def test_standard_code_lookup(self):
"""genetic_code should hold codes keyed by id as string and number"""
sgc_new = GeneticCode(*self.ncbi_standard)
sgc_number = genetic_code(1)
sgc_string = genetic_code("1")
sgc_empty = genetic_code()
for sgc in sgc_new, sgc_number, sgc_string, sgc_empty:
self.assertEqual(sgc.code_sequence, "FFLLSSSSYY**CC*WLLLLPPPPHHQQR" "RRRIIIMTTTTNNKKSSRRVVVVAAAADDEEGGGG")
self.assertEqual(
sgc.start_codon_sequence, "---M---------------M--" "-------------M----------------------------"
)
self.assertEqual(sgc.start_codons, {"TTG": "M", "CTG": "M", "ATG": "M"})
self.assertEqual(sgc.id, 1)
self.assertEqual(sgc.name, "Standard Nuclear")
self.assertEqual(sgc["TTT"], "F")
self.assertEqual(sgc.is_start("ATG"), True)
self.assertEqual(sgc.is_start("AAA"), False)
self.assertEqual(sgc.is_stop("TAA"), True)
self.assertEqual(sgc.is_stop("AAA"), False)
mtgc = genetic_code(2)
self.assertEqual(mtgc.name, "Vertebrate Mitochondrial")
self.assertEqual(mtgc.is_start("AUU"), True)
self.assertEqual(mtgc.is_stop("UGA"), False)
self.assertEqual(sgc_new.changes(mtgc), {"AGA": "R*", "AGG": "R*", "ATA": "IM", "TGA": "*W"})
self.assertEqual(mtgc.changes(sgc_new), {"AGA": "*R", "AGG": "*R", "ATA": "MI", "TGA": "W*"})
self.assertEqual(mtgc.changes(mtgc), {})
self.assertEqual(
mtgc.changes("FFLLSSSSYY**CC*WLLLLPPPPHHQQRRRRIIIMTTT" "TNNKKSSRRVVVVAAAADDEEGGGG"),
{"AGA": "*R", "AGG": "*R", "ATA": "MI", "TGA": "W*"},
)
def test_standard_code_lookup(self):
"""genetic_code should hold codes keyed by id as string and number"""
sgc_new = GeneticCode(*self.ncbi_standard)
sgc_number = genetic_code(1)
sgc_string = genetic_code('1')
sgc_empty = genetic_code()
for sgc in sgc_new, sgc_number, sgc_string, sgc_empty:
self.assertEqual(sgc.code_sequence, 'FFLLSSSSYY**CC*WLLLLPPPPHHQQR'
'RRRIIIMTTTTNNKKSSRRVVVVAAAADDEEGGGG')
self.assertEqual(sgc.start_codon_sequence, '---M---------------M--'
'-------------M----------------------------')
self.assertEqual(
sgc.start_codons, {'TTG': 'M', 'CTG': 'M', 'ATG': 'M'})
self.assertEqual(sgc.id, 1)
self.assertEqual(sgc.name, 'Standard Nuclear')
self.assertEqual(sgc['TTT'], 'F')
self.assertEqual(sgc.is_start('ATG'), True)
self.assertEqual(sgc.is_start('AAA'), False)
self.assertEqual(sgc.is_stop('TAA'), True)
self.assertEqual(sgc.is_stop('AAA'), False)
mtgc = genetic_code(2)
self.assertEqual(mtgc.name, 'Vertebrate Mitochondrial')
self.assertEqual(mtgc.is_start('AUU'), True)
self.assertEqual(mtgc.is_stop('UGA'), False)
self.assertEqual(sgc_new.changes(mtgc), {'AGA': 'R*', 'AGG': 'R*',
'ATA': 'IM', 'TGA': '*W'})
self.assertEqual(mtgc.changes(sgc_new), {'AGA': '*R', 'AGG': '*R',
'ATA': 'MI', 'TGA': 'W*'})
self.assertEqual(mtgc.changes(mtgc), {})
self.assertEqual(mtgc.changes('FFLLSSSSYY**CC*WLLLLPPPPHHQQRRRRIIIMTTT'
'TNNKKSSRRVVVVAAAADDEEGGGG'), {'AGA': '*R',
'AGG': '*R', 'ATA': 'MI', 'TGA': 'W*'})
def test_standard_code_lookup(self):
"""genetic_code should hold codes keyed by id as string and number"""
sgc_new = GeneticCode(*self.ncbi_standard)
sgc_number = genetic_code(1)
sgc_string = genetic_code('1')
sgc_empty = genetic_code()
for sgc in sgc_new, sgc_number, sgc_string, sgc_empty:
self.assertEqual(
sgc.code_sequence, 'FFLLSSSSYY**CC*WLLLLPPPPHHQQR'
