Renske J. Dupar

There is increasing interest in quantitatively combining phenotypic information and existing mathematical frameworks for cell state dynamics. We used hiPSC-derived endothelial cells as a controllable model system that adopts two distinct phenotypes at different magnitudes of shear stress. We trained a diffusion autoencoder model on timelapse imaging data to extract interpretable morphological features from brightfield. In this feature space, we found that observed phenotypic states correspond to stable fixed points of an inferred dynamical system. Cell migration coherence at these stable fixed points further distinguishes the states. Imaging cells across intermediate shear stresses revealed a regime of bistability, indicating that the shear-stress-dependent cell state transition occurs as a bifurcation. In N-terminally truncated VE-cadherin-expressing cells, we found that orientation and coherent migration were preserved, but morphology and migration speed were not. We demonstrate how machine learning and dynamical systems can be used in tandem to quantitatively characterize phenotypic cell states.

Cell states are increasingly conceptualized as attractors of high-dimensional dynamical systems, yet quantitative approaches for integrating phenotypic information into this framework remain limited. Here, we take an image-based approach that combines unsupervised machine learning (ML) with timelapse imaging to extract and characterize the temporal dynamics of morphological features. Using a cell line with endogenously tagged VE-cadherin, we acquired brightfield and fluorescence timelapse images of human induced pluripotent stem cell-derived endothelial cell (hiPSC-EC) monolayers, which adopt distinct phenotypes at two different magnitudes of shear stress in terms of their morphology, behavior, and VE-cadherin organization. To quantify these phenotypic cell states without segmentation, we trained a diffusion autoencoder to predict VE-cadherin signal from brightfield images. We identified interpretable ML-based features representing cell orientation, elongation, and local density. Treating these variables as dimensions of a morphological state space, we estimated a data-driven vector field and found that the two observed phenotypic cell states correspond to stable fixed points of the inferred dynamical system. Mapping measured cell migration coherence onto this space further distinguished the states. Imaging cells across intermediate shear stresses revealed a regime of bistability in which both states coexist, indicating that the shear-stress-dependent transition between endothelial cell states occurs as a bifurcation of the inferred dynamical system. Finally, we applied this method to study an N-terminal truncation of VE-cadherin, finding that mutated cells preserve alignment and coherent migration, but exhibit altered morphology and increased migration speed. This work demonstrates the applicability of a dynamical systems approach to quantitatively characterize morphological aspects of cell state from interpretable ML-based features.

The epithelial-to-mesenchymal transition (EMT) is a widely studied cell state change, yet differences in model design and measurement approaches limit comparison across studies. Addressing this challenge requires experimental model systems and analysis frameworks that support standardization across contexts. Here, we show that human induced pluripotent stem (hiPS) cells in defined cell culture geometries, two-dimensional colonies and three-dimensional lumenoids, enable multimodal measurements of EMT dynamics within a single experimental platform. Using fixed-cell and live-cell image-based assays, we quantify changes in cell migration, EMT-related molecular markers, cell–cell junction organization and interactions with the basement membrane, a specialized form of the extracellular matrix, during EMT induced in hiPS cells. We identify cell culture geometry-dependent differences in the timing of migration onset and show that basement membrane integrity can be quantitatively linked to these differences. Together, these results establish an imaging-based framework for analysis of cell state transitions and provide accessible datasets and tools.

Salmon is the most commonly consumed finfish in the United States of America (USA), and the mislabeling of salmon is a widespread problem. Washington State is a global supplier of wild-caught Pacific salmon and local salmon mislabeling results in substantial economic, ecological, and cultural impacts. Previous studies in Washington State identified high levels of mislabeled salmon in both markets and restaurants, resulting in local legislation being passed that requires proper labeling of salmon products, including identifying it as wild-caught or farm-raised. To investigate whether recent legislative efforts reduced salmon fraud rates, we acquired and genetically barcoded salmon samples from 67 grocery stores and 52 sushi restaurants in Seattle, Washington. DNA from each salmon sample was isolated and the cytochrome c oxidase gene was sequenced to identify the fish species. Our study, conducted from 2022–2023, revealed 18% of salmon samples from both grocery stores and sushi restaurants were mislabeled. While most samples were acquired during the fall months when wild salmon is in season, we still observed a high salmon mislabeling rate. Unlike grocery stores, Seattle sushi restaurants often sold farmed salmon mislabeled as wild salmon. Specifically, substitutions of vendor-claimed wild salmon with farmed salmon occurred in 32.3% of sushi restaurant samples compared to 0% of grocery store samples. Additionally, occurrences of wild salmon being substituted with another salmon species (wild or farmed) occurred in 38.7% of sushi restaurant samples compared to 11.1% of grocery store samples. All salmon substitutions in sushi restaurants harmed the customer financially as they were given a cheaper market-priced fish. In grocery stores, however, we did not detect significant economic loss to customers due to salmon mislabeling. Taken together, it is important to continue to develop and enforce legislation in Washington State that prevents salmon fraud and promotes ecologically sustainable fishing practices.