Protein-protein interaction priors shape biologically coherent latent spaces for causally concordant cross-omic translation
Preprint
Abstract
Deep learning models routinely compress omics into low-dimensional codes, yet many equally accurate embeddings fail to reflect how cells are wired, which limits explanation and causal reasoning. We present a simple, architecture-agnostic approach to make latent spaces biologically legible: a protein-protein interaction (PPI) prior that softly steers autoencoder units to recruit genes that are proximal on the interactome while discouraging redundant reuse. Applied to large DNA methylation (∼155k) and RNAseq (∼993k) compendia and to knowledge-driven (STRING), structure-predicted (RoseTTAFold2-PPI), and union interactomes, this objective reorganizes methylation latents into compact, non-overlapping network neighborhoods without sacrificing reconstruction accuracy. The resulting units map cleanly onto biological processes such as cell-cycle control, immune signaling, proteostasis, mitochondrial metabolism, and RNA handling, with a limited, hub-enriched overlap that plausibly bridges modules. We then asked whether this structured geometry transfers downstream. Using paired TCGA cohorts spanning 23 cancers, omic translators trained on these embeddings, especially a shared-latent bidirectional model, outperformed full-matrix baselines in biologically concordant directions (methylation to transcription, genomics to methylation and transcription) and, crucially, inherited the mechanistic imprint of the upstream encoder. Analytical sensitivity mapping showed that translators fed PPI-guided embeddings preferentially learned known cancer drivers and enriched hallmark pathways, whereas accuracy-matched models trained on non-constrained embeddings did not. Thus, the prior not only regularizes but passes forward a functional coordinate system that makes subsequent predictors mechanistically aware. By keeping biology in the loss rather than hard-wiring it into the network, our approach scales to very large cohorts, preserves flexibility for understudied genes, and yields latents that are both performant and interpretable. More broadly, it outlines a practical route to mechanism-anchored representation learning that propagates explanatory structure into downstream tasks, advancing explainable AI for multi-omic analysis and clinical decision support.Keywords
Funding Information
- Wallenberg AI, Autonomous Systems and Software Program (WASP) and SciLifeLab and Wallenberg National Program for Data-Driven Life Science (WASPDDLS21-040/KAW 2020.0239)
This publication has 40 references indexed in Scilit:
- Advances in cancer DNA methylation analysis with methPLIER: use of non-negative matrix factorization and knowledge-based constraints to enhance biological interpretabilityExperimental & Molecular Medicine, 2024
- VEGA is an interpretable generative model for inferring biological network activity in single-cell transcriptomicsNature Communications, 2021
- Learning interpretable cellular and gene signature embeddings from single-cell transcriptomic dataNature Communications, 2021
- CellBox: Interpretable Machine Learning for Perturbation Biology with Application to the Design of Cancer Combination TherapyCell Systems, 2021
- Predicting Drug Response and Synergy Using a Deep Learning Model of Human Cancer CellsCancer Cell, 2020
- Pathway-Guided Deep Neural Network toward Interpretable and Predictive Modeling of Drug SensitivityJournal of Chemical Information and Modeling, 2020
- Deriving disease modules from the compressed transcriptional space embedded in a deep autoencoderNature Communications, 2020
- MultiPLIER: A Transfer Learning Framework for Transcriptomics Reveals Systemic Features of Rare DiseaseCell Systems, 2019
- Massive mining of publicly available RNA-seq data from human and mouseNature Communications, 2018
- Using deep learning to model the hierarchical structure and function of a cellNature Methods, 2018