TY - JOUR
T1 - Using Emulation to Engineer and Understand Simulations of Biological Systems
AU - Alden, Kieran
AU - Cosgrove, Jason
AU - Coles, Mark
AU - Timmis, Jon
N1 - Funding Information:
JC is supported by the Wellcome Trust 4-year PhD programme studentship: Combating Infectious Disease: Computational Approaches in Translation Science (WT095024MA). JC and KA are part-funded by the Wellcome Trust (204829) through the Centre for Future Health at the University of York. MC is funded in part by the Medical Research Council (G0601156 and MR/K021125/1), NC3Rs (NC/K999527/1), and the Human Frontiers Science Program (RGP0006/2009-C). JT is supported by the EPSRC (EP/K040820/1). Kieran Alden and Jason Cosgrove contributed equally to this work.
Publisher Copyright:
© 2004-2012 IEEE.
PY - 2020/1/1
Y1 - 2020/1/1
N2 - Modeling and simulation techniques have demonstrated success in studying biological systems. As the drive to better capture biological complexity leads to more sophisticated simulators, it becomes challenging to perform statistical analyses that help translate predictions into increased understanding. These analyses may require repeated executions and extensive sampling of high-dimensional parameter spaces: analyses that may become intractable due to time and resource limitations. Significant reduction in these requirements can be obtained using surrogate models, or emulators, that can rapidly and accurately predict the output of an existing simulator. We apply emulation to evaluate and enrich understanding of a previously published agent-based simulator of lymphoid tissue organogenesis, showing an ensemble of machine learning techniques can reproduce results obtained using a suite of statistical analyses within seconds. This performance improvement permits incorporation of previously intractable analyses, including multi-objective optimization to obtain parameter sets that yield a desired response, and Approximate Bayesian Computation to assess parametric uncertainty. To facilitate exploitation of emulation in simulation-focused studies, we extend our open source statistical package, spartan, to provide a suite of tools for emulator development, validation, and application. Overcoming resource limitations permits enriched evaluation and refinement, easing translation of simulator insights into increased biological understanding.
AB - Modeling and simulation techniques have demonstrated success in studying biological systems. As the drive to better capture biological complexity leads to more sophisticated simulators, it becomes challenging to perform statistical analyses that help translate predictions into increased understanding. These analyses may require repeated executions and extensive sampling of high-dimensional parameter spaces: analyses that may become intractable due to time and resource limitations. Significant reduction in these requirements can be obtained using surrogate models, or emulators, that can rapidly and accurately predict the output of an existing simulator. We apply emulation to evaluate and enrich understanding of a previously published agent-based simulator of lymphoid tissue organogenesis, showing an ensemble of machine learning techniques can reproduce results obtained using a suite of statistical analyses within seconds. This performance improvement permits incorporation of previously intractable analyses, including multi-objective optimization to obtain parameter sets that yield a desired response, and Approximate Bayesian Computation to assess parametric uncertainty. To facilitate exploitation of emulation in simulation-focused studies, we extend our open source statistical package, spartan, to provide a suite of tools for emulator development, validation, and application. Overcoming resource limitations permits enriched evaluation and refinement, easing translation of simulator insights into increased biological understanding.
KW - approximate Bayesian computation
KW - Emulation
KW - ensemble
KW - machine learning
KW - mechanistic modeling
KW - multi-objective optimization
KW - sensitivity analysis
KW - Machine Learning
KW - Algorithms
KW - Models, Biological
KW - Computer Simulation
KW - Bayes Theorem
KW - Systems Biology/methods
UR - http://www.scopus.com/inward/record.url?scp=85048201102&partnerID=8YFLogxK
U2 - 10.1109/TCBB.2018.2843339
DO - 10.1109/TCBB.2018.2843339
M3 - Article
C2 - 29994223
AN - SCOPUS:85048201102
SN - 1545-5963
VL - 17
SP - 302
EP - 315
JO - IEEE/ACM Transactions on Computational Biology and Bioinformatics
JF - IEEE/ACM Transactions on Computational Biology and Bioinformatics
IS - 1
M1 - 8374844
ER -