Commit 948ad068 authored by nlecouvr's avatar nlecouvr
Browse files

srcipt to find and locate all GATC sites

parent f29e7c36
import re
import matplotlib.pyplot as plt
import numpy as np
import pandas
from Bio import SeqIO, motifs
from Bio.Seq import Seq
from Bio.SeqRecord import SeqRecord
def main():
f = open("/home/nathan/projects/vscode_nextflow/nextflow-nathan/results/GATC/sites.bed", "w")
motif = "GATC"
pos_list = list()
for seq_record in SeqIO.parse("/home/nathan/projects/vscode_nextflow/nextflow-nathan/data/genome/data_G.fasta", "fasta"):
chrom =
for match in re.finditer(motif, str(seq_record.seq)):
start_pos = match.start() +1
end_pos = match.end() + 1
line = f"{chrom}\t{start_pos}\t{end_pos}\n"
if __name__ == "__main__":
\ No newline at end of file
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment