Article

Unifying multimodal single-cell data with a mixture-of-experts <i>β</i> -variational autoencoder framework

2025-03-06

Abstract excerpt

Multimodal single-cell assays profile complementary layers of cell state, but integration is complicated by modality mismatch, sparsity, and uneven cohort coverage. We present UniVI ( Uni fied V ariational I nference), a scalable mixture-of-experts β -variational autoencoder that learns a shared latent space while preserving modality-specific structure. UniVI couples modality-specific encoders/de-coders with a...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: bb8b6d81-ae91-5b21-9d0e-b01733ece339
DOI: 10.1101/2025.02.28.640429

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Unifying multimodal single-cell data with a mixture-of-experts <i>β</i> -variational autoencoder frameworkDOI 10.1101/2025.02.28.640429Read

MIDAS: a deep generative model for mosaic integration and knowledge transfer of single-cell multimodal dataSemantic proximity Read

multiHIVE: Hierarchical Multimodal Deep Generative Modeling for Single-cell MultiomicsSemantic proximity Read

Robust probabilistic modeling for single-cell multimodal mosaic integration and imputation via scVAEITSemantic proximity Read

ARCADIA Reveals Spatially Dependent Transcriptional Programs through Integration of scRNA-seq and Spatial ProteomicsSemantic proximity Read

Multi-view deep learning of highly multiplexed imaging data improves association of cell states with clinical outcomesSemantic proximity Read

scWeave: A deep learning model that bidirectionally translates between gene expression and chromatin structure at single-cell resolutionSemantic proximity Read

CAPTAIN: A multimodal foundation model pretrained on co-assayed single-cell RNA and proteinSemantic proximity Read

multiHIVE: Hierarchical Multimodal Deep Generative Model for Single-cell Multiomics IntegrationSemantic proximity Read

Population-level integration of single-cell datasets enables multi-scale analysis across samplesSemantic proximity Read

Partially Shared Multi-Modal Embedding Learns Holistic Representation of Cell StateSemantic proximity Read

Integrating single-cell multimodal epigenomic data using 1D-convolutional neural networksSemantic proximity Read

Online single-cell data integration through projecting heterogeneous datasets into a common cell-embedding spaceSemantic proximity Read