abc smc for parameter estimation and model selection with
play

ABC SMC for parameter estimation and model selection with - PowerPoint PPT Presentation

May 07, 2023 •30 likes •580 views

Nature Precedings : doi:10.1038/npre.2011.5964.1 : Posted 13 May 2011 ABC SMC for parameter estimation and model selection with applications in systems biology Tina Toni Department of Biological Engineering, Massachusetts Institute of

  1. Nature Precedings : doi:10.1038/npre.2011.5964.1 : Posted 13 May 2011 ABC SMC for parameter estimation and model selection with applications in systems biology Tina Toni Department of Biological Engineering, Massachusetts Institute of Technology, USA & Theoretical Systems Biology Group, Imperial College London, UK ABC in London, 05/05/2011 Tina Toni ABC in systems biology 05/05/2011 1 / 25

  2. Nature Precedings : doi:10.1038/npre.2011.5964.1 : Posted 13 May 2011 Motivation Complex biological systems Models often ODE or stochastic master equations High dimensional parameter space Time course, non-equidistant, missing data Interested in Characterization of distributions over parameters rather than point estimates. What dynamic behaviour can reproduce data? Which models represent suitable hypothesis about the system? Tina Toni ABC in systems biology 05/05/2011 2 / 25

  3. Nature Precedings : doi:10.1038/npre.2011.5964.1 : Posted 13 May 2011 Outline Parameter estimation 1 ABC basics ABC SMC Application: Modeling bacterial stress response Model selection 2 ABC SMC for model selection Application: Epo signaling pathway Application: Phosphorylation dynamics Tina Toni ABC in systems biology 05/05/2011 3 / 25

  4. Nature Precedings : doi:10.1038/npre.2011.5964.1 : Posted 13 May 2011 Parameter estimation ABC basics Approximate Bayesian Computation basics 1 Sample θ c from P ( θ ). 2 Simulate a data set D c from the model with θ c . 3 If dist ( D , D c ) ≤ ǫ , accept θ c , otherwise reject. 4 Return to 1 . x x x x time Prior Posterior P ( θ ) P ( θ | D )

  5. Nature Precedings : doi:10.1038/npre.2011.5964.1 : Posted 13 May 2011 Parameter estimation ABC basics Approximate Bayesian Computation basics 1 Sample θ c from P ( θ ). 2 Simulate a data set D c from the model with θ c . 3 If dist ( D , D c ) ≤ ǫ , accept θ c , otherwise reject. 4 Return to 1 . x x x x time Prior Posterior P ( θ ) P ( θ | D )

  6. Nature Precedings : doi:10.1038/npre.2011.5964.1 : Posted 13 May 2011 Parameter estimation ABC basics Approximate Bayesian Computation basics 1 Sample θ c from P ( θ ). 2 Simulate a data set D c from the model with θ c . 3 If dist ( D , D c ) ≤ ǫ , accept θ c , otherwise reject. 4 Return to 1 . x x x x time Prior Posterior P ( θ ) P ( θ | D )

  7. Nature Precedings : doi:10.1038/npre.2011.5964.1 : Posted 13 May 2011 Parameter estimation ABC basics Approximate Bayesian Computation basics 1 Sample θ c from P ( θ ). 2 Simulate a data set D c from the model with θ c . 3 If dist ( D , D c ) ≤ ǫ , accept θ c , otherwise reject. 4 Return to 1 . x x x x time Prior Posterior P ( θ ) P ( θ | D )

  8. Nature Precedings : doi:10.1038/npre.2011.5964.1 : Posted 13 May 2011 Parameter estimation ABC basics Approximate Bayesian Computation basics 1 Sample θ c from P ( θ ). 2 Simulate a data set D c from the model with θ c . 3 If dist ( D , D c ) ≤ ǫ , accept θ c , otherwise reject. 4 Return to 1 . x x x x time Prior Posterior P ( θ ) P ( θ | D )

  9. Nature Precedings : doi:10.1038/npre.2011.5964.1 : Posted 13 May 2011 Parameter estimation ABC basics Approximate Bayesian Computation basics 1 Sample θ c from P ( θ ). 2 Simulate a data set D c from the model with θ c . 3 If dist ( D , D c ) ≤ ǫ , accept θ c , otherwise reject. 4 Return to 1 . x x x x time Prior Posterior P ( θ ) P ( θ | D ) Tina Toni ABC in systems biology 05/05/2011 4 / 25

