← Back to all news
arXiv Machine Learning By Chenglei Yu, Chuanrui Wang, Bangyan Liao, Tailin Wu

PACE: Geometry-Aware Bridge Transport for Single-Cell Trajectory Inference

Read the original on arXiv Machine Learning →

PACE is a trajectory inference framework that reconstructs continuous transport dynamics from destructive single‑cell time‑course snapshots. It uses a state‑ and time‑dependent anisotropic Riemannian metric to guide transport along tangent directions, alternates between refining cross‑time couplings and fitting neural bridges, and distills the learned dynamics into a global velocity field. Across multiple datasets, PACE outperforms existing methods, reducing key distance metrics by an average of 23.7% and improving RNA‑velocity alignment by 15.4%.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
4d ago

Multiscale Supervised Unbalanced Optimal Transport Flow Matching

Multiscale Supervised Unbalanced Optimal Transport Flow Matching (MUST‑FM) is a simulation‑free framework that scales unbalanced optimal transport (UOT) for single‑cell trajectory inference by exploiting hierarchical data structure. It optionally incorporates supervised transition priors, such as cell lineages, to guide displacement fields and mass variations. Experiments demonstrate reduced computational overhead and robust, biologically meaningful trajectory inference on atlas‑scale single‑cell datasets.

By Qiangwei Peng, Lezhi Chen, Peijie Zhou
diffusion
More like this →
arXiv AI
Oct 9

Finsler Flow Matching: Dynamics-Aware Geodesic Interpolation for Single-Snapshot Trajectory Inference

The paper introduces Finsler Flow Matching (FFM), a method for learning continuous stochastic dynamics from discrete Markov transition graphs in single‑cell snapshot data. FFM constructs a Finsler geometry using first and second local moments, learns directed geodesics via neural networks, and employs these to build geometry‑aware stochastic paths that can be simulated without explicit score or flow matching. Benchmark tests show that FFM better recovers intermediate cellular states, especially when dynamics are directional or anisotropic.

By Niklas Canova, Jonas Simon Fleck
diffusionbenchmarks
More like this →
arXiv AI
Sep 7

Simulation-free Unbalanced Dynamic Optimal Transport with General Growth Penalty

The paper introduces SUDO, a simulation‑free framework for unbalanced dynamic optimal transport (UDOT) that supports general convex growth penalties beyond the quadratic Wasserstein‑Fisher‑Rao case. By showing that concave penalties lead to degenerate solutions, the authors focus on convex penalties, learning conditional paths and transport costs to solve a semi‑coupling problem and then applying unbalanced flow matching. On benchmark datasets, SUDO matches the accuracy of analytical WFR solvers while being faster than simulation‑based methods, and it also handles asymmetric penalties that better reflect proliferation‑dominant biological priors.

By Junda Ying, Yuxuan Wang, Bowen Yang, Peijie Zhou, Lei Zhang
diffusionbenchmarks
More like this →