Files
obikmer/scripts/docker_debug/gen_fasta_real.py
T

39 lines
1.5 KiB
Python
Raw Normal View History

#!/usr/bin/env python3
"""gen_fasta_real.py N OUTDIR GENOMES_DIR [WINDOW] [SEED] [MUT]
N derived genomes built from *real* genomes (GENOMES_DIR/*.fna.gz): each one is
a random window of WINDOW bp of a randomly chosen real genome, point-mutated at
rate MUT (default 3 %, which alters ~47 % of 21-mers), so a merge both finds
k-mers already present in the destination and creates new ones, with realistic
sequence statistics (no dedicated degenerate structure).
"""
import glob, gzip, random, sys
n, out, gdir = int(sys.argv[1]), sys.argv[2], sys.argv[3]
window = int(sys.argv[4]) if len(sys.argv) > 4 else 300_000
seed = int(sys.argv[5]) if len(sys.argv) > 5 else 20261118
mut = float(sys.argv[6]) if len(sys.argv) > 6 else 0.03
rng = random.Random(seed)
def read_fna(path):
seq = []
with gzip.open(path, "rt") as fh:
for line in fh:
if not line.startswith(">"):
seq.append(line.strip().upper())
return "".join(seq)
genomes = [read_fna(p) for p in sorted(glob.glob(f"{gdir}/*.fna.gz"))]
genomes = [g for g in genomes if len(g) > window]
for i in range(n):
g = rng.choice(genomes)
start = rng.randrange(0, len(g) - window)
s = list(g[start:start + window])
for j in range(len(s)):
if s[j] in "ACGT" and rng.random() < mut:
s[j] = rng.choice("ACGT")
seq = "".join(c if c in "ACGT" else "A" for c in s)
with open(f"{out}/R{i:03d}.fasta", "w") as fh:
fh.write(f">R{i:03d}\n")
for k in range(0, len(seq), 80):
fh.write(seq[k:k + 80] + "\n")