  10. Nature Precedings : doi:10.1038/npre.2011.5964.1 : Posted 13 May 2011 Parameter estimation ABC basics Approximate Bayesian Computation basics 1 Sample θ c from P ( θ ). 2 Simulate a data set D c from the model with θ c . 3 If dist ( D , D c ) ≤ ǫ , accept θ c , otherwise reject. 4 Return to 1 . x x x x time Prior Posterior P ( θ ) P ( θ | D ) Tina Toni ABC in systems biology 05/05/2011 4 / 25

  11. Nature Precedings : doi:10.1038/npre.2011.5964.1 : Posted 13 May 2011 Parameter estimation ABC basics Approximate Bayesian Computation basics 1 Sample θ c from P ( θ ). 2 Simulate a data set D c from the model with θ c . 3 If dist ( D , D c ) ≤ ǫ , accept θ c , otherwise reject. 4 Return to 1 . x x x x time Prior Posterior P ( θ ) P ( θ | D )

  12. Nature Precedings : doi:10.1038/npre.2011.5964.1 : Posted 13 May 2011 Parameter estimation ABC basics Approximate Bayesian Computation basics 1 Sample θ c from P ( θ ). 2 Simulate a data set D c from the model with θ c . 3 If dist ( D , D c ) ≤ ǫ , accept θ c , otherwise reject. 4 Return to 1 . x x x x time Prior Posterior P ( θ ) P ( θ | D )

  13. Nature Precedings : doi:10.1038/npre.2011.5964.1 : Posted 13 May 2011 Parameter estimation ABC basics Approximate Bayesian Computation basics 1 Sample θ c from P ( θ ). 2 Simulate a data set D c from the model with θ c . 3 If dist ( D , D c ) ≤ ǫ , accept θ c , otherwise reject. 4 Return to 1 . x x x x time P ( θ | dist ( D , D c ) ≤ ǫ ) Prior Posterior P ( θ ) P ( θ | D )

  14. Nature Precedings : doi:10.1038/npre.2011.5964.1 : Posted 13 May 2011 Parameter estimation ABC basics Approximate Bayesian Computation basics 1 Sample θ c from P ( θ ). 2 Simulate a data set D c from the model with θ c . 3 If dist ( D , D c ) ≤ ǫ , accept θ c , otherwise reject. 4 Return to 1 . x x x x time P ( θ | dist ( D , D c ) ≤ ǫ ) Prior Posterior P ( θ ) P ( θ | D )

  15. Nature Precedings : doi:10.1038/npre.2011.5964.1 : Posted 13 May 2011 Parameter estimation ABC SMC ABC SMC (Sequential Monte Carlo) Prior Posterior (Sisson et al., 2007, PNAS) Tina Toni ABC in systems biology 05/05/2011 5 / 25

  16. Nature Precedings : doi:10.1038/npre.2011.5964.1 : Posted 13 May 2011 Parameter estimation ABC SMC ABC SMC (Sequential Monte Carlo) Prior Intermediate Distributions Posterior (Sisson et al., 2007, PNAS) Tina Toni ABC in systems biology 05/05/2011 5 / 25

  17. Nature Precedings : doi:10.1038/npre.2011.5964.1 : Posted 13 May 2011 Parameter estimation ABC SMC ABC SMC (Sequential Monte Carlo) . . . ǫ 1 ǫ 2 ǫ T Prior Intermediate Distributions Posterior (Sisson et al., 2007, PNAS) Tina Toni ABC in systems biology 05/05/2011 5 / 25

  18. Nature Precedings : doi:10.1038/npre.2011.5964.1 : Posted 13 May 2011 Parameter estimation ABC SMC ABC SMC (Sequential Monte Carlo) . . . ǫ 1 ǫ 2 ǫ T Prior Intermediate Distributions Posterior (Sisson et al., 2007, PNAS) Tina Toni ABC in systems biology 05/05/2011 5 / 25

  19. Nature Precedings : doi:10.1038/npre.2011.5964.1 : Posted 13 May 2011 Parameter estimation ABC SMC ABC SMC (Sequential Monte Carlo) Population 1 . . . ǫ 1 ǫ 2 ǫ T Prior Intermediate Distributions Posterior (Sisson et al., 2007, PNAS) Tina Toni ABC in systems biology 05/05/2011 5 / 25

  20. Nature Precedings : doi:10.1038/npre.2011.5964.1 : Posted 13 May 2011 Parameter estimation ABC SMC ABC SMC (Sequential Monte Carlo) Population 1 . . . ǫ 1 ǫ 2 ǫ T Prior Intermediate Distributions Posterior (Sisson et al., 2007, PNAS) Tina Toni ABC in systems biology 05/05/2011 5 / 25

