Dehkharghanian Taher, Hashemiaghdam Arsalan, Ashrafi Ghazaleh
McMaster University, Faculty of Health Sciences, Hamilton, Ontario, Canada.
Washington University School of Medicine in St. Louis, Needleman Center for Neurometabolism and Axonal Therapeutics, Department of Cell Biology and Physiology, Department of Genetics, St. Louis, Missouri, United States.
Neurophotonics. 2022 Oct;9(4):041410. doi: 10.1117/1.NPh.9.4.041410. Epub 2022 Jun 27.
The firefly enzyme luciferase has been used in a wide range of biological assays, including bioluminescence imaging of adenosine triphosphate (ATP). The biosensor Syn-ATP utilizes subcellular targeting of luciferase to nerve terminals for optical measurement of ATP in this compartment. Manual analysis of Syn-ATP signals is challenging due to signal heterogeneity and cellular motion in long imaging sessions. Here, we have leveraged machine learning tools to develop a method for analysis of bioluminescence images. Our goal was to create a semiautomated pipeline for analysis of bioluminescence imaging to improve measurements of ATP content in nerve terminals. We developed an image analysis pipeline that applies machine learning toolkits to distinguish neurons from background signals and excludes neural cell bodies, while also incorporating user input. Side-by-side comparison of manual and semiautomated image analysis demonstrated that the latter improves precision and accuracy of ATP measurements. Our method streamlines data analysis and reduces user-introduced bias, thus enhancing the reproducibility and reliability of quantitative ATP imaging in nerve terminals.
萤火虫酶荧光素酶已被广泛应用于各种生物学检测中，包括三磷酸腺苷（ATP）的生物发光成像。生物传感器Syn-ATP利用荧光素酶在亚细胞水平靶向神经末梢，以便对该区域的ATP进行光学测量。由于长时间成像过程中的信号异质性和细胞运动，手动分析Syn-ATP信号具有挑战性。在这里，我们利用机器学习工具开发了一种生物发光图像分析方法。我们的目标是创建一个用于生物发光成像分析的半自动流程，以改善神经末梢中ATP含量的测量。我们开发了一种图像分析流程，该流程应用机器学习工具包来区分神经元与背景信号，并排除神经细胞体，同时还纳入了用户输入。手动和半自动图像分析的并行比较表明，后者提高了ATP测量的精度和准确性。我们的方法简化了数据分析并减少了用户引入的偏差，从而提高了神经末梢定量ATP成像的可重复性和可靠性。
