def main():
file_name = 'datasets/rosalind_orf.txt'
seq_dict = parse_fasta(file_name)
for key in seq_dict:
dna = seq_dict[key]
orfs = orf_translate(dna)
print('\n'.join(orfs))
with open('solutions/rosalind_orf.txt', 'w') as output_file:
output_file.write('\n'.join(orfs))
def main():
file_name = 'datasets/rosalind_lcsm.txt'
seq_dict = parse_fasta(file_name)
seq_list = []
for key in seq_dict:
seq_list.append(seq_dict[key])
shared_motif = longest_shared_motif(seq_list)
print(shared_motif)
with open('solutions/rosalind_lcsm.txt', 'w') as output_file:
output_file.write(shared_motif)
def main():
file_name = 'datasets/rosalind_pmch.txt'
seq_dict = parse_fasta(file_name)
seq_list = []
for key in seq_dict:
seq_list.append(seq_dict[key])
rna = seq_list[0]
num_perfect_matching = perfect_matching(rna)
print(str(num_perfect_matching))
with open('solutions/rosalind_pmch.txt', 'w') as output_file:
output_file.write(str(num_perfect_matching))
def main():
file_name='datasets/rosalind_revp.txt'
seq_dict = parse_fasta(file_name)
for key in seq_dict:
dna=seq_dict[key]
restrict_sites, len_sites=restriction_sites(dna)
for i in range(len(restrict_sites)):
print(str(restrict_sites[i])+' '+str(len_sites[i]))
with open('solutions/rosalind_revp.txt', 'w') as output_file:
for i in range(len(restrict_sites)):
output_file.write(str(restrict_sites[i])+' '+str(len_sites[i])+'\n')
def main():
file_name = 'datasets/rosalind_kmer.txt'
seq_dict = parse_fasta(file_name)
seq_list = []
for key in seq_dict:
seq_list.append(seq_dict[key])
dna = seq_list[0]
kmer_count = k_mer_sequence(dna)
print(' '.join(map(str, (kmer_count))))
with open('solutions/rosalind_kmer.txt', 'w') as output_file:
output_file.write(' '.join(map(str, (kmer_count))))
def main():
file_name = 'datasets/rosalind_long.txt'
seq_dict = parse_fasta(file_name)
seq_list = []
for key in seq_dict:
seq_list.append(seq_dict[key])
final_sequence = shortest_super_sequence(seq_list)
print(final_sequence)
print(len(final_sequence))
with open('solutions/rosalind_long.txt', 'w') as output_file:
output_file.write(final_sequence)
def main():
file_name = 'datasets/rosalind_sseq.txt'
seq_dict = parse_fasta(file_name)
seq_list = []
for key in seq_dict:
seq_list.append(seq_dict[key])
dna = seq_list[0]
motif = seq_list[1]
splice_pos = spliced_motif(dna, motif)
print(' '.join(map(str, (splice_pos))))
with open('solutions/rosalind_sseq.txt', 'w') as output_file:
output_file.write(' '.join(map(str, (splice_pos))))
def main():
file_name = 'datasets/rosalind_edit.txt'
seq_dict = parse_fasta(file_name)
seq_list = []
for key in seq_dict:
seq_list.append(seq_dict[key])
seq1 = seq_list[0]
seq2 = seq_list[1]
edit_distance_value = edit_distance(seq1, seq2)
print(str(edit_distance_value))
with open('solutions/rosalind_edit.txt', 'w') as output_file:
output_file.write(str(edit_distance_value))
def main():
file_name='datasets/rosalind_lcsq.txt'
seq_dict = parse_fasta(file_name)
seq_list=[]
for key in seq_dict:
seq_list.append(seq_dict[key])
seq1 = seq_list[0]
seq2 = seq_list[1]
lcs = shared_spliced_motif(seq1, seq2)
print(lcs)
with open('solutions/rosalind_lcsq.txt', 'w') as output_file:
output_file.write(lcs)
def main():
file_name = 'datasets/rosalind_glob.txt'
seq_dict = parse_fasta(file_name)
seq_list = []
for key in seq_dict:
seq_list.append(seq_dict[key])
seq1 = seq_list[0]
seq2 = seq_list[1]
indel_penalty = 5
scoring_matrix = BLOSUM62()
max_score = global_alignment_score(seq1, seq2, scoring_matrix,
indel_penalty)
print(str(max_score))
with open('solutions/rosalind_glob.txt', 'w') as output_file:
output_file.write(str(max_score))
def main():
file_name='datasets/rosalind_pdst.txt'
seq_dict = parse_fasta(file_name)
seq_list=[]
for key in seq_dict:
seq_list.append(seq_dict[key])
distance_plot=distance_matrix(seq_list)
for i in range(len(distance_plot[0])):
for j in range(len(distance_plot[0])):
print(str(distance_plot[i][j])+' ')
print()
with open('solutions/rosalind_pdst.txt', 'w') as output_file:
for i in range(len(distance_plot[0])):
for j in range(len(distance_plot[0])):
output_file.write(str(distance_plot[i][j])+' ')
output_file.write('\n')
def main():
file_name = 'datasets/rosalind_oap.txt'
seq_dict = parse_fasta(file_name)
seq_list = []
for key in seq_dict:
seq_list.append(seq_dict[key])
seq1 = seq_list[0]
seq2 = seq_list[1]
max_score, aligned_seq1, aligned_seq2 = overlap_alignment(seq1, seq2)
print(str(max_score))
print(aligned_seq1)
print(aligned_seq2)
with open('solutions/rosalind_oap.txt', 'w') as output_data:
output_data.write(str(max_score) + '\n')
output_data.write(aligned_seq1 + '\n')
output_data.write(aligned_seq2)
def main():
file_name = 'datasets/rosalind_cons.txt'
seq_dict = parse_fasta(file_name)
sequence_list = []
for key in seq_dict:
sequence_list.append(seq_dict[key])
dict_cons, array_cons = consensus_profile(sequence_list)
con_seq = consensus_sequence(array_cons)
print(con_seq)
for key in dict_cons:
print(key + ': ' + ' '.join(map(str, (dict_cons[key]))))
with open('solutions/rosalind_cons.txt', 'w') as output_file:
output_file.write(con_seq + '\n')
for key in dict_cons:
output_file.write(key + ': ' +
' '.join(map(str, (dict_cons[key]))) + '\n')
def main():
file_name='datasets/rosalind_loca.txt'
seq_dict = parse_fasta(file_name)
seq_list=[]
for key in seq_dict:
seq_list.append(seq_dict[key])
seq1 = seq_list[0]
seq2 = seq_list[1]
indel_penalty = 5
scoring_matrix = PAM250()
max_score, aligned_seq1, aligned_seq2 = local_alignment_subsequence(seq1, seq2, scoring_matrix, indel_penalty)
print(str(max_score))
print(aligned_seq1)
print(aligned_seq2)
with open('solutions/rosalind_loca.txt', 'w') as output_data:
output_data.write(str(max_score)+'\n')
output_data.write(aligned_seq1+'\n')
output_data.write(aligned_seq2)