ABSTRACT
Of major interest to systems biology is to characterize the way that genes interact with each other in the context of gene regulatory networks (GRNs). In particular, Kalman filtering has been shown to be effective in this regard for GRNs modeled via ordinary differential equations. Performance of the Kalman-filter-based approach is highly dependent on the accuracy level of the noise statistics considered in the inference problem. However, in many cases the exact knowledge of noise statistics is missing. Therefore, robust inference is of great practical importance. In this paper, we propose an inference method based on intrinsically Bayesian robust (IBR) Kalman filtering. The IBR Kalman filter provides optimal performance on average relative to an uncertainty class of possible noise statistics. The IBR Kalman filter can be found in a similar way that an ordinary Kalman filter is found except that the noise covariance matrices are replaced by their "effective" counterparts and the Kalman gain matrix is replaced by the effective Kalman gain matrix. In this paper, we apply IBR Kalman filtering to infer a yeast cell cycle network whose dynamics are modeled via a set of continuous nonlinear ordinary differential equations.
- R. Dehghannasiri, M. S. Esfahani, and E. R. Dougherty. A Bayesian framework for robust Kalman filtering under uncertain noise statistics. In Proceedings of the Asilomar Conf. Signals, Systems and Computers, 2016.Google ScholarCross Ref
- L. Qian, H. Wang, and E. R. Dougherty. Inference of noisy nonlinear differential equation models for gene regulatory networks using genetic programming and Kalman filtering. IEEE Trans. Signal Process., 56(7):3327--3339, 2008. Google ScholarDigital Library
Index Terms
- Inference of Nonlinear ODE-Based Gene Regulatory Networks via Intrinsically Bayesian Robust Kalman Filtering
Recommendations
Inference of Noisy Nonlinear Differential Equation Models for Gene Regulatory Networks Using Genetic Programming and Kalman Filtering
Part IIA key issue in genomic signal processing is the inference of gene regulatory networks. These are used both to understand the role of biological regulation in phenotypic determination and to derive therapeutic strategies for genetic-based diseases. In ...
Inference of Gene Regulatory Network by Bayesian Network Using Metropolis-Hastings Algorithm
ADMA '07: Proceedings of the 3rd international conference on Advanced Data Mining and ApplicationsBayesian networks are widely used to infer genes regulatory network from their transcriptional expression data. Bayesian network of the best score is usually chosen as genes regulatory model. However, without the hint from biological ground truth, and ...
Intrinsically Bayesian Robust Classifier for Single-Cell Gene Expression Time Series in Gene Regulatory Networks
ACM-BCB '17: Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology,and Health InformaticsThis paper studies expression-based classification under the assumption that single-cell measurements are sampled at a sufficient rate to detect regulatory timing. Observations are expression trajectories. In effect, classification is performed on data ...
Comments