CellBRIDGE: Learning Cellular Trajectories via Interaction-Aware Alignment

Silas Ruhrberg Estévez, Nicolas Huynh, Tennison Liu, Roderik M. Kortlever, Gerard I. Evan, David L. Bentley, Mihaela Van Der Schaar
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:28345-28381, 2026.

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 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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-estevez26b, title = {{C}ell{BRIDGE}: Learning Cellular Trajectories via Interaction-Aware Alignment}, author = {Est\'{e}vez, Silas Ruhrberg and Huynh, Nicolas and Liu, Tennison and Kortlever, Roderik M. and Evan, Gerard I. and Bentley, David L. and Van Der Schaar, Mihaela}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {28345--28381}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/estevez26b/estevez26b.pdf}, url = {https://proceedings.mlr.press/v306/estevez26b.html}, 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 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.} }
Endnote
%0 Conference Paper %T CellBRIDGE: Learning Cellular Trajectories via Interaction-Aware Alignment %A Silas Ruhrberg Estévez %A Nicolas Huynh %A Tennison Liu %A Roderik M. Kortlever %A Gerard I. Evan %A David L. Bentley %A Mihaela Van Der Schaar %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-estevez26b %I PMLR %P 28345--28381 %U https://proceedings.mlr.press/v306/estevez26b.html %V 306 %X 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.
APA
Estévez, S.R., Huynh, N., Liu, T., Kortlever, R.M., Evan, G.I., Bentley, D.L. & Van Der Schaar, M.. (2026). CellBRIDGE: Learning Cellular Trajectories via Interaction-Aware Alignment. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:28345-28381 Available from https://proceedings.mlr.press/v306/estevez26b.html.

Related Material