TI$^2$PS: A Topology-Informed Inverse Design Framework for Stochastic Multicellular Pattern Formation
Machine Learning
Summary
The authors developed a new method to figure out the rules that govern how cells arrange themselves in groups, using a computer model where each cell acts like an individual agent. They combined a way to describe complex patterns mathematically (Betti vectors) with a technique to reverse-engineer the model’s settings (inverse surrogate modeling). Testing their method on zebrafish skin patterns showed it could find the right settings more accurately than other existing approaches, even with less data. This helps better understand how multicellular patterns form from cell behaviors.
Authors
Kenji Komiya, Andrew Kailiang Jin, Ryo Nishikimi, Kunio Kashino
Abstract
This study proposes a novel framework to estimate parameters for reproducing target multicellular patterns using an agent-based model (ABM). Two major challenges in multicellular ABMs are estimating cell-level parameters (agent-specific variables) and quantitatively evaluating the topological characteristics of multicellular arrangements under stochastic cell proliferation and death. To address these challenges, we integrate two approaches: Betti vectors and inverse surrogate modeling. The Betti vectors obtained through topological data analysis can consistently represent features of a wide range of multicellular spatial configurations. The inverse surrogate modeling enables direct inference of the corresponding ABM parameters from the target patterns. We validated the proposed framework using zebrafish pigment pattern formation, a representative model of pattern formation driven by multicellular interactions. The results demonstrate that our framework successfully estimates ABM parameters and outperforms conventional methods such as PointNet++. Notably, the proposed method, which used only 10% of the training data, outperformed PointNet++, which used 100% of the data, across all evaluation metrics.