PulseAugur
EN
LIVE 15:21:32

New ML methods model cell trajectories using interaction and geometry

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.

RANK_REASON Two academic papers published on arXiv presenting novel methods for biological data analysis.

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

COVERAGE [2]

  1. arXiv cs.LG TIER_1 English(EN) · Silas Ruhrberg Est\'evez, Nicolas Huynh, Tennison Liu, Roderik M. Kortlever, Gerard I. Evan, David L. Bentley, Mihaela van der Schaar ·

    CellBRIDGE: Learning Cellular Trajectories via Interaction-Aware Alignment

    arXiv:2605.30635v1 Announce Type: new Abstract: Inferring dynamics from population snapshots is a fundamental challenge in machine learning and biology. In scRNA-sequencing (scRNA-seq), destructive measurements preclude direct tracking of individual cells across time, making traj…

  2. arXiv cs.LG TIER_1 English(EN) · Chenglei Yu, Chuanrui Wang, Bangyan Liao, Tailin Wu ·

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

    arXiv:2605.18587v2 Announce Type: replace-cross Abstract: Single-cell trajectory inference from destructive time-course snapshots is fundamentally ill-posed: neither cross-time cell correspondences nor continuous trajectories are observed, so the snapshot distributions alone do n…