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)
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)
parser = argparse.ArgumentParser(description='Computes a pairwise similarity matrix from a fasta file.')
parser.add_argument('-f',help='name of the fasta file',required=True)
parser.add_argument('-s',help='name of subsitution matrix from BioPython',required=True,choices=MatrixInfo.available_matrices)
parser.add_argument('-go',help='gap opening score',type=float,required=True)
parser.add_argument('-ge',help='gap extension score',type=float,required=True)
args = parser.parse_args()
# Parse fasta file #
seqs = list(SeqIO.parse(args.f,'fasta'))
# Get substitution matrix
substitution_matrix = getattr(MatrixInfo,args.s)
#Pairwise alignment
aligner = PairwiseAligner()
aligner.open_gap_score, aligner.extend_gap_score = args.go, args.ge
aligner.substitution_matrix = substitution_matrix
# Align sequences and build matrix
def similarity_matrix(seqs,n=len(seqs)):
similarity_matrix = np.zeros([n,n])
for i in range(len(seqs)):
for j in range(len(seqs)):
alignment = aligner.align(seqs[i].seq,seqs[j].seq)
similarity_matrix[i][j] = alignment.score
return similarity_matrix
m = similarity_matrix(seqs)
def print_matrix(m):
for i in m:
aligners['global'].substitution_matrix = sub_matrix
if not args.open_gap_score:
args.open_gap_score = -11
if not args.extend_gap_score:
args.extend_gap_score = -1
aligners['global'].open_gap_score = args.open_gap_score
aligners['global'].extend_gap_score = args.extend_gap_score
if args.sim_algo == 'smith-waterman':
aligners['local'] = PairwiseAligner()
aligners['local'].mode = 'local'
if args.seq_type in ('dna', 'rna'):
aligners['local'].match = args.match_score
aligners['local'].mismatch = args.mismatch_score
else:
aligners['local'].substitution_matrix = sub_matrix
aligners['local'].open_gap_score = args.open_gap_score
aligners['local'].extend_gap_score = args.extend_gap_score
# Karlin-Altschul parameter values
if args.seq_type in ('dna', 'rna'):
if ((args.match_score, args.mismatch_score) in KA_PARAMS['na']
and (abs(args.open_gap_score), abs(args.extend_gap_score))
in KA_PARAMS['na'][(args.match_score, args.mismatch_score)]):
args.ka_gapped_l = KA_PARAMS['na'][(args.match_score,
args.mismatch_score)][(
abs(args.open_gap_score),
abs(args.extend_gap_score))][0]
args.ka_gapped_k = KA_PARAMS['na'][(args.match_score,
args.mismatch_score)][(
abs(args.open_gap_score),
abs(args.extend_gap_score))][1]