发表机构
Beijing International Center for Mathematical Research, Peking University; Center for Quantitative Biology, Peking University; Center for Machine Learning Research, Peking University; National Engineering Laboratory for Big Data Analysis and Applications, Beijing; AI for Science Institute, Beijing; School of Mathematical Sciences, Peking University; Institute for Artificial Intelligence, Peking University(北京大学北京国际数学研究中心; 北京大学定量生物学中心; 北京大学机器学习研究中心; 北京大数据分析与应用国家工程实验室; 北京科学智能研究院; 北京大学数学科学学院; 北京大学人工智能研究院)
机构由 AI 辅助整理,请以论文原文为准。AI 中文总结
本文提出TP-DATE框架,动态推广Gromov-Wasserstein最优传输,通过路径作用和旅行对流匹配实现无模拟的连续轨迹重建,在空间转录组学数据上更好地保留空间结构并改善3D动态重建。
AI 中文摘要
Gromov-Wasserstein最优传输(GW-OT)通过引入结构感知的传输代价扩展了经典最优传输。这对于空间转录组学尤为重要,因为动态重建除了匹配表达模式外,还应保持组织结构。虽然静态公式已被广泛用于此类结构感知对齐,但用于重建连续轨迹的一般动态公式仍然缺失。我们提出了旅行对动态对齐与轨迹估计(TP-DATE),这是一个理论性和计算性框架,以无模拟方式动态推广GW-OT。我们通过路径作用制定了一类广泛的静态和动态二次型最优传输(QOT),并证明了静态-动态等价性。我们进一步开发了旅行对流匹配,它允许相互作用的条件路径,并将其相互作用边缘化为单一向量场。在合成和真实空间转录组学数据上,TP-DATE更好地保留了空间结构,并改善了连续3D动态重建。
英文摘要
Gromov--Wasserstein optimal transport (GW-OT) extends classical optimal transport by introducing structure-aware transport cost. This is particularly relevant for spatial transcriptomics, where dynamical reconstruction should preserve tissue structure in addition to matching expression patterns. While static formulations have been widely used for such structure-aware alignment, a general dynamic formulation for reconstructing continuous trajectories is still missing. We introduce Travelling Pair Dynamical Alignment and Trajectory Estimation (TP-DATE), a theoretical and computational framework to generalize GW-OT dynamically in a simulation-free manner. We formulate a broad class of static and dynamic Quadratic-form OT (QOT) through path actions and prove the static dynamic equivalence. We further develop travelling-pair flow matching, which allows interacting conditional paths and marginalizes their interactions into a single vector field. On synthetic and real spatial transcriptomics data, TP-DATE better preserves spatial structure and improves continuous 3D dynamics reconstruction.