1. Cell Biology
  2. Computational and Systems Biology

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
https://doi.org/10.7554/eLife.10047
Share this article
Cite this article
  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
  2. Download BibTeX
  3. Download .RIS

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.

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

  • 7,048
    views
  • 1,229
    downloads
  • 40
    citations

Views, downloads and citations are aggregated across all versions of this paper published by eLife.

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

Categories and tags

Research organism

Further reading

    1. Cell Biology
    2. Developmental Biology

    The exocyst complex controls multiple events in the pathway of regulated exocytosis

    Sofía Suárez Freire, Sebastián Perez-Pandolfo ... Mariana Melani
    Research Article

    Eukaryotic cells depend on exocytosis to direct intracellularly synthesized material toward the extracellular space or the plasma membrane, so exocytosis constitutes a basic function for cellular homeostasis and communication between cells. The secretory pathway includes biogenesis of secretory granules (SGs), their maturation and fusion with the plasma membrane (exocytosis), resulting in release of SG content to the extracellular space. The larval salivary gland of Drosophila melanogaster is an excellent model for studying exocytosis. This gland synthesizes mucins that are packaged in SGs that sprout from the trans-Golgi network and then undergo a maturation process that involves homotypic fusion, condensation, and acidification. Finally, mature SGs are directed to the apical domain of the plasma membrane with which they fuse, releasing their content into the gland lumen. The exocyst is a hetero-octameric complex that participates in tethering of vesicles to the plasma membrane during constitutive exocytosis. By precise temperature-dependent gradual activation of the Gal4-UAS expression system, we have induced different levels of silencing of exocyst complex subunits, and identified three temporarily distinctive steps of the regulated exocytic pathway where the exocyst is critically required: SG biogenesis, SG maturation, and SG exocytosis. Our results shed light on previously unidentified functions of the exocyst along the exocytic pathway. We propose that the exocyst acts as a general tethering factor in various steps of this cellular process.

    1. Cell Biology
    2. Developmental Biology

    The sperm hook as a functional adaptation for migration and self-organized behavior

    Heungjin Ryu, Kibum Nam ... Jung-Hoon Park
    Research Article

    In most murine species, spermatozoa exhibit a falciform apical hook at the head end. The function of the sperm hook is not yet clearly understood. In this study, we investigate the role of the sperm hook in the migration of spermatozoa through the female reproductive tract in Mus musculus (C57BL/6), using a deep tissue imaging custom-built two-photon microscope. Through live reproductive tract imaging, we found evidence indicating that the sperm hook aids in the attachment of spermatozoa to the epithelium and facilitates interactions between spermatozoa and the epithelium during migration in the uterus and oviduct. We also observed synchronized sperm beating, which resulted from the spontaneous unidirectional rearrangement of spermatozoa in the uterus. Based on live imaging of spermatozoa-epithelium interaction dynamics, we propose that the sperm hook plays a crucial role in successful migration through the female reproductive tract by providing anchor-like mechanical support and facilitating interactions between spermatozoa and the female reproductive tract in the house mouse.

    1. Cell Biology

    Spatiotemporal recruitment of the ubiquitin-specific protease USP8 directs endosome maturation

    Yue Miao, Yongtao Du ... Mei Ding
    Research Article

    The spatiotemporal transition of small GTPase Rab5 to Rab7 is crucial for early-to-late endosome maturation, yet the precise mechanism governing Rab5-to-Rab7 switching remains elusive. USP8, a ubiquitin-specific protease, plays a prominent role in the endosomal sorting of a wide range of transmembrane receptors and is a promising target in cancer therapy. Here, we identified that USP8 is recruited to Rab5-positive carriers by Rabex5, a guanine nucleotide exchange factor (GEF) for Rab5. The recruitment of USP8 dissociates Rabex5 from early endosomes (EEs) and meanwhile promotes the recruitment of the Rab7 GEF SAND-1/Mon1. In USP8-deficient cells, the level of active Rab5 is increased, while the Rab7 signal is decreased. As a result, enlarged EEs with abundant intraluminal vesicles accumulate and digestive lysosomes are rudimentary. Together, our results reveal an important and unexpected role of a deubiquitinating enzyme in endosome maturation.