|
| 1 | +"""FASTQ test data generation for benchmarking.""" |
| 2 | +import gzip |
| 3 | +import random |
| 4 | +import time |
| 5 | +from pathlib import Path |
| 6 | + |
| 7 | + |
| 8 | +def generate_data(r1_gz: Path, r2_gz: Path, num_pairs: int, seed: int = 2026): |
| 9 | + """Generate random paired-end FASTQ reads (independent R1/R2).""" |
| 10 | + READ_LEN = 150 |
| 11 | + BATCH = 100_000 |
| 12 | + BASES = b"ACGT" |
| 13 | + QUAL_POOL = 512 |
| 14 | + rng = random.Random(seed) |
| 15 | + |
| 16 | + pool = [] |
| 17 | + for _ in range(QUAL_POOL): |
| 18 | + q = bytearray(READ_LEN) |
| 19 | + for j in range(READ_LEN): |
| 20 | + if j < 5 or j > READ_LEN - 10: |
| 21 | + q[j] = rng.randint(20, 35) + 33 |
| 22 | + else: |
| 23 | + q[j] = rng.randint(30, 40) + 33 |
| 24 | + pool.append(bytes(q)) |
| 25 | + |
| 26 | + t0 = time.time() |
| 27 | + written = 0 |
| 28 | + with gzip.open(r1_gz, "wb", compresslevel=1) as f1, \ |
| 29 | + gzip.open(r2_gz, "wb", compresslevel=1) as f2: |
| 30 | + while written < num_pairs: |
| 31 | + n = min(BATCH, num_pairs - written) |
| 32 | + b1 = bytearray() |
| 33 | + b2 = bytearray() |
| 34 | + for i in range(n): |
| 35 | + rid = written + i + 1 |
| 36 | + name = f"@SIM:BENCH:1:{1101 + rid // 10000000}:{rid % 50000}:{(rid * 7) % 50000}".encode() |
| 37 | + s1 = bytes(rng.choices(BASES, k=READ_LEN)) |
| 38 | + s2 = bytes(rng.choices(BASES, k=READ_LEN)) |
| 39 | + q1 = pool[rng.randint(0, QUAL_POOL - 1)] |
| 40 | + q2 = pool[rng.randint(0, QUAL_POOL - 1)] |
| 41 | + b1 += name + b" 1:N:0:ATCG\n" + s1 + b"\n+\n" + q1 + b"\n" |
| 42 | + b2 += name + b" 2:N:0:ATCG\n" + s2 + b"\n+\n" + q2 + b"\n" |
| 43 | + f1.write(bytes(b1)) |
| 44 | + f2.write(bytes(b2)) |
| 45 | + written += n |
| 46 | + if written % 1_000_000 == 0: |
| 47 | + e = time.time() - t0 |
| 48 | + eta = (num_pairs - written) / (written / e) |
| 49 | + print(f" {100 * written / num_pairs:5.1f}% {written / 1e6:.0f}M pairs" |
| 50 | + f" {written / e / 1e6:.2f}M/s ETA {eta:.0f}s", flush=True) |
| 51 | + |
| 52 | + print(f" Generated in {time.time() - t0:.1f}s") |
| 53 | + |
| 54 | + |
| 55 | +def generate_merge_data(r1_gz: Path, r2_gz: Path, num_pairs: int, seed: int = 2026): |
| 56 | + """Generate overlapping PE reads for merge/correction testing. |
| 57 | +
|
| 58 | + Each pair derives from a random fragment with insert size ~220bp (sd=30). |
| 59 | + R2 is the reverse complement of the fragment's 3' end. Mismatches are |
| 60 | + injected in the overlap region with low quality on R2 to trigger base |
| 61 | + correction (R1 Q30+ vs R2 Q10-14 at mismatch positions). |
| 62 | + """ |
| 63 | + READ_LEN = 150 |
| 64 | + BATCH = 100_000 |
| 65 | + BASES = b"ACGT" |
| 66 | + COMP = bytes.maketrans(b"ACGT", b"TGCA") |
| 67 | + QUAL_POOL = 512 |
| 68 | + INSERT_MEAN = 220 |
| 69 | + INSERT_SD = 30 |
