Authors: Anastasia Litinetskaya, Maiia Schulman, Fabiola Curion, Artur Szalata, Alireza Omidi, Mohammad Lotfollahi, Fabian Theis
Preprint in bioRxiv, 2025
Abstract
Constructing joint representations from multimodal single-cell datasets is crucial for understanding cellular heterogeneity and function. Traditional methods, such as factor analysis and kNN-based approaches, face computational limitations with scalability across large datasets and multiple modalities. In this work, we demonstrate the product-of-experts VAE-based model, which offers a flexible, scalable solution for integrating multimodal data, allowing for the seamless mapping of both unimodal and multimodal queries onto a reference atlas.
We evaluate how different strategies for combining modalities in the VAE framework impact query-to-reference mapping across diverse datasets, including CITE-seq and spatial metabolomics. Our benchmarks assess batch effect correction, biological signal preservation, and imputation of missing modalities. We showcase our approach in a mosaic setting, integrating CITE-seq and multiome data to accurately map unimodal and multimodal queries into the joint latent space.
Are you wondering how to integrate scRNAseq and scATAC-seq or combine it with a CITE-seq to have tiromodal single-cell reference atlas? How about mapping a new query data (e.g., a new scATAC or scRNA)? Check out our new Multigrate vignette: scarches.readthedocs.io/en/latest/mult…
