A machine learning pipeline revealing heterogeneous responses to drug perturbations on vascular smooth muscle cell spheroid morphology and formation.

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.

Phosphoinositide Signaling and Mechanotransduction in Cardiovascular Biology and Disease.

Phosphoinositides, which are membrane-bound phospholipids, are critical signaling molecules located at the interface between the extracellular matrix, cell membrane, and cytoskeleton. Phosphoinositides are essential regulators of many biological and cellular processes, including but not limited to cell migration, proliferation, survival, and differentiation, as well as cytoskeletal rearrangements and actin dynamics. Over the years, a multitude of studies have uniquely implicated phosphoinositide signaling as being crucial in cardiovascular biology and a dominant force in the development of cardiovascular disease and its progression. Independently, the cellular transduction of mechanical forces or mechanotransduction in cardiovascular cells is widely accepted to be critical to their homeostasis and can drive aberrant cellular phenotypes and resultant cardiovascular disease. Given the versatility and diversity of phosphoinositide signaling in the cardiovascular system and the dominant regulation of cardiovascular cell functions by mechanotransduction, the molecular mechanistic overlap and extent to which these two major signaling modalities converge in cardiovascular cells remain unclear. In this review, we discuss and synthesize recent findings that rightfully connect phosphoinositide signaling to cellular mechanotransduction in the context of cardiovascular biology and disease, and we specifically focus on phosphatidylinositol-4,5-phosphate, phosphatidylinositol-4-phosphate 5-kinase, phosphatidylinositol-3,4,5-phosphate, and phosphatidylinositol 3-kinase. Throughout the review, we discuss how specific phosphoinositide subspecies have been shown to mediate biomechanically sensitive cytoskeletal remodeling in cardiovascular cells. Additionally, we discuss the direct interaction of phosphoinositides with mechanically sensitive membrane-bound ion channels in response to mechanical stimuli. Furthermore, we explore the role of phosphoinositide subspecies in association with critical downstream effectors of mechanical signaling in cardiovascular biology and disease.