Micropilot: Automation of fluorescence microscopy-based imaging for systems biology

Advanced Light Microscopy Facility, European Molecular Biology Laboratory, Heidelberg, Germany.
Nature Methods (Impact Factor: 32.07). 01/2011; 8(3):246-9. DOI: 10.1038/nmeth.1558
Source: PubMed


Quantitative microscopy relies on imaging of large cell numbers but is often hampered by time-consuming manual selection of specific cells. The 'Micropilot' software automatically detects cells of interest and launches complex imaging experiments including three-dimensional multicolor time-lapse or fluorescence recovery after photobleaching in live cells. In three independent experimental setups this allowed us to statistically analyze biological processes in detail and is thus a powerful tool for systems biology.

Download full-text


Available from: Thomas Walter, Jun 03, 2014
34 Reads
  • Source
    • "The power of machine learning can be further leveraged by a seamless integration into the image-acquisition process (Conrad et al., 2011). As state-of-the-art microscopes support full motorization and specimen interaction (e.g. by photobleaching at defined image areas or compound dispensing), automatic online recognition of phenotypes enables intelligent imaging workflows with highly sophisticated biological assays. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Recent advances in microscope automation provide new opportunities for high-throughput cell biology, such as image-based screening. High-complex image analysis tasks often make the implementation of static and predefined processing rules a cumbersome effort. Machine-learning methods, instead, seek to use intrinsic data structure, as well as the expert annotations of biologists to infer models that can be used to solve versatile data analysis tasks. Here, we explain how machine-learning methods work and what needs to be considered for their successful application in cell biology. We outline how microscopy images can be converted into a data representation suitable for machine learning, and then introduce various state-of-the-art machine-learning algorithms, highlighting recent applications in image-based screening. Our Commentary aims to provide the biologist with a guide to the application of machine learning to microscopy assays and we therefore include extensive discussion on how to optimize experimental workflow as well as the data analysis pipeline.
    Journal of Cell Science 11/2013; 126(24). DOI:10.1242/jcs.123604 · 5.43 Impact Factor
  • Source
    • "In this context, it is important to take into account the cellular event of interest: a pan-cellular signal increase will be easier to interpret and require less elaborate algorithms – a simple signal threshold may suffice (Wenus et al., 2009) – than the recognition of a DNA damage repair pattern specific to HZE impacts (clustered foci). The latter requires more detailed feature extraction (texture, shape, objects, intensity, etc.) and integration of machine learning techniques, in which robust classifiers are established by means of training data sets (Carpenter et al., 2006; Jones et al., 2009; Conrad et al., 2011). This form of phenotype recognition can also be used for identification of cell culture condition in darkfield mode (Wei et al., 2008), although extraction of simple parameters such as culture density, cell morphology and cell granularity may be sufficient. "
    [Show abstract] [Hide abstract]
    ABSTRACT: A major concern for long-term deep space missions is the detrimental impact of cosmic radiation on human health. Especially the presence of high-energy particles of high atomic mass (HZE) represents a serious threat. To contribute to a fundamental understanding of space radiation effects and to help improving risk assessment for humans on the Moon, the ESA Lunar Lander mission model payload includes a package dedicated to cell-based radiobiology experiments in the form of an Autonomous Microscope for Examination of Radiation Effects (AMERE). The purpose of this setup is to enable real-time visualization of DNA damage repair in living cells after traversal of HZE particles on the Moon. To assess the feasibility of this challenging experiment, we have analysed the biological and technological demands. In this article, we discuss the experimental concept, the biological considerations and describe the implications for system design.
    Planetary and Space Science 08/2012; 74(1). DOI:10.1016/j.pss.2012.07.015 · 1.88 Impact Factor
  • Source
    • "Many fluorescent probes and dyes are now available to allow the observation of various features of specimens, such as cell walls, organelles, and numerous proteins (Cutler et al., 2000; Pawley, 2006). The challenge has shifted from image acquisition to image analysis and is compounded by the automation of the acquisition process via time-series or automated, feature-driven image capture (Conrad et al., 2011). "
    [Show abstract] [Hide abstract]
    ABSTRACT: It is increasingly important in life sciences that many cell-scale and tissue-scale measurements are quantified from confocal microscope images. However, extracting and analyzing large-scale confocal image data sets represents a major bottleneck for researchers. To aid this process, CellSeT software has been developed, which utilizes tissue-scale structure to help segment individual cells. We provide examples of how the CellSeT software can be used to quantify fluorescence of hormone-responsive nuclear reporters, determine membrane protein polarity, extract cell and tissue geometry for use in later modeling, and take many additional biologically relevant measures using an extensible plug-in toolset. Application of CellSeT promises to remove subjectivity from the resulting data sets and facilitate higher-throughput, quantitative approaches to plant cell research.
    The Plant Cell 04/2012; 24(4):1353-61. DOI:10.1105/tpc.112.096289 · 9.34 Impact Factor
Show more