def disambiguateaa(input, output):
"""Replace IUPAC ambiguous amino acids with unambiguous ones
Specifically, make the following replacements:
B => DN
X => ACDEFGHIKLMNPQRSTVWY
Z => EQ
J => LI,
U => C (selenocysteine)
O => K (pyrrolysine)
If there are multiple possible replacements, this operation will output a
sequence for each possible option. Use caution with sequences that are
highly ambiguous (e.g., with many Xs), as in this case a single sequence
could lead to an explosion in the output.
INPUT and OUTPUT are paths to fasta files or "-" to specify STDIN/STDOUT.
"""
for (name, ambig, qual) in readfq(input):
n = num_disambiguated_iupac_aa(ambig)
digits = floor(log10(n)) + 1
fmt = f"{name}|disambig_{{:0{digits}d}}"
for (i, unambig) in enumerate(disambiguate_iupac_aa(ambig)):
if n > 1:
name = fmt.format(i + 1)
print(f">{name}\n{unambig}", file=output)
def test_O(self):
ambig = Seq("AAOAA")
disambig = {str(p) for p in disambiguate_iupac_aa(ambig)}
assert disambig == {"AAKAA"}
def test_adjacent_ambig(self):
ambig = Seq("AAJJAA")
# map to str here bc of annoying biopython warning when hashing a Seq
proteins = set(map(str, disambiguate_iupac_aa(ambig)))
assert len(proteins) == 4
assert proteins == {"AALLAA", "AALIAA", "AAILAA", "AAIIAA"}
def test_Z(self):
ambig = Seq("AAZAA")
disambig = {str(p) for p in disambiguate_iupac_aa(ambig)}
assert disambig == {"AAEAA", "AAQAA"}
def test_J(self):
ambig = Seq("AAJAA")
disambig = {str(p) for p in disambiguate_iupac_aa(ambig)}
assert disambig == {"AALAA", "AAIAA"}
def test_X(self):
ambig = Seq("AAXAA")
disambig = {str(p) for p in disambiguate_iupac_aa(ambig)}
assert disambig == {"AA{}AA".format(aa) for aa in all_aa_protein_seq}
def test_B(self):
ambig = Seq("AABAA")
disambig = {str(p) for p in disambiguate_iupac_aa(ambig)}
assert disambig == {"AADAA", "AANAA"}
def test_unambig(self):
proteins = list(disambiguate_iupac_aa(all_aa_protein_seq))
assert len(proteins) == 1
assert proteins[0] == all_aa_protein_seq
def test_adjacent_ambig(self):
ambig = Seq("AAJJAA", protein)
proteins = set(disambiguate_iupac_aa(ambig))
assert len(proteins) == 4
assert proteins == {"AALLAA", "AALIAA", "AAILAA", "AAIIAA"}
def test_U(self):
ambig = Seq("AAUAA", protein)
disambig = {str(p) for p in disambiguate_iupac_aa(ambig)}
assert disambig == {"AACAA"}
