def main():
seqs = list(parse_fasta('problem_datasets/rosalind_long.txt').values())
answer = getContig(seqs)
print('Shortest superstring is %i nucleotides long.' % len(answer))
with open('output/rosalind_long_out.txt', 'w') as f:
f.write(answer)
def main():
seqs = list(parse_fasta('problem_datasets/rosalind_long.txt').values())
answer = getContig(seqs)
print('Shortest superstring is %i nucleotides long.' % len(answer))
with open('output/rosalind_long_out.txt', 'w') as f:
f.write(answer)
def main():
strings = parse_fasta('problem_datasets/rosalind_pdst.txt')
matrix = distance_matrix(strings)
with open('output/rosalind_pdst_out.txt', 'w') as outfile:
for line in matrix:
outfile.write(' '.join(map(str, line))+'\n')
def main():
rna = parse_fasta('problem_datasets/rosalind_pmch.txt')
perfect = factorial(rna.count('A')) * factorial(rna.count('C'))
print(perfect)
with open('output/rosalind_pmch_out.txt', 'w') as outfile:
outfile.write(str(perfect))
def main():
s, t = parse_fasta('problem_datasets/rosalind_loca.txt')
alignment = alignment_score(s, t, PAM250(), -5)
with open('output/rosalind_loca_out.txt', 'w') as outfile:
outfile.write('\n'.join(alignment))
print('Maximum alignment score =', alignment[0])
def main():
s, t = parse_fasta('problem_datasets/rosalind_edta.txt', 'seq')
aligned = edit_dist_with_align(s, t)
with open('output/rosalind_edta_out.txt', 'w') as outfile:
outfile.write('\n'.join(aligned))
print('Edit distance =', aligned[0])
def main():
seq = parse_fasta('problem_datasets/rosalind_orf.txt')
peptides = raw_translate(seq)
orfs = find_orfs(peptides)
with open('output/rosalind_orf_out.txt', 'w') as outfile:
outfile.write('\n'.join(orfs))
def main():
s, t = parse_fasta('problem_datasets/rosalind_smgb.txt', True)
alignment = semiglobal_align(s, t)
with open('output/rosalind_smgb_out.txt', 'w') as outfile:
outfile.write('\n'.join(alignment))
print('Maximum alignment score =', alignment[0])
def main():
s, t = parse_fasta('problem_datasets/rosalind_lcsq.txt')
seq = longest_sub(s, t)
with open('output/rosalind_lcsq_out.txt', 'w') as outfile:
outfile.write(seq)
print('The longest common subsequence is', len(seq), 'bases long.')
def main():
s, t = parse_fasta("problem_datasets/rosalind_loca.txt", True)
alignment = alignment_score(s, t, PAM250(), -5)
with open("output/rosalind_loca_out.txt", "w") as outfile:
outfile.write("\n".join(alignment))
print("Maximum alignment score =", alignment[0])
def main():
s, t = parse_fasta('problem_datasets/rosalind_smgb.txt', True)
alignment = semiglobal_align(s, t)
with open('output/rosalind_smgb_out.txt', 'w') as outfile:
outfile.write('\n'.join(alignment))
print('Maximum alignment score =', alignment[0])
def main():
s, t = parse_fasta('problem_datasets/rosalind_gaff.txt', True)
alignment = global_align_with_affine(s, t, BLOSUM62(), -11, -1)
with open('output/rosalind_gaff_out.txt', 'w') as f:
f.write('\n'.join(alignment))
print('Maximum alignment score =', alignment[0])
def main():
rna = parse_fasta('problem_datasets/rosalind_pmch.txt')
perfect = factorial(rna.count('A')) * factorial(rna.count('C'))
print(perfect)
with open('output/rosalind_pmch_out.txt', 'w') as outfile:
outfile.write(str(perfect))
def main():
s, t = parse_fasta('problem_datasets/rosalind_edta.txt')
aligned = edit_dist_with_align(s, t)
with open('output/rosalind_edta_out.txt', 'w') as outfile:
outfile.write('\n'.join(map(str, aligned)))
print('Edit distance =', aligned[0])
def main():
s, t = parse_fasta('problem_datasets/rosalind_lcsq.txt')
seq = longest_sub(s, t)
with open('output/rosalind_lcsq_out.txt', 'w') as outfile:
outfile.write(seq)
print('The longest common subsequence is', len(seq), 'bases long.')