  21. Nature Precedings : doi:10.1038/npre.2011.5964.1 : Posted 13 May 2011 Parameter estimation ABC SMC ABC SMC (Sequential Monte Carlo) Population 1 . . . ǫ 1 ǫ 2 ǫ T Prior Intermediate Distributions Posterior (Sisson et al., 2007, PNAS) Tina Toni ABC in systems biology 05/05/2011 5 / 25

  22. Nature Precedings : doi:10.1038/npre.2011.5964.1 : Posted 13 May 2011 Parameter estimation ABC SMC ABC SMC (Sequential Monte Carlo) Population 1 Population 2 . . . ǫ 1 ǫ 2 ǫ T Prior Intermediate Distributions Posterior (Sisson et al., 2007, PNAS) Tina Toni ABC in systems biology 05/05/2011 5 / 25

  23. Nature Precedings : doi:10.1038/npre.2011.5964.1 : Posted 13 May 2011 Parameter estimation ABC SMC ABC SMC (Sequential Monte Carlo) Population 1 Population 2 Population T . . . ǫ 1 ǫ 2 ǫ T Prior Intermediate Distributions Posterior (Sisson et al., 2007, PNAS) Tina Toni ABC in systems biology 05/05/2011 5 / 25

  24. Nature Precedings : doi:10.1038/npre.2011.5964.1 : Posted 13 May 2011 Parameter estimation ABC SMC ABC SMC (Sequential Monte Carlo) Population 1 Population 2 Population T . . . ǫ 1 ǫ 2 ǫ T Prior Intermediate Distributions Posterior (Sisson et al., 2007, PNAS) Tina Toni ABC in systems biology 05/05/2011 5 / 25

  25. Nature Precedings : doi:10.1038/npre.2011.5964.1 : Posted 13 May 2011 Parameter estimation ABC SMC Weights π t ( θ t ) w t ( θ t ) = η t ( θ t ) � η t ( θ t ) = 1 ( π ( θ t ) > 0) 1 ( dist < ǫ t ) π t − 1 ( θ t − 1 ) K t ( θ t | θ t − 1 ) d θ t − 1 π ( θ ( i ) t ) w ( i ) = t � N j =1 w ( j ) t − 1 K t ( θ ( i ) t | θ ( j ) t − 1 ) (Toni et al. , J. R. Soc. Interface, 2009) Tina Toni ABC in systems biology 05/05/2011 6 / 25

  26. Nature Precedings : doi:10.1038/npre.2011.5964.1 : Posted 13 May 2011 Parameter estimation Application: Modeling bacterial stress response Application: Modeling phage shock protein response in Escherichia coli Signal Phage damages the membrane of bacteria (we call this stress). Response Reduced motility Anaerobic respiration Start membrane repair mechanisms etc. Tina Toni ABC in systems biology 05/05/2011 7 / 25

Recommend

Model selection and parameter estimation with covariates in logistic regression missing

Model selection and parameter estimation with covariates in logistic regression missing

Model selection and parameter estimation with missing Model selection and parameter estimation with covariates in logistic regression missing covariates in logistic regression models models Fabrizio Workshop on Model Selection 2008

450 views • 24 slides
1 Estimation from outbreaks when R 0 &lt; 1 Estimating R 0 : from epidemic data If case data are

1 Estimation from outbreaks when R 0 &lt; 1 Estimating R 0 : from epidemic data If case data are

Outline Parameter estimation, uncertainty, Estimating R 0 model fitting, model selection, Parameter estimation - Likelihood approaches and sensitivity and uncertainty analysis - Bayesian approaches Fitting more complex models Jamie

240 views • 12 slides
Gravitational Wave Data Analysis: II. Model Selection and Parameter Estimation Chris Van Den

Gravitational Wave Data Analysis: II. Model Selection and Parameter Estimation Chris Van Den

Gravitational Wave Data Analysis: II. Model Selection and Parameter Estimation Chris Van Den Broeck Kavli RISE Summer School on Gravitational Waves, Cambridge, UK, 23-27 September 2019 Bayesian inference Aim: use available data to

707 views • 47 slides
Parameter Estimation and Model Selection of Gravitational-Wave Signals Contaminated by Transient

Parameter Estimation and Model Selection of Gravitational-Wave Signals Contaminated by Transient

Parameter Estimation and Model Selection of Gravitational-Wave Signals Contaminated by Transient Detector Noise Glitches Jade Powell OzGrav, Swinburne University of Technology 2. Gravitational Wave Detectors 3. Detector Locations 4.