'RRRIIIMTTTTNNKKSSRRVVVVAAAADDEEGGGG')
self.assertEqual(
sgc.start_codon_sequence, '---M---------------M--'
'-------------M----------------------------')
self.assertEqual(sgc.start_codons, {
'TTG': 'M',
'CTG': 'M',
'ATG': 'M'
})
self.assertEqual(sgc.id, 1)
self.assertEqual(sgc.name, 'Standard Nuclear')
self.assertEqual(sgc['TTT'], 'F')
self.assertEqual(sgc.is_start('ATG'), True)
self.assertEqual(sgc.is_start('AAA'), False)
self.assertEqual(sgc.is_stop('TAA'), True)
self.assertEqual(sgc.is_stop('AAA'), False)
mtgc = genetic_code(2)
self.assertEqual(mtgc.name, 'Vertebrate Mitochondrial')
self.assertEqual(mtgc.is_start('AUU'), True)
self.assertEqual(mtgc.is_stop('UGA'), False)
self.assertEqual(sgc_new.changes(mtgc), {
'AGA': 'R*',
'AGG': 'R*',
'ATA': 'IM',
'TGA': '*W'
})
self.assertEqual(mtgc.changes(sgc_new), {
'AGA': '*R',
'AGG': '*R',
'ATA': 'MI',
'TGA': 'W*'
})
self.assertEqual(mtgc.changes(mtgc), {})
self.assertEqual(
mtgc.changes('FFLLSSSSYY**CC*WLLLLPPPPHHQQRRRRIIIMTTT'
'TNNKKSSRRVVVVAAAADDEEGGGG'), {
'AGA': '*R',
'AGG': '*R',
'ATA': 'MI',
'TGA': 'W*'
})
def two_dna_point_mutants_to_aa(wt_sequence):
"""
wt_sequence (string) DNA sequence
assumes starting from correct reading frame
"""
AA_sequences = set()
orig_code = genetic_code(11)
AA_sequences.add(orig_code.translate(wt_sequence).sequence)
for k1, char1 in enumerate(wt_sequence[:-1]):
for k2, char2 in enumerate(wt_sequence[k1+1:]):
for mutant1 in ['A','C','G','U']:
if mutant1 == char1:
continue
for mutant2 in ['A','C','G','U']:
if k1 == 0:
if k2 < len(wt_sequence):
this_dna_string = ""+mutant1+wt_sequence[k1+1:k2]+mutant2+wt_sequence[k2+1:]
else:
this_dna_string = ""+mutant1+wt_sequence[k1+1:k2]+mutant2
if k1 > 0 and k1 < len(wt_sequence)-1:
if k2 < len(wt_sequence):
this_dna_string = ""+wt_sequence[0:k1]+mutant1+wt_sequence[k1+1:k2]+mutant2+wt_sequence[k2+1:]
else:
this_dna_string = ""+wt_sequence[0:k1]+mutant1+wt_sequence[k1+1:k2]+mutant2
if k1 == len(wt_sequence)-1:
this_dna_string = ""+wt_sequence[0:k1]+mutant1+mutant2
this_sequence = orig_code.translate(this_dna_string).sequence
if '*' in this_sequence[:-1]:
continue
else:
AA_sequences.add(this_sequence)
return AA_sequences
def all_dna_point_mutants_to_aa(wt_sequence):
"""
wt_sequence (string) DNA sequence
assumes starting from correct reading frame
"""
AA_sequences = set()
orig_code = genetic_code(11)
AA_sequences.add(orig_code.translate(wt_sequence).sequence)
for k, char in enumerate(wt_sequence):
for mutant in ['A','C','G','U']:
if mutant == char:
continue
if k == 0:
this_dna_string = ""+mutant+wt_sequence[k+1:]
if k > 0 and k < len(wt_sequence):
this_dna_string = ""+wt_sequence[0:k]+mutant+wt_sequence[k+1:]
if k == len(wt_sequence):
this_dna_string = ""+wt_sequence[0:k]+mutant
this_sequence = orig_code.translate(this_dna_string).sequence
if '*' in this_sequence[:-1]:
continue
else:
AA_sequences.add(this_sequence)
return AA_sequences
def dna_to_aa(sequence, try_frames=False):
"""
Translates from the input DNA nucleotide sequence to amino acid sequence
Arguments:
----------
sequence : str
DNA nucleotide sequence
Optional:
---------
try_frames : Bool
if True, tries 6 possible reading frames, translates all to amino
acids and chooses sequence with fewest stop codons