def main():
s, t = parse_fasta('problem_datasets/rosalind_laff.txt', True)
alignment = local_align_with_affine(s, t, BLOSUM62(), -11, -1)
with open('output/rosalind_laff_out.txt', 'w') as outfile:
outfile.write('\n'.join(alignment))
print('Maximum alignment score =', alignment[0])
def main():
''' The input file for this problem contains two FASTA sequences, which can
be split into seperate sequences based on the position of the header
lines.
'''
s, t = parse_fasta('problem_datasets/rosalind_sseq.txt')
pos = find_subsequence(s, t)
print(' '.join(pos))
def main():
strings = list(parse_fasta('problem_datasets/rosalind_corr.txt').values())
strings += [rev_comp(i) for i in strings]
corr = error_correct(strings)
with open('output/rosalind_corr_out.txt', 'w') as outfile:
for i in corr:
outfile.write('->'.join(i) + '\n')
def main(filename):
dat = parse_fasta(filename)
if len(dat.values()) > 2:
print "More than two sequences in input file, " \
"only calculting edit distance between" \
" two sequences"
# need to clarify message as parse_fasta retuns a dict,
# not just first two seqs
print calc_edit_distance(dat.values()[0], dat.values()[1])
def main():
sequences = parse_fasta('problem_datasets/rosalind_lcsm.txt')
answer = longest_motif(sequences)
if answer != None:
print(answer)
else:
print('No common substring found.')
def main():
sequences = parse_fasta('rosalind_cons.txt')
profile = profile_matrix(sequences)
consensus = consensus_seq(profile)
with open('rosalind_cons_out.txt', 'w') as outfile:
outfile.write(consensus + '\n')
for line in format_profile(profile):
outfile.write(line + '\n')
def main():
''' The input file for this problem contains two FASTA sequences, which can
be split into seperate sequences based on the position of the header
lines.
'''
s, t = list(parse_fasta('problem_datasets/rosalind_sseq.txt').values())[:2]
pos = findSubSeq(s, t)
print(' '.join(pos))
def main():
sequences = list(parse_fasta('problem_datasets/rosalind_cons.txt').values())
profile = profile_matrix(sequences)
consensus = consensus_seq(profile)
with open('output/rosalind_cons_out.txt', 'w') as outfile:
outfile.write(consensus + '\n')
for line in format_profile(profile):
outfile.write(line + '\n')
def main(filename):
dat = parse_fasta(filename)
if len(dat.values()) > 2:
print "More than two sequences in input file, " \
"only calculting edit distance between" \
" two sequences"
# need to clarify message as parse_fasta retuns a dict,
# not just first two seqs
print calc_edit_distance(dat.values()[0], dat.values()[1])
def main():
sequences = parse_fasta('problem_datasets/rosalind_cons.txt')
profile = profile_matrix(sequences)
consensus = consensus_seq(profile)
with open('output/rosalind_cons_out.txt', 'w') as outfile:
outfile.write(consensus + '\n')
for line in format_profile(profile):
outfile.write(line + '\n')
def main():
strings = parse_fasta('problem_datasets/rosalind_corr.txt')
strings += [rev_comp(i) for i in strings]
corr = error_correct(strings)
with open('output/rosalind_corr_out.txt', 'w') as outfile:
for i in corr:
outfile.write('->'.join(i) + '\n')
def main():
