TMO: ASYMMETRIC CROSS-MODAL ATTENTION FOR LEARNING CELL-STATE-DEPENDENT REGULATORY LAGS FROM SINGLE-CELL MULTIOMIC DATA

Abstract

BackgroundSingle-cell multi-omics technologies simultaneously measure chromatin accessibility (ATAC) and gene expression (RNA), providing a unique window into the temporal ordering of regulatory events during differentiation. However, most computational models treat the two modalities symmetrically, ignoring the directional relationship between chromatin and transcription, and existing lag-aware methods estimate a single global lag per gene, failing to capture cell-state-dependent dynamics. Methods and ResultsWe introduce Temporal Multi-Omics (TMO), a deep learning framework that learns signed, cell-state-conditional regulatory lags ({Delta}{tau}) using asymmetric cross-modal attention. TMO projects RNA and ATAC into 50 latent components each, tokenises each cell as a sequence of 100 tokens, and uses a two-pass transformer in which a data-driven lag prior - derived from a sliding-window cross-correlation function - directly biases attention asymmetrically. On four independent 10x Multiome datasets (mouse brain, human brain, mouse kidney, human PBMC), the asymmetric model achieves Lag Concordance Scores (LCS) of 0.988-0.999, compared to 0.048-0.108 for an architecturally identical symmetric baseline. A stratified 80/20 held-out experiment confirms that the learned component-lag ordering generalises to unseen cells (held-out LCS 0.85-0.99). Clustered {Delta}{tau} heatmaps show positive {Delta}{tau} (ATAC-led priming) in early pseudotime and negative {Delta}{tau} (RNA-led, activity-dependent regulation) in late pseudotime; the ATAC-RNA correlation heatmap exhibits a U-shaped pattern indicative of developmental decoupling. Components with the most positive {Delta}{tau} are enriched for chromatin organization and stem cell differentiation (FDR 0.98, far outperforming a symmetric baseline ( View larger version (38K): org.highwire.dtl.DTLVardef@b1410eorg.highwire.dtl.DTLVardef@1262578org.highwire.dtl.DTLVardef@165edf9org.highwire.dtl.DTLVardef@ea8aa4_HPS_FORMAT_FIGEXP M_FIG O_FLOATNOFigure 1:C_FLOATNO Graphical Abstract | TMO - Temporal Multi-Omics. TMO uses asymmetric cross-modal attention in a two-pass transformer to learn signed, cell-state-conditional regulatory lags ({Delta}{tau}) between chromatin accessibility (ATAC) and gene expression (RNA) from paired single-cell multi-omic data. A data-driven lag prior derived from a sliding-window cross-correlation function biases ATAC-to-RNA attention, enabling the model to capture ATAC-led priming (positive {Delta}{tau}, red) early in differentiation and RNA-led, activity-dependent regulation (negative {Delta}{tau}, blue) late in differentiation. Across four tissues, the asymmetric model achieves Lag Concordance Scores (LCS) of 0.988-0.999, while a symmetric baseline collapses to <0.11. Independent ChIP-seq and Perturb-seq validations confirm that the learned lags reflect genuine transcription factor binding and respond to genetic perturbations. TMO is open-source, scalable, and available as a Scanpy-like Python package (tmopy). Made with BioRender. C_FIG