Contrasting action and posture coding with hierarchical deep neural network models of proprioception

  1. Kai J Sandbrink
  2. Pranav Mamidanna
  3. Claudio Michaelis
  4. Matthias Bethge
  5. Mackenzie W Mathis  Is a corresponding author
  6. Alexander Mathis  Is a corresponding author
  1. École Polytechnique Fédérale de Lausanne, Switzerland
  2. Eberhard Karls Universität Tübingen, Germany

Abstract

Biological motor control is versatile, efficient, and depends on proprioceptive feedback. Muscles are flexible and undergo continuous changes, requiring distributed adaptive control mechanisms that continuously account for the body's state. The canonical role of proprioception is representing the body state. We hypothesize that the proprioceptive system could also be critical for high-level tasks such as action recognition. To test this theory, we pursued a task-driven modeling approach, which allowed us to isolate the study of proprioception. We generated a large synthetic dataset of human arm trajectories tracing characters of the Latin alphabet in 3D space, together with muscle activities obtained from a musculoskeletal model and model-based muscle spindle activity. Next, we compared two classes of tasks: trajectory decoding and action recognition, which allowed us to train hierarchical models to decode either the position and velocity of the end-effector of one's posture or the character (action) identity from the spindle firing patterns. We found that artificial neural networks could robustly solve both tasks, and the networks'units show tuning properties similar to neurons in the primate somatosensory cortex and the brainstem. Remarkably, we found uniformly distributed directional selective units only with the action-recognition-trained models and not the trajectory-decoding-trained models. This suggests that proprioceptive encoding is additionally associated with higher-level functions such as action recognition and therefore provides new, experimentally testable hypotheses of how proprioception aids in adaptive motor control.

Data availability

The computational dataset and code to create it is available at https://github.com/amathislab/DeepDraw

Article and author information

Author details

  1. Kai J Sandbrink

    Brain Mind Institute, École Polytechnique Fédérale de Lausanne, Genève, Switzerland
    Competing interests
    No competing interests declared.
  2. Pranav Mamidanna

    Tübingen AI Center, Eberhard Karls Universität Tübingen, Tübingen, Germany
    Competing interests
    No competing interests declared.
  3. Claudio Michaelis

    Tübingen AI Center, Eberhard Karls Universität Tübingen, Tübingen, Germany
    Competing interests
    No competing interests declared.
  4. Matthias Bethge

    Tübingen AI Center, Eberhard Karls Universität Tübingen, Tübingen, Germany
    Competing interests
    No competing interests declared.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0002-6417-7812
  5. Mackenzie W Mathis

    Brain Mind Institute, École Polytechnique Fédérale de Lausanne, Genève, Switzerland
    For correspondence
    mackenzie@post.harvard.edu
    Competing interests
    Mackenzie W Mathis, Reviewing editor, eLife.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0001-7368-4456
  6. Alexander Mathis

    Brain Mind Institute, École Polytechnique Fédérale de Lausanne, Genève, Switzerland
    For correspondence
    alexander.mathis@epfl.ch
    Competing interests
    No competing interests declared.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0002-3777-2202

Funding

Swiss National Science Foundation (310030_201057)

  • Mackenzie W Mathis

Swiss National Science Foundation (310030_212516)

  • Alexander Mathis

Rowland Institute at Harvard

  • Kai J Sandbrink
  • Mackenzie W Mathis
  • Alexander Mathis

The funders had no role in study design, data collection and interpretation, or the decision to submit the work for publication.

Copyright

© 2023, Sandbrink 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

  • 9
    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. Kai J Sandbrink
  2. Pranav Mamidanna
  3. Claudio Michaelis
  4. Matthias Bethge
  5. Mackenzie W Mathis
  6. Alexander Mathis
(2023)
Contrasting action and posture coding with hierarchical deep neural network models of proprioception
eLife 12:e81499.
https://doi.org/10.7554/eLife.81499

Share this article

https://doi.org/10.7554/eLife.81499

Further reading

    1. Computational and Systems Biology
    2. Microbiology and Infectious Disease
    Saugat Poudel, Jason Hyun ... Bernhard O Palsson
    Research Article

    The Staphylococcus aureus clonal complex 8 (CC8) is made up of several subtypes with varying levels of clinical burden; from community-associated methicillin-resistant S. aureus USA300 strains to hospital-associated (HA-MRSA) USA500 strains and ancestral methicillin-susceptible (MSSA) strains. This phenotypic distribution within a single clonal complex makes CC8 an ideal clade to study the emergence of mutations important for antibiotic resistance and community spread. Gene-level analysis comparing USA300 against MSSA and HA-MRSA strains have revealed key horizontally acquired genes important for its rapid spread in the community. However, efforts to define the contributions of point mutations and indels have been confounded by strong linkage disequilibrium resulting from clonal propagation. To break down this confounding effect, we combined genetic association testing with a model of the transcriptional regulatory network (TRN) to find candidate mutations that may have led to changes in gene regulation. First, we used a De Bruijn graph genome-wide association study to enrich mutations unique to the USA300 lineages within CC8. Next, we reconstructed the TRN by using independent component analysis on 670 RNA-sequencing samples from USA300 and non-USA300 CC8 strains which predicted several genes with strain-specific altered expression patterns. Examination of the regulatory region of one of the genes enriched by both approaches, isdH, revealed a 38-bp deletion containing a Fur-binding site and a conserved single-nucleotide polymorphism which likely led to the altered expression levels in USA300 strains. Taken together, our results demonstrate the utility of reconstructed TRNs to address the limits of genetic approaches when studying emerging pathogenic strains.

    1. Computational and Systems Biology
    Masaaki Uematsu, Jeremy M Baskin
    Tools and Resources

    Plasmid construction is central to life science research, and sequence verification is arguably its costliest step. Long-read sequencing has emerged as a competitor to Sanger sequencing, with the principal benefit that whole plasmids can be sequenced in a single run. Nevertheless, the current cost of nanopore sequencing is still prohibitive for routine sequencing during plasmid construction. We develop a computational approach termed Simple Algorithm for Very Efficient Multiplexing of Oxford Nanopore Experiments for You (SAVEMONEY) that guides researchers to mix multiple plasmids and subsequently computationally de-mixes the resultant sequences. SAVEMONEY defines optimal mixtures in a pre-survey step, and following sequencing, executes a post-analysis workflow involving sequence classification, alignment, and consensus determination. By using Bayesian analysis with prior probability of expected plasmid construction error rate, high-confidence sequences can be obtained for each plasmid in the mixture. Plasmids differing by as little as two bases can be mixed as a single sample for nanopore sequencing, and routine multiplexing of even six plasmids per 180 reads can still maintain high accuracy of consensus sequencing. SAVEMONEY should further democratize whole-plasmid sequencing by nanopore and related technologies, driving down the effective cost of whole-plasmid sequencing to lower than that of a single Sanger sequencing run.