| 70 | + MIN_INSERT = READ_LEN + 30 # need >= 30bp overlap for fastp |
| 71 | + MAX_INSERT = 2 * READ_LEN - 1 |
| 72 | + MISMATCH_RATE = 0.015 |
| 73 | + |
| 74 | + rng = random.Random(seed) |
| 75 | + |
| 76 | + pool = [] |
| 77 | + for _ in range(QUAL_POOL): |
| 78 | + q = bytearray(READ_LEN) |
| 79 | + for j in range(READ_LEN): |
| 80 | + if j < 5 or j > READ_LEN - 10: |
| 81 | + q[j] = rng.randint(25, 35) + 33 |
| 82 | + else: |
| 83 | + q[j] = rng.randint(30, 40) + 33 |
| 84 | + pool.append(bytes(q)) |
| 85 | + |
| 86 | + def revcomp(seq: bytes) -> bytes: |
| 87 | + return seq.translate(COMP)[::-1] |
| 88 | + |
| 89 | + t0 = time.time() |
| 90 | + written = 0 |
| 91 | + with gzip.open(r1_gz, "wb", compresslevel=1) as f1, \ |
| 92 | + gzip.open(r2_gz, "wb", compresslevel=1) as f2: |
| 93 | + while written < num_pairs: |
| 94 | + n = min(BATCH, num_pairs - written) |
| 95 | + b1 = bytearray() |
| 96 | + b2 = bytearray() |
| 97 | + for i in range(n): |
| 98 | + rid = written + i + 1 |
| 99 | + name = f"@SIM:MERGE:1:{1101 + rid // 10000000}:{rid % 50000}:{(rid * 7) % 50000}".encode() |
| 100 | + |
| 101 | + # Sample insert size from truncated normal distribution |
| 102 | + insert = int(rng.gauss(INSERT_MEAN, INSERT_SD)) |
| 103 | + insert = max(MIN_INSERT, min(MAX_INSERT, insert)) |
| 104 | + |
| 105 | + # Generate fragment and derive reads |
| 106 | + frag = bytearray(rng.choices(BASES, k=insert)) |
| 107 | + s1 = bytes(frag[:READ_LEN]) |
| 108 | + s2 = bytearray(revcomp(bytes(frag[insert - READ_LEN:]))) |
| 109 | + |
| 110 | + q1 = bytearray(pool[rng.randint(0, QUAL_POOL - 1)]) |
| 111 | + q2 = bytearray(pool[rng.randint(0, QUAL_POOL - 1)]) |
| 112 | + |
| 113 | + # Inject mismatches in R2 overlap with low quality to trigger correction |
| 114 | + overlap_len = 2 * READ_LEN - insert |
| 115 | + n_mm = max(1, int(overlap_len * MISMATCH_RATE)) |
| 116 | + n_mm = min(n_mm, min(4, int(overlap_len * 0.19))) |
| 117 | + overlap_start = READ_LEN - overlap_len |
| 118 | + for p in rng.sample(range(overlap_start, READ_LEN), n_mm): |
| 119 | + alts = [b for b in BASES if b != s2[p]] |
| 120 | + s2[p] = rng.choice(alts) |
| 121 | + q2[p] = rng.randint(10 + 33, 14 + 33) # Q10-14 |
| 122 | + |
| 123 | + b1 += name + b" 1:N:0:ATCG\n" + s1 + b"\n+\n" + bytes(q1) + b"\n" |
| 124 | + b2 += name + b" 2:N:0:ATCG\n" + bytes(s2) + b"\n+\n" + bytes(q2) + b"\n" |
| 125 | + f1.write(bytes(b1)) |
| 126 | + f2.write(bytes(b2)) |
| 127 | + written += n |
| 128 | + if written % 1_000_000 == 0: |
| 129 | + e = time.time() - t0 |
| 130 | + eta = (num_pairs - written) / (written / e) |
| 131 | + print(f" {100 * written / num_pairs:5.1f}% {written / 1e6:.0f}M pairs" |
| 132 | + f" {written / e / 1e6:.2f}M/s ETA {eta:.0f}s", flush=True) |
| 133 | + |
| 134 | + print(f" Generated in {time.time() - t0:.1f}s") |
0 commit comments