Towards Useful and Private Synthetic Omics: Community Benchmarking of Generative Models for Transcriptomics Data
Hakime Öztürk, Tejumade Afonja, Joonas Jälkö, Rūta Binkytė, Pablo Rodríguez-Mier, Sebastian Lobentanzer, A B Wicks, Jules Kreuer, Sofiane Ouaari, Nico Pfeifer, Shane Menzies, Sikha Pentyala, Daniil Filienko, Steven Golob, P.S. McKeever, , Antti Honkela
The paper benchmarks generative models for synthetic bulk RNA-seq data, finding trade-offs between utility, biological preservation, and privacy risks across different methods.
bioRxiv · Mar 4, 2026 · PreprintBioinformatics