Back

High-resolution digital dissociation of brain tumors with deep multimodal autoencoder

Sun, J.; Pan, Y.; Lin, T.; Smith, K.; Onar-Thomas, A.; Robinson, G. W.; Zhang, W.; Northcott, P. A.; Li, Q.

2025-01-03 bioinformatics
10.1101/2025.01.02.631152 bioRxiv
Show abstract

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.

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.