Speaker
Description
Cellular models based on single-cell RNAseq data have emerged as a common tool for a system-level exploration of cell mechanisms, especially relevant for tasks such as gene regulatory network (GRN) inference or cell trajectory prediction. Some early mechanistic models allow dataset simulation from GRNs, thus using underlying biological knowledge and offering greater interpretability. However, these models cannot be calibrated from scRNAseq data to formulate predictions. In contrast, multiple generative models fitted on temporal snapshots of scRNAseq data can predict cell trajectories, but most until recently were based on non-mechanistic models lacking explicit GRN formulation. Yet since a GRN encodes the regulatory interactions driving gene expression dynamics, GRN structure and cell trajectories are two facets of the same process. Addressing this, new generative models calibrate a GRN from temporal data and use it to constrain trajectory inference, exploiting this coupling so that both tasks reinforce each other. In our recent work, we evaluate this joint modeling performance gain by benchmarking recent GRN-driven generative models (including \cite{Zh, Be, Is, Ma, Ri}) against state-of-the-art methods performing these tasks separately. We evaluate their ability to reconstruct gene networks from simulated and curated datasets, assess the biological coherence of reconstructed trajectories, predict cell states at held-out timepoints, and generalize to unseen perturbations.
Bibliography
@article{Zh, title={Joint trajectory and network inference via reference fitting}, rights={Creative Commons Attribution 4.0 International}, url={https://arxiv.org/abs/2409.06879}, DOI={10.48550/ARXIV.2409.06879}, publisher={arXiv}, author={Zhang, Stephen Y}, year={2024} }
@article{Be, title={A scalable gene network model of regulatory dynamics in single cells}, rights={Creative Commons Attribution 4.0 International}, url={https://arxiv.org/abs/2503.20027}, DOI={10.48550/ARXIV.2503.20027}, publisher={arXiv}, author={Bertin, Paul and Viviano, Joseph D. and Tejada-Lapuerta, Alejandro and Wang, Weixu and Bauer, Stefan and Theis, Fabian J. and Bengio, Yoshua}, year={2025} }
@article{Is, title={RENGE infers gene regulatory networks using time-series single-cell RNA-seq data with CRISPR perturbations}, volume={6}, ISSN={2399-3642}, url={https://www.nature.com/articles/s42003-023-05594-4}, DOI={10.1038/s42003-023-05594-4}, number={1}, journal={Communications Biology}, author={Ishikawa, Masato and Sugino, Seiichi and Masuda, Yoshie and Tarumoto, Yusuke and Seto, Yusuke and Taniyama, Nobuko and Wagai, Fumi and Yamauchi, Yuhei and Kojima, Yasuhiro and Kiryu, Hisanori and Yusa, Kosuke and Eiraku, Mototsugu and Mochizuki, Atsushi}, year={2023}, month=dec, pages={1290}, language={en} }
@article{Ma, title={CardamomOT: a novel mechanistic optimal transport-based framework for joint gene regulatory network and trajectory inference}, rights={Creative Commons Attribution 4.0 International}, url={https://arxiv.org/abs/2409.06879}, DOI={10.48550/ARXIV.2409.06879}, publisher={arXiv}, author={Zhang, Stephen Y}, year={2024} }
@article{Ri,
title={Simulation-free Structure Learning for Stochastic Dynamics},
author={Rimawi-Fine, Noah El and Stecklov, Adam and Nelson, Lucas and Blanchette, Mathieu and Tong, Alexander and Zhang, Stephen Y and Atanackovic, Lazar},
journal={arXiv preprint arXiv:2510.16656},
year={2025}
}