default = False
Returns:
--------
aa_sequence : str
sequence of one-letter amino acid codes
"""
orig_code = genetic_code(11)
if not try_frames:
return orig_code.translate(sequence).sequence
sequence = DNASequence(sequence)
translated = orig_code.translate_six_frames(sequence)
stops = [aastring.sequence.count('*') for aastring in translated]
return translated[stops.index(min(stops))].sequence
def two_dna_point_mutants_to_aa(wt_sequence):
"""
Finds all potential sequences which can be achieved by making 2 nucleotide
mutations and translating to amino acid sequence
Ignores mutations that lead to nonsense instead of missense mutations
Assumes wt_sequence starts on the correct reading frame
Makes double mutants via nested loops through each nucleotide in the sequence twice,
is therefore VERY SLOW
Arguments:
----------
wt_sequence : str
DNA nucleotide sequence
Returns:
--------
AA_sequences : set of str
each str is a unique sequence of one-letter amino acid codes
"""
AA_sequences = set()
orig_code = genetic_code(11)
AA_sequences.add(orig_code.translate(wt_sequence).sequence)
for k1, char1 in enumerate(wt_sequence[:-1]):
for k2, char2 in enumerate(wt_sequence[k1 + 1:]):
for mutant1 in ['A', 'C', 'G', 'U']:
if mutant1 == char1:
continue
for mutant2 in ['A', 'C', 'G', 'U']:
if k1 == 0:
if k2 < len(wt_sequence):
this_dna_string = "" + mutant1 + wt_sequence[
k1 + 1:k2] + mutant2 + wt_sequence[k2 + 1:]
else:
this_dna_string = "" + mutant1 + wt_sequence[
k1 + 1:k2] + mutant2
if k1 > 0 and k1 < len(wt_sequence) - 1:
if k2 < len(wt_sequence):
this_dna_string = "" + wt_sequence[
0:k1] + mutant1 + wt_sequence[
k1 + 1:k2] + mutant2 + wt_sequence[k2 + 1:]
else:
this_dna_string = "" + wt_sequence[
0:k1] + mutant1 + wt_sequence[k1 +
1:k2] + mutant2
if k1 == len(wt_sequence) - 1:
this_dna_string = "" + wt_sequence[
0:k1] + mutant1 + mutant2
this_sequence = orig_code.translate(
this_dna_string).sequence
if '*' in this_sequence[:-1]:
continue
else:
AA_sequences.add(this_sequence)
return AA_sequences
def make_single_mutant(sequence,wt_res,res_num,mut_res,first_res=1):
"""
sequence (string) DNA sequence
wt_res (char) single letter amino acid code of wildtype residue to be mutated
res_num (int) residue id number of residue to be mutated
mut_res (char) single letter amino acid code of mutant residue
first_res (int) residue id number of first residue in sequence (default = 1)
DNA sequence needs to start with the first residue of the protein (no promoter, etc)
take DNA sequence, convert to AA, define AA point mutant, find corresponding codon of wt and mut, output forward and reverse primers
DNA sequence should be only the kinase domain
Desired mutation must require only a single nucleotide change
"""
orig_code = genetic_code(11)
sequence = sequence.upper()
aa_sequence = orig_code.translate(sequence).sequence
if not str(wt_res) == aa_sequence[res_num-first_res]:
raise IOError("Desired residue not found -- check wildtype residue name and id, and first residue id")
# start of codon of residue of interest is at (res_num - first_res)*3
wt_codon = DNASequence(sequence[(res_num - first_res)*3:(res_num - first_res)*3+3])
mut_codons = orig_code.synonyms[mut_res]
mut_codon = None
for codon in mut_codons:
