- PIANO introduces a probabilistic generative autoencoder for gene expression, explicitly modelling covariate effects to deconfound single-cell and multi-omics data.
- Robustly corrects strong batch effects and integrates data across species, single-cell and spatial transcriptomics, enabling accurate cross-modal comparisons.
- Scales to over 100 million cells, trains tenfold faster than prior methods, and models disease progression and drug perturbations.
Cell Rep Methods. 2026 Nov 12:101661. doi: 10.1016/j.crmeth.2026.101661. Online ahead of print.
ABSTRACT
Single-cell RNA technologies enable the routine acquisition of transcriptomic atlases. However, these molecular profiles are influenced by overlapping sources of variation. Since these covariates confound comparisons, data integration is the first step in most analyses. Three challenges remain: correcting strong batch effects, scaling to millions of cells, and modeling how covariates influence gene expression. To address these challenges, we developed PIANO, probabilistic inference autoencoder networks for multi-omics, a deep learning framework whose central feature is a generative model of gene expression data. Additionally, PIANO achieves robust integrations and trains 10× faster than previous methods. PIANO accurately integrates single-cell data across species and across single-cell and spatial transcriptomics modalities. As practical applications, PIANO models spatially resolved gene expression during Alzheimer’s disease progression in human brains and integrates over 100 million cancer cells to model drug perturbations. In summary, PIANO’s integration and generative modeling capabilities will empower novel insights for a wide range of future studies.
PMID:43020064 | DOI:10.1016/j.crmeth.2026.101661
Share Evidence Blueprint
Save to Google Notes

Search Google Scholar
⭐ My Revision List

