SNPgen: Phenotype-Supervised Genotype Representation and Synthetic Data Generation via Latent Diffusion
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915854296285184 |
|---|---|
| author | Lampis, Andrea Massi, Michela Carlotta Pirastu, Nicola Ieva, Francesca Matteucci, Matteo Di Angelantonio, Emanuele |
| author_facet | Lampis, Andrea Massi, Michela Carlotta Pirastu, Nicola Ieva, Francesca Matteucci, Matteo Di Angelantonio, Emanuele |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_10873 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SNPgen: Phenotype-Supervised Genotype Representation and Synthetic Data Generation via Latent Diffusion Lampis, Andrea Massi, Michela Carlotta Pirastu, Nicola Ieva, Francesca Matteucci, Matteo Di Angelantonio, Emanuele Machine Learning Genomics 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. |
| title | SNPgen: Phenotype-Supervised Genotype Representation and Synthetic Data Generation via Latent Diffusion |
| topic | Machine Learning Genomics |
| url | https://arxiv.org/abs/2603.10873 |