# Get the collection of sequences.
#seqs = ['ATATCCG', 'TCCG', 'ATGTACTG', 'ATGTCTG']
seqs = parse_fasta('problem_datasets/rosalind_mult.txt')
# Create two arrays to keep track of which sequences are already aligned.
alignment = ['' for i in seqs]
remaining = [i for i in range(len(seqs))]
# Start by aligning the two most similar sequences.
scores = {}
for i in range(len(seqs)):
for j in range(len(seqs)-1, i, -1):
scores[(i, j)] = alignment_score(seqs[i], seqs[j])
a, b = max(scores)
max_score, matrix = scores[(a, b)]
alignment[a], alignment[b] = align_sequences(seqs[a], seqs[b], matrix)
remaining.remove(a)
remaining.remove(b)
# Pick the sequence that aligned best to one of the already aligned
# sequences and align it to the set; repeat until all sequences are
# aligned.
while len(remaining) > 0:
scores = {}
i = remaining[0]
for j in range(len(alignment)):
if alignment[j] != '':
scores[j] = alignment_score(seqs[i], alignment[j])
best = max(scores)
best_score, matrix = scores[best]
max_score += best_score
alignment[i], alignment[j] = align_sequences(seqs[i], alignment[best], matrix)
remaining.remove(i)
# Calulate the maxumum score
max_score = 0
for i in range(len(alignment)):
for j in range(len(alignment)-1, i, -1):
max_score += alignment_score(alignment[i], alignment[j])[0]
# Output the answer.
with open('output/rosalind_mult_out.txt', 'w') as outfile:
outfile.write(str(max_score) + '\n')
outfile.write('\n'.join(alignment))
print('-'*37 + 'ANSWER' + '-'*37)
with open('output/rosalind_mult_out.txt', 'r') as answer:
print(answer.read())
def main():
sequences = list(parse_fasta('problem_datasets/rosalind_splc.txt').values())
rna = max(sequences, key=len)
introns = [i for i in sequences if i != rna]
spliced = splice_RNA(rna, introns)
peptide = translate(spliced)
with open('output/rosalind_splc_out.txt', 'w') as outfile:
outfile.write(peptide)
def main():
s, t = parse_fasta('problem_datasets/rosalind_gap.txt')
alignment = semiglobal_align(s, t)
with open('output/rosalind_gap_out.txt', 'w') as outfile:
outfile.write('\n'.join(alignment))
print('-'*37 + 'ANSWER' + '-'*37)
with open('output/rosalind_gap_out.txt', 'r') as answer:
print(answer.read())
def main():
sequences = list(
parse_fasta('problem_datasets/rosalind_splc.txt').values())
rna = max(sequences, key=len)
introns = [i for i in sequences if i != rna]
spliced = splice_RNA(rna, introns)
peptide = translate(spliced)
with open('output/rosalind_splc_out.txt', 'w') as outfile:
outfile.write(peptide)
def main():
# Extract sequences from a fasta file.
seqs = parse_fasta('problem_datasets/rosalind_long.txt')
# Find the shortest superstring.
answer = shortest_contig(seqs)
# Write the answer.
open('output/rosalind_long_out.txt', 'w').write(answer)
# Optional: Print the length of the superstring.
print('Shortest superstring is %i nucleotides long.' % len(answer))
def main():
# Read in the two sequences.
s, t = parse_fasta('problem_datasets/rosalind_sims.txt')
# Get the alignment.
alignment = fitting_alignment(s, t)
# Save the answer.
with open('output/rosalind_sims_out.txt', 'w') as outfile:
outfile.write('\n'.join(alignment))
# Optional: Print the alignment score.
print('Optimal fitting alignment score =', alignment[0])
def main():
# Read in the two strings.
s, t = parse_fasta('problem_datasets/rosalind_oap.txt')
# Find the alignment.
alignment = overlap_align(s, t)
# Output the answer.
with open('output/rosalind_oap_out.txt', 'w') as outfile:
outfile.write('\n'.join(alignment))
# Optional: Print the max alignment score.
print('Maximum alignment score =', alignment[0])
def main():
sequences = parse_fasta('problem_datasets/rosalind_splc.txt')
rna = max(sequences, key=len)
introns = [i for i in sequences if i != rna]
spliced = splice_RNA(rna, introns)
peptide = translate(spliced)
if peptide == '':
print('No exon found.')
