B0241
Title: Dataset matching and its applications in single-cell multi-omics
Authors: Shuxiao Chen - University of Pennsylvania (United States) [presenting]
Zongming Ma - University of Pennsylvania (United States)
Abstract: One-way matching of a pair of datasets with low-rank signals is studied. Under a stylized model, we first derive information-theoretic limits of matching. We then show that linear assignment with projected data achieves fast rates of convergence and sometimes even minimax rate optimality for this task. We further design a new matching algorithm that accommodates the case where the covariates are only partially aligned. The practical use of the proposed algorithms is illustrated in several single-cell multi-omics data examples, including batch effect removal in sequencing data, integration of proteomics data, and spatial transfer in multiplex imaging data.