A deep generative model for multi-view profiling of single-cell RNA-seq and ATAC-seq data

Abstract

Here, we present a multi-modal deep generative model, the single-cell Multi-View Profiler (scMVP), which is designed for handling sequencing data that simultaneously measure gene expression and chromatin accessibility in the same cell, including SNARE-seq, sci-CAR, Paired-seq, SHARE-seq, and Multiome from 10X Genomics. scMVP generates common latent representations for dimensionality reduction, cell clustering, and developmental trajectory inference and generates separate imputations for differential analysis and cis-regulatory element identification. scMVP can help mitigate data sparsity issues with imputation and accurately identify cell groups for different joint profiling techniques with common latent embedding, and we demonstrate its advantages on several realistic datasets.

Integrated single-cell (phospho-)protein and RNA detection uncovers phenotypic characteristics of human antibody secreting cells

“…Computational strategies encounter several considerations as how to define anchors, scalability and handling missing data ( 43 ). Several of these challenges are being addressed by recently developed tools including MOFA+ ( 24 ), multiVI ( 44 ), COBOLT ( 45 ), StabMap ( 46 ) scMVP ( 47 ), and Bridge Integration ( 48 ). So-far there was no illustration of integrating mRNA datasets with a comprehensive intracellular phospho-protein and transcription factor dataset using a common set of surface proteins.…”

Interpretable deep generative models for genomics

“…Recently, there has been great interest in integrative analysis of multi-modal data resulting from sequencing technologies that measures two modalities such as SNARE-Seq 71 measuring gene expression and chromatin accessibility as well as CITE-Seq 96 measuring gene expression and protein expression. Even for methods that modifies VAE to jointly model two modalities (totalVI 97 , multiVI 98 , scMVP 99 , BABEL 100 , and Cobolt 101 ), an interpretability term could be applied to understand how individual features of each modality relate to features of another modality such as linking enhancers based on chromatin accessibility to its target genes.…”

Single cell cancer epigenetics

“…It is also necessary to evaluate the integration of multi-omics data, including paired multimodal data. New multi-omic integrative pipelines were recently designed to facilitate the analysis of multiple layers of epigenetic data simultaneously, such as MOFA+ [138,139], scMVP [140], Babel [141], Maestro [142], or EpiScanpy [116]. In addition, new user-friendly interfaces, such as ShinyArchR for scATAC-seq [143] or ChromSCape for scHi-C [144], will make analysis more accessible for nonbioinformaticians.…”