Learning dynamics from large biological data sets: Machine learning meets systems biology. Issue 22 (August 2020)

• Record Type: Journal Article
• Authors: Gilpin, William; Huang, Yitong; Forger, Daniel B.
• Is Part Of: Current opinion in systems biology. Issue 22(2020)
• Page Start: 1
• Page End: 7
• Publication Date: 2020-08
• Subjects: Machine learning -- Systems biology -- Neural networks -- Unsupervised learning; Systems biology -- Periodicals; 570
• DOI: 10.1016/j.coisb.2020.07.009
• Languages: English
• ISSNs: 2452-3100

Abstract

Abstract: In the past few decades, mathematical models based on dynamical systems theory have provided new insight into diverse biological systems. In this review, we ask whether the recent success of machine learning techniques for large-scale biological data analysis provides a complementary or competing approach to more traditional modeling approaches. Recent applications of machine learning to the problem of learning biological dynamics in diverse systems range from neuroscience to animal behavior. We compare the underlying mechanisms and limitations of traditional dynamical models with those of machine learning models. We highlight the unique role that traditional modeling has played in providing predictive insights into biological systems, and we propose several avenues for bridging traditional dynamical systems theory with large-scale analysis enabled by machine learning. Highlights: Unsupervised learning allows dynamics to be extracted from large biological data sets. Extracted dynamics can inform the development of mechanistic mathematical models. Machine learning models can be analyzed using tools from dynamical systems theory.