genetics/alg/ampf.py

import os
from Bio import SeqIO

# Ścieżki do katalogów i plików FASTA
data_dir = "../data"
output_dir = "../out"
os.makedirs(output_dir, exist_ok=True)

# Pliki primerów
primer_ITS1_file = os.path.join(data_dir, "ITS1.fasta")
primer_ITS4_file = os.path.join(data_dir, "ITS4.fasta")

# Funkcja do wczytywania sekwencji primerów z plików FASTA
def load_primer(primer_file):
    record = SeqIO.read(primer_file, "fasta")
    return str(record.seq)

# Funkcja do znajdowania pozycji amplifikowanych regionów
def find_amplified_regions(genome_seq, primer_its1, primer_its4):
    its1_positions = []
    its4_positions = []
    
    # Szukanie dopasowań dla ITS1
    pos = genome_seq.find(primer_its1)
    while pos != -1:
        its1_positions.append(pos)
        pos = genome_seq.find(primer_its1, pos + 1)
        
    # Szukanie dopasowań dla ITS4
    pos = genome_seq.find(primer_its4)
    while pos != -1:
        its4_positions.append(pos)
        pos = genome_seq.find(primer_its4, pos + 1)
        
    # Znajdowanie regionów amplifikowanych między primerami ITS1 i ITS4
    amplified_regions = []
    for start in its1_positions:
        for end in its4_positions:
            if end > start:
                amplified_region = genome_seq[start:end + len(primer_its4)]
                amplified_regions.append((start, end + len(primer_its4), amplified_region))
                break  # Przerwij po znalezieniu pierwszego pasującego ITS4 po ITS1
    return amplified_regions

# Wczytywanie primerów ITS1 i ITS4
primer_ITS1 = load_primer(primer_ITS1_file)
primer_ITS4 = load_primer(primer_ITS4_file)

# Lista plików genomów do analizy
genome_files = [
    os.path.join(data_dir, filename)
    for filename in ["217314860.fasta", "2187833333.fasta", "2813891763.fasta", "2813891767.fasta", "599088294.fasta"]
]

# Analiza amplifikacji dla każdego pliku genomu
for genome_file in genome_files:
    with open(genome_file) as f:
        genome_record = SeqIO.read(f, "fasta")
        genome_seq = str(genome_record.seq)

    # Znajdowanie amplifikowanych regionów
    amplified_regions = find_amplified_regions(genome_seq, primer_ITS1, primer_ITS4)

    # Zapis wyników dla każdego pliku genomu do ../out
    output_filename = f"amplified_regions_{os.path.basename(genome_file)}.txt"
    output_path = os.path.join(output_dir, output_filename)
    with open(output_path, "w") as output_file:
        output_file.write(f"Amplified Regions for {os.path.basename(genome_file)}:\n")
        for start, end, region in amplified_regions:
            output_file.write(f"Start: {start}, End: {end}, Length: {len(region)}\n")
            output_file.write(f"Region sequence: {region}\n\n")
    
    print(f"Amplified regions for {os.path.basename(genome_file)} saved to {output_path}")