primer_clip.py @ 6:b9dc7c967ee6 draft default tip

v0.0.16 Python 3 compatible print function

5:530c8d6fedd8

"""

import re
import sys

from galaxy_utils.sequence.fasta import fastaReader, fastaWriter
from galaxy_utils.sequence.fastq import fastqReader, fastqWriter

if "-v" in sys.argv or "--version" in sys.argv:
    print "v0.0.12"
    sys.exit(0)

try:
    from Bio.Seq import reverse_complement
    from Bio.SeqIO.SffIO import SffIterator, SffWriter
except ImportError:

    else:
        ambiguous_dna_re[letter] = "[%s]" % values


def make_reg_ex(seq):
    return "".join(ambiguous_dna_re[letter] for letter in seq)


def make_reg_ex_mm(seq, mm):
    if mm > 2:
        raise NotImplementedError("At most 2 mismatches allowed!")
    seq = seq.upper()
    yield make_reg_ex(seq)
    for i in range(1, mm + 1):

                                                  % (pattern, len(pattern), seq, len(seq)))
                yield make_reg_ex(pattern)


def load_primers_as_re(primer_fasta, mm, rc=False):
    # Read primer file and record all specified sequences
    primers = set()
    in_handle = open(primer_fasta, "rU")
    reader = fastaReader(in_handle)
    count = 0
    for record in reader:

    return count, re.compile("|".join(primers))  # make one monster re!


# Read primer file and record all specified sequences
count, primer = load_primers_as_re(primer_fasta, mm, rc)
print "%i primer sequences" % count

short_neg = 0
short_clipped = 0
clipped = 0
negs = 0

else:
    sys.exit("Unsupported file type %r" % seq_format)
in_handle.close()
out_handle.close()

print "Kept %i clipped reads," % clipped
print "discarded %i short." % short_clipped
if keep_negatives:
    print "Kept %i non-matching reads," % negs
    print "discarded %i short." % short_neg

6:b9dc7c967ee6

"""

import re
import sys

if "-v" in sys.argv or "--version" in sys.argv:
    print("v0.0.16")
    sys.exit(0)

from galaxy_utils.sequence.fasta import fastaReader, fastaWriter
from galaxy_utils.sequence.fastq import fastqReader, fastqWriter

try:
    from Bio.Seq import reverse_complement
    from Bio.SeqIO.SffIO import SffIterator, SffWriter
except ImportError:

    else:
        ambiguous_dna_re[letter] = "[%s]" % values


def make_reg_ex(seq):
    """Make regular expression for ambiguous DNA."""
    return "".join(ambiguous_dna_re[letter] for letter in seq)


def make_reg_ex_mm(seq, mm):
    """Make regular expression for mis-matches."""
    if mm > 2:
        raise NotImplementedError("At most 2 mismatches allowed!")
    seq = seq.upper()
    yield make_reg_ex(seq)
    for i in range(1, mm + 1):

                                                  % (pattern, len(pattern), seq, len(seq)))
                yield make_reg_ex(pattern)


def load_primers_as_re(primer_fasta, mm, rc=False):
    """Load primers as regular expressions.

    Read primer file and record all specified sequences.
    """
    primers = set()
    in_handle = open(primer_fasta, "rU")
    reader = fastaReader(in_handle)
    count = 0
    for record in reader:

    return count, re.compile("|".join(primers))  # make one monster re!


# Read primer file and record all specified sequences
count, primer = load_primers_as_re(primer_fasta, mm, rc)
print("%i primer sequences" % count)

short_neg = 0
short_clipped = 0
clipped = 0
negs = 0

else:
    sys.exit("Unsupported file type %r" % seq_format)
in_handle.close()
out_handle.close()

print("Kept %i clipped reads," % clipped)
print("discarded %i short." % short_clipped)
if keep_negatives:
    print("Kept %i non-matching reads," % negs)
    print("discarded %i short." % short_neg)