1. Cell Biology
  2. Computational and Systems Biology
Download icon

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
Research Article
  • Cited 15
  • Views 5,420
  • Annotations
Cite this article as: eLife 2016;5:e10047 doi: 10.7554/eLife.10047

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

Publication 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

  • 5,420
    Page views
  • 1,086
    Downloads
  • 15
    Citations

Article citation count generated by polling the highest count across the following sources: Crossref, Scopus, 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)

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

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

Further reading

    1. Cell Biology
    2. Developmental Biology
    Eric R Brooks et al.
    Research Article

    Neural tube closure defects are a major cause of infant mortality, with exencephaly accounting for nearly one-third of cases. However, the mechanisms of cranial neural tube closure are not well understood. Here we show that this process involves a tissue-wide pattern of apical constriction controlled by Sonic hedgehog (Shh) signaling. Midline cells in the mouse midbrain neuroepithelium are short with large apical surfaces, whereas lateral cells are taller and undergo synchronous apical constriction, driving neural fold elevation. Embryos lacking the Shh effector Gli2 fail to produce appropriate midline cell architecture, whereas embryos with expanded Shh signaling, including the IFT-A complex mutants Ift122 and Ttc21b and embryos expressing activated Smoothened, display apical constriction defects in lateral cells. Disruption of lateral, but not midline, cell remodeling results in exencephaly. These results reveal a morphogenetic program of patterned apical constriction governed by Shh signaling that generates structural changes in the developing mammalian brain.

    1. Cell Biology
    Tomás Edreira et al.
    Research Article

    In fission yeast, the septation initiation network (SIN) ensures temporal coordination between actomyosin ring (CAR) constriction with membrane ingression and septum synthesis. However, questions remain about CAR regulation under stress conditions. We show that Rgf1p (Rho1p GEF), participates in a delay of cytokinesis under cell wall stress (blankophor, BP). BP did not interfere with CAR assembly or the rate of CAR constriction, but did delay the onset of constriction in the wild type cells but not in the rgf1Δ cells. This delay was also abolished in the absence of Pmk1p, the MAPK of the cell integrity pathway (CIP), leading to premature abscission and a multi-septated phenotype. Moreover, cytokinesis delay correlates with maintained SIN signaling and depends on the SIN to be achieved. Thus, we propose that the CIP participates in a checkpoint, capable of triggering a CAR constriction delay through the SIN pathway to ensure that cytokinesis terminates successfully.