A versatile single-cell cross-modality translation method via dual-aligned variational autoencoders

Recent advancements for simultaneously profiling multi-omic modalities within individual cells have enabled the interrogation of cellular heterogeneity and molecular hierarchy. However, technical limitations lead to highly noisy multi-modal data and substantial costs. Although computational methods have been proposed to translate single-cell data across modalities, broad applications of the methods still remain impeded by formidable challenges. Here, we proposed scButterfly, a versatile single-cell cross-modality translation method based on dual-aligned variational autoencoders and innovative data augmentation schemes. With comprehensive experiments on multiple datasets, we provide compelling evidence of scButterfly's superiority over baseline methods in preserving cellular heterogeneity while translating datasets of various contexts and in revealing cell type-specific biological insights. Besides, we demonstrate the extensive applications of scButterfly for integrative multi-omics analysis of single-modality data, data enhancement of poor-quality single-cell multi-omics, and automatic cell type annotation of scATAC-seq data. Additionally, scButterfly can be generalized to unpaired data training and perturbation-response analysis via our data augmentation and optimal transport strategies. Moreover, scButterfly exhibits the capability in consecutive translation from epigenome to transcriptome to proteome and has the potential to decipher novel biomarkers.