OmicSync: Reliability-Aware Spatial Multi-Omics Clustering with Evidence-Constrained LLM Reasoning
2026-08-24 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed OmicSync, a tool that groups spots in tissue samples based on multiple types of biological data while also showing how confident it is in each grouping. It uses a combination of machine learning and language models to explain why each group was formed, highlighting which data types mattered most and how sure the model is. They also created OmicSync-R, which improves grouping by using feedback from the explanations to refine the model. Testing on real tissue samples showed that OmicSync and OmicSync-R perform better or comparably to existing methods while providing transparent and trustworthy results.
spatial multi-omicsdomain clusteringuncertainty quantificationlanguage modelscross-modal fusioncell-type supervisionmissing-modality imputationreinforcement learningspatial proteomicsevidence-constrained reasoning
Authors
Rabeya Tus Sadia, Qiang Ye, Qiang Cheng
Abstract
Spatial multi-omics technologies jointly profile gene expression, surface proteins, and histology at each tissue spot, yet most spatial domain discovery methods provide only cluster assignments, without indicating assignment reliability, modality contributions, or why a domain decision should be trusted. We present OmicSync, a reliability-aware spatial multi-omics framework that couples unsupervised domain clustering with evidence-constrained LLM reasoning using model-derived per-spot signals, including assignment confidence, epistemic routing uncertainty, and modality-routing weights. These signals are converted into structured evidence dictionaries and used to generate standard, stepwise, counterfactual, contrastive, and uncertainty-focused explanations. OmicSync integrates a KAN-GCN backbone with spatial encoding, cross-modal fusion, uncertainty-aware routing, cell-type supervision, and missing-modality imputation. We further introduce OmicSync-R, which closes the reasoning-clustering loop by using automatically computed reasoning-quality scores as REINFORCE rewards, allowing reasoning coherence to shape the latent structure without backpropagating through the language model. Across four 10x CytAssist FFPE spatial proteomics benchmarks, OmicSync achieves the best average rank on Human Tonsil (1.44), Glioblastoma (1.78), and Tonsil Add-on (1.22), and second-best on Human Breast Cancer (2.33). OmicSync-R further improves ARI on Human Breast Cancer from 45.73 to 46.72 and outperforms existing methods on six of nine clustering metrics. Together, OmicSync and OmicSync-R enable reliability-aware, spot-level auditable spatial domain discovery guided by evidence-constrained reasoning.