def sims(f, debug=False, align="fit"):
"""Main driver to solve the SIMS problem."""
(s, t), score, gap_score = ro.fafsa_values(f), ra.FixedCost(1, -1), -1
d, (ss, tt) = ra.optimal_alignment(s, t, score, gap_score, gap_score, align=align, debug=debug)
print d
print ss
print tt
def glob(f):
'''Main driver to solve this problem.'''
x, y = ro.fafsa_values(f)
d, (xx, yy) = optimal_alignment(x, y, ra.BLOSUM62, -5)
print d
print xx
print yy
def gcon(f, debug=False, optimal_alignment=optimal_alignment_separate_arrays):
"""Main driver to solve the GCON problem."""
x, y = ro.fafsa_values(f)
d, (xx, yy) = optimal_alignment(x, y, ra.BLOSUM62, -5, 0, debug=debug)
print xx
print yy
return d
def gaff(f, score=ra.BLOSUM62, gap_init= -11, gap_ext= -1, debug=False):
'''Main driver to solve the GAFF problem.'''
x, y = ro.fafsa_values(f)
d, (xx, yy) = ra.optimal_alignment(x, y, score, gap_init, gap_ext, debug=debug)
print d
print xx
print yy
def mult(f, match_score=0, mismatch_score= -1, gap_score= -1, debug=False):
'''Main driver to solve this problem.'''
s = ro.fafsa_values(f)
score = lambda x, y: match_score if x == y else mismatch_score
c = align4(s, score, gap_score=gap_score)
# print c
print ro.join_list([c[-1, -1, -1, -1][0]] + list(alignment4(s, c)), delimiter='\n')
def edta(f, debug=False):
'''Main driver to solve this problem.'''
x, y = ro.fafsa_values(f)
d, (xx, yy) = edit_distance_alignment(x, y, debug=debug)
print d
print xx
print yy
def osym(f, debug=1):
'''Main driver to solve the GLOB problem.'''
(x, y), score, gap_score = ro.fafsa_values(f), ra.FixedCost(1, -1), -1
a = ra.global_alignment_score_matrix((x, y), score, gap_score, debug=debug)
m = a[:-1, :-1] + np.flipud(np.fliplr(ra.global_alignment_score_matrix((''.join(reversed(x)), ''.join(reversed(y))), ra.FixedCost(1, -1), -1, debug=debug)[:-1, :-1])) + \
np.array([[score(x[i], y[j]) for j in xrange(len(y))] for i in xrange(len(x))])
print m[-1, -1]
print np.sum(m)
def gcon(f, debug=False):
'''Main driver to solve the GCON problem.'''
x, y = ro.fafsa_values(f)
d, (xx, yy) = ra.optimal_alignment(x, y, ra.BLOSUM62, -5, 0, debug=debug)
print d
print xx
print yy
return d
def laff(f, debug=0):
'''Main driver to solve the LOCA problem.'''
x, y = ro.fafsa_values(f)
d, (xx, yy) = optimal_alignment_array_form(x, y, ra.BLOSUM62, -11, -1, debug=debug, gap_symbol='-')
if debug:
print x
print y
print ra.score_of(xx, yy, ra.BLOSUM62, -11, -1) # , debug=True)
return ro.join_list((d, xx, yy), delimiter='\n')
def oap(f, debug=False):
'''Main driver to solve this problem.'''
x, y = ro.fafsa_values(f)
score = lambda x, y: 1 if x == y else -2
c, I, J = semi_global_alignment((x, y), score, -2, debug=debug)
row_max = (np.argmax(c[:, -1]), len(y))
col_max = (len(x), np.argmax(c[-1, :]))
print c
print row_max, col_max
overall_max = row_max if c[row_max[0], row_max[1]] > c[col_max[0], col_max[1]] else col_max
print c[overall_max[0], overall_max[1]]
print ro.join_list(alignment_from_matrix((x, y), overall_max, c, I, J), delimiter='\n')
def gaff(
f, score=ra.BLOSUM62, gap_init=-11, gap_ext=-1, debug=False, optimal_alignment=optimal_alignment_separate_arrays
):
"""Main driver to solve the GAFF problem."""
