SNPgen: Phenotype-Supervised Genotype Representation and Synthetic Data Generation via Latent Diffusion

TL;DR

SNPgen is a novel two-stage framework that generates phenotype-supervised synthetic genotypes using latent diffusion, enabling privacy-preserving data sharing while maintaining utility for genomic prediction tasks.

Contribution

It introduces a conditional latent diffusion approach combined with GWAS-guided variant selection for realistic, phenotype-aligned synthetic genotype generation.

Findings

Synthetic data matches real-data predictive performance.

High allele frequency correlation with source data.

Zero identical matches, ensuring privacy protection.

Abstract

Polygenic risk scores and other genomic analyses require large individual-level genotype datasets, yet strict data access restrictions impede sharing. Synthetic genotype generation offers a privacy-preserving alternative, but most existing methods operate unconditionally, producing samples without phenotype alignment, or rely on unsupervised compression, creating a gap between statistical fidelity and downstream task utility. We present SNPgen, a two-stage conditional latent diffusion framework for generating phenotype-supervised synthetic genotypes. SNPgen combines GWAS-guided variant selection (1,024-2,048 trait-associated SNPs) with a variational autoencoder for genotype compression and a latent diffusion model conditioned on binary disease labels via classifier-free guidance. Evaluated on 458,724 UK Biobank individuals across four complex diseases (coronary artery disease, breast cancer, type 1 and type 2 diabetes), models trained on synthetic data matched real-data predictive performance in a train-on-synthetic, test-on-real protocol, approaching genome-wide PRS methods that use $2$-$6\times$ more variants. Privacy analysis confirmed zero identical matches, near-random membership inference (AUC $\approx 0.50$), preserved linkage disequilibrium structure, and high allele frequency correlation ($r \geq 0.95$) with source data. A controlled simulation with known causal effects verified faithful recovery of the imposed genetic association structure.