CoChat

Trajectory-oriented Bayesian experiment design versus Fisher A-optimal design: an in depth comparison study

Open access
Weber, Patrick, Kramer, Andrei, Dingler, Clemens, Radde, Nicole · 2012 · Bioinformatics

The DOI matches its Crossref record; 25 of the 25 references it cites were found in a registry or an index.

Abstract

Motivation: Experiment design strategies for biomedical models with the purpose of parameter estimation or model discrimination are in the focus of intense research. Experimental limitations such as sparse and noisy data result in unidentifiable parameters and render-related design tasks challenging problems. Often, the temporal resolution of data is a limiting factor and the amount of possible experimental interventions is finite. To address this issue, we propose a Bayesian experiment design algorithm to minimize the prediction uncertainty for a given set of experiments and compare it to traditional A-optimal design. Results: In an in depth numerical study involving an ordinary differential equation model of the trans-Golgi network with 12 partly non-identifiable parameters, we minimized the prediction uncertainty efficiently for predefined scenarios. The introduced method results in twice the prediction precision as the same amount of A-optimal designed experiments while introducing a useful stopping criterion. The simulation intensity of the algorithm's major design step is thereby reasonably affordable. Besides smaller variances in the predicted trajectories compared with Fisher design, we could also achieve smaller parameter posterior distribution entropies, rendering this method superior to A-optimal Fisher design also in the parameter space. Availability: Necessary software/toolbox information are available in the supplementary material. The project script including example data can be downloaded from http://www.ist.uni-stuttgart.de/%7eweber/BayesFisher2012. Contact: patrick.weber@ist.uni-stuttgart.de Supplementary Information: Supplementary data are available at Bioinformatics online.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1093/bioinformatics/bts377

Cites

25 of 25 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1. Predicted trajectories for the experiment outcome after an initial training experiment is performed. Trajectories are depicted together with the trajectories' empirical variance. The first row depicts the model fit for the initial experiment. The measurement time instances suggested by our design algorithm are depicted by vertical lines. The second row evinces the proposed measurements for the second successor experiment. For experimental inputs corresponding to experiment index i, we refer to Supplementary Table S3
Fig. 1. Predicted trajectories for the experiment outcome after an initial training experiment is performed. Trajectories are depicted together with the trajectories' empirical variance. The first row depicts the model fit for the initial experiment. The measurement time instances suggested by our design algorithm are depicted by vertical lines. The second row evinces the proposed measurements for the second successor experiment. For experimental inputs corresponding to experiment index i, we refer to Supplementary Table S3CC BY · PubMed Central
Fig. 2. Model for secretion control at the trans-Golgi network. Grey nodes denote latent variables, black nodes measurable species. Active species are denoted with an asterisk. Self-loops describe linear degradation terms. Dashed boxes depict turnover reactions. The inputs ‘u’ indicate experimentally possible perturbations of synthesis rates. Blue text explains biological processes depicted by corresponding edge. SM and PC are not contained in the model but shown for completeness of the SM synthesis reaction
Fig. 2. Model for secretion control at the trans-Golgi network. Grey nodes denote latent variables, black nodes measurable species. Active species are denoted with an asterisk. Self-loops describe linear degradation terms. Dashed boxes depict turnover reactions. The inputs ‘u’ indicate experimentally possible perturbations of synthesis rates. Blue text explains biological processes depicted by corresponding edge. SM and PC are not contained in the model but shown for completeness of the SM synthesis reactionCC BY · PubMed Central
Fig. 3. Mean expected prediction uncertainty for all 27 experiments after the model has been trained with up to four experiments chosen by the Bayesian or the A-optimal design criterion. We additionally averaged over five different runs
Fig. 3. Mean expected prediction uncertainty for all 27 experiments after the model has been trained with up to four experiments chosen by the Bayesian or the A-optimal design criterion. We additionally averaged over five different runsCC BY · PubMed Central
Fig. 4. Mean posterior distribution entropy estimates after the model has been trained with up to four experiments chosen by the Bayesian or the A-optimal design criterion, respectively. Five runs of the overall experiment design exercise have been performed
Fig. 4. Mean posterior distribution entropy estimates after the model has been trained with up to four experiments chosen by the Bayesian or the A-optimal design criterion, respectively. Five runs of the overall experiment design exercise have been performedCC BY · PubMed Central
Fig. 5. Estimated marginal distributions of three parameters of the posterior sample after the model has been trained with four experiments chosen by the Bayesian or the A-optimal design criterion. Y-axis limits denote the boundaries of the log uniform prior
Fig. 5. Estimated marginal distributions of three parameters of the posterior sample after the model has been trained with four experiments chosen by the Bayesian or the A-optimal design criterion. Y-axis limits denote the boundaries of the log uniform priorCC BY · PubMed Central
Fig. 6. Repeated decision making (n = 100) of the Bayesian (black) and the A-optimal Fisher (grey) experiment design. Big spots indicate more frequently chosen combinations of experiments and sampling times
Fig. 6. Repeated decision making (n = 100) of the Bayesian (black) and the A-optimal Fisher (grey) experiment design. Big spots indicate more frequently chosen combinations of experiments and sampling timesCC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Cited by

See all 14

Metadata

Authors
Weber, P., Kramer, A., Dingler, C., & Radde, N.
Affiliations
University of Stuttgart (DE)
Corresponding author
Weber, Patrick
Venue
Bioinformatics
Published
2012-09-03
Volume
28
Issue
18
Pages
i535-i541
ISSN
  • 1367-4803 (ISSN-L)
  • 1367-4811
OpenAlex
W2146888637
Cited by
14
References
25
Citations by year
2019: 2 · 2018: 4 · 2017: 2 · 2016: 1 · 2015: 2 · 2014: 2 · 2013: 1
FWCI
2.12
Type
journal article
Language
en
Open access
Locations
  • Bioinformatics (publishedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
Funders
  • Deutsche Forschungsgemeinschaft (EXC 3101, EXC 310)
  • Universität Stuttgart (EXC310/1)
Topics
  • Social Sciences › Decision Sciences › Management Science and Operations Research › Optimal Experimental Design Methods
  • Physical Sciences › Engineering › Control and Systems Engineering › Control Systems and Identification
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Gene Regulatory Network Analysis
Keywords
A-optimal design, Fisher information, forecast uncertainty, parameter identifiability, ordinary differential equation model, stopping rules, model discrimination, biomedical model
MeSH terms
Algorithms, Bayes Theorem, Models, Biological, Research Design, trans-Golgi Network, Uncertainty, Secretory Pathway

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.