x, y = ro.fafsa_values(f)
d, (xx, yy) = optimal_alignment(x, y, score, gap_init, gap_ext, debug=debug)
# d, (xx, yy) = optimal_alignment(x, y, ra.BLOSUM62, -12, -1, debug=debug)
print x
print y
print ra.score_of(xx, yy, score, gap_init, gap_ext)
print
print d
print xx
print yy
return d
def smgb(f, debug=False):
"""Main driver to solve this problem."""
x, y = ro.fafsa_values(f) # [r.seq for r in SeqIO.parse('rosalind_smgb.dat', 'fasta')]
c, p = semi_global_alignment((x, y), debug=debug)
# row_max = (np.argmax(c[:, -1]), len(y))
# col_max = (len(x), np.argmax(c[-1, :]))
m, n = len(x), len(y)
row_max = (np.argmax([c[i][n] for i in xrange(m + 1)]), n)
col_max = (m, np.argmax(c[-1]))
overall_max = row_max if c[row_max[0]][row_max[1]] > c[col_max[0]][col_max[1]] else col_max
if debug >= 2:
print np.array(c)
print np.array(p)
# print row_max, col_max
print overall_max
print c[overall_max[0]][overall_max[1]]
print ro.join_list(alignment_from_matrix((x, y), overall_max, c, p), delimiter="\n")
def laff_yesimon(f):
score = ra.BLOSUM62
s, t = ro.fafsa_values(f)
sl, tl = len(s), len(t)
T = np.zeros((sl + 1, tl + 1), dtype=np.character)
V = np.zeros((sl + 1, tl + 1))
F = np.zeros((sl + 1, tl + 1))
G = np.zeros((sl + 1, tl + 1))
for i, j in product(xrange(1, sl + 1), xrange(1, tl + 1)):
cost = score(s[i - 1], t[j - 1])
F[i, j] = V[i - 1, j - 1] + cost
G[i, j] = max(F[i - 1, j] - 12, G[i - 1, j] - 1, F[i, j - 1] - 12, G[i, j - 1] - 1)
V[i, j] = v = max(F[i, j], G[i, j], 0)
if v == F[i, j]: T[i, j] = 'D'
elif v == G[i, j]:
if v == F[i - 1, j] - 12 or G[i - 1, j] - 1: T[i, j] = 'L'
else: T[i, j] = 'U'
elif v == 0: T[i, j] = ''
i, j = np.unravel_index(np.argmax(V), V.shape)
print(int(V[i, j]))
sa = ''
ta = ''
while T[i, j]:
direction = T[i, j]
if direction == 'D':
sa += s[i - 1]
ta += t[j - 1]
i, j = i - 1, j - 1
elif direction == 'L':
ta += t[j - 1]
i = i - 1
elif direction == 'U':
sa += s[i - 1]
j = j - 1
print(''.join(reversed(sa)))
print(''.join(reversed(ta)))
def sseq(f):
return " ".join(it.imap(str, sseq_indices(*ro.fafsa_values(f))))
def pmch(f):
c = Counter(ro.fafsa_values(f)[0])
return factorial(c['A']) * factorial(c['G'])
def corr(f):
'''Finds and prints all matches, probably with an average complexity of O(n m log m) where n=#strings
and m = size of strings.'''
return '\n'.join('%s->%s' % x for x in match_errors(ro.fafsa_values(f)))
def ctea(f, debug=False):
'''Main driver to solve this problem.'''
