Created
August 8, 2024 17:58
-
-
Save StephenFordham/649f4762e843d7083ece9321a8291584 to your computer and use it in GitHub Desktop.
Repeat_confirmation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from Bio import SeqIO | |
| def read_fasta_sequence(file_path): | |
| sequence = "" | |
| with open(file_path, 'r') as file: | |
| for line in file: | |
| if not line.startswith('>'): | |
| sequence += line.strip() | |
| return sequence | |
| def count_sequence_repeats(fasta_file, repeat_sequence_file): | |
| """ | |
| Counts how many times a repeat sequence is found in a given FASTA file. | |
| Parameters: | |
| fasta_file (str): Path to the input FASTA file. | |
| repeat_sequence_file (str): Path to the FASTA file containing the repeat sequence. | |
| Returns: | |
| int: Number of times the repeat sequence is found in the FASTA file. | |
| """ | |
| # Read the repeat sequence from the FASTA file | |
| repeat_sequence = read_fasta_sequence(repeat_sequence_file) | |
| count = 0 | |
| for record in SeqIO.parse(fasta_file, "fasta"): | |
| count += record.seq.count(repeat_sequence) | |
| return count |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment