Department of Biology, University of Oxford, Oxford, United Kingdom.
Department of Physics and Astronomy, University of Sheffield, Sheffield, United Kingdom.
PLoS Comput Biol. 2023 Oct 9;19(10):e1011524. doi: 10.1371/journal.pcbi.1011524. eCollection 2023 Oct.
Most bacteria live attached to surfaces in densely-packed communities. While new experimental and imaging techniques are beginning to provide a window on the complex processes that play out in these communities, resolving the behaviour of individual cells through time and space remains a major challenge. Although a number of different software solutions have been developed to track microorganisms, these typically require users either to tune a large number of parameters or to groundtruth a large volume of imaging data to train a deep learning model-both manual processes which can be very time consuming for novel experiments. To overcome these limitations, we have developed FAST, the Feature-Assisted Segmenter/Tracker, which uses unsupervised machine learning to optimise tracking while maintaining ease of use. Our approach, rooted in information theory, largely eliminates the need for users to iteratively adjust parameters manually and make qualitative assessments of the resulting cell trajectories. Instead, FAST measures multiple distinguishing 'features' for each cell and then autonomously quantifies the amount of unique information each feature provides. We then use these measurements to determine how data from different features should be combined to minimize tracking errors. Comparing our algorithm with a naïve approach that uses cell position alone revealed that FAST produced 4 to 10 fold fewer tracking errors. The modular design of FAST combines our novel tracking method with tools for segmentation, extensive data visualisation, lineage assignment, and manual track correction. It is also highly extensible, allowing users to extract custom information from images and seamlessly integrate it into downstream analyses. FAST therefore enables high-throughput, data-rich analyses with minimal user input. It has been released for use either in Matlab or as a compiled stand-alone application, and is available at https://bit.ly/3vovDHn, along with extensive tutorials and detailed documentation.
大多数细菌生活在密集的附着在表面的群落中。虽然新的实验和成像技术开始为研究这些群落中发生的复杂过程提供了一个窗口，但要在时间和空间上解析单个细胞的行为仍然是一个主要挑战。尽管已经开发了许多不同的软件解决方案来跟踪微生物，但这些方案通常需要用户调整大量参数，或者对大量成像数据进行groundtruth 以训练深度学习模型——这两个过程都是手动的，对于新的实验来说非常耗时。为了克服这些限制，我们开发了 FAST，即特征辅助分割/跟踪器，它使用无监督机器学习来优化跟踪，同时保持易用性。我们的方法根植于信息论，在很大程度上消除了用户手动迭代调整参数和对生成的细胞轨迹进行定性评估的需要。相反，FAST 为每个细胞测量多个不同的“特征”，然后自动量化每个特征提供的独特信息量。然后，我们使用这些测量值来确定应如何组合来自不同特征的数据，以最小化跟踪误差。将我们的算法与仅使用细胞位置的简单方法进行比较，结果表明 FAST 产生的跟踪误差减少了 4 到 10 倍。FAST 的模块化设计将我们新颖的跟踪方法与分割工具、广泛的数据可视化、谱系分配和手动跟踪修正相结合。它还具有高度可扩展性，允许用户从图像中提取自定义信息，并将其无缝集成到下游分析中。因此，FAST 可以在最小的用户输入下实现高通量、数据丰富的分析。它可以在 Matlab 中使用，也可以作为编译的独立应用程序使用，并且可以在 https://bit.ly/3vovDHn 上获得，同时还提供了广泛的教程和详细的文档。
