def de_brujin_adjacency_list(dnas):
adj_list = set()
for dna in dnas:
revc = reverse_complement(dna)
adj_list.add((dna[:-1], dna[1:]))
adj_list.add((revc[:-1], revc[1:]))
return adj_list
def find_orfs(seq):
"""Find all potential open reading frames in a sequence."""
frames = []
for i in range(3):
frames.append(transcribe(seq[i:]))
frames.append(transcribe(reverse_complement(seq)[i:]))
orfs = set()
codons = load_codons()
for frame in frames:
i = 0
recording = False
current_orf = ''
while True:
codon = frame[i:i + 3]
aa = codons.get(codon, 'Stop')
if len(codon) != 3:
break # Because reached end of frame
if codon == 'AUG':
recording = True
if aa != 'Stop' and recording:
current_orf += aa
elif aa == 'Stop':
recording = False
orfs.add(current_orf)
current_orf = ''
i += 3
orfs.remove('')
orfs = extract_subseqs(orfs)
return orfs
def reverse_palindrome(dna):
size = len(dna)
for start in range(size):
for length in range(4, 13):
piece = dna[start:start + length]
if len(piece) >= 4 and piece == reverse_complement(piece):
yield (start + 1, length)
def reverse_palindromes(dna):
sites = []
for length in range(4, 13):
for start in range(0, len(dna) - length + 1):
segment = dna[start:start + length]
if segment == revc.reverse_complement(segment):
sites.append((start + 1, length))
return sites
def is_reverse_palindrome(seq):
if len(seq) == 0:
return True
elif len(seq) == 1:
return False
elif seq[0] == revc.reverse_complement(seq[-1]):
return is_reverse_palindrome(seq[1:-1])
else:
return False
def setup_assemble_genome(S):
reads = set(S) | {reverse_complement(i) for i in S}
while True:
genome = assemble_genome(reads)
if genome:
return genome
else:
reads = {read[:-1]
for read in reads} | {read[1:]
for read in reads}
def correct_errors(seqs):
corrections = []
c = Counter(seqs)
correct = [item for item in c if c[item] >= 2]
reverse = {reverse_complement(s) for s in correct}
seqset = set(correct)
for s in [item for item in c if c[item] < 2]:
if s not in reverse:
for fix in (f for f in seqset | reverse if hamming(s, f) == 1):
corrections.append((s, fix))
return corrections
def correct_errors(seqs):
corrections = []
c = Counter(seqs)
correct = [item for item in c if c[item] >= 2]
reverse = {reverse_complement(s) for s in correct}
seqset = set(correct)
for s in [item for item in c if c[item] < 2]:
if s not in reverse:
for fix in (f for f in seqset | reverse if hamming(s, f) == 1):
corrections.append((s, fix))
return corrections
def find_reverse_palindromes(dna: str,
minlen: int = 4,
maxlen: int = 12) -> Dict[int, int]:
palindromes = {}
for i in range(len(dna) - minlen + 1):
for j in range(minlen, maxlen + 1):
if i + j > len(dna):
continue
substring = dna[i:i + j]
if is_reverse_palindrome(substring):
print(i, j, substring, reverse_complement(substring))
palindromes[i + 1] = j
return palindromes
def find_candidate_proteins(dna: str) -> List[str]:
rna = _convert_to_rna(dna)
revcomp = _convert_to_rna(reverse_complement(dna))
candidate_proteins = set()
for i in range(len(rna) - 2):
codon = rna[i:i+3]
rev_codon = revcomp[i:i+3]
if codon == 'AUG':
candidate_proteins.add(_create_protein(rna, startpos=i))
elif rev_codon == 'AUG':
candidate_proteins.add(_create_protein(revcomp, startpos=i))
elif codon == 'AUG' and rev_codon == 'AUG':
candidate_proteins.add(_create_protein(rna, startpos=i))
candidate_proteins.add(_create_protein(revcomp, startpos=i))
return sorted([p for p in candidate_proteins if p is not None])
def open_reading_frames(dna_):
dnac = revc.reverse_complement(dna_)
rna_ = rna.convert_to_rna(dna_)
rnac = rna.convert_to_rna(dnac)
proteins = []
for i in range(3):
proteins.append(prot.translate(rna_[i:], stop='*'))
proteins.append(prot.translate(rnac[i:], stop='*'))
candidates = []
for protein in proteins:
