Improving nonhomogeneous dynamic Bayesian networks with sequentially coupled parameters (original) (raw)
Related papers
A new Bayesian piecewise linear regression model for dynamic network reconstruction
BMC Bioinformatics, 2021
Background Linear regression models are important tools for learning regulatory networks from gene expression time series. A conventional assumption for non-homogeneous regulatory processes on a short time scale is that the network structure stays constant across time, while the network parameters are time-dependent. The objective is then to learn the network structure along with changepoints that divide the time series into time segments. An uncoupled model learns the parameters separately for each segment, while a coupled model enforces the parameters of any segment to stay similar to those of the previous segment. In this paper, we propose a new consensus model that infers for each individual time segment whether it is coupled to (or uncoupled from) the previous segment. Results The results show that the new consensus model is superior to the uncoupled and the coupled model, as well as superior to a recently proposed generalized coupled model. Conclusions The newly proposed model...
Statistical Applications in Genetics and Molecular Biology, 2012
An important and challenging problem in systems biology is the inference of gene regulatory networks from short non-stationary time series of transcriptional profiles. A popular approach that has been widely applied to this end is based on dynamic Bayesian networks (DBNs), although traditional homogeneous DBNs fail to model the non-stationarity and time-varying nature of the gene regulatory processes. Various authors have therefore recently proposed combining DBNs with multiple changepoint processes to obtain time varying dynamic Bayesian networks (TV-DBNs). However, TV-DBNs are not without problems. Gene expression time series are typically short, which leaves the model over-flexible, leading to over-fitting or inflated inference uncertainty. In the present paper, we introduce a Bayesian regularization scheme that addresses this difficulty. Our approach is based on the rationale that changes in gene regulatory processes appear gradually during an organism's life cycle or in response to a changing environment, and we have integrated this notion in the prior distribution of the TV-DBN parameters. We have extensively tested our regularized TV-DBN model on synthetic data, in which we have simulated short non-homogeneous time series produced from a system subject to gradual change. We have then applied our method to real-world gene expression time series, measured during the life cycle of Drosophila melanogaster, under artificially generated constant light condition in Arabidopsis thaliana, and from a synthetically designed strain of Saccharomyces cerevisiae exposed to a changing environment.
Non-homogeneous dynamic Bayesian networks with edge-wise sequentially coupled parameters
Bioinformatics, 2019
Motivation: Non-homogeneous dynamic Bayesian networks (NH-DBNs) are a popular tool for learning networks with time-varying interaction parameters. A multiple changepoint process is used to divide the data into disjoint segments and the network interaction parameters are assumed to be segment-specific. The objective is to infer the network structure along with the segmentation and the segment-specific parameters from the data. The conventional (uncoupled) NH-DBNs do not allow for information exchange among segments, and the interaction parameters have to be learned separately for each segment. More advanced coupled NH-DBN models allow the interaction parameters to vary but enforce them to stay similar over time. As the enforced similarity of the network parameters can have counter-productive effects, we propose a new consensus NH-DBN model that combines features of the uncoupled and the coupled NH-DBN. The new model infers for each individual edge whether its interaction parameter stays similar over time (and should be coupled) or if it changes from segment to segment (and should stay uncoupled). Results: Our new model yields higher network reconstruction accuracies than state-of-the-art models for synthetic and yeast network data. For gene expression data from A.thaliana our new model infers a plausible network topology and yields hypotheses about the light-dependencies of the gene interactions.
Lecture Notes in Computer Science, 2014
Dynamic aspects of regulatory networks are typically investigated by measuring relevant variables at multiple points in time. Current state-of-the-art approaches for gene network reconstruction directly build on such data, making the strong assumption that the system evolves in a synchronous fashion and in discrete time. However, omics data generated with increasing time-course granularity allow to model gene networks as systems whose state evolves in continuous time, thus improving the model's expressiveness. In this work continuous time Bayesian networks are proposed as a new approach for regulatory network reconstruction from time-course expression data. Their performance is compared to that of two state-of-the-art methods: dynamic Bayesian networks and Granger causality. The comparison is accomplished using both simulated and experimental data. Continuous time Bayesian networks achieve the highest F-measure on both datasets. Furthermore, precision, recall and F-measure degrade in a smoother way than those of dynamic Bayesian networks and Granger causality, when the complexity of the gene regulatory network increases.
Lecture Notes in Computer Science, 2009
Feedback loops and recurrent structures are essential to the regulation and stable control of complex biological systems. The application of dynamic as opposed to static Bayesian networks is promising in that, in principle, these feedback loops can be learned. However, we show that the widely applied BGe score is susceptible to learning spurious feedback loops, which are a consequence of non-linear regulation and autocorrelation in the data. We propose a non-linear generalisation of the BGe model, based on a mixture model, and demonstrate that this approach successfully represses spurious feedback loops.
Modelling Gene Networks by a Dynamic Bayesian Network-based Model with Time Lag Estimation
The First International Workshop on Data Analytics for Targeted Healthcare (DANTH 13), Gold Coast, Australia, 2013
Due to the needs to discover the immense information and understand the underlying mechanism of gene regulations, modelling gene regulatory networks (GRNs) from gene expression data has attracted the interests of numerous researchers. To this end, the dynamic Bayesian network (DBN) has emerged as a popular method in GRNs modelling as it is able to model time-series gene expression data and feedback loops. Nevertheless, the commonly found missing values in gene expression data, the inability to take account of the transcriptional time lag, and the redundant computation time caused by the large search space, frequently inhibits the effectiveness of DBN in modelling GRNs from gene expression data. This paper proposes a DBNbased model (IST-DBN) with missing values imputation, potential regulators selection, and time lag estimation to tackle the aforementioned problems. To evaluate the performance of IST-DBN, we applied the model on the S. cerevisiae cell cycle time-series expression data. The experimental results revealed IST-DBN has decreased computation time and better accuracy in identifying gene-gene relationships when compared with existing DBN-based model and conventional DBN. Furthermore, we expect the resultant networks from IST-DBN to be applied as a general framework for potential gene intervention research.
Bioinformatics, 2018
Motivation: Non-homogeneous dynamic Bayesian networks (NH-DBNs) are a popular modelling tool for learning cellular networks from time series data. In systems biology, time series are often measured under different experimental conditions, and not rarely only some network interaction parameters depend on the condition while the other parameters stay constant across conditions. For this situation, we propose a new partially NH-DBN, based on Bayesian hierarchical regression models with partitioned design matrices. With regard to our main application to semi-quantitative (immunoblot) timecourse data from mammalian target of rapamycin complex 1 (mTORC1) signalling, we also propose a Gaussian process-based method to solve the problem of non-equidistant time series measurements. Results: On synthetic network data and on yeast gene expression data the new model leads to improved network reconstruction accuracies. We then use the new model to reconstruct the topologies of the circadian clock network in Arabidopsis thaliana and the mTORC1 signalling pathway. The inferred network topologies show features that are consistent with the biological literature. Availability and implementation: All datasets have been made available with earlier publications. Our Matlab code is available upon request.
A Bayesian Model Framework for Reconstructing Gene Network Ms
2014
Gene regulatory networks provide the systematic view of molecular interactions in a complex living system. Reconstructing large-scale gene regulatory networks is challenging problems in systems biology. For reliable gene regulatory network reconstruction from large burst sets of biological data require a proper integration technique. In this paper, we are employing Recurrent Neural Network (RNN) for modeling the dynamical behavior of gene regulatory systems and then we are applying Bayesian Model for training the RNN Model. This approach is tested against experimental data of normal and tumour prostate samples. The objective is to find regulatory interaction among genes and represent in terms of graph where genes are going to act as nodes in the graph and regulatory interactions are represented in terms directed edges.
Springer eBooks, 2007
Gaussian process dynamical systems (GPDS) represent Bayesian nonparametric approaches to inference of nonlinear dynamical systems, and provide a principled framework for the learning of biological networks from multiple perturbed time series measurements of gene or protein expression. Such approaches are able to capture the full richness of complex ODE models, and can be scaled for inference in moderately large systems containing hundreds of genes. Related hierarchical approaches allow for inference from multiple datasets in which the underlying generative networks are assumed to have been rewired, either by context-dependent changes in network structure, evolutionary processes, or synthetic manipulation. These approaches can also be used to leverage experimentally determined network structures from one species into another where the network structure is unknown. Collectively, these methods provide a comprehensive and flexible platform for inference from a diverse range of data, with applications in systems and synthetic biology, as well as spatiotemporal modelling of embryo development. In this chapter we provide an overview of GPDS approaches and highlight their applications in the biological sciences, with accompanying tutorials available as a Jupyter notebook from https://github.com/cap76/GPDS.
Current Bioinformatics, 2014
In the post-genome era, designing and conducting novel experiments have become increasingly common for modern researchers. However, the major challenge faced by researchers is surprisingly not the complexity in designing new experiments or obtaining the data generated from the experiments, but instead it is the huge amount of data to be processed and analyzed in the quest to produce meaningful information and knowledge. Gene regulatory network (GRN) inference from gene expression data is one of the common examples of such challenge. Over the years, GRN inference has witnessed a number of transitions, and an increasing amount of new computational and statistical-based methods have been applied to automate the procedure. One of the widely used approaches for GRN inference is the dynamic Bayesian network (DBN). In this review paper, we first discuss the evolution of molecular biology research from reductionism to holism. This is followed by a brief insight on various computational and statistical methods used in GRN inference before focusing on reviewing the current development and applications of DBN-based methods. Chai et al. Category Inference Model Logical models Boolean networks Probabilistic Boolean networks [30, 31] Bayesian networks Continuous models Continuous linear models [32] Dynamic Bayesian networks Ordinary differential equations Regulated flux balance analysis [33] Single-molecule level Stochastic simulation algorithm [34] Inferring Gene Regulatory Networks