Single-tooth resolved, whole-mouth prediction of early childhood caries via spatiotemporal variations of plaque microbiota

Early Childhood Caries (ECC) demonstrates marked tooth specificity, highlighting the critical need for single-tooth-level prevention. We profiled 2504 dental plaque microbiomes from 89 preschoolers across two cohorts, tracking microbial compositional and functional changes at a single-tooth resolution over 11 months. In healthy children, microbiomes exhibited an ecological gradient from anterior to posterior maxillary teeth and high symmetry between paired teeth, patterns disrupted in caries-active children due to caries-driven microbial reorganization. Leveraging tooth-specific disease-associated taxa/genes and spatially related clinical/microbiome features, we developed Spatial Microbial Indicators of Caries (Spatial-MiC) using machine-learning techniques, achieving 98% accuracy for diagnosing ECC at single-tooth resolution and 93% accuracy in predicting new caries two months in advance in perceived-healthy teeth. This high-resolution spatiotemporal microbiome map of ECC and healthy development untangles the microbial etiology at the single-tooth level, identifies a characteristic microbiome signature for each tooth, and forms the basis for tooth-specific ECC prevention strategies.