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

  • 6,913
    views
  • 1,215
    downloads
  • 38
    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

Further reading

    1. Cell Biology
    Ruichen Yang, Hongshang Chu ... Baojie Li
    Research Article

    Elastic cartilage constitutes a major component of the external ear, which functions to guide sound to the middle and inner ears. Defects in auricle development cause congenital microtia, which affects hearing and appearance in patients. Mutations in several genes have been implicated in microtia development, yet, the pathogenesis of this disorder remains incompletely understood. Here, we show that Prrx1 genetically marks auricular chondrocytes in adult mice. Interestingly, BMP-Smad1/5/9 signaling in chondrocytes is increasingly activated from the proximal to distal segments of the ear, which is associated with a decrease in chondrocyte regenerative activity. Ablation of Bmpr1a in auricular chondrocytes led to chondrocyte atrophy and microtia development at the distal part. Transcriptome analysis revealed that Bmpr1a deficiency caused a switch from the chondrogenic program to the osteogenic program, accompanied by enhanced protein kinase A activation, likely through increased expression of Adcy5/8. Inhibition of PKA blocked chondrocyte-to-osteoblast transformation and microtia development. Moreover, analysis of single-cell RNA-seq of human microtia samples uncovered enriched gene expression in the PKA pathway and chondrocyte-to-osteoblast transformation process. These findings suggest that auricle cartilage is actively maintained by BMP signaling, which maintains chondrocyte identity by suppressing osteogenic differentiation.

    1. Cancer Biology
    2. Cell Biology
    Timothy J Walker, Eduardo Reyes-Alvarez ... Lois M Mulligan
    Research Article

    Internalization from the cell membrane and endosomal trafficking of receptor tyrosine kinases (RTKs) are important regulators of signaling in normal cells that can frequently be disrupted in cancer. The adrenal tumor pheochromocytoma (PCC) can be caused by activating mutations of the rearranged during transfection (RET) receptor tyrosine kinase, or inactivation of TMEM127, a transmembrane tumor suppressor implicated in trafficking of endosomal cargos. However, the role of aberrant receptor trafficking in PCC is not well understood. Here, we show that loss of TMEM127 causes wildtype RET protein accumulation on the cell surface, where increased receptor density facilitates constitutive ligand-independent activity and downstream signaling, driving cell proliferation. Loss of TMEM127 altered normal cell membrane organization and recruitment and stabilization of membrane protein complexes, impaired assembly, and maturation of clathrin-coated pits, and reduced internalization and degradation of cell surface RET. In addition to RTKs, TMEM127 depletion also promoted surface accumulation of several other transmembrane proteins, suggesting it may cause global defects in surface protein activity and function. Together, our data identify TMEM127 as an important determinant of membrane organization including membrane protein diffusability and protein complex assembly and provide a novel paradigm for oncogenesis in PCC where altered membrane dynamics promotes cell surface accumulation and constitutive activity of growth factor receptors to drive aberrant signaling and promote transformation.