hctsa: A Computational Framework for Automated Time-Series Phenotyping Using Massive Feature Extraction

• Published in: Cell systems Vol. 5; no. 5; pp. 527 - 531.e3
• Main Authors: Fulcher, Ben D., Jones, Nick S.
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 22.11.2017
• Subjects: high-throughput phenotyping; time-series analysis; high-throughput phenotyping; time-series analysis
• ISSN: 2405-4712; 2405-4720
• DOI: 10.1016/j.cels.2017.10.001

Phenotype measurements frequently take the form of time series, but we currently lack a systematic method for relating these complex data streams to scientifically meaningful outcomes, such as relating the movement dynamics of organisms to their genotype or measurements of brain dynamics of a patient to their disease diagnosis. Previous work addressed this problem by comparing implementations of thousands of diverse scientific time-series analysis methods in an approach termed highly comparative time-series analysis. Here, we introduce hctsa, a software tool for applying this methodological approach to data. hctsa includes an architecture for computing over 7,700 time-series features and a suite of analysis and visualization algorithms to automatically select useful and interpretable time-series features for a given application. Using exemplar applications to high-throughput phenotyping experiments, we show how hctsa allows researchers to leverage decades of time-series research to quantify and understand informative structure in time-series data. [Display omitted] •Fully documented and comprehensively tested software framework, hctsa•Automatically identify interpretable quantitative phenotypes from time-series data•Uses over 7,700 features from scientific time-series analysis literature•Provides biological understanding from C. elegans and Drosophila movement data A new software tool, hctsa, uses massive feature extraction to automatically identify informative and interpretable quantitative phenotypes from time-series data.