Bioinformatics/Subsequence: Difference between revisions

=={{header|Python}}==

{{works with|Python|3.8}}

{{libheader|regex}}

<lang python>

from random import choice

import regex as re

import time

def generate_sequence(n: int ) -> list:

return "".join([ choice(['A','C','G','T']) for _ in range(n) ])

def dna_findall(needle: str, haystack: str) -> None:

if sum(1 for _ in re.finditer(needle, haystack, overlapped=True)) == 0:

print("No matches found")

else:

print(f"Found {needle} at the following indices: ")

for match in re.finditer(needle, haystack, overlapped=True):

print(f"{match.start()}:{match.end()} ")

dna_seq = generate_sequence(200)

sample_seq = generate_sequence(4)

c = 1

for i in dna_seq:

print(i, end="") if c % 20 != 0 else print(f"{i}")

c += 1

print(f"\nSearch Sample: {sample_seq}")

dna_findall(sample_seq, dna_seq)

</lang>

{{out}}

TTGCCCCTGTACTGAGCCCA

TAAGCTTGCACTCAAGGTTT

TGCCCCCTCATATTATAACG

CATCCATTATACAAAACCGA

TACCCTTCCGCATATTATGA

AAAGTGGCGAAGTGCCTTGA

TTTGCATTCATAGTACAACG

GTGCAAAAGCATTGTATGTC

TCACATTTACATGGGAAATG

CCTAGTAGGTGCAAGACCTG

Search Sample: TACA

Found TACA at the following indices:

69:73

133:137

167:171