skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Deep reinforcement learning of cell movement in the early stage of C.elegans embryogenesis

Abstract

Motivation: Cell movement in the early phase of Caenorhabditis elegans development is regulated by a highly complex process in which a set of rules and connections are formulated at distinct scales. Previous efforts have demonstrated that agent-based, multi-scale modeling systems can integrate physical and biological rules and provide new avenues to study developmental systems. However, the application of these systems to model cell movement is still challenging and requires a comprehensive understanding of regulatory networks at the right scales. Recent developments in deep learning and reinforcement learning provide an unprecedented opportunity to explore cell movement using 3D time-lapse microscopy images. Results: We present a deep reinforcement learning approach within an agent-based modeling system to characterize cell movement in the embryonic development of C.elegans. Our modeling system captures the complexity of cell movement patterns in the embryo and overcomes the local optimization problem encountered by traditional rule-based, agent-based modeling that uses greedy algorithms. Here, we tested our model with two real developmental processes: the anterior movement of the Cpaaa cell via intercalation and the rearrangement of the superficial left-right asymmetry. In the first case, the model results suggested that Cpaaa’s intercalation is an active directional cell movement caused by the continuousmore » effects from a longer distance (farther than the length of two adjacent cells), as opposed to a passive movement caused by neighbor cell movements. In the second case, a leader-follower mechanism well explained the collective cell movement pattern in the asymmetry rearrangement. These results showed that our approach to introduce deep reinforcement learning into agent-based modeling can test regulatory mechanisms by exploring cell migration paths in a reverse engineering perspective. Lastly, this model opens new doors to explore the large datasets generated by live imaging. Availability and implementation: Source code is available at https://github.com/zwang84/drl4cellmovement.« less

Authors:
 [1]; ORCiD logo [2];  [1]; ORCiD logo [3];  [1];  [3]
  1. Univ. of Tennessee, Knoxville, TN (United States). Dept. of Electrical Engineering and Computer Science
  2. Univ. of Tennessee, Knoxville, TN (United States). Dept. of Electrical Engineering and Computer Science; Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States). Environmental Science Division
  3. Sloan-Kettering Inst., New York, NY (United States). Developmental Biology Program
Publication Date:
Research Org.:
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Sponsoring Org.:
USDOE; National Institutes of Health (NIH)
OSTI Identifier:
1463974
Grant/Contract Number:  
AC05-00OR22725; R01GM097576; P30CA008748
Resource Type:
Accepted Manuscript
Journal Name:
Bioinformatics
Additional Journal Information:
Journal Volume: 34; Journal Issue: 18; Journal ID: ISSN 1367-4803
Publisher:
Oxford University Press
Country of Publication:
United States
Language:
English
Subject:
59 BASIC BIOLOGICAL SCIENCES

Citation Formats

Wang, Zi, Wang, Dali, Li, Chengcheng, Xu, Yichi, Li, Husheng, and Bao, Zhirong. Deep reinforcement learning of cell movement in the early stage of C.elegans embryogenesis. United States: N. p., 2018. Web. doi:10.1093/bioinformatics/bty323.
Wang, Zi, Wang, Dali, Li, Chengcheng, Xu, Yichi, Li, Husheng, & Bao, Zhirong. Deep reinforcement learning of cell movement in the early stage of C.elegans embryogenesis. United States. doi:10.1093/bioinformatics/bty323.
Wang, Zi, Wang, Dali, Li, Chengcheng, Xu, Yichi, Li, Husheng, and Bao, Zhirong. Wed . "Deep reinforcement learning of cell movement in the early stage of C.elegans embryogenesis". United States. doi:10.1093/bioinformatics/bty323. https://www.osti.gov/servlets/purl/1463974.
@article{osti_1463974,
title = {Deep reinforcement learning of cell movement in the early stage of C.elegans embryogenesis},
author = {Wang, Zi and Wang, Dali and Li, Chengcheng and Xu, Yichi and Li, Husheng and Bao, Zhirong},
abstractNote = {Motivation: Cell movement in the early phase of Caenorhabditis elegans development is regulated by a highly complex process in which a set of rules and connections are formulated at distinct scales. Previous efforts have demonstrated that agent-based, multi-scale modeling systems can integrate physical and biological rules and provide new avenues to study developmental systems. However, the application of these systems to model cell movement is still challenging and requires a comprehensive understanding of regulatory networks at the right scales. Recent developments in deep learning and reinforcement learning provide an unprecedented opportunity to explore cell movement using 3D time-lapse microscopy images. Results: We present a deep reinforcement learning approach within an agent-based modeling system to characterize cell movement in the embryonic development of C.elegans. Our modeling system captures the complexity of cell movement patterns in the embryo and overcomes the local optimization problem encountered by traditional rule-based, agent-based modeling that uses greedy algorithms. Here, we tested our model with two real developmental processes: the anterior movement of the Cpaaa cell via intercalation and the rearrangement of the superficial left-right asymmetry. In the first case, the model results suggested that Cpaaa’s intercalation is an active directional cell movement caused by the continuous effects from a longer distance (farther than the length of two adjacent cells), as opposed to a passive movement caused by neighbor cell movements. In the second case, a leader-follower mechanism well explained the collective cell movement pattern in the asymmetry rearrangement. These results showed that our approach to introduce deep reinforcement learning into agent-based modeling can test regulatory mechanisms by exploring cell migration paths in a reverse engineering perspective. Lastly, this model opens new doors to explore the large datasets generated by live imaging. Availability and implementation: Source code is available at https://github.com/zwang84/drl4cellmovement.},
doi = {10.1093/bioinformatics/bty323},
journal = {Bioinformatics},
number = 18,
volume = 34,
place = {United States},
year = {2018},
month = {4}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Save / Share: