Dataset Information

Comprehensive machine learning analysis of Hydra behavior reveals a stable basal behavioral repertoire.

ABSTRACT: Animal behavior has been studied for centuries, but few efficient methods are available to automatically identify and classify it. Quantitative behavioral studies have been hindered by the subjective and imprecise nature of human observation, and the slow speed of annotating behavioral data. Here, we developed an automatic behavior analysis pipeline for the cnidarian Hydra vulgaris using machine learning. We imaged freely behaving Hydra, extracted motion and shape features from the videos, and constructed a dictionary of visual features to classify pre-defined behaviors. We also identified unannotated behaviors with unsupervised methods. Using this analysis pipeline, we quantified 6 basic behaviors and found surprisingly similar behavior statistics across animals within the same species, regardless of experimental conditions. Our analysis indicates that the fundamental behavioral repertoire of Hydra is stable. This robustness could reflect a homeostatic neural control of "housekeeping" behaviors which could have been already present in the earliest nervous systems.

SUBMITTER: Han S

PROVIDER: S-EPMC5922975 | biostudies-literature | 2018 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Comprehensive machine learning analysis of Hydra behavior reveals a stable basal behavioral repertoire.

Han Shuting S Taralova Ekaterina E Dupre Christophe C Yuste Rafael R

eLife 20180328

Animal behavior has been studied for centuries, but few efficient methods are available to automatically identify and classify it. Quantitative behavioral studies have been hindered by the subjective and imprecise nature of human observation, and the slow speed of annotating behavioral data. Here, we developed an automatic behavior analysis pipeline for the cnidarian Hydra vulgaris using machine learning. We imaged freely behaving Hydra, extracted motion and shape features from the ...[more]

PMID: 29589829

Similar Datasets

Project description:Since its discovery by Abraham Trembley in 1744, hydra has been a popular research organism. Features like spectacular regeneration capacity, peculiar tissue dynamics, continuous pattern formation, unique evolutionary position, and an apparent lack of organismal senescence make hydra an intriguing animal to study. While a large body of work has taken place, particularly in the domain of evolutionary developmental biology of hydra, in recent years, the focus has shifted to molecular mechanisms underlying various phenomena. DNA repair is a fundamental cellular process that helps to maintain integrity of the genome through multiple repair pathways found across taxa, from archaea to higher animals. DNA repair capacity and senescence are known to be closely associated, with mutations in several repair pathways leading to premature ageing phenotypes. Analysis of DNA repair in an animal like hydra could offer clues into several aspects including hydra's purported lack of organismal ageing, evolution of DNA repair systems in metazoa, and alternative functions of repair proteins. We review here the different DNA repair mechanisms known so far in hydra. Hydra genes from various DNA repair pathways show very high similarity with their vertebrate orthologues, indicating conservation at the level of sequence, structure, and function. Notably, most hydra repair genes are more similar to deuterostome counterparts than to common model invertebrates, hinting at ancient evolutionary origins of repair pathways and further highlighting the relevance of organisms like hydra as model systems. It appears that hydra has the full repertoire of DNA repair pathways, which are employed in stress as well as normal physiological conditions and may have a link with its observed lack of senescence. The close correspondence of hydra repair genes with higher vertebrates further demonstrates the need for deeper studies of various repair components, their interconnections, and functions in this early metazoan.

Project description:Mouse behavior is a primary outcome in evaluations of therapeutic efficacy. Exhaustive, continuous, multiparametric behavioral phenotyping is a valuable tool for understanding the pathophysiological status of mouse brain diseases. Automated home cage behavior analysis produces highly granulated data both in terms of number of features and sampling frequency. Previously, we demonstrated several ways to reduce feature dimensionality. In this study, we propose novel approaches for analyzing 33-Hz data generated by CleverSys software. We hypothesized that behavioral patterns within short time windows are reflective of physiological state, and that computer modeling of mouse behavioral routines can serve as a predictive tool in classification tasks. To remove bias due to researcher decisions, our data flow is indifferent to the quality, value, and importance of any given feature in isolation. To classify day and night behavior, as an example application, we developed a data preprocessing flow and utilized logistic regression (LG), support vector machines (SVM), random forest (RF), and one-dimensional convolutional neural networks paired with long short-term memory deep neural networks (1DConvBiLSTM). We determined that a 5-min video clip is sufficient to classify mouse behavior with high accuracy. LG, SVM, and RF performed similarly, predicting mouse behavior with 85% accuracy, and combining the three algorithms in an ensemble procedure increased accuracy to 90%. The best performance was achieved by combining the 1DConv and BiLSTM algorithms yielding 96% accuracy. Our findings demonstrate that computer modeling of the home-cage ethome can clearly define mouse physiological state. Furthermore, we showed that continuous behavioral data can be analyzed using approaches similar to natural language processing. These data provide proof of concept for future research in diagnostics of complex pathophysiological changes that are accompanied by changes in behavioral profile.

Dataset Information

Comprehensive machine learning analysis of Hydra behavior reveals a stable basal behavioral repertoire.

Publications

Comprehensive machine learning analysis of <i>Hydra</i> behavior reveals a stable basal behavioral repertoire.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets