发表机构
University College London; Yale University（伦敦大学学院; 耶鲁大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
Pheno-GS提出测地线Sinkhorn方法，结合图正则化、非平衡OT与批量热扩散，实现大规模患者单细胞数据的快速准确距离计算。
AI 中文摘要
高通量单细胞数据现在在大规模患者队列中广泛收集。从细胞水平数据理解患者层面的异质性推动了表型组图谱（phenoscaping）的发展：将每个单细胞分布嵌入为“数据点”，距离由最优传输（OT）定义。在此规模下，计算所有患者数据集对之间的几何感知OT仍是一个开放挑战，因为现有方法要么依赖扭曲流形结构的欧几里得地面度量，要么在稀疏、不均匀采样或大规模数据下失效。我们提出Pheno-GS（表型组规模的测地线Sinkhorn），通过三个组件在噪声、非平衡和大规模设置下计算准确且可扩展的测地线传输距离：（1）图连通性正则化，用于在稀疏/不连通流形上定义良好的测地线；（2）通过KL边际惩罚的非平衡OT公式；（3）批量矩阵算法，在一次热扩散中计算所有成对距离（对于500个分布，比Geodesic Sinkhorn快200倍以上）。我们在合成基准和一个CyTOF扰动数据集上验证了Pheno-GS。
英文摘要
High-throughput single-cell data is now collected across large patient cohorts. Understanding patient-level heterogeneity from cellular-level data motivates phenoscaping: embedding each single-cell distribution as a "datapoint," with distances given by optimal transport (OT). Computing geometry-aware OT at this scale, between all pairs of patient datasets, remains an open challenge, since existing methods either rely on Euclidean ground metrics that distort manifold structure or fail under sparse, unevenly sampled, or large-scale data. We present \textbf{Pheno-GS} (Phenoscape-scale Geodesic Sinkhorn), which computes accurate, scalable geodesic transport distances under noisy, unbalanced, large-scale settings via three components: ($1$) graph connectivity regularization for well-defined geodesics on sparse/disconnected manifolds; ($2$) an unbalanced OT formulation via KL marginal penalties; and ($3$) a batched matrix algorithm computing all pairwise distances in one heat diffusion (over $200 \times$ faster than Geodesic Sinkhorn for $500$ distributions). We validate Pheno-GS on synthetic benchmarks and a CyTOF perturbation dataset.
CommentsCamera-ready version accepted at IEEE MLSP 2026; notation corrections to mathematical typesetting
