def create_graphs(ext=1):
gs = []
g = []
for line in create_strings(ext=ext):
numbers = [int(s) for s in line.split(' ')]
if len(numbers) == 1:
pass
elif len(numbers) == 2:
if len(g) > 0:
gs.append(g)
g = [(numbers[0], numbers[1])]
else:
g.append((numbers[0], numbers[1], numbers[2]))
if len(g) > 0:
gs.append(g)
return gs
i, j, di, dj = moves[(i, j)]
if di == 0:
s1.append('-')
t1.append(t[j])
elif dj == 0:
s1.append(s[i])
t1.append('-')
else:
s1.append(s[i])
t1.append(t[j])
return score, s1[:-1][::-1], t1[:-1][::-1]
def ba5h(s, t):
d, s1, t1 = align([s0 for s0 in s], [t0 for t0 in t],
build_matrix=build_matrix,
backtrack=backtrack)
return (d, ''.join(s1), ''.join(t1))
if __name__ == '__main__':
import timeit
start_time = timeit.default_timer()
strings = create_strings(ext=1)
d, s1, t1 = ba5h(strings[0], strings[1])
print('Score = {0}'.format(d))
print(s1)
print(t1)
print('Elapsed Time = {0}'.format(timeit.default_timer() - start_time))
while i>0 and j>0:
index = argmax([0,
distances[i-1,j] - indel_cost,
distances[i,j-1] - indel_cost,
distances[i-1,j-1] + score(v[i-1],w[j-1])])
i1,j1 = [(0,j-1), (i-1,j), (i,j-1), (i-1,j-1)][index]
v1.append(v[i1] if i1<i else '-')
w1.append(w[j1] if j1<j else '-')
i,j = i1,j1
return sum(score(u,v) for u,v in zip(v1,w1)),v1[::-1],w1[::-1]
score,u1,v1=dynamic_programming([vv for vv in v],[ww for ww in w])
return score,''.join(u1),''.join(v1)
if __name__=='__main__':
from helpers import create_strings
#d,s1,t1 = oap('CTAAGGGATTCCGGTAATTAGACAG',
#'ATAGACCATATGTCAGTGACTGTGTAA')
start_time = time()
strings = create_strings('oap',fasta=1,ext=4)
d,s1,t1 = oap(strings[0],strings[1])
print ('{0}'.format(d))
print (s1)
print (t1)
print (time()-start_time)
with open('oap.txt','w') as o:
o.write('{0}\n'.format(d))
o.write('{0}\n'.format(s1))
o.write('{0}\n'.format(t1))
match_t = True
if match_s and match_t:
if gap > 0:
score -= (sigma + (gap - 1) * epsilon)
gap = 0
if (s[i], t[i]) in replace_score:
score += replace_score[(s[i], t[i])]
else:
score += replace_score[(t[i], s[i])]
if gap > 0:
score -= (sigma + (gap - 1) * epsilon)
return score
if __name__ == '__main__':
from helpers import create_strings
#score,s,t = gaff('PRTEINS','PRTWPSEIN')
strings = create_strings(fasta=True, ext=3)
#print (strings[0])
#print (strings[1])
score, s, t = gaff(strings[0], strings[1])
print(score, get_score(s, t))
print(s)
print(t)
with open('gaff.txt', 'w') as o:
o.write('{0}\n'.format(get_score(s, t)))
o.write('{0}\n'.format(s))
o.write('{0}\n'.format(t))
from graphs import gs
if __name__ == '__main__':
from helpers import create_strings
#graphs = [
#[(3, 2),
#(3 ,2),
#(2, 1)],
#[(3, 2),
#(3, 2),
#(1, 2)]
#]
graphs = []
edges = []
for s in create_strings(ext=2):
if len(s) == 0:
if len(edges) > 0:
graphs.append(edges)
edges = []
else:
values = [int(x) for x in s.split(" ")]
if len(values) > 1:
edges.append(values)
if len(edges) > 0:
graphs.append(edges)
print(' '.join([str(gs(edges)) for edges in graphs]))
from graphs import sc
if __name__ == '__main__':
from helpers import create_strings
#graphs = [
#2,
#[(3, 2),
#(3 ,2),
#(2, 1)],
#[(3, 2),
#(3, 2),
#(1, 2)]
#]
graphs = []
edges = []
for s in create_strings(ext=1):
if len(s) == 0:
if len(edges) > 0:
graphs.append(edges)
edges = []
else:
values = [int(x) for x in s.split(" ")]
if len(values) > 1:
edges.append(values)
if len(edges) > 0:
graphs.append(edges)
print(' '.join([str(sc(g)) for g in graphs]))
# BA5M.py Find a Highest-Scoring Multiple Sequence Alignment
from align import FindHighestScoringMultipleSequenceAlignment
