Search papers, labs, and topics across Lattice.
This paper introduces the Counterfactual Directionality Score (CDS), a novel framework for quantifying directional influence between node populations in spatial graphs, particularly in biological contexts. By employing a Neighbor Influence Model (NIM) and structured counterfactual interventions, the authors effectively measure the impact of perturbations on node states while maintaining essential spatial and structural properties. Experimental results demonstrate that CDS accurately captures directional influence in synthetic graphs and shows promise in real-world applications, such as spatial transcriptomics data, revealing biologically relevant interactions.
CDS not only quantifies directional influence in complex spatial graphs but also remains robust against confounding signals, making it a game-changer for understanding cell-cell interactions in biological systems.
Quantifying directional influence between node populations is a fundamental problem in graph-based modeling, particularly in spatial biological systems where cell-cell interactions shape functional outcomes. Existing approaches based on attention, attribution, or correlation capture associations but do not provide a principled framework for evaluating directional effects under controlled perturbations. We introduce a framework for structured counterfactual interventions in graph-based models to estimate directional influence between node types. Our approach trains a Neighbor Influence Model (NIM) to predict node states from local neighborhoods and applies constrained interventions that modify neighborhood composition while preserving key spatial and structural properties. We define the Counterfactual Directionality Score (CDS), which measures the change in predicted node state induced by targeted perturbations, and provide a theoretical interpretation of CDS as a finite-difference measure of local intervention sensitivity. To obtain valid uncertainty estimates, we introduce a core-level bootstrap procedure that accounts for dependencies within spatial samples. Experiments on synthetic spatial graphs with known directional structure show that CDS recovers directional influence, remains well calibrated under null conditions, and is robust to confounding signals, while preliminary results on spatial transcriptomics data reveal biologically plausible and consistent interactions across tissue cores.
