Abstract
Machine learning approaches have shown great promise in biology and medicine discovering hidden information to further understand complex biological and pathological processes. In this study, we developed a deep learning-based machine learning algorithm to meaningfully process image data and facilitate studies in vascular biology and pathology. Vascular injury and atherosclerosis are characterized by neointima formation caused by the aberrant accumulation and proliferation of vascular smooth muscle cells (VSMCs) within the vessel wall. Understanding how to control VSMC behaviors would promote the development of therapeutic targets to treat vascular diseases. However, the response to drug treatments among VSMCs with the same diseased vascular condition is often heterogeneous. Here, to identify the heterogeneous responses of drug treatments, we created an in vitro experimental model system using VSMC spheroids and developed a machine learning-based computational method called HETEROID (heterogeneous spheroid). First, we established a VSMC spheroid model that mimics neointima-like formation and the structure of arteries. Then, to identify the morphological subpopulations of drug-treated VSMC spheroids, we used a machine learning framework that combines deep learning-based spheroid segmentation and morphological clustering analysis. Our machine learning approach successfully showed that FAK, Rac, Rho, and Cdc42 inhibitors differentially affect spheroid morphology, suggesting that multiple drug responses of VSMC spheroid formation exist. Overall, our HETEROID pipeline enables detailed quantitative drug characterization of morphological changes in neointima formation, that occurs in vivo, by single-spheroid analysis.
Highlights
Machine learning approaches have shown great promise in biology and medicine discovering hidden information to further understand complex biological and pathological processes
FAK phosphorylation is critical in the regulation of both cell-cell adhesion and cell proliferation during the process of neointima formation[11,12,22,55,56], we first tested the inhibition of FAK phosphorylation on vascular smooth muscle cells (VSMCs) spheroid formation by culturing human aortic VSMCs (Fig. 2) and mouse aortic VSMCs (Fig. S1) to form spheroids in the presence of either PF57322811 or dimethyl sulfoxide (DMSO)
We identified spheroid morphological clusters of VSMCs with unique drug responses, suggesting the following: (i) Types N1 and N4 morphologies mostly depend on the disruption of FAK and Rac, (ii) Type N3 morphology mainly depends on the disruption of Rho and Rac, (iii) Type N2 morphology depends on the disruption of FAK, Rac, and Rho (Fig. 6E,F), and (iv) Cluster #3 morphology from the previous initial clustering analysis depends on the disruption of only Cdc[42] (Figs. 5E, 6F)
Summary
Machine learning approaches have shown great promise in biology and medicine discovering hidden information to further understand complex biological and pathological processes. We created VSMC spheroids, which are spherical cellular aggregates consisting of multiple layers of VSMCs35,36, using a hanging drop culture technique[37,38] (Fig. 1A) This new spheroid model can mimic VSMC-mediated neointima formation in the vessel wall, similar to animal models[8,12,39,40] that simulate human pathologies such as restenosis and atherosclerosis. Using this system, we characterized the effects of the inhibition of FAK phosphorylation and Rac, Rho, and Cdc[42] activation on spheroid formation and morphology. To analyze the image data, we developed an ML framework that combines high-performance deep learningbased spheroid segmentation (Fig. 1B) and morphological clustering analysis (Fig. 1C) to identify the effects
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have