if __name__=='__main__':
from helpers import create_strings
s,u,v,w = FindHighestScoringMultipleSequenceAlignment('ATATCCG','TCCGA','ATGTACTG')
print (s)
print (u)
print (v)
print (w)
s1,u1,v1,w1 = FindHighestScoringMultipleSequenceAlignment('TGTTTAAAAATGTCCGCAACCATTTC',
'GATATAAAACAGGGATAACTGCAATGG',
'CCTGCTACTTTATGCCGTCTCCATATGCG')
print (s1)
print (u1)
print (v1)
print (w1)
ss=create_strings(ext=3)
s2,u2,v2,w2 = FindHighestScoringMultipleSequenceAlignment(ss[0],ss[1],ss[2])
print (s2)
print (u2)
print (v2)
print (w2)
action='store_true',
help='process sample dataset')
parser.add_argument('--extra',
default=False,
action='store_true',
help='process extra dataset')
parser.add_argument('--rosalind',
default=False,
action='store_true',
help='process Rosalind dataset')
args = parser.parse_args()
if args.sample:
print(NumberPerfectMatchings('AGCUAGUCAU'))
if args.extra:
Input, Expected = read_strings('data/....txt', init=0)
...
if args.rosalind:
Input = create_strings(path='./data', fasta=True)
Result = NumberPerfectMatchings(Input[0])
print(Result)
with open(f'{os.path.basename(__file__).split(".")[0]}.txt', 'w') as f:
f.write(f'{Result}\n')
elapsed = time.time() - start
minutes = int(elapsed / 60)
seconds = elapsed - 60 * minutes
print(f'Elapsed Time {minutes} m {seconds:.2f} s')
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with GNU Emacs. If not, see <http://www.gnu.org/licenses/>
# GCON Global Alignment with Constant Gap Penalty
from helpers import create_strings
from align import san_kai
def gcon(s, t):
score, s1, t1 = san_kai([s0 for s0 in s], [t0 for t0 in t],
sigma=5,
epsilon=0)
return score, ''.join(s1), ''.join(t1)
if __name__ == '__main__':
from Bio.SubsMat.MatrixInfo import blosum62
import sys
score = -float('inf')
if sys.argv[1] == '--sample':
score, _, _ = gcon('PLEASANTLY', 'MEANLY')
elif sys.argv[1] == '--test':
strings = create_strings('gcon', ext=3, fasta=True)
score, _, _ = gcon(strings[0], strings[1])
else:
score, _, _ = gcon(sys.argv[1], sys.argv[2])
print(score)
# Copyright (C) 2019 Greenweaves Software Limited
#
# This is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This software is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with GNU Emacs. If not, see <http://www.gnu.org/licenses/>
# BA5I Find a Highest-Scoring Overlap Alignment of Two Strings
from align import create_distance_matrix, overlap_assignment
if __name__ == '__main__':
from helpers import create_strings
strings = create_strings('ba5i', ext=1)
d, s1, t1 = overlap_assignment(strings[0], strings[1])
print('{0}'.format(d))
print(s1)
print(t1)
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with GNU Emacs. If not, see <http://www.gnu.org/licenses/>
#
# prsm Matching a Spectrum to a Protein
from spectrum import prsm
if __name__ == '__main__':
from helpers import create_strings
i = 0
s = []
R = []
for ll in create_strings(ext=3):
if i == 0:
n = int(ll)
elif i < n + 1:
s.append(ll)
else:
R.append(float(ll))
i += 1
m, s_max = prsm(s, R)
print(m)
print(s_max)
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with GNU Emacs. If not, see <http://www.gnu.org/licenses/>
# HDAG Hamiltonian Path in DAG
#
if __name__=='__main__':
from helpers import create_strings
gs = []
g = []
for line in create_strings(ext=1):
if len(line)==0:
if len(g)>0:
gs.append(g)
g=[]
continue
numbers = [int(s) for s in line.split(' ')]
if len(numbers)==1:
continue
elif len(numbers)==2:
g.append((numbers[0],numbers[1]))
if len(g)>0:
gs.append(g)