State-Transition Model for Malaria Symptoms

Aims/ objectives: To develop a state-transition model for malaria symptoms. Study design: Longitudinal study. Place and Duration of Study: Department of Mathematics Masinde Muliro University of Science and Technology between January 2015 and December 2015. Methodology: We included 300 students (patients) with liver malaria disease, with or without the medical history of malaria disease, physical examination for signs and symptoms for both specific and non-specific symptom, investigation of the disease through laboratory test (BS test) and diagnostic test results. the focus of this study was to develop state-transition model for malaria symptoms. Bayesian method using Markov Chain Monte Carlo via Gibbs sampling algorithm was implemented for obtaining the parameter estimates. Results: The results of the study showed a significant association between malaria disease and observed symptoms Conclusion: The study findings provides a useful information that can be used for predicting malaria disease in areas where Blood slide test and rapid diagnostic test for malaria disease is not possible.

Application of Gibbs Sampling in Modelling the Utilization Rate of Raw Materials for Drug Coating

Drug coating is one of the most important processes in the modern pharmaceutical industry. Improving the utilization rate of raw materials (URRM) in the drug coating process is thus important for cost saving and efficiency enhancement. There is little existing research on this topic in the literature of applied statistics. In this paper, motivated by a real dataset collected from a pharmaceutical company in China, we propose to use a novel predictive model that integrates a Bayesian framework with the Gibbs sampling algorithm to characterize the pattern of URRM. Based on certain prior distributional assumptions, the Gibbs sampling algorithm is then applied to sample the posterior distribution of the parameters to obtain more accurate and robust estimation results. By using the proposed method, the drugs can be properly separated into several categories with different patterns of URRM, and the pattern of each category can be properly recognized with selected covariates, which achieves the goals of clustering, variable selection, and regression simultaneously, and provides valuable insights into the improvement of the URRM for drug coating. Numerical studies show that the proposed method works well in practice.

Direct Estimation of Diagnostic Classification Model Attribute Mastery Profiles via a Collapsed Gibbs Sampling Algorithm

This paper proposes a novel collapsed Gibbs sampling algorithm that marginalizes model parameters and directly samples latent attribute mastery patterns in diagnostic classification models. This estimation method makes it possible to avoid boundary problems in the estimation of model item parameters by eliminating the need to estimate such parameters. A simulation study showed the collapsed Gibbs sampling algorithm can accurately recover the true attribute mastery status in various conditions. In a real data analysis, the collapsed Gibbs sampling algorithm indicated good classification agreement with results from a previous study.

DegSampler: Gibbs sampling strategy for predicting E3-binding sites with position-specific prior information

Background: The ubiquitin-proteasome system is a pathway in eukaryotic cells for degrading polyubiquitin-tagged proteins through the proteasomal machinery to control various cellular processes and maintain intracellular homeostasis. In this system, the E3 ubiquitin ligase (hereinafter E3) plays an important role in selectively recognizing and binding to specific regions of its substrate proteins. The relationship between a substrate protein and its sites bound by E3s is not well understood. Thus, it is challenging to computationally identify such sites in substrate proteins. Results: In this study, we proposed a collapsed Gibbs sampling algorithm called DegSampler (Degron Sampler) to identify the binding sites of E3s. DegSampler employs a position-specific prior probability distribution, based on the estimated information of the disorder-to-order region bound by any protein. Conclusions: Our computational experiments show that DegSampler achieved 5 and 3.5 times higher the F-measure values of MEME and GLAM2, respectively. Thus DegSampler is the first model demonstrating an effective way of using estimated information on disorder-to-order binding regions in motif discovery. We expect our results to improve further as higher quality proteome-wide disorder-to-order binding region data become available.

Precipitation Downscaling with Gibbs Sampling: An Improved Method for Producing Realistic, Weather-Dependent, and Anisotropic Fields

Downscaling precipitation fields is a necessary step in a number of applications, especially in hydrological modeling where the meteorological forcings are frequently available at too coarse resolution. In this article, we review the Gibbs sampling disaggregation model (GSDM), a stochastic downscaling technique originally proposed by Gagnon et al. The method is capable of introducing realistic, weather-dependent, and possibly anisotropic fine-scale details, while preserving the mean rain rate over the coarse-scale pixels. The main developments compared to the former version are (i) an adapted Gibbs sampling algorithm that enforces the downscaled fields to have a similar texture to that of the analysis fields, (ii) an extensive test of various meteorological predictors for controlling specific aspects of the texture such as the anisotropy and the spatial variability, and (iii) a review of the regression equations used in the model for defining the conditional distributions. A perfect-model experiment is conducted over a domain in the southeastern United States. The metrics used for verification are based on the concept of gridded, stratified variogram, which is introduced as an effective way of reproducing the abilities of human eyes for detecting differences in the field texture. Results indicate that the best overall performances are obtained with the most sophisticated, predictor-based GSDM variant. The 600-hPa wind is found to be the best year-round predictor for controlling the anisotropy. For the spatial variability, kinematic predictors such as wind shear are found to be best during the convective periods, while instability indices are more informative elsewhere.

A Unified Bayesian Model for Generalized Community Detection in Attribute Networks

Identification of community structures and the underlying semantic characteristics of communities are essential tasks in complex network analysis. However, most methods proposed so far are typically only applicable to assortative community structures, that is, more links within communities and fewer links between different communities, which ignore the rich diversity of community regularities in real networks. In addition, the node attributes that provide rich semantics information of communities and networks can facilitate in-depth community detection of structural information. In this paper, we propose a novel unified Bayesian generative model to detect generalized communities and provide semantic descriptions simultaneously by combining network topology and node attributes. The proposed model is composed of two closely correlated parts by a transition matrix; we first apply the concept of a mixture model to describe network regularities and then adjust the classic Latent Dirichlet Allocation (LDA) topic model to identify community semantically. Thus, the model can detect broad types of network structure regularities, including assortative structures, disassortative structures, and mixture structures and provide multiple semantic descriptions for the communities. To optimize the objective function of the model, we use an effective Gibbs sampling algorithm. Experiments on a number of synthetic and real networks show that our model has superior performance compared with some baselines on community detection.