OmicsTransformer: self-supervised masked consistency and uncertainty-aware fusion for robust multi-omics prediction
TL;DR
OmicTransformer is presented, an end-to-end framework that projects each omics modality into latent patches, enforces masked semantic consistency through an Exponential Cosine Consistency Loss, models global patch dependencies with a Transformer encoder, and fuses modalities by sample-specific uncertainty.
Abstract
Abstract Motivation Multi-omics integration can improve cancer diagnosis and prognosis, but current models are limited by extreme dimensionality, redundant raw-feature similarities, missing assays, and incomplete pathway priors. We ask whether biologically meaningful patient manifolds can be learned directly from high-dimensional multi-omics data without heuristic graph construction or fixed knowledge-base constraints. Results We present OmicsTransformer, an end-to-end framework that projects each omics modality into latent patches, enforces masked semantic consistency through an Exponential Cosine Consistency Loss, models global patch dependencies with a Transformer encoder, and fuses modalities by sample-specific uncertainty. Across eight diagnostic and prognostic cohorts, OmicsTransformer achieved strong performance, including 89.4% accuracy for TCGA-BRCA subtyping and 90.6% area under the receiver operating characteristic curve (AUC) for TCGA-LGG grading. It improved recurrence prediction over the pathway-restricted DeepKEGG baseline by approximately 21.5 percentage points in accuracy (ACC) on TCGA-LIHC and 11.1 percentage points in ACC on TCGA-BLCA. Variance-weighted attribution with ensemble stability selection recovered reproducible cross-modal biomarker cores and non-canonical progression drivers. Availability and implementation Source code and datasets are freely available at https://github.com/FFJXX/OmicTransformer and https://doi.org/10.6084/m9.figshare.31523905. OmicsTransformer is implemented in PyTorch.