Our bridge integration is illustrated in Fig. 1b and described fully in the Supplementary Methods, and we note a few key points below. First, our procedure makes no assumptions about the relationships between modalities, as these are learned automatically from the multi-omic dataset. Second, the key advance we present here is a transformation to project datasets profiling different modalities to be represented by a shared set of features. Once transformed, the final alignment step is compatible with a wide diversity of single-cell integration techniques including Harmony38, mnnCorrect39, Seurat19, Scanorama40, or scVI41. In this manuscript, we perform this step with an implementation of the mnnCorrect algorithm39.
