Adaptive Metropolis-coupled MCMC for BEAST 2
With ever more complex models used to study evolutionary patterns, approaches that facilitate efficient inference under such models are needed. Metropolis-coupled Markov chain Monte Carlo (MCMC) has long been used to speed up phylogenetic analyses and to make use of multi-core CPUs. Metropolis-coupl...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2020-09-01
|
| Series: | PeerJ |
| Subjects: | |
| Online Access: | https://peerj.com/articles/9473.pdf |
| _version_ | 1827608901490573312 |
|---|---|
| author | Nicola F. Müller Remco R. Bouckaert |
| author_facet | Nicola F. Müller Remco R. Bouckaert |
| author_sort | Nicola F. Müller |
| collection | DOAJ |
| description | With ever more complex models used to study evolutionary patterns, approaches that facilitate efficient inference under such models are needed. Metropolis-coupled Markov chain Monte Carlo (MCMC) has long been used to speed up phylogenetic analyses and to make use of multi-core CPUs. Metropolis-coupled MCMC essentially runs multiple MCMC chains in parallel. All chains are heated except for one cold chain that explores the posterior probability space like a regular MCMC chain. This heating allows chains to make bigger jumps in phylogenetic state space. The heated chains can then be used to propose new states for other chains, including the cold chain. One of the practical challenges using this approach, is to find optimal temperatures of the heated chains to efficiently explore state spaces. We here provide an adaptive Metropolis-coupled MCMC scheme to Bayesian phylogenetics, where the temperature difference between heated chains is automatically tuned to achieve a target acceptance probability of states being exchanged between individual chains. We first show the validity of this approach by comparing inferences of adaptive Metropolis-coupled MCMC to MCMC on several datasets. We then explore where Metropolis-coupled MCMC provides benefits over MCMC. We implemented this adaptive Metropolis-coupled MCMC approach as an open source package licenced under GPL 3.0 to the Bayesian phylogenetics software BEAST 2, available from https://github.com/nicfel/CoupledMCMC. |
| first_indexed | 2024-03-09T07:22:17Z |
| format | Article |
| id | doaj.art-cf0a43ba00c34d9dbe7dcd8836c827a3 |
| institution | Directory Open Access Journal |
| issn | 2167-8359 |
| language | English |
| last_indexed | 2024-03-09T07:22:17Z |
| publishDate | 2020-09-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ |
| spelling | doaj.art-cf0a43ba00c34d9dbe7dcd8836c827a32023-12-03T07:15:35ZengPeerJ Inc.PeerJ2167-83592020-09-018e947310.7717/peerj.9473Adaptive Metropolis-coupled MCMC for BEAST 2Nicola F. Müller0Remco R. Bouckaert1Department of Biosystems Science and Engineering, ETH Zürich, Basel, SwitzerlandSchool of Computer Science, University of Auckland, Auckland, New ZealandWith ever more complex models used to study evolutionary patterns, approaches that facilitate efficient inference under such models are needed. Metropolis-coupled Markov chain Monte Carlo (MCMC) has long been used to speed up phylogenetic analyses and to make use of multi-core CPUs. Metropolis-coupled MCMC essentially runs multiple MCMC chains in parallel. All chains are heated except for one cold chain that explores the posterior probability space like a regular MCMC chain. This heating allows chains to make bigger jumps in phylogenetic state space. The heated chains can then be used to propose new states for other chains, including the cold chain. One of the practical challenges using this approach, is to find optimal temperatures of the heated chains to efficiently explore state spaces. We here provide an adaptive Metropolis-coupled MCMC scheme to Bayesian phylogenetics, where the temperature difference between heated chains is automatically tuned to achieve a target acceptance probability of states being exchanged between individual chains. We first show the validity of this approach by comparing inferences of adaptive Metropolis-coupled MCMC to MCMC on several datasets. We then explore where Metropolis-coupled MCMC provides benefits over MCMC. We implemented this adaptive Metropolis-coupled MCMC approach as an open source package licenced under GPL 3.0 to the Bayesian phylogenetics software BEAST 2, available from https://github.com/nicfel/CoupledMCMC.https://peerj.com/articles/9473.pdfBayesianPhylogeneticsPhylodynamicsCoalescentParallel tempering |
| spellingShingle | Nicola F. Müller Remco R. Bouckaert Adaptive Metropolis-coupled MCMC for BEAST 2 PeerJ Bayesian Phylogenetics Phylodynamics Coalescent Parallel tempering |
| title | Adaptive Metropolis-coupled MCMC for BEAST 2 |
| title_full | Adaptive Metropolis-coupled MCMC for BEAST 2 |
| title_fullStr | Adaptive Metropolis-coupled MCMC for BEAST 2 |
| title_full_unstemmed | Adaptive Metropolis-coupled MCMC for BEAST 2 |
| title_short | Adaptive Metropolis-coupled MCMC for BEAST 2 |
| title_sort | adaptive metropolis coupled mcmc for beast 2 |
| topic | Bayesian Phylogenetics Phylodynamics Coalescent Parallel tempering |
| url | https://peerj.com/articles/9473.pdf |
| work_keys_str_mv | AT nicolafmuller adaptivemetropoliscoupledmcmcforbeast2 AT remcorbouckaert adaptivemetropoliscoupledmcmcforbeast2 |