Taken together, these results demonstrate the accuracy, robustness, and flexibility of our bridge integration procedure. We demonstrate applications on multiple modalities and data types, as well as best-in-class performance via quantitative and ground-truth benchmark comparisons. We demonstrate how cross-modality mapping can help interpret and improve the resolution of cell type annotation, including extremely rare cell types whose identification is facilitated by curated annotation in a reference dataset. Moreover, projecting datasets into a harmonized space also enables exploration of cross-modality relationships.
