Dictionary learning for integrative, multimodal, and scalable single-cell analysis

Mapping single-cell sequencing profiles to comprehensive reference datasets represents a powerful alternative to unsupervised analysis. Reference datasets, however, are predominantly constructed from single-cell RNA-seq data, and cannot be used to annotate datasets that do not measure gene expression. Here we introduce bridge integration, a method to harmonize singlecell datasets across modalities by leveraging a multi-omic dataset as a molecular bridge. Each cell in the multi-omic dataset comprises an element in a dictionary, which can be used to reconstruct unimodal datasets and transform them into a shared space. We demonstrate that our procedure can accurately harmonize transcriptomic data with independent single cell measurements of chromatin accessibility, histone modifications, DNA methylation, and protein levels. Moreover, we demonstrate how dictionary learning can be combined with sketching techniques to substantially improve computational scalability, and harmonize 8.6 million human immune cell profiles from sequencing and mass cytometry experiments. Our approach aims to broaden the utility of single-cell reference datasets and facilitate comparisons across diverse molecular modalities. AvailabilityInstallation instructions, documentations, and vignettes are available at http://www.satijalab.org/seurat

Integrated analysis of multimodal single-cell data

The simultaneous measurement of multiple modalities, known as multimodal analysis, represents an exciting frontier for single-cell genomics and necessitates new computational methods that can define cellular states based on multiple data types. Here, we introduce weighted-nearest neighbor analysis, an unsupervised framework to learn the relative utility of each data type in each cell, enabling an integrative analysis of multiple modalities. We apply our procedure to a CITE-seq dataset of hundreds of thousands of human white blood cells alongside a panel of 228 antibodies to construct a multimodal reference atlas of the circulating immune system. We demonstrate that integrative analysis substantially improves our ability to resolve cell states and validate the presence of previously unreported lymphoid subpopulations. Moreover, we demonstrate how to leverage this reference to rapidly map new datasets, and to interpret immune responses to vaccination and COVID-19. Our approach represents a broadly applicable strategy to analyze single-cell multimodal datasets, including paired measurements of RNA and chromatin state, and to look beyond the transcriptome towards a unified and multimodal definition of cellular identity. AvailabilityInstallation instructions, documentation, tutorials, and CITE-seq datasets are available at http://www.satijalab.org/seurat