Response to comments on "SpatialDG: a novel spatial domain identification method for spatially resolved transcriptomics data based on dual-graph neural network".

SpatialDG achieves the higher three-seed mean ARI on all 12 slices in a matched DLPFC reevaluation using a reference-label-independent checkpoint-selection rule.

• Why it matters: The work addresses concerns that epoch selection in SpatialDG may rely on reference labels, potentially biasing performance estimates.
• What they did: The authors reevaluated SpatialDG and Spatial-MGCN on matched DLPFC data, applying the same reference-label-independent checkpoint-selection rule across methods.
• The result: Under this controlled reevaluation, SpatialDG’s three-seed mean ARI is higher on every one of the 12 slices, supporting robustness to the checkpoint-selection concern.

AI summary of the abstract · may contain errors · not medical advice · read the paper.