def test_reverse_complements(self):
"""Test double reverse complement preserves the sequence."""
sorted_amb_rna = sorted(ambiguous_rna_values)
sorted_amb_dna = sorted(ambiguous_dna_values)
for sequence in [
Seq.Seq("".join(sorted_amb_rna)),
Seq.Seq("".join(sorted_amb_dna)),
Seq.Seq("".join(sorted_amb_rna), Alphabet.generic_rna),
Seq.Seq("".join(sorted_amb_dna), Alphabet.generic_dna),
Seq.Seq("".join(sorted_amb_rna).replace("X", ""),
IUPAC.IUPACAmbiguousRNA()),
Seq.Seq("".join(sorted_amb_dna).replace("X", ""),
IUPAC.IUPACAmbiguousDNA()),
Seq.Seq("AWGAARCKG"),
]: # Note no U or T
reversed_sequence = sequence.reverse_complement()
self.assertEqual(str(sequence),
str(reversed_sequence.reverse_complement()))
def setUp(self):
self.test_seqs = [
Seq.Seq("TCAAAAGGATGCATCATG", IUPAC.unambiguous_dna),
Seq.Seq("ATGAAACTG"),
Seq.Seq("ATGAARCTG"),
Seq.Seq("AWGAARCKG"), # Note no U or T
Seq.Seq("".join(ambiguous_rna_values)),
Seq.Seq("".join(ambiguous_dna_values)),
Seq.Seq("".join(ambiguous_rna_values), Alphabet.generic_rna),
Seq.Seq("".join(ambiguous_dna_values), Alphabet.generic_dna),
Seq.Seq("".join(ambiguous_rna_values), IUPAC.IUPACAmbiguousRNA()),
Seq.Seq("".join(ambiguous_dna_values), IUPAC.IUPACAmbiguousDNA()),
Seq.Seq("AWGAARCKG", Alphabet.generic_dna),
Seq.Seq("AUGAAACUG", Alphabet.generic_rna),
Seq.Seq("ATGAAACTG", IUPAC.unambiguous_dna),
Seq.Seq("ATGAAACTGWN", IUPAC.ambiguous_dna),
Seq.Seq("AUGAAACUG", Alphabet.generic_rna),
Seq.Seq("AUGAAACUG", IUPAC.unambiguous_rna),
Seq.Seq("AUGAAACUGWN", IUPAC.ambiguous_rna),
Seq.Seq("ATGAAACTG", Alphabet.generic_nucleotide),
Seq.MutableSeq("ATGAAACTG", Alphabet.generic_dna),
Seq.MutableSeq("AUGaaaCUG", IUPAC.unambiguous_rna),
]
compl_values = complement(values).replace(
"T", "U") # need to help as no alphabet
print "%s={%s} --> {%s}=%s" % \
(ambig_char, values, compl_values, ambiguous_rna_complement[ambig_char])
assert set(compl_values) == set(
ambiguous_rna_values[ambiguous_rna_complement[ambig_char]])
print
print "Reverse complements:"
for sequence in [
Seq.Seq("".join(sorted(ambiguous_rna_values))),
Seq.Seq("".join(sorted(ambiguous_dna_values))),
Seq.Seq("".join(sorted(ambiguous_rna_values)), Alphabet.generic_rna),
Seq.Seq("".join(sorted(ambiguous_dna_values)), Alphabet.generic_dna),
Seq.Seq("".join(sorted(ambiguous_rna_values)).replace("X", ""),
IUPAC.IUPACAmbiguousRNA()),
Seq.Seq("".join(sorted(ambiguous_dna_values)).replace("X", ""),
IUPAC.IUPACAmbiguousDNA()),
Seq.Seq("AWGAARCKG")
]: # Note no U or T
print "%s -> %s" \
% (repr(sequence), repr(Seq.reverse_complement(sequence)))
assert str(sequence) \
== str(Seq.reverse_complement(Seq.reverse_complement(sequence))), \
"Dobule reverse complement didn't preserve the sequence!"
