HELICS: Biobank-scale Conditional Synthetic Genome Generation via Latent Flow Matching
Abstract
Individual-level genotype data underpin genetic discovery, disease-risk modeling, and therapeutic development, yet many critical settings remain data-limited, including underrepresented ancestries, rare or imbalanced disease cohorts, and restricted-access biobanks. Conditional synthetic genome generation would support privacy-aware benchmarking, simulation, and data augmentation, but requires learning an ultra-high-dimensional discrete distribution over hundreds of thousands to tens of millions of correlated single-nucleotide polymorphisms (SNPs), or sites of DNA variation. We introduce HELICS: High-fidelity gEneration via Latent Interpolant Conditional Synthesis, a phasing-free latent flow matching framework for genome-wide SNP-level generation from biobank-scale genotype data. HELICS tokenizes chromosomes with convolutional autoencoders, reducing >600K SNPs to 4,096 continuous latent tokens, and trains a transformer parameterized conditional flow matching model over the concatenated multi-chromosome latent representation. Trained on over 417K genomes in the UK Biobank, HELICS generates genome-wide common-variant synthetic cohorts without haplotype phasing and achieves stronger fidelity to real genotypes than existing haplotype-based simulators, including high allele-frequency agreement in external evaluation and superior preservation of local and long-range SNP correlation structure. Conditioning on ancestry and genetic liability summaries enables targeted generation across genetic risk profiles; in perturbation analyses, by increasing the conditioned disease trait liability, HELICS induces SNP-level dosage changes in generated genomes that are highly correlated with published association weights. HELICS provides a scalable generative modeling framework for SNP-level genome data and a path toward conditional synthetic cohorts for data-limited genetic studies.
Related
- trFlow: ultrafast all-atom protein conformational ensemble generation via conditional flow matching
- TopoFlow: Evolutionarily Conditioned Flow Matching for Protein Conformational Ensemble Generation
- Evaluating in-context learning with prompting regimes for transformer-based synthetic health tabular data generation
- Wigner–Ville-Based Conditional Autoencoder For Biosonar Generation And Joint Range And Off-Axis Estimation With A Single Hydrophone
- OmniTCR: a foundation model unifying T cell receptor recognition prediction and conditional sequence generation
BibTeX
@misc{abdelazim2026helics,
title = {{HELICS: Biobank-scale Conditional Synthetic Genome Generation via Latent Flow Matching}},
author = {Ahmad Abdel-Azim and Xihong Lin},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.36361},
eprint = {2610.36361},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.36361},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - HELICS: Biobank-scale Conditional Synthetic Genome Generation via Latent Flow Matching
AU - Ahmad Abdel-Azim
AU - Xihong Lin
PY - 2026
DA - 2026/10/26
PB - arXiv
DO - 10.48550/arxiv.2610.36361
UR - https://arxiv.org/abs/2610.36361
AB - Individual-level genotype data underpin genetic discovery, disease-risk modeling, and therapeutic development, yet many critical settings remain data-limited, including underrepresented ancestries, rare or imbalanced disease cohorts, and restricted-access biobanks. Conditional synthetic genome generation would support privacy-aware benchmarking, simulation, and data augmentation, but requires learning an ultra-high-dimensional discrete distribution over hundreds of thousands to tens of millions of correlated single-nucleotide polymorphisms (SNPs), or sites of DNA variation. We introduce HELICS: High-fidelity gEneration via Latent Interpolant Conditional Synthesis, a phasing-free latent flow matching framework for genome-wide SNP-level generation from biobank-scale genotype data. HELICS tokenizes chromosomes with convolutional autoencoders, reducing >600K SNPs to 4,096 continuous latent tokens, and trains a transformer parameterized conditional flow matching model over the concatenated multi-chromosome latent representation. Trained on over 417K genomes in the UK Biobank, HELICS generates genome-wide common-variant synthetic cohorts without haplotype phasing and achieves stronger fidelity to real genotypes than existing haplotype-based simulators, including high allele-frequency agreement in external evaluation and superior preservation of local and long-range SNP correlation structure. Conditioning on ancestry and genetic liability summaries enables targeted generation across genetic risk profiles; in perturbation analyses, by increasing the conditioned disease trait liability, HELICS induces SNP-level dosage changes in generated genomes that are highly correlated with published association weights. HELICS provides a scalable generative modeling framework for SNP-level genome data and a path toward conditional synthetic cohorts for data-limited genetic studies.
ER -