ContextFlow: Context-Aware Flow Matching For Trajectory Inference From Spatial Omics Data
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914566256984064 |
|---|---|
| author | Rathod, Santanu Subhash Ceccarelli, Francesco Holden, Sean B. Liò, Pietro Zhang, Xiao Tanevski, Jovan |
| author_facet | Rathod, Santanu Subhash Ceccarelli, Francesco Holden, Sean B. Liò, Pietro Zhang, Xiao Tanevski, Jovan |
| contents | Inferring trajectories from longitudinal spatially-resolved omics data is fundamental to understanding the dynamics of structural and functional tissue changes in development, regeneration and repair, disease progression, and response to treatment. We propose ContextFlow, a novel context-aware flow matching framework that incorporates prior knowledge to guide the inference of structural tissue dynamics from spatially resolved omics data. Specifically, ContextFlow integrates local tissue organization and ligand-receptor communication patterns into a transition plausibility matrix that regularizes the optimal transport objective. By embedding these contextual constraints, ContextFlow generates trajectories that are not only statistically consistent but also biologically meaningful, making it a generalizable framework for modeling spatiotemporal dynamics from longitudinal, spatially resolved omics data. Evaluated on three datasets, ContextFlow consistently outperforms state-of-the-art flow matching methods across multiple quantitative and qualitative metrics of inference accuracy and biological coherence. Our code is available at: \href{https://github.com/santanurathod/ContextFlow}{ContextFlow} |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_02952 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ContextFlow: Context-Aware Flow Matching For Trajectory Inference From Spatial Omics Data Rathod, Santanu Subhash Ceccarelli, Francesco Holden, Sean B. Liò, Pietro Zhang, Xiao Tanevski, Jovan Machine Learning Inferring trajectories from longitudinal spatially-resolved omics data is fundamental to understanding the dynamics of structural and functional tissue changes in development, regeneration and repair, disease progression, and response to treatment. We propose ContextFlow, a novel context-aware flow matching framework that incorporates prior knowledge to guide the inference of structural tissue dynamics from spatially resolved omics data. Specifically, ContextFlow integrates local tissue organization and ligand-receptor communication patterns into a transition plausibility matrix that regularizes the optimal transport objective. By embedding these contextual constraints, ContextFlow generates trajectories that are not only statistically consistent but also biologically meaningful, making it a generalizable framework for modeling spatiotemporal dynamics from longitudinal, spatially resolved omics data. Evaluated on three datasets, ContextFlow consistently outperforms state-of-the-art flow matching methods across multiple quantitative and qualitative metrics of inference accuracy and biological coherence. Our code is available at: \href{https://github.com/santanurathod/ContextFlow}{ContextFlow} |
| title | ContextFlow: Context-Aware Flow Matching For Trajectory Inference From Spatial Omics Data |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2510.02952 |