print
###########################################################################
test_seqs = [
s,
ambiguous_rna_values,
)
from Bio.Data.CodonTable import TranslationError, standard_dna_table
from Bio.Seq import MutableSeq
test_seqs = [
Seq.Seq("TCAAAAGGATGCATCATG", IUPAC.unambiguous_dna),
Seq.Seq("T", IUPAC.ambiguous_dna),
Seq.Seq("ATGAAACTG"),
Seq.Seq("ATGAARCTG"),
Seq.Seq("AWGAARCKG"), # Note no U or T
Seq.Seq("".join(ambiguous_rna_values)),
Seq.Seq("".join(ambiguous_dna_values)),
Seq.Seq("".join(ambiguous_rna_values), Alphabet.generic_rna),
Seq.Seq("".join(ambiguous_dna_values), Alphabet.generic_dna),
Seq.Seq("".join(ambiguous_rna_values), IUPAC.IUPACAmbiguousRNA()),
Seq.Seq("".join(ambiguous_dna_values), IUPAC.IUPACAmbiguousDNA()),
Seq.Seq("AWGAARCKG", Alphabet.generic_dna),
Seq.Seq("AUGAAACUG", Alphabet.generic_rna),
Seq.Seq("ATGAAACTG", IUPAC.unambiguous_dna),
Seq.Seq("ATGAAA-CTG", Alphabet.generic_dna),
Seq.Seq("ATGAAACTGWN", IUPAC.ambiguous_dna),
Seq.Seq("AUGAAACUG", Alphabet.generic_rna),
Seq.Seq("AUGAAA==CUG", Alphabet.generic_rna),
Seq.Seq("AUGAAACUG", IUPAC.unambiguous_rna),
Seq.Seq("AUGAAACUGWN", IUPAC.ambiguous_rna),
Seq.Seq("ATGAAACTG", Alphabet.generic_nucleotide),
Seq.Seq("AUGAAACTG", Alphabet.generic_nucleotide), # U and T
Seq.MutableSeq("ATGAAACTG", Alphabet.generic_dna),
Seq.MutableSeq("AUGaaaCUG", IUPAC.unambiguous_rna),
Seq.Seq("ACTGTCGTCT", Alphabet.generic_protein),
print
print "RNA Ambiguity mapping:", sorted_dict(ambiguous_rna_values)
print "RNA Complement mapping:", sorted_dict(ambiguous_rna_complement)
for ambig_char, values in sorted(ambiguous_rna_values.iteritems()):
compl_values = complement(values).replace("T","U") # need to help as no alphabet
print("%s={%s} --> {%s}=%s" % \
(ambig_char, values, compl_values, ambiguous_rna_complement[ambig_char]))
assert set(compl_values) == set(ambiguous_rna_values[ambiguous_rna_complement[ambig_char]])
print
print("Reverse complements:")
for sequence in [Seq.Seq("".join(sorted(ambiguous_rna_values))),
Seq.Seq("".join(sorted(ambiguous_dna_values))),
Seq.Seq("".join(sorted(ambiguous_rna_values)), Alphabet.generic_rna),
Seq.Seq("".join(sorted(ambiguous_dna_values)), Alphabet.generic_dna),
Seq.Seq("".join(sorted(ambiguous_rna_values)).replace("X",""), IUPAC.IUPACAmbiguousRNA()),
Seq.Seq("".join(sorted(ambiguous_dna_values)).replace("X",""), IUPAC.IUPACAmbiguousDNA()),
Seq.Seq("AWGAARCKG")]: # Note no U or T
print("%s -> %s" \
% (repr(sequence), repr(Seq.reverse_complement(sequence))))
assert str(sequence) \
== str(Seq.reverse_complement(Seq.reverse_complement(sequence))), \
"Dobule reverse complement didn't preserve the sequence!"
print
###########################################################################
test_seqs = [s,t,u,
Seq.Seq("ATGAAACTG"),
"ATGAAACtg",
#TODO - Fix ambiguous translation