def setUp(self):
aligner = PairwiseAligner()
aligner.internal_open_gap_score = -1
aligner.internal_extend_gap_score = -0.0
aligner.match_score = +1
aligner.mismatch_score = -1
aligner.mode = "local"
self.aligner = aligner
def bioPython_default_local_aligner(a, b):
aligner = PairwiseAligner()
aligner.mode = 'local'
aligner.match_score = 2
aligner.mismatch_score = -3
aligner.open_gap_score = -7
aligner.extend_gap_score = -2
sequence1 = SeqIO.read('./resource/fasta' + str(a) + '.fasta', 'fasta')
sequence2 = SeqIO.read('./resource/fasta' + str(b) + '.fasta', 'fasta')
alignments = aligner.align(sequence1.seq, sequence2.seq)
def nw_bio(seq1, seq2, cost_table):
aligner = PairwiseAligner(alphabet=list(set(seq1 + seq2)))
aligner.match_score = cost_table[0]
aligner.mismatch_score = cost_table[1]
aligner.gap_score = cost_table[2]
alignments = aligner.align(seq1, seq2)
formated_alignments = []
for i in range(len(alignments)):
als = str(alignments[i]).split("\n")
formated_alignments.append([als[0], als[2], int(alignments[i].score)])
return formated_alignments
def create_aligner() -> PairwiseAligner:
"""
Creates an aligner that can be used to search for proteins.
"""
aligner = PairwiseAligner(mode="local")
# By default we want matches and penalize mismatches.
aligner.mismatch_score = -1
aligner.match_score = 1
# left or right gaps shouldn't count negatively due to the local search.
aligner.query_left_gap_score = 0
aligner.query_right_gap_score = 0
aligner.target_right_gap_score = 0
aligner.target_left_gap_score = 0
# Gaps in the middle should count negatively to narrow down the search space.
aligner.query_internal_gap_score = -1
aligner.target_internal_gap_score = -1
return aligner
def perform_randomized_tests(n=1000):
"""Perform randomized tests and compare to pslMap.
Run this function to perform 8 x n mappings for alignments of randomly
generated sequences, get the alignment in PSL format, and compare the
result to that of pslMap.
"""
aligner = PairwiseAligner()
aligner.internal_open_gap_score = -1
aligner.internal_extend_gap_score = -0.0
aligner.match_score = +1
aligner.mismatch_score = -1
aligner.mode = "local"
for i in range(n):
nBlocks1 = random.randint(1, 10)
nBlocks2 = random.randint(1, 10)
test_random(aligner, nBlocks1, nBlocks2, "+", "+")
test_random(aligner, nBlocks1, nBlocks2, "+", "-")
test_random(aligner, nBlocks1, nBlocks2, "-", "+")
test_random(aligner, nBlocks1, nBlocks2, "-", "-")
test_random_sequences("+", "+")
test_random_sequences("+", "-")
test_random_sequences("-", "+")
test_random_sequences("-", "-")
type=str,
required=True)
parser.add_argument('-r',
'--reference',
help='Reference to be aligned to',
type=str,
required=True)
parser.add_argument('-n',
'--seq_name',
help='Name of the aligned sequence',
type=str,
required=True)
args = parser.parse_args()
aligner = PairwiseAligner()
aligner.mode = 'global'
aligner.match_score = 1
aligner.mismatch_score = 0
aligner.open_gap_score = -2
aligner.extend_gap_score = -1
ref = SeqIO.read(args.reference, "fasta")
ref.seq = str(ref.seq.upper()).replace('-', 'N')
cons = SeqIO.read(args.infile, "fasta")
aln = aligner.align(ref.seq, cons.seq)
with open(args.outfile, 'w') as out:
print(">", args.seq_name, file=out)
print(str(aln[0]).strip().split('\n')[2], file=out)