arXiv cs.AI· Zihan Wang, Jianzhe Li, Zhenyi Zhang, Peijie Zhou·· 10 小时前AI 评分27
HORIZON:用水平流匹配学习单细胞时空动态
Horizontal Flow Matching for Single-Cell Spatiotemporal Dynamics
AI 导读
研究者提出水平流匹配方法,学习组织构型、分子状态与细胞丰度的变化,且不受切片间共享刚体运动干扰,并据此构建模型 HORIZON。HORIZON 采用等变 Transformer 从当前组织预测速度与增长,可由单张初始快照连续生成组织。在四个空间转录组时间序列上,HORIZON 重建组织几何、基因表达与细胞丰度的精度优于现有空间及非平衡轨迹方法,并能插值留出的发育阶段。
正文 · 原文
Abstract:Learning the spatiotemporal dynamics of cells from spatial transcriptomics requires connecting snapshots of different cells acquired in different coordinate frames. A rotation or translation of a section can appear as cell movement and distort the inferred correspondence. We introduce horizontal flow matching, which learns changes in tissue organization, molecular state, and cell abundance up to shared rigid motion. The dynamics follow a continuity--reaction equation whose action assigns no cost to shared rigid motion, and the resulting horizontal projector removes this component from spatial prediction errors during learning and from predicted velocities during generation. An equivalent endpoint problem jointly estimates correspondence and relative pose in Wasserstein--Fisher--Rao geometry and yields analytic paths whose velocity and growth serve as regression targets. Regressing these targets recovers the horizontal dynamics under ideal population conditions. Our model, HORIZON, uses an equivariant transformer to predict velocity and growth from the current tissue, so that a tissue can be generated continuously from a single initial snapshot. On a simulated tissue observed in perturbed coordinate frames, alignment improves reconstruction and projection reduces rigid drift. On four spatial transcriptomics time courses, HORIZON reconstructs tissue geometry, gene expression, and cell abundance more accurately than existing spatial and unbalanced trajectory methods, and interpolates held-out developmental stages.
| Comments: | 38 pages, 7 figures |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Quantitative Methods (q-bio.QM) |
| Cite as: | arXiv:2611.24764 [cs.LG] |
| (or arXiv:2611.24764v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2611.24764 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zihan Wang [view email]
[v1]
Wed, 18 Nov 2026 17:16:53 UTC (2,963 KB)
来源:arXiv cs.AI · arxiv.org