PACE: Geometry-Aware Bridge Transport for Single-Cell Trajectory Inference
Two new research papers introduce advanced machine learning techniques for inferring cellular development trajectories from single-cell RNA sequencing data. CellBRIDGE uses interaction-aware alignment to model ligand-receptor signaling, improving trajectory estimates and enabling in silico perturbations. PACE employs geometry-aware bridge transport, constructing a Riemannian metric to refine cross-time cell couplings and distill dynamics into a continuous-time velocity field, outperforming existing methods on various datasets. AI
IMPACT These methods offer new ways to analyze complex biological systems, potentially accelerating drug discovery and our understanding of cellular processes.