if wt_codon.distance(DNASequence(codon))*3 == 1:
mut_codon = codon
if not mut_codon:
print("Cannot make desired mutant with a single base change")
mut_codon = make_mutant(wt_codon, mut_codons)
good_melting_temp = False
start_ix = max(0,(res_num-first_res)*3-11)
end_ix = min(len(sequence),(res_num+1-first_res)*3+11)
while not good_melting_temp:
if end_ix - start_ix > 45:
print("Acceptable melting temp was not found")
break
forward_primer = sequence[start_ix:(res_num - first_res)*3]+mut_codon+sequence[(res_num+1 - first_res)*3:end_ix]
forward_primer = forward_primer.lower()
good_melting_temp, start_ix, end_ix = check_melting_temp(forward_primer, start_ix, end_ix, len(sequence))
forward_sequence = DNASequence(forward_primer)
reverse_sequence = forward_sequence.rc()
reverse_primer = reverse_sequence.sequence
return forward_primer, reverse_primer
def dna_to_aa(sequence, try_frames=False):
"""
sequence (string) DNA sequence
will search for correct reading frame
"""
orig_code = genetic_code(11)
if not try_frames:
return orig_code.translate(sequence).sequence
sequence = DNASequence(sequence)
translated = orig_code.translate_six_frames(sequence)
stops = [aastring.sequence.count('*') for aastring in translated]
return translated[stops.index(min(stops))].sequence
def __init__(self, sequence, first_res=1):
"""
Arguments:
----------
sequence : str
original DNA nucleotide sequence, treated as wild type
first_res : int
residue id number of first residue in sequence (default = 1)
"""
orig_code = genetic_code(11)
sequence = sequence.upper()
aa_sequence = orig_code.translate(sequence).sequence
self.sequence = sequence
self.aa_sequence = aa_sequence
self.first_res = first_res
self.orig_code = orig_code
return
def all_dna_point_mutants_to_aa(wt_sequence):
"""
Finds all potential sequences which can be achieved by making a single nucleotide
mutation and translating to amino acid sequence
Ignores mutations that lead to nonsense instead of missense mutations
Assumes wt_sequence starts on the correct reading frame
Arguments:
----------
wt_sequence : str
DNA nucleotide sequence
Returns:
--------
AA_sequences : set of str
each str is a unique sequence of one-letter amino acid codes
"""
AA_sequences = set()
orig_code = genetic_code(11)
AA_sequences.add(orig_code.translate(wt_sequence).sequence)
for k, char in enumerate(wt_sequence):
for mutant in ['A', 'C', 'G', 'U']:
if mutant == char:
continue
if k == 0:
this_dna_string = "" + mutant + wt_sequence[k + 1:]
if k > 0 and k < len(wt_sequence):
this_dna_string = "" + wt_sequence[0:k] + mutant + wt_sequence[
k + 1:]
if k == len(wt_sequence):
this_dna_string = "" + wt_sequence[0:k] + mutant
this_sequence = orig_code.translate(this_dna_string).sequence
if '*' in this_sequence[:-1]:
continue
else:
AA_sequences.add(this_sequence)
return AA_sequences
def test_genetic_code_with_invalid_id(self):
with self.assertRaises(ValueError):
genetic_code(30)
def test_genetic_code_with_too_many_args(self):
with self.assertRaises(TypeError):
genetic_code(1, 2)
def test_genetic_code_with_invalid_id(self):
with self.assertRaises(ValueError):
genetic_code(30)
def test_genetic_code_with_too_many_args(self):
with self.assertRaises(TypeError):
genetic_code(1, 2)