else:
with open('output/rosalind_splc_out.txt', 'w') as outfile:
outfile.write(peptide)
def main(filename):
dat = parse_fasta(filename)
profile = dna_profile(dat.values())
print profile_consensus(profile)
print_profile(profile)
def main():
s = parse_fasta('problem_datasets/rosalind_kmp.txt')
with open('output/rosalind_kmp_out.txt', 'w') as outfile:
outfile.write(' '.join(map(str, failure_array(s))))
def main():
strings = list(parse_fasta('problem_datasets/rosalind_lcsq.txt').values())
seq = longest_sub(strings[0], strings[1])
with open('output/rosalind_lcsq_out.txt', 'w') as outfile:
outfile.write(seq)
def main():
# Get the sequences from the .txt file.
s, t = parse_fasta('problem_datasets/rosalind_osym.txt')
# Compute the maximum alignment score, and the sum of all alignment scores.
print('\n'.join(map(str, align_to_symbols(s, t))))
def main():
# Read in the two input strings.
s, t = parse_fasta('problem_datasets/rosalind_ctea.txt')
# Print the number of optimal alignments (modulo 2^27 - 1).
print(count_alignments(s, t))
def main():
sequences = list(parse_fasta('problem_datasets/rosalind_lcsm.txt').values())
answer = longest_motif(sequences)
print(answer)
def main():
s1, s2 = parse_fasta('problem_datasets/rosalind_tran.txt')
print(pointMutations(s1, s2))
def main():
s, t = parse_fasta('problem_datasets/rosalind_edit.txt')
print(edit_dist(s, t))
def main():
fastas = parse_fasta('problem_datasets/rosalind_gc.txt', no_id=False)
max_h, max_gc = compute_gc(fastas)
print(max_h, '\n', '%.6f' % max_gc, sep='')
def main():
s, t = parse_fasta('problem_datasets/rosalind_mgap.txt')
print(max_global_align_gaps(s, t))
def main():
dataset = parse_fasta('problem_datasets/rosalind_grph.txt', no_id=False)
with open('output/rosalind_grph_out.txt', 'w') as outfile:
for line in overlap_seqs(dataset):
outfile.write(line + '\n')
def main():
fastas = parse_fasta('problem_datasets/rosalind_gc.txt')
max_h, max_gc = compute_gc(fastas)
print(max_h, '\n', '%.6f' % max_gc, sep='')
def main():
s1, s2 = parse_fasta('problem_datasets/rosalind_tran.txt')
print(pointMutations(s1, s2))
def main(filename):
dat = parse_fasta(filename)
profile = dna_profile(dat.values())
print profile_consensus(profile)
print_profile(profile)
def main(filename):
dat = parse_fasta(filename)
for i in find_max_gc(dat):
print i
def main():
strings = list(parse_fasta('problem_datasets/rosalind_lcsq.txt').values())
seq = longest_sub(strings[0], strings[1])
with open('output/rosalind_lcsq_out.txt', 'w') as outfile:
outfile.write(seq)
def main():
s, t = parse_fasta('problem_datasets/rosalind_glob.txt')
max_score = global_align(s, t, BLOSUM62(), -5)
print(max_score)
def main():
dataset = parse_fasta('problem_datasets/rosalind_grph.txt', no_id=False)
with open('output/rosalind_grph_out.txt', 'w') as outfile:
for line in overlap_seqs(dataset):
outfile.write(line + '\n')
def main():
sequences = list(
parse_fasta('problem_datasets/rosalind_lcsm.txt').values())
answer = longest_motif(sequences)
print(answer)
def main():
s = parse_fasta('problem_datasets/rosalind_mmch.txt')
print(max_matches(s))
def main():
s, t = parse_fasta('problem_datasets/rosalind_gcon.txt')
max_score = global_align(s, t, BLOSUM62(), -5)
print(max_score)