for i, aa in enumerate(protein):
if aa == 'M':
for j, aa_stop in enumerate(protein[i + 1:]):
if aa_stop == '*':
candidates.append(protein[i:i + j + 1])
break
return set(candidates)
def error_corrections(reads):
# seen contains only the read, seen_twice contains both the read and its reverse complement
seen, seen_twice = set(), set()
corrections = {}
for read in reads:
read_revc = reverse_complement(read)
if read in seen_twice:
continue
elif read in seen or read_revc in seen:
seen.discard(read)
seen.discard(read_revc)
seen_twice.add(read)
seen_twice.add(read_revc)
else:
seen.add(read)
for i in seen:
for j in seen_twice:
if hamming_distance(i, j) == 1:
corrections[i] = j
break
return corrections
#!/usr/bin/env python
from __future__ import print_function
import os
from revc import reverse_complement
if __name__ == "__main__":
with open(os.path.join('data', 'rosalind_dbru.txt')) as dataset:
dna_set = set(s[:-1] for s in dataset)
reverse_complements = {reverse_complement(s) for s in dna_set}
dna_strings = dna_set | reverse_complements
item = dna_strings.pop()
k = len(item) - 1
dna_strings.add(item)
adj_list = {(r[0:k], r[1:k + 1]) for r in dna_strings}
for adj in sorted(adj_list):
print('(' + adj[0] + ', ' + adj[1] + ')')
from prot import prepare_codon_table
from revp import read_fasta
from revc import reverse_complement
from rna import rna_transcription
from subs import substring_find
if __name__ == "__main__":
with open(os.path.join('data', 'rosalind_orf.txt')) as dataset:
seqs = read_fasta(dataset)
codon_table = prepare_codon_table(os.path.join('data', 'codon_table'))
output = []
dna = seqs.popitem()[1]
rna = (rna_transcription(dna), rna_transcription(reverse_complement(dna)))
for seq in rna:
for offset in (0, 1, 2):
for start_pos in substring_find(seq[offset:], 'AUG'):
current = []
for codon in (seq[i:i + 3]
for i in range(start_pos, len(seq), 3)):
if len(codon) == 3:
if codon_table[codon] == 'Stop' and current:
output.append(''.join(current))
current = []
elif codon == 'AUG' or current:
current.append(codon_table[codon])
print("\n".join(set(output)))
#!/usr/bin/env python
from __future__ import print_function
import os
from revc import reverse_complement
if __name__ == "__main__":
with open(os.path.join('data', 'rosalind_pcov.txt')) as dataset:
reads = {s.rstrip() for s in dataset}
reverse_complements = {reverse_complement(s) for s in reads}
dna_strings = reads | reverse_complements
item = dna_strings.pop()
k = len(item) - 1
dna_strings.add(item)
adj_list = {(head, tail)
for (head, tail) in {(r[0:k], r[1:k + 1]) for r in dna_strings}
if any(head in dna or tail in dna for dna in dna_strings)}
superstring = []
c = adj_list.pop()
while adj_list:
superstring.append(c[1][k - 1:])
next_edge = {n for n in adj_list if n[0] == c[1]}
if next_edge:
c = (adj_list & next_edge).pop()
from prot import prepare_codon_table
from revp import read_fasta
from revc import reverse_complement
from rna import rna_transcription
from subs import substring_find
if __name__ == "__main__":
with open(os.path.join("data", "rosalind_orf.txt")) as dataset:
seqs = read_fasta(dataset)
codon_table = prepare_codon_table(os.path.join("data", "codon_table"))
output = []
dna = seqs.popitem()[1]
rna = (rna_transcription(dna), rna_transcription(reverse_complement(dna)))
for seq in rna:
for offset in (0, 1, 2):
for start_pos in substring_find(seq[offset:], "AUG"):
current = []
for codon in (seq[i : i + 3] for i in range(start_pos, len(seq), 3)):
if len(codon) == 3:
if codon_table[codon] == "Stop" and current:
output.append("".join(current))
current = []
elif codon == "AUG" or current:
current.append(codon_table[codon])
print("\n".join(set(output)))
def is_reverse_palindrome(dna: str) -> bool:
if dna == reverse_complement(dna):
return True
return False