CellBRIDGE: Learning Cellular Trajectories via Interaction-Aware Alignment
About
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 trajectory inference underdetermined. Optimal Transport (OT) provides a principled framework for snapshot alignment, but a long-standing modeling question is which cost functions yield biologically meaningful couplings. Standard OT approaches rely on gene-expression distances, implicitly treating cells as independent points and neglecting structured cell-cell communication mediated by ligand-receptor signaling. We introduce CellBRIDGE (Cell-Based Regularized Interaction-Driven Gene Expression), which augments feature-based OT with a directed, typed interaction cost derived from ligand-receptor activity. By explicitly modeling cell-cell communication, CellBRIDGE improves cross-snapshot couplings and downstream trajectory estimates across synthetic and real scRNA-seq datasets relative to feature-only baselines. Notably, CellBRIDGE enables mechanistically interpretable in silico perturbations: on lung cancer data, silencing specific ligand-receptor pairs induces trajectory shifts that recapitulate expected effects of targeted pathway inhibition.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Trajectory Interpolation | Light V1 | W1 Error2.36 | 18 | |
| Trajectory Interpolation | Dendritic Stimulus | W1 Distance/Error3.624 | 18 | |
| Trajectory Interpolation | Lung Tumor | W11.971 | 18 | |
| Interpolation for continuous time dynamics | Macrophage Stimulus PIC (test) | W1 Score5.346 | 17 | |
| Interpolation for continuous time dynamics | Macrophage Stimulus CPG (test) | W1 Score4.427 | 17 | |
| Interpolation for continuous time dynamics | Macrophage Stimulus PCSK3 (test) | W1 Score4.325 | 17 | |
| Interpolation for continuous time dynamics | Macrophage Stimulus LPS (test) | W1 Score4.874 | 17 | |
| Trajectory Interpolation | Mouse development cell atlas E7.5 → E8 | W1 Metric3.054 | 6 | |
| Trajectory Interpolation | Mouse development cell atlas E7.75 → E8.25 | W1 Metric3.131 | 6 |