x, y = ro.fafsa_values(f)
return edit_distance_and_count(x, y, 2 ** 27 - 1, debug=debug)
def assemble_fafsa(file_name, fraction, hash_type='rolling'):
return assemble(ro.fafsa_values(file_name), fraction, hash_type=hash_type)
i, j, s = m, n, ''
while i > 0 and j > 0:
if x[i - 1] == y[j - 1]: i, j, s = i - 1, j - 1, x[i - 1] + s
else:
if c[i - 1, j] > c[i, j - 1]: i -= 1
else: j -= 1
return s
def lcsq2(x, y): # Integrated DP+backtracking, O(mn) time, O(min(m,n)) storage
m, n = len(x), len(y)
if m < n: return lcsq2(y, x)
c_old, c, s_old, s = [0] * (n + 1), [0] * (n + 1), [''] * (n + 1), [''] * (n + 1)
for xi in x:
c_old[:] = c[:]; s_old[:] = s[:]
for j, yj in enumerate(y, 1):
if xi == yj: c[j], s[j] = c_old[j - 1] + 1, s_old[j - 1] + xi
else:
if c_old[j] > c[j - 1]: c[j], s[j] = c_old[j], s_old[j]
else: c[j], s[j] = c[j - 1], s[j - 1]
return s[-1]
lcsq_solution = lambda f: lcsq2(*ro.fafsa_values(f))
if __name__ == "__main__":
print lcsq('TAC', 'TCA')
print lcsq2('TAC', 'TCA')
print lcsq('AACCTTGG', 'ACACTGTGA')
print lcsq2('AACCTTGG', 'ACACTGTGA')
print lcsq_solution('rosalind_lcsq_sample.dat')
print lcsq_solution('rosalind_lcsq.dat')
def tran(f):
transitions, transversions = count_tran(*ro.fafsa_values(f))
return transitions / transversions
def gaff_burschka(f):
x, y = ro.fafsa_values(f)
return optimal_alignment_gaff_burschka(x, y, -11, -1)
s, t, u, v, i, j, k, l = '', '', '', '', len(x), len(y), len(z), len(w)
# print i, j, k, l
while i or j or k or l:
ip, jp, kp, lp = c[i, j, k, l][1]
s, t, u, v = \
(gap_symbol if ip == i else x[i - 1]) + s, \
(gap_symbol if jp == j else y[j - 1]) + t, \
(gap_symbol if kp == k else z[k - 1]) + u, \
(gap_symbol if lp == l else w[l - 1]) + v
i, j, k, l = ip, jp, kp, lp
# print i, j, k,l
return s, t, u, v
def test_align2(f, (i, j), match_score=0, mismatch_score= -1, gap_score= -1, debug=False):
'''Two-string test.'''
s = ro.fafsa_values(f)
score = lambda x, y: match_score if x == y else mismatch_score
print (s[i], s[j])
c = ra.global_alignment_matrix((s[i], s[j]), score, gap_score=gap_score)
# print c
print ro.join_list([c[-1, -1][0]] + list(ra.alignment_from_matrix((s[i], s[j]), c)), delimiter='\n')
def test_align3(f, (i, j, k), match_score=0, mismatch_score= -1, gap_score= -1, debug=False):
'''Three-string test.'''
s = ro.fafsa_values(f)
score = lambda x, y: match_score if x == y else mismatch_score
print (s[i], s[j], s[k])
c = align3((s[i], s[j], s[k]), score, gap_score=gap_score)
# print c
print ro.join_list([c[-1, -1, -1][0]] + list(alignment3((s[i], s[j], s[k]), c)), delimiter='\n')
def gaff_yesimon(f):
x, y = ro.fafsa_values(f)
return optimal_alignment_gaff_yesimon(x, y)
def gcon_yesimon(f):
x, y = ro.fafsa_values(f)
return optimal_alignment_yesimon(x, y, -5)
def loca(f, debug=False):
'''Main driver to solve the LOCA problem.'''
x, y = ro.fafsa_values(f)
d, (xx, yy) = ra.optimal_alignment(x, y, ra.PAM250, -5, -5, align='local', debug=debug, gap_symbol='')
return ro.join_list((d, xx, yy), delimiter='\n')
def mmch(f):
s = ro.fafsa_values(f)[0]
#return num_max_matching(s), long(num_max_matching_luiz(s))
print s
print len(s)
return num_max_matching(s), long(num_max_matching_luiz(s))
def edit(f):
"""Main driver to solve this problem."""
return edit_distance(*ro.fafsa_values(f)), edit_distance_lean(*ro.fafsa_values(f))