Active machine learning-driven experimentation to determine compound effects on protein patterns

  1. Armaghan W Naik
  2. Joshua D Kangas
  3. Devin P Sullivan
  4. Robert F Murphy  Is a corresponding author
  1. Carnegie Mellon University, United States

Abstract

High throughput screening determines the effects of many conditions on a given biological target. Currently, to estimate the effects of those conditions on other targets requires either strong modeling assumptions (e.g. similarities among targets) or separate screens. Ideally, data-driven experimentation could be used to learn accurate models for many conditions and targets without doing all possible experiments. We have previously described an active machine learning algorithm that can iteratively choose small sets of experiments to learn models of multiple effects. We now show that, with no prior knowledge and with liquid handling robotics and automated microscopy under its control, this learner accurately learned the effects of 48 chemical compounds on the subcellular localization of 48 proteins while performing only 29% of all possible experiments. The results represent the first practical demonstration of the utility of active learning-driven biological experimentation in which the set of possible phenotypes is unknown in advance.

Article and author information

Author details

  1. Armaghan W Naik

    Computational Biology Department, Center for Bioimage Informatics, Carnegie Mellon University, Pittsburgh, United States
    Competing interests
    The authors declare that no competing interests exist.
  2. Joshua D Kangas

    Computational Biology Department, Center for Bioimage Informatics, Carnegie Mellon University, Pittsburgh, United States
    Competing interests
    The authors declare that no competing interests exist.
  3. Devin P Sullivan

    Computational Biology Department, Center for Bioimage Informatics, Carnegie Mellon University, Pittsburgh, United States
    Competing interests
    The authors declare that no competing interests exist.
  4. Robert F Murphy

    Computational Biology Department, Center for Bioimage Informatics, Carnegie Mellon University, Pittsburgh, United States
    For correspondence
    murphy@cmu.edu
    Competing interests
    The authors declare that no competing interests exist.

Reviewing Editor

  1. Uwe Ohler, Duke, Germany

Version history

  1. Received: July 13, 2015
  2. Accepted: January 28, 2016
  3. Accepted Manuscript published: February 3, 2016 (version 1)
  4. Version of Record published: March 7, 2016 (version 2)

Copyright

© 2016, Naik et al.

This article is distributed under the terms of the Creative Commons Attribution License permitting unrestricted use and redistribution provided that the original author and source are credited.

Metrics

  • 6,856
    Page views
  • 1,212
    Downloads
  • 34
    Citations

Article citation count generated by polling the highest count across the following sources: Scopus, Crossref, PubMed Central.

Download links

A two-part list of links to download the article, or parts of the article, in various formats.

Downloads (link to download the article as PDF)

Open citations (links to open the citations from this article in various online reference manager services)

Cite this article (links to download the citations from this article in formats compatible with various reference manager tools)

  1. Armaghan W Naik
  2. Joshua D Kangas
  3. Devin P Sullivan
  4. Robert F Murphy
(2016)
Active machine learning-driven experimentation to determine compound effects on protein patterns
eLife 5:e10047.
https://doi.org/10.7554/eLife.10047

Share this article

https://doi.org/10.7554/eLife.10047

Further reading

    1. Biochemistry and Chemical Biology
    2. Cell Biology
    Kristian Davidsen, Jonathan S Marvin ... Lucas B Sullivan
    Research Article

    Intracellular levels of the amino acid aspartate are responsive to changes in metabolism in mammalian cells and can correspondingly alter cell function, highlighting the need for robust tools to measure aspartate abundance. However, comprehensive understanding of aspartate metabolism has been limited by the throughput, cost, and static nature of the mass spectrometry (MS)-based measurements that are typically employed to measure aspartate levels. To address these issues, we have developed a green fluorescent protein (GFP)-based sensor of aspartate (jAspSnFR3), where the fluorescence intensity corresponds to aspartate concentration. As a purified protein, the sensor has a 20-fold increase in fluorescence upon aspartate saturation, with dose-dependent fluorescence changes covering a physiologically relevant aspartate concentration range and no significant off target binding. Expressed in mammalian cell lines, sensor intensity correlated with aspartate levels measured by MS and could resolve temporal changes in intracellular aspartate from genetic, pharmacological, and nutritional manipulations. These data demonstrate the utility of jAspSnFR3 and highlight the opportunities it provides for temporally resolved and high-throughput applications of variables that affect aspartate levels.

    1. Cell Biology
    2. Immunology and Inflammation
    Chinky Shiu Chen Liu, Tithi Mandal ... Dipyaman Ganguly
    Research Article

    T cells are crucial for efficient antigen-specific immune responses and thus their migration within the body, to inflamed tissues from circulating blood or to secondary lymphoid organs, plays a very critical role. T cell extravasation in inflamed tissues depends on chemotactic cues and interaction between endothelial adhesion molecules and cellular integrins. A migrating T cell is expected to sense diverse external and membrane-intrinsic mechano-physical cues, but molecular mechanisms of such mechanosensing in cell migration are not established. We explored if the professional mechanosensor Piezo1 plays any role during integrin-dependent chemotaxis of human T cells. We found that deficiency of Piezo1 in human T cells interfered with integrin-dependent cellular motility on ICAM-1-coated surface. Piezo1 recruitment at the leading edge of moving T cells is dependent on and follows focal adhesion formation at the leading edge and local increase in membrane tension upon chemokine receptor activation. Piezo1 recruitment and activation, followed by calcium influx and calpain activation, in turn, are crucial for the integrin LFA1 (CD11a/CD18) recruitment at the leading edge of the chemotactic human T cells. Thus, we find that Piezo1 activation in response to local mechanical cues constitutes a membrane-intrinsic component of the ‘outside-in’ signaling in human T cells, migrating in response to chemokines, that mediates integrin recruitment to the leading edge.