Automated, predictive, and interpretable inference of Caenorhabditis elegans escape dynamics

BRYAN DANIELS, William S. Ryu, Ilya Nemenman

Research output: Contribution to journalArticle

Abstract

The roundworm Caenorhabditis elegans exhibits robust escape behavior in response to rapidly rising temperature. The behavior lasts for a few seconds, shows history dependence, involves both sensory and motor systems, and is too complicated to model mechanistically using currently available knowledge. Instead we model the process phenomenologically, and we use the Sir Isaac dynamical inference platform to infer the model in a fully automated fashion directly from experimental data. The inferred model requires incorporation of an unobserved dynamical variable and is biologically interpretable. The model makes accurate predictions about the dynamics of the worm behavior, and it can be used to characterize the functional logic of the dynamical system underlying the escape response. This work illustrates the power of modern artificial intelligence to aid in discovery of accurate and interpretable models of complex natural systems.

Original languageEnglish (US)
Pages (from-to)7226-7231
Number of pages6
JournalProceedings of the National Academy of Sciences of the United States of America
Volume116
Issue number15
DOIs
StatePublished - Apr 9 2019

Fingerprint

Caenorhabditis elegans
Artificial Intelligence
History
Temperature

Keywords

  • Dynamical systems
  • Machine learning
  • Nociception
  • Phenomenological models

ASJC Scopus subject areas

  • General

Cite this

Automated, predictive, and interpretable inference of Caenorhabditis elegans escape dynamics. / DANIELS, BRYAN; Ryu, William S.; Nemenman, Ilya.

In: Proceedings of the National Academy of Sciences of the United States of America, Vol. 116, No. 15, 09.04.2019, p. 7226-7231.

Research output: Contribution to journalArticle

@article{5d31d9b0406a4a2baad45319e4692ce7,
title = "Automated, predictive, and interpretable inference of Caenorhabditis elegans escape dynamics",
abstract = "The roundworm Caenorhabditis elegans exhibits robust escape behavior in response to rapidly rising temperature. The behavior lasts for a few seconds, shows history dependence, involves both sensory and motor systems, and is too complicated to model mechanistically using currently available knowledge. Instead we model the process phenomenologically, and we use the Sir Isaac dynamical inference platform to infer the model in a fully automated fashion directly from experimental data. The inferred model requires incorporation of an unobserved dynamical variable and is biologically interpretable. The model makes accurate predictions about the dynamics of the worm behavior, and it can be used to characterize the functional logic of the dynamical system underlying the escape response. This work illustrates the power of modern artificial intelligence to aid in discovery of accurate and interpretable models of complex natural systems.",
keywords = "Dynamical systems, Machine learning, Nociception, Phenomenological models",
author = "BRYAN DANIELS and Ryu, {William S.} and Ilya Nemenman",
year = "2019",
month = "4",
day = "9",
doi = "10.1073/pnas.1816531116",
language = "English (US)",
volume = "116",
pages = "7226--7231",
journal = "Proceedings of the National Academy of Sciences of the United States of America",
issn = "0027-8424",
number = "15",

}

TY - JOUR

T1 - Automated, predictive, and interpretable inference of Caenorhabditis elegans escape dynamics

AU - DANIELS, BRYAN

AU - Ryu, William S.

AU - Nemenman, Ilya

PY - 2019/4/9

Y1 - 2019/4/9

N2 - The roundworm Caenorhabditis elegans exhibits robust escape behavior in response to rapidly rising temperature. The behavior lasts for a few seconds, shows history dependence, involves both sensory and motor systems, and is too complicated to model mechanistically using currently available knowledge. Instead we model the process phenomenologically, and we use the Sir Isaac dynamical inference platform to infer the model in a fully automated fashion directly from experimental data. The inferred model requires incorporation of an unobserved dynamical variable and is biologically interpretable. The model makes accurate predictions about the dynamics of the worm behavior, and it can be used to characterize the functional logic of the dynamical system underlying the escape response. This work illustrates the power of modern artificial intelligence to aid in discovery of accurate and interpretable models of complex natural systems.

AB - The roundworm Caenorhabditis elegans exhibits robust escape behavior in response to rapidly rising temperature. The behavior lasts for a few seconds, shows history dependence, involves both sensory and motor systems, and is too complicated to model mechanistically using currently available knowledge. Instead we model the process phenomenologically, and we use the Sir Isaac dynamical inference platform to infer the model in a fully automated fashion directly from experimental data. The inferred model requires incorporation of an unobserved dynamical variable and is biologically interpretable. The model makes accurate predictions about the dynamics of the worm behavior, and it can be used to characterize the functional logic of the dynamical system underlying the escape response. This work illustrates the power of modern artificial intelligence to aid in discovery of accurate and interpretable models of complex natural systems.

KW - Dynamical systems

KW - Machine learning

KW - Nociception

KW - Phenomenological models

UR - http://www.scopus.com/inward/record.url?scp=85064140200&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064140200&partnerID=8YFLogxK

U2 - 10.1073/pnas.1816531116

DO - 10.1073/pnas.1816531116

M3 - Article

VL - 116

SP - 7226

EP - 7231

JO - Proceedings of the National Academy of Sciences of the United States of America

JF - Proceedings of the National Academy of Sciences of the United States of America

SN - 0027-8424

IS - 15

ER -