def solution(dataset: list) -> str:
fasta = read_fasta(lines=dataset)
Seq1, Seq2 = fasta[0], fasta[1]
w, h = len(Seq1), len(Seq2)
Matrix = [[0 for x in range(w + 1)] for y in range(h + 1)]
for i, ibase in enumerate(Seq1, 1):
for j, jbase in enumerate(Seq2, 1):
if ibase == jbase:
Matrix[j][i] = Matrix[j - 1][i - 1] + 1
else:
Matrix[j][i] = max(Matrix[j - 1][i], Matrix[j][i - 1])
# remove zeros
Matrix = [M[1:] for M in Matrix[1:]]
# print(" ", " ".join([nt for nt in Seq1]))
# for i, b in enumerate(Seq2):
# print(b, " ".join([str(s) for s in Matrix[i]]))
# len(LCS) == Matrix[len(Seq2) - 1][len(Seq1) - 1]
i, j = len(Seq1) - 1, len(Seq2) - 1
LCS = []
while i > -1 and j > -1:
if Seq1[i] == Seq2[j]:
LCS.append(Seq1[i])
j -= 1
i -= 1
elif Matrix[j][i - 1] == Matrix[j][i]:
i -= 1
elif Matrix[j - 1][i] == Matrix[j][i]:
j -= 1
return "".join(LCS)[::-1]
def slow_solution(dataset: list) -> str:
sequences = read_fasta(lines=dataset)
k = 3
graph = []
for s in sequences: # O(n**2)
for t in sequences:
if s == t:
# stop cycling
continue
if s[-k:] == t[:k]:
graph.append((s.id, t.id))
return "\n".join([f"{edge[0]} {edge[1]}" for edge in graph])
def solution(dataset: list) -> str:
sequences = read_fasta(lines=dataset)
nucleotides = ["A", "C", "G", "T"]
all_counts = []
consensus = ""
for nts in zip(*sequences):
nt_counts = Counter(nts)
consensus += nt_counts.most_common(1)[0][0]
all_counts.append([str(nt_counts[nt]) for nt in nucleotides])
profile_matrix = "\n".join([
f"{nt}: {' '.join(counts)}"
for nt, counts in zip(nucleotides, zip(*all_counts))
])
return f"{consensus}\n{profile_matrix}"
def solution(dataset: list) -> str:
sequences = read_fasta(lines=dataset)
k = 3
edges = []
nodes = []
for s in sequences: # O(n * ( n - 1 ) / 2) == O(n**2), but runs twice as fast
# check what other nodes in the graph s connects to
for t in nodes:
if s.endswith(t[:k]):
edges.append((s.id, t.id))
if t.endswith(s[:k]):
edges.append((t.id, s.id))
# add node to graph
nodes.append(s)
return "\n".join([f"{edge[0]} {edge[1]}" for edge in edges])
def solution(dataset: list) -> str:
sequences = read_fasta(lines=dataset)
DNA = sequences[0]
subsequence = sequences[1]
indices = []
offest = 0
for base in subsequence:
loc = DNA[offest:].find_one(base)
offest = loc + offest + 1
indices.append(str(offest))
# sanity check
for i, idx in enumerate(indices):
try:
assert subsequence[i] == DNA[int(idx) - 1]
except:
print(f"{subsequence[i]} != {DNA[int(idx)-1]} at {idx}")
return " ".join(indices)