1. Computational and Systems Biology
  2. Neuroscience
Download icon

Low-dimensional learned feature spaces quantify individual and group differences in vocal repertoires

  1. Jack Goffinet
  2. Samuel Brudner
  3. Richard Mooney
  4. John Pearson  Is a corresponding author
  1. Duke University, United States
Research Article
  • Cited 0
  • Views 269
  • Annotations
Cite this article as: eLife 2021;10:e67855 doi: 10.7554/eLife.67855

Abstract

Increases in the scale and complexity of behavioral data pose an increasing challenge for data analysis. A common strategy involves replacing entire behaviors with small numbers of handpicked, domain-specific features, but this approach suffers from several crucial limitations. For example, handpicked features may miss important dimensions of variability, and correlations among them complicate statistical testing. Here, by contrast, we apply the variational autoencoder (VAE), an unsupervised learning method, to learn features directly from data and quantify the vocal behavior of two model species: the laboratory mouse and the zebra finch. The VAE converges on a parsimonious representation that outperforms handpicked features on a variety of common analysis tasks, enables the measurement of moment-by-moment vocal variability on the timescale of tens of milliseconds in the zebra finch, provides strong evidence that mouse ultrasonic vocalizations do not cluster as is commonly believed, and captures the similarity of tutor and pupil birdsong with qualitatively higher fidelity than previous approaches. In all, we demonstrate the utility of modern unsupervised learning approaches to the quantification of complex and high-dimensional vocal behavior.

Data availability

Dataset 1---------Online, publicly available MUPET dataset: ~5GB Available at: https://github.com/mvansegbroeck/mupet/wiki/MUPET-wiki Figs: 2, 3, 4d-eDataset 2----------Single zebra finch data: ~200-400 MB of audio generated as part of work in progress in Mooney Lab. Figs: 2e-f, 4a-c, 5a, 5d, 6b-eDataset 3---------Mouse USV dataset: ~30-40 GB of audio generated as part of work in progress in Mooney Lab. Figs: 4fDataset 5---------This is a subset of dataset 3, taken from a single mouse: ~1GB of audio. Figs: 5b-e, 6aDataset 6---------10 zebra finch pupil/tutor pairs: ~60 GB of audio generated as part of work in progress in Mooney Lab. Figs: 7Upon acceptance, all Datasets 2-6 will be archived in the Duke Digital Repository (https://research.repository.duke.edu). DOI in process.

The following previously published data sets were used

Article and author information

Author details

  1. Jack Goffinet

    Computer Science, Duke University, Durham, United States
    Competing interests
    The authors declare that no competing interests exist.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0001-6729-0848
  2. Samuel Brudner

    Neurobiology, Duke University, Durham, United States
    Competing interests
    The authors declare that no competing interests exist.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0002-6043-9328
  3. Richard Mooney

    Department of Neurobiology, Duke University, Durham, United States
    Competing interests
    The authors declare that no competing interests exist.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0002-3308-1367
  4. John Pearson

    Biostatistics & Bioinformatics, Neurobiology, Center for Cognitive Neuroscience, Psychology and Neuroscience, Electrical and Computer Engineering, Duke University, Durham, United States
    For correspondence
    john.pearson@duke.edu
    Competing interests
    The authors declare that no competing interests exist.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0002-9876-7837

Funding

National Institute of Mental Health (R01-MH117778)

  • Richard Mooney

National Institute of Neurological Disorders and Stroke (R01-NS118424)

  • Richard Mooney
  • John Pearson

National Institute on Deafness and Other Communication Disorders (R01-DC013826)

  • Richard Mooney
  • John Pearson

National Institute of Neurological Disorders and Stroke (R01-NS099288)

  • Richard Mooney

Eunice Kennedy Shriver National Institute of Child Health and Human Development (F31-HD098772)

  • Samuel Brudner

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

Ethics

Animal experimentation: All data generated in conjunction for this study were generated by experiments performed in strict accordance with the recommendations in the Guide for the Care and Use of Laboratory Animals of the National Institutes of Health. All of the animals were handled according to approved institutional animal care and use committee (IACUC) protocols of Duke University, protocol numbers A171-20-08 and A172-20-08.

Reviewing Editor

  1. Jesse H Goldberg, Cornell University, United States

Publication history

  1. Received: February 24, 2021
  2. Accepted: May 12, 2021
  3. Accepted Manuscript published: May 14, 2021 (version 1)

Copyright

© 2021, Goffinet 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

  • 269
    Page views
  • 49
    Downloads
  • 0
    Citations

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

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. Computational and Systems Biology
    James Oliver Patterson et al.
    Research Article

    Maintenance of cell size homeostasis is a property that is conserved throughout eukaryotes. Cell size homeostasis is brought about by the co-ordination of cell division with cell growth, and requires restriction of smaller cells from undergoing mitosis and cell division, whilst allowing larger cells to do so. Cyclin-CDK is the fundamental driver of mitosis and therefore ultimately ensures size homeostasis. Here we dissect determinants of CDK activity in vivo to investigate how cell size information is processed by the cell cycle network in fission yeast. We develop a high-throughput single-cell assay system of CDK activity in vivo and show that inhibitory tyrosine phosphorylation of CDK encodes cell size information, with the phosphatase PP2A aiding to set a size threshold for division. CDK inhibitory phosphorylation works synergistically with PP2A to prevent mitosis in smaller cells. Finally, we find that diploid cells of equivalent size to haploid cells exhibit lower CDK activity in response to equal cyclin-CDK enzyme concentrations, suggesting that CDK activity is reduced by increased DNA levels. Therefore, scaling of cyclin-CDK levels with cell size, CDK inhibitory phosphorylation, PP2A, and DNA-dependent inhibition of CDK activity, all inform the cell cycle network of cell size, thus contributing to cell-size homeostasis.

    1. Computational and Systems Biology
    2. Genetics and Genomics
    Graham Gower et al.
    Tools and Resources Updated

    Studies in a variety of species have shown evidence for positively selected variants introduced into a population via introgression from another, distantly related population—a process known as adaptive introgression. However, there are few explicit frameworks for jointly modelling introgression and positive selection, in order to detect these variants using genomic sequence data. Here, we develop an approach based on convolutional neural networks (CNNs). CNNs do not require the specification of an analytical model of allele frequency dynamics and have outperformed alternative methods for classification and parameter estimation tasks in various areas of population genetics. Thus, they are potentially well suited to the identification of adaptive introgression. Using simulations, we trained CNNs on genotype matrices derived from genomes sampled from the donor population, the recipient population and a related non-introgressed population, in order to distinguish regions of the genome evolving under adaptive introgression from those evolving neutrally or experiencing selective sweeps. Our CNN architecture exhibits 95% accuracy on simulated data, even when the genomes are unphased, and accuracy decreases only moderately in the presence of heterosis. As a proof of concept, we applied our trained CNNs to human genomic datasets—both phased and unphased—to detect candidates for adaptive introgression that shaped our evolutionary history.