Maximum profile likelihood estimation of differential equation parameters through model based smoothing state estimates.

Statistical inference for biochemical models often faces a variety of characteristic challenges. In this paper we examine state and parameter estimation for the JAK-STAT intracellular signalling mechanism, which exemplifies the implementation intricacies common in many biochemical inference problems. We introduce an extension to the Generalized Smoothing approach for estimating delay differential equation models, addressing selection of complexity parameters, choice of the basis system, and appropriate optimization strategies. Motivated by the JAK-STAT system, we further extend the generalized smoothing approach to consider a nonlinear observation process with additional unknown parameters, and highlight how the approach handles unobserved states and unevenly spaced observations. The methodology developed is generally applicable to problems of estimation for differential equation models with delays, unobserved states, nonlinear observation processes, and partially observed histories.

[1]  A. Gelman,et al.  Physiological Pharmacokinetic Analysis Using Population Modeling and Informative Prior Distributions , 1996 .

[2]  Julio R. Banga,et al.  Solving nonconvex climate control problems: pitfalls and algorithm performances , 2004, Appl. Soft Comput..

[3]  Jiguo Cao,et al.  Parameter estimation for differential equations: a generalized smoothing approach , 2007 .

[4]  Giles Hooker,et al.  Parameterizing state–space models for infectious disease dynamics by generalized profiling: measles in Ontario , 2011, Journal of The Royal Society Interface.

[5]  B. Silverman,et al.  Functional Data Analysis , 1997 .

[6]  R. Kass.  Nonlinear Regression Analysis and its Applications , 1990 .

[7]  Neil D. Lawrence,et al.  Accelerating Bayesian Inference over Nonlinear Differential Equations with Gaussian Processes , 2008, NIPS.

[8]  Christodoulos A. Floudas,et al.  Deterministic Global Optimization in Nonlinear Optimal Control Problems , 2000, J. Glob. Optim..

[9]  M. Mackey,et al.  Modelling transcriptional feedback loops: the role of Gro/TLE1 in Hes1 oscillations , 2006, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[10]  I. Dusanter-Fourt,et al.  The structure, regulation and function of the Janus kinases (JAKs) and the signal transducers and activators of transcription (STATs). , 1997, European journal of biochemistry.

[11]  J. Varah.  A Spline Least Squares Method for Numerical Parameter Estimation in Differential Equations , 1982 .

[12]  M. S. Varziri,et al.  Parameter Estimation in Continuous-Time Dynamic Models in the Presence of Unmeasured States and Nonstationary Disturbances , 2008 .

[13]  J. Timmer,et al.  Identification of nucleocytoplasmic cycling as a remote sensor in cellular signaling by databased modeling , 2003, Proceedings of the National Academy of Sciences of the United States of America.

[14]  Jens Timmer,et al.  Comprehensive estimation of input signals and dynamics in biochemical reaction networks , 2012, Bioinform..

[15]  G. Hooker,et al.  Parameter estimation in differential equation models with constrained states , 2012 .

[16]  Ursula Klingmüller,et al.  Structural and practical identifiability analysis of partially observed dynamical models by exploiting the profile likelihood , 2009, Bioinform..

[17]  M. Chial,et al.  in simple , 2003 .

[18]  Jonas S. Almeida,et al.  Decoupling dynamical systems for pathway identification from metabolic profiles , 2004, Bioinform..

[19]  P. James McLellan,et al.  Approximate Maximum Likelihood Parameter Estimation for Nonlinear Dynamic Models: Application to a Laboratory-Scale Nylon Reactor Model , 2008 .

[20]  S. Busenberg,et al.  Mathematical models of the early embryonic cell cycle: the role of MPF activation and cyclin degradation , 1994, Journal of mathematical biology.

[21]  B. Welch.  The structure , 1992 .

[22]  Fathalla A. Rihan,et al.  Numerical modelling in biosciences using delay differential equations , 2000 .

[23]  L Wang,et al.  Robust Estimation for Ordinary Differential Equation Models , 2011, Biometrics.

[24]  W. Newey,et al.  A Simple, Positive Semi-Definite, Heteroskedasticity and Autocorrelationconsistent Covariance Matrix , 1986 .

[25]  Hongyu Zhao,et al.  Asymptotic efficiency and finite-sample properties of the generalized profiling estimation of parameters in ordinary differential equations , 2009, 0903.3400.

[26]  P. James McLellan,et al.  Parameter estimation in continuous-time dynamic models using principal differential analysis , 2006, Comput. Chem. Eng..

[27]  J. Marron,et al.  SCALE SPACE VIEW OF CURVE ESTIMATION , 2000 .

[28]  Xiaohua Xia,et al.  On Identifiability of Nonlinear ODE Models and Applications in Viral Dynamics , 2011, SIAM Rev..

[29]  Hulin Wu,et al.  Parameter Estimation for Differential Equation Models Using a Framework of Measurement Error in Regression Models , 2008, Journal of the American Statistical Association.

[30]  N. Brunel.  Parameter estimation of ODE’s via nonparametric estimators , 2007, 0710.4190.

[31]  H. Voss,et al.  Parameter estimation in nonlinear delayed feedback systems from noisy data , 2002 .

[32]  David Campbell,et al.  Smooth functional tempering for nonlinear differential equation models , 2012, Stat. Comput..

[33]  Liangliang Wang,et al.  Estimating Parameters in Delay Differential Equation Models , 2012 .

[34]  Julian Lewis.  Autoinhibition with Transcriptional Delay A Simple Mechanism for the Zebrafish Somitogenesis Oscillator , 2003, Current Biology.