MODE: high-resolution digital dissociation with deep multimodal autoencoder

In single cell biology, the complexity of tissues may hinder lineage cell mapping or tumor microenvi-ronment decomposition, requiring digital dissociation of bulk tissues. Many deconvolution methods focus on transcriptomic assay, not easily applicable to other omics due to ambiguous cell markers and reference-to-target difference. Here, we present MODE, a multimodal autoencoder pipeline linking multi-dimensional features to jointly predict personalized multi-omic profiles and cellular compositions, using pseudo-bulk data constructed by internal non-transcriptomic reference and external scRNA-seq data. MODE was evaluated through rigorous simulation experiments and real multiomic data from multiple tissue types, outperforming nine deconvolution pipelines with superior generalizability and fidelity.