from __future__ import print_function
import os
from functools import reduce
from revp import read_fasta
def longest_common_substring(s1, s2):
''' See
http://en.wikipedia.org/wiki/Longest_common_substring_problem#Pseudocode
for more details '''
L = {}
z = 0
for i, c1 in enumerate(s1):
for j, c2 in enumerate(s2):
if c1 == c2:
L[(i, j)] = L.get((i - 1, j - 1), 0) + 1
if L[(i, j)] > z:
z = L[(i, j)]
ret = s1[i - z + 1:i + 1]
return ret
if __name__ == "__main__":
with open(os.path.join('data', 'rosalind_lcsm.txt')) as dataset:
seqs = read_fasta(dataset)
print(reduce(longest_common_substring, set(seqs.values())))
#!/usr/bin/env python
from __future__ import print_function
import os
from math import factorial
from revp import read_fasta
def perfect_matchings(seq):
return factorial(seq.count('G')) * factorial(seq.count('A'))
if __name__ == "__main__":
with open(os.path.join('data', 'rosalind_pmch.txt')) as dataset:
seq = read_fasta(dataset).popitem()[1]
print(perfect_matchings(seq))
#!/usr/bin/env python
from __future__ import print_function
import os
from math import factorial
from revp import read_fasta
def maximum_matchings(seq):
min_gc, max_gc = sorted([seq.count('G'), seq.count('C')])
min_au, max_au = sorted([seq.count('A'), seq.count('U')])
return (factorial(max_gc) // factorial(max_gc - min_gc) *
factorial(max_au) // factorial(max_au - min_au))
if __name__ == "__main__":
with open(os.path.join('data', 'rosalind_mmch.txt')) as dataset:
seq = read_fasta(dataset).popitem()[1]
print(maximum_matchings(seq))
UNIPROT_URL = 'http://www.uniprot.org/uniprot/'
def find_N_glycosylation_motif(protein):
finds = []
for pos in substring_find(protein, 'N'):
if len(protein[pos-1:pos + 3]) == 4:
if (protein[pos] != 'P' and protein[pos + 1] in ('S', 'T')
and protein[pos + 2] != 'P'):
finds.append(pos)
return finds
if __name__ == "__main__":
with open(os.path.join('data', 'rosalind_mprt.txt')) as dataset:
uniprot_ids = [r.rstrip() for r in dataset.readlines()]
proteins = {}
for uniprot_id in uniprot_ids:
prot = urlopen('{0}{1}.fasta'.format(UNIPROT_URL, uniprot_id))
proteins[uniprot_id] = read_fasta(prot).popitem()[1]
prot.close()
for protein in proteins:
pos = find_N_glycosylation_motif(proteins[protein])
if pos:
print(protein)
print(*pos)
