In silico generation of gene expression profiles using diffusion models
Alice Lacan, Romain André, Michèle Sebag, Blaise Hanczar · 2026
Read In silico generation of gene expression profiles using diffusion models by Alice Lacan, Romain André, Michèle Sebag, Blaise Hanczar (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13418420.txt.
Description
Alice Lacan and colleagues tested diffusion models in 2026 for creating synthetic gene-expression data to ease small-sample problems in precision medicine. RNA data sets often hold too few samples for deep learning, and earlier synthetic generators leaned on variational autoencoders and adversarial networks.
Diffusion models trained on landmark genes predicted better on cancer and tissue reference data, and methods that rebuild the full transcriptome lifted diffusion, autoencoder, and adversarial models alike. Researchers gain a strong new synthetic-data option for training models where patient samples stay scarce. The work matters where gene data are precious and every sample counts.
Catalog record
| CREATOR | Alice Lacan, Romain André, Michèle Sebag, Blaise Hanczar |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 52 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |