RII Track-4: NSF: Developing 3D Models of Live-Endothelial Cell Dynamics with Application Appropriate Validation

这个研究基础设施改善轨道-4 EPSCoR研究员项目将提供奖学金的助理教授和培训的研究生在威奇托州立大学。 通过识别和预测一个细胞或一组细胞的可观察特征来了解人类生命的功能是一个巨大的挑战。血管内皮细胞（EC）是生命功能不可或缺的一组细胞。它们形成了一个广泛的细胞网络，可以根据刺激进行感知和改变。PI将在华盛顿州西雅图的艾伦细胞科学研究所（AICS）进行研究。PI和AICS合作者将从有限的信息中开发实时EC动态的3D模型，并进行适当的应用验证。该项目的价值在于它能够将活细胞行为和亚细胞形状联系起来，这将揭示对人类健康和疾病的见解。该项目将帮助在多学科环境中培养博士生，以解决复杂的STEM问题，该研究将用于为PI在WSU教授的两门课程开发新的课程材料。此外，PI将向威奇托公立学校（WPS）介绍。WPS代表了一个丰富的机会，鼓励代表性不足的群体留在STEM，并对当地威奇托社区产生积极影响。最后，工作，培训和研究基础设施的增强，加上思想的交叉施肥将使PI能够在资助期后维持该项目。当计算模型与实验相结合时，它们会产生影响。然而，经常会出现脱节。特别是，细胞形态与实验条件不匹配或未测量。 形态学和亚细胞组织是内皮功能的重要决定因素。该奖学金将支持PI在艾伦细胞科学研究所（AICS）和所在机构的活动，以开发和验证机器学习算法，从而仅从一个易于在活细胞上成像的标签预测活细胞的亚细胞形态，并开发空间统计模型，以验证形态预测与应用程序适当的验证。原代人真皮微血管内皮细胞将暴露于稳定的单向流体剪切应力。当暴露于流体剪切应力时，将通过共聚焦显微镜测定活细胞形态。这些图像将作为机器学习的参考数据集。第二个目标是使用机器学习仅从荧光标记的细胞膜图像预测3D亚细胞形态。另一个目标是开发空间统计模型，以验证机器学习预测的3D亚细胞形态。这种方法将使我们能够探索剪切内皮细胞的组织，细胞形状，功能和力学之间的联系。该奖项反映了NSF的法定使命，并已被认为是值得通过使用基金会的智力价值和更广泛的影响审查标准进行评估的支持。

This Research Infrastructure Improvement Track-4 EPSCoR Research Fellows project will provide a fellowship to an Assistant Professor and training for a graduate student at Wichita State University. Understanding how human life functions, by identifying and predicting observable characteristics of a cell or group of cells, is a grand challenge. A group of cells integral to how life functions are endothelial cells (ECs) lining blood vessels. They form an extensive cellular network that senses and changes based on stimuli. The PI will conduct research at the Allen Institute for Cell Science (AICS) in Seattle, WA. The PI and AICS collaborators will develop 3D models of live-EC dynamics from limited information, with application appropriate validation. This project’s value lies in its ability to connect live-cell behavior and subcellular shape, which would reveal insights into human health and disease. This project will help train a PhD student in a multidisciplinary environment to solve a complex STEM problem, and the research will be used to develop new course material for two courses the PI teaches at WSU. In addition, the PI will present to the Wichita Public Schools (WPS). The WPS represents a rich opportunity to encourage underrepresented groups to remain in STEM and make a positive impact on the local Wichita community. Finally, the work, training, and the research infrastructure enhancement, coupled with the cross-fertilization of ideas will empower the PI to sustain this project past the funding period. Computational models are impactful when they are coupled to experiments. However, there is often a disconnect. In particular, the cell morphology does not match the conditions of the experiments or is not measured. Morphology and subcellular organization are important determinants of endothelial function. The fellowship will support the PI’s activities at the Allen Institute for Cell Science (AICS) and the home institution to developed and validate machine learning algorithms to predict subcellular morphology of live cells from only one label that is easily imaged on live cells and develop spatial statistical models to validate morphology predictions with application appropriate validation. Primary human dermal microvascular endothelial cells will be exposed to steady unidirectional fluid shear stress. While exposed to fluid shear stress live-cell morphology will be determined by confocal microscopy. These images will serve as a reference data set for machine learning. The second objective is to use machine learning to predict 3D subcellular morphology from only images of fluorescently labeled cell membranes. An additional objective is to develop spatial statistical models to validate the 3D subcellular morphology predicted from machine learning. This approach will allow us to explore the connection between organization, cell shape, function, and mechanics for sheared endothelial cells.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.