508 views • 31 slides
I 4 - Bayesian parameter estimation in a normal model STAT 587 (Engineering) Iowa State

I 4 - Bayesian parameter estimation in a normal model STAT 587 (Engineering) Iowa State

I 4 - Bayesian parameter estimation in a normal model STAT 587 (Engineering) Iowa State University September 18, 2020 Bayesian parameter estimation Bayesian parameter estimation Recall that Bayesian parameter estimation involves p ( | y ) =

439 views • 20 slides
Bioinformatics: Network Analysis Model Fitting COMP 572 (BIOS 572 / BIOE 564) - Fall 2013 Luay

Bioinformatics: Network Analysis Model Fitting COMP 572 (BIOS 572 / BIOE 564) - Fall 2013 Luay

Bioinformatics: Network Analysis Model Fitting COMP 572 (BIOS 572 / BIOE 564) - Fall 2013 Luay Nakhleh, Rice University 1 Outline Parameter estimation Model selection 2 Parameter Estimation 3 Generally speaking, parameter

839 views • 55 slides
A Maximum A-Posteriori Based Algorithm for Dynamic Load Model Parameter Estimation Siming Guo and

A Maximum A-Posteriori Based Algorithm for Dynamic Load Model Parameter Estimation Siming Guo and

A Maximum A-Posteriori Based Algorithm for Dynamic Load Model Parameter Estimation Siming Guo and Prof. Thomas Overbye sguo6@illinois.edu September 21, 2015 Measurement based parameter estimation 1.05 1 Voltage [pu] 0.95 0.9 0.85 0 0.2

511 views • 11 slides
Tuning parameter selection for voxel-wise brain connectivity estimation via low dimensional

Tuning parameter selection for voxel-wise brain connectivity estimation via low dimensional

Introduction Covariance matrix Precision matrix Theoretical Results A feasible approach Tuning parameter selection for voxel-wise brain connectivity estimation via low dimensional submatrices Bin Nan Department of Biostatistics University

641 views • 27 slides
Maximum likelihood parameter estimation Maximum likelihood parameter estimation For an HMM

Maximum likelihood parameter estimation Maximum likelihood parameter estimation For an HMM

Maximum likelihood parameter estimation Maximum likelihood parameter estimation For an HMM with observed state data X , and s states, For some observed data O = o 1 o n , and a model, we do the same: here a bigram model,

270 views • 3 slides
Metti 5 Optimization for nonlinear parameter estimation and function estimation Lecture 7

Metti 5 Optimization for nonlinear parameter estimation and function estimation Lecture 7

Metti 5 Optimization for nonlinear parameter estimation and function estimation Lecture 7 Roscoff, June 13-18, 2011 Objectives Direct problem input BC Model State solution IC Parameters

869 views • 69 slides
Estimation of the long Memory parameter using an Infinite Source Poisson model applied to

Estimation of the long Memory parameter using an Infinite Source Poisson model applied to

A short introduction to Long memory The model Estimation Bibliography Estimation of the long Memory parameter using an Infinite Source Poisson model applied to transmission rate measurements Fran cois Roueff Ecole Nat. Sup. des T el

803 views • 45 slides
Shrinkage estimation of the three-parameter logistic model Michela Battauz (joint with Ruggero

Shrinkage estimation of the three-parameter logistic model Michela Battauz (joint with Ruggero

Shrinkage estimation of the three-parameter logistic model Michela Battauz (joint with Ruggero Bellio) Department of Economics and Statistics University of Udine (Italy) Psychoco 2020 Michela Battauz Shrinkage estimation of the 3PL model

782 views • 20 slides
Adaptive estimation in functional linear model: a model selection approach Angelina Roche joint

Adaptive estimation in functional linear model: a model selection approach Angelina Roche joint

Estimation Functional linear model Adaptive estimation in functional linear model: a model selection approach Angelina Roche joint work with lodie Brunel and Andr Mas I3M-Universit Montpellier II 7 mes Journes de Statistique

540 views • 43 slides
Parameter Estimation and Structural Model Updating Using Modal Methods in the Presence of

Parameter Estimation and Structural Model Updating Using Modal Methods in the Presence of

SICON Final Conference Rome, September 21-25, 2009, SICON FC Parameter Estimation and Structural Model Updating Using Modal Methods in the Presence of Nonlinearity Jean-Claude Golinval University of Liege, Belgium Department of Aerospace and

1.01k views • 73 slides
10601 Machine Learning Model and feature selection Model selection issues We have seen some

10601 Machine Learning Model and feature selection Model selection issues We have seen some

10601 Machine Learning Model and feature selection Model selection issues We have seen some of this before Selecting features (or basis functions) Logistic regression SVMs Selecting parameter value Prior strength

611 views • 31 slides
A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection (Kohavi,

A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection (Kohavi,

Introduction Methods for Accuracy Estimation Methodology Results and Discussion Summary A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection (Kohavi, 1995) Panagiotis Adamopoulos Department of Information,

419 views • 16 slides
Fractional model parameter estimation in the frequency domain using set membership methods Firas

Fractional model parameter estimation in the frequency domain using set membership methods Firas

Fractional model parameter estimation in the frequency domain using set membership methods Firas KHEMANE, Rachid MALTI, Xavier MOREAU SWIM June 15th 2011 1 / 43 Objectives Fractional system modeling using uncertain frequency responses

715 views • 43 slides
Parameter Estimation in Coupled Models : Opportunities and Challenges A talk on

Parameter Estimation in Coupled Models : Opportunities and Challenges A talk on

Parameter Estimation in Coupled Models : Opportunities and Challenges A talk on Model Development and Analysis MAPP webinar conference, 11 Dec., Washington DC, USA Shaoqing Zhang GFDL/NOAA Co-Work

313 views • 14 slides
Outline Introduction Knowledge Structures Parameter Estimation Maximum Likelihood Estimation

Outline Introduction Knowledge Structures Parameter Estimation Maximum Likelihood Estimation

Faculty of Science Introduction Knowledge Structures Parameter Estimation Implementation in R Concluding Remarks Department of Psychology Outline Introduction Knowledge Structures Parameter Estimation Maximum Likelihood Estimation

647 views • 9 slides
Parameter Estimation Saravanan Vijayakumaran sarva@ee.iitb.ac.in Department of Electrical

Parameter Estimation Saravanan Vijayakumaran sarva@ee.iitb.ac.in Department of Electrical

Parameter Estimation Saravanan Vijayakumaran sarva@ee.iitb.ac.in Department of Electrical Engineering Indian Institute of Technology Bombay October 25, 2012 1 / 44 Motivation System Model used to Derive Optimal Receivers s ( t ) y ( t )

786 views • 44 slides
Parameter Estimation Saravanan Vijayakumaran sarva@ee.iitb.ac.in Department of Electrical

Parameter Estimation Saravanan Vijayakumaran sarva@ee.iitb.ac.in Department of Electrical

Parameter Estimation Saravanan Vijayakumaran sarva@ee.iitb.ac.in Department of Electrical Engineering Indian Institute of Technology Bombay October 21, 2013 1 / 24 Motivation System Model used to Derive Optimal Receivers s ( t ) y ( t )

289 views • 24 slides
Parameter estimation (cont.) Dr. Jarad Niemi STAT 544 - Iowa State University January 24, 2019

Parameter estimation (cont.) Dr. Jarad Niemi STAT 544 - Iowa State University January 24, 2019

Parameter estimation (cont.) Dr. Jarad Niemi STAT 544 - Iowa State University January 24, 2019 Jarad Niemi (STAT544@ISU) Parameter estimation (cont.) January 24, 2019 1 / 32 Outline Normal model, unknown mean Jeffreys prior Natural

756 views • 32 slides
Maximum-likelihood and Bayesian parameter estimation Andrea Passerini passerini@disi.unitn.it

Maximum-likelihood and Bayesian parameter estimation Andrea Passerini passerini@disi.unitn.it

Maximum-likelihood and Bayesian parameter estimation Andrea Passerini passerini@disi.unitn.it Machine Learning Maximum-likelihood and Bayesian parameter estimation Parameter estimation Setting Data are sampled from a probability distribution

856 views • 52 slides
Model selection and estimation for latent variable models Presented by Emi Tanaka School of

Model selection and estimation for latent variable models Presented by Emi Tanaka School of

Model selection and estimation for latent variable models Presented by Emi Tanaka School of Mathematics and Statisitcs dr.emi.tanaka@gmail.com @statsgen Download pdf of these slides June 26th 2019 @ EcoSta2019 1 / 18 here. Motivation Many

894 views • 18 slides

More recommend