In this