Available Now

Synthetic cfDNA
That Works

Unlimited biologically accurate cfDNA data for NIPT algorithm development, validation, and research. Off-the-shelf datasets or fully customised generation.

100%T21 SensitivityZ-score detection
75%T18/T13 SensitivityMatches clinical detection at 1M depth
100%SpecificityNo false positives
92.9%Distribution Matchvs real cfDNA

T18/T13 sensitivity at 75% matches clinical detection patterns at 1M depth — higher depth improves sensitivity, as in real NIPT.

Download a Free T21 Sample

1M fragments, 15% fetal fraction, HDF5 format. Evaluate in your own pipeline — no sign-up required.

HDF5 format226 MBTrisomy 21
Download Sample

Choose Your Data Package

Off-the-shelf datasets for immediate use, or custom generation to your exact specifications.

Standard Dataset

Ready-to-use cfDNA samples

£5,000 – £10,000

  • 1M fragments per sample
  • 31 samples included (Normal, T21, T18, T13)
  • Fetal fractions: 8%, 10%, 15%
  • HDF5 format with full sequences
  • Ground truth labels for all samples

Research Partnership

For academic institutions

£100,000 – £500,000

  • Everything in Custom Generation
  • Academic pricing available
  • Co-authorship opportunities
  • Technical collaboration
  • Publication support

Proof That It Works

Our synthetic cfDNA has been validated through a 4-level framework covering distributional accuracy, z-score detection, and downstream task performance.

01

Distributional Similarity

Fragment sizes, GC content, nucleotide patterns, and end motifs match real cfDNA.

92.9% similarity score
02

Z-Score Detection

Clinical NIPT z-score method correctly detects trisomies in synthetic samples.

100% T21, 75% T18/T13
03

Classifier Training

Adding synthetic data to real training data improves model performance.

+0.102 AUC improvement
04

Controllability

Generation parameters produce expected outputs (fetal fraction, conditions).

100% parameter accuracy

What You Can Build

Algorithm Development

Train and validate NIPT detection algorithms with unlimited labelled data. Test edge cases like low fetal fraction that are rare in real datasets.

Method Validation

Validate new NIPT methods against known ground truth. Test sensitivity at different fetal fractions and read depths.

ML Model Training

Augment limited real data with synthetic samples. Our validation shows +10% AUC improvement in low-data regimes.

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.

What's Included

ParameterStandard DatasetCustom Generation
Fragments per sample1,000,0001M - 16M (configurable)
Fragment length range50-250 bp50-250 bp
Fetal fraction8%, 10%, 15%2% - 25%
ConditionsNormal, T21, T18, T13107 including SCAs, microdeletions, microduplications, monogenic, oncology
Output formatHDF5 with sequences, positions, chromosomesHDF5, FASTQ, or custom
MetadataJSON per sample (FF, condition, params)Full provenance tracking
Ground truth labelsYesYes
DeliverySecure download linkSecure download or cloud storage

Book a 15-min Demo

See the data, ask questions, and find the right package for your needs.