Beyond benchmarking: an expert-guided consensus approach to spatially aware clustering
TL;DR
This work presents SACCELERATOR, an open-source, extensible framework that formalizes expert-guided spatial clustering analysis, and proposes a consensus-guided workflow where descriptive spatial metrics highlight high-entropy regions of method disagreement, enabling targeted feedback for tissue experts.
Abstract
Spatial omics technologies have revolutionized the study of tissue architecture and cellular heterogeneity by integrating molecular profiles with spatial localization. In spatially resolved transcriptomics, delineating higher-order anatomical structures is critical for understanding how cellular organization affects function. However, the reliability of current benchmarks of spatially aware clustering (SAC) methods is undermined by their narrow focus on Visium and brain tissue datasets and the incorrect interpretation of manual annotation as ground truth. Here we present SACCELERATOR, a community-driven, extensible framework that standardizes data formatting, method integration and metric evaluation, enabling rapid inclusion of new methods and datasets. Our analysis revealed substantial limitations in the generalizability and reproducibility of SAC methods and shows that anatomical labels commonly used as ground truths are often biased, error prone and unsuitable for benchmarking. Rather than ranking methods, we propose a consensus-guided workflow where descriptive spatial metrics highlight high-entropy regions of method disagreement, enabling targeted feedback for tissue experts. Applied to brain and cancer datasets, this approach uncovered biologically meaningful patterns overlooked by individual SAC methods and manual annotations, highlighting the need for iterative, expert-in-the-loop evaluation. Benchmarking spatially aware clustering is challenging. SACCELERATOR is an open-source, extensible framework that formalizes expert-guided spatial clustering analysis.