from readros import read_rosalind as rr
word = list(rr('test.txt').values())[0]
table = [0] * (len(word) + 1)
def kmp_table(W, T):
pos = 1
cnd = 0
T[0] = -1
while pos < len(W):
if W[pos] == W[cnd]:
T[pos] = T[cnd] + 1
else:
T[pos] = cnd
cnd = T[cnd]
while cnd >= 0 and W[pos] != W[cnd]:
cnd = T[cnd]
pos = pos + 1
cnd = cnd + 1
T[pos] = cnd
return T
a = [abs(x) for x in kmp_table(word, table)]
del a[0]
from readros import read_rosalind as rr
textd = rr("rosalind_grph.txt")
listbeg = []
listend = []
for k, v in textd.items():
listbeg.append(k)
listend.append(k)
listbeg.append(v[:3])
listend.append(v[-3:])
dictpref = dict(zip(listbeg[::2], listbeg[1::2]))
dictsuf = dict(zip(listend[::2], listend[1::2]))
text_file = open("Output.txt", "w")
for k, v in dictsuf.items():
for a, b in dictpref.items():
if b == v and k != a:
stri = k + " " + a
text_file.write(stri)
text_file.write("\n")
text_file.close()
from readros import read_rosalind as rr
import numpy as np
seq = list(rr("test.txt").values())
dst = np.zeros((len(seq), len(seq)))
def difference(a, b):
c = 0
for i in range(len(a)):
if a[i] != b[i]:
c += 1
return c / len(a)
for i in range(len(seq)):
for j in range(len(seq)):
dst[i][j] = difference(seq[i], seq[j])
for row in dst:
for a in row:
print('{0:.5f}'.format(a), end=" ")
print()
from readros import read_rosalind as rr
sequence = rr("test.txt")
SEQUENCES = list(sequence.values())
print(SEQUENCES)
from readros import read_rosalind as rr
sequences = list(rr("test.txt").values())
transitions = 0
transversions = 0
for i in range(0, len(sequences[0])):
if sequences[0][i] == "A" and sequences[1][i] == "G" or sequences[0][
i] == "G" and sequences[1][i] == "A":
transitions += 1
elif sequences[0][i] == "C" and sequences[1][i] == "T" or sequences[0][
i] == "T" and sequences[1][i] == "C":
transitions += 1
elif sequences[0][i] != sequences[1][i]:
transversions += 1
print('{0:.11f}'.format(transitions / transversions))
from readros import read_rosalind as rr
from itertools import product
import re
import sre_constants
seq = rr('test.txt').values()
seq = list(seq)
seq = str(seq[0])
bases = ['A', 'T', 'C', 'G']
new_data = []
for kmers in product(bases, repeat=4):
new_data.append(''.join(kmers))
kmer_list = []
seq_divided = []
new_data.sort()
for i in range(len(seq)):
seq_divided.append(seq[i:i+4])
for kmer in new_data:
kmer_list.append(seq_divided.count(kmer))
print(*kmer_list)
a = []
b = []
#Find all start codons and cut all previous bases
for i in range(0, len(DNA)):
if DNA[i:i+3] == "AUG":
a.append(DNA[i:])
#Find all stop codons and cut the string before them, resulting in a string in "AUG....." format
for i in a:
for j in range(0, len(i), 3):
if i[j:j+3] == "UAA" or i[j:j+3] == "UGA" or i[j:j+3] == "UAG" and i[:j] not in b:
b.append(i[:j])
break
return b
dna = list(rr("rosalind_splc.txt").values())
dna = dna[0]
dna = dna.replace("T", "U")
#Find all proteins in sequence (without reverse-complementing it)
prereverse = findstartstop(dna)
for i in range(0, len(prereverse)):
prereverse[i] = translate(prereverse[i],3)
prereverse[i] = "".join(prereverse[i])
rdna = reverse_complement(dna)
postreverse = findstartstop(rdna)
for i in range(0, len(postreverse)):
postreverse[i] = translate(postreverse[i],3)
postreverse[i] = "".join(postreverse[i])
whole = prereverse
for i in postreverse:
from readros import read_rosalind as rr
import numpy as np
text = rr("test.txt")
subs = list(text.values())
subst = [list(i) for i in subs]
subst = np.array(subst)
subst = subst.transpose()
subst = subst.tolist()
cstr = []
alist = []
clist = []
glist = []
tlist = []
for i in range(0, len(subst)):
ca = subst[i].count("A")
alist.append(ca)
for i in range(0, len(subst)):
ca = subst[i].count("C")
clist.append(ca)
for i in range(0, len(subst)):
ca = subst[i].count("T")
tlist.append(ca)
for i in range(0, len(subst)):
ca = subst[i].count("G")
glist.append(ca)
for i in range(0, len(alist)):
cslist = [alist[i], clist[i], tlist[i], glist[i]]