Available Now
How we
tested it
Locked claims only: AUC 0.87 on real karyotyped T21, and T21/T18/T13 at 8% FF on a purely synthetic WisecondorX reference panel. Labelled FASTQ for caller testing.
Validated against 26 real clinical cfDNA samples (6 T21 patients, 20 euploid) from Lun et al. 2014, PRJNA215135.
Train Synthetic, Test Real
Detecting Real T21 With Synthetic Training Data
We trained a classifier entirely on synthetic cfDNA — zero real patient data in training. Then tested it blind on 26 real clinical samples from an independent dataset (Lun et al. 2014, PRJNA215135), including 6 karyotype-confirmed trisomy 21 cases.
Per-Patient Results
Four of six real T21 samples sit below a z-score of 3.0 on a standard reference (NIPD-66 is a known ~1–2% FF anomaly). The table is a TSTR result, not a product claim that these files beat clinical NIPT.
| Patient | Z-Score (real ref) | Standard NIPT | TSTR Detection |
|---|---|---|---|
| NIPD-03 | 5.45 | Detected | Above all euploid |
| NIPD-60 | 3.43 | Borderline | Above all euploid |
| NIPD-07 | 2.47 | FAIL | Above all euploid |
| NIPD-50 | 1.57 | FAIL | Above all euploid |
| NIPD-04 | 1.29 | FAIL | Below 2 euploid |
| NIPD-66 | 0.86 | FAIL (anomaly) | Below 14 euploid |
Summary Metrics
| Metric | Value | Notes |
|---|---|---|
| TSTR AUC | 0.867 | 6 T21 vs 20 euploid, trained entirely on synthetic |
| Adjusted AUC | 0.980 | Excluding NIPD-66 (genuine anomaly, FF ~1-2%) |
| Augmented AUC | 0.942 | Real + synthetic outperforms real-only (0.883) by +5.8pp |
| Permutation p-value | 0.002 | 2/1000 random label shuffles matched observed AUC |
| Low-z T21 ranking | See table | TSTR ranking on this cohort, not a claim that files beat clinical NIPT |
Key Finding
NIPD-66 is a genuine anomaly — chr21 fraction only 0.027pp above the euploid mean, implying fetal fraction ~1-2%. This sample would fail any chromosome-fraction NIPT method. Excluding it, the adjusted AUC is 0.980 and 4 of 5 T21 samples rank above all 20 euploid samples.
WisecondorX
Detection on a synthetic panel
Fetal fraction was 8%. Fifty synthetic euploid samples form the reference panel — not a clinical panel. Do not read this as 100% on the public 1M ZIP or at 2% FF.
| Condition | Samples | Z-Score Range | Detection |
|---|---|---|---|
| Trisomy 21 | 3 | 4.7 - 6.5 | Rank 1 (all) |
| Trisomy 18 | 3 | 6.2 - 8.2 | Rank 1 (all) |
| Trisomy 13 | 3 | 7.5 - 9.0 | Rank 1-2 |
| Euploid controls | 50 | -1.2 - 1.1 | No false calls on this panel |
Augmentation Value
Synthetic Data Rescues Low-Data Regimes
When real training samples are scarce — the reality for rare aneuploidies — adding synthetic data dramatically improves classifier performance. 100 random stratified splits per condition.
| N Real Samples | Real-Only AUC | Augmented AUC | Improvement | Win Rate |
|---|---|---|---|---|
| 3 | 0.661 | 0.858 | +0.197 | 88% |
| 5 | 0.691 | 0.832 | +0.141 | 83% |
| 7 | 0.725 | 0.887 | +0.163 | 87% |
| 10 | 0.768 | 0.877 | +0.109 | 75% |
| 20 | 0.898 | 0.944 | +0.046 | 26% |
Practical Impact
With only 3 real training samples, synthetic augmentation improves AUC by +19.7 points (0.661 → 0.858) and wins 88% of random splits. Augmented models also have consistently lower variance — synthetic data stabilises training.
Data Products
Choose Your Data Package
Self-serve aneuploidy starter pack at $399, deeper four-file packs, or catalogue/generate on the dashboard.
Aneuploidy starter pack
T21 + T18 + T13 + matched euploid as one checkout
$399
- 4M PE each at 8% FF
- Deeper packs $200–$800 for the same four files
- 107 conditions available via catalogue/generate, not the homepage SKU
- Delivered as paired-end FASTQ
- Pack quantity 1 — not a 25-sample minimum
Catalogue & generate
Conditions beyond the starter pack, self-serve on the dashboard
Self-serve
- Same generation path as the starter pack
- Catalogue reuse or generate a new file
- Questions: kyle@eabhaseq.com
Validation
How we tested it
Our synthetic cfDNA has been validated end-to-end: generated sequences are aligned to GRCh38, then tested against real karyotype-confirmed clinical samples.
Alignment & Realism
Insert size peaks at 166bp (mono-nucleosome). Alignment yield depends on the generator path; do not treat a single MAPQ percentage as a product spec.
Train Synthetic, Test Real
Classifier trained entirely on synthetic data detects real karyotyped T21 samples. Tested on 26 unique clinical samples from PRJNA215135 (Lun et al. 2014).
WisecondorX on a synthetic panel
WisecondorX analysis detects all synthetic trisomies (T21, T18, T13) at 8% fetal fraction. Augmenting real data with synthetic improves AUC by up to +19.7 points.
Statistical Rigour
Permutation testing (1,000 resamples) and bootstrap CIs confirm results are not due to chance. Low-data augmentation tested across 100 random splits per condition.
Applications
What You Can Build
Algorithm Development
Train and validate NIPT detection algorithms with labelled synthetic data. Test edge cases like low fetal fraction that are rare in real datasets.
Synthetic reference panels
WisecondorX detected T21/T18/T13 at 8% FF using a synthetic euploid reference panel — not a clinical panel or a physical control.
Pipeline verification
Drop FASTQ into the analysis step. This does not exercise extraction or the sequencer.
Privacy-Compliant Research
Conduct research without patient data concerns. Synthetic data contains no identifiable information.
Education & Training
Train clinical scientists and bioinformaticians with realistic data. Perfect for courses and workshops.
Benchmark Creation
Create standardised benchmarks with known ground truth for comparing NIPT methods across laboratories.
Specifications
What's Included
| Parameter | Standard Dataset | Custom Generation |
|---|---|---|
| Fragments per sample | 4M (starter) | 4M–32M |
| Fragment length range | 50-250 bp | 50-250 bp |
| Fetal fraction | 8% default | 1% - 25% |
| Conditions | T21, T18, T13 + euploid controls | 107 including SCAs, microdeletions, microduplications, monogenic, oncology |
| Output format | paired-end FASTQ | paired-end FASTQ |
| Minimum order | 1 pack | 1 sample |
| Metadata | JSON per sample (FF, condition, params) | Full provenance tracking |
| Ground truth labels | Yes | Yes |
| Delivery | Secure download link | Secure download |
Order the files, or start with the free sample
Self-serve $399 starter pack. Catalogue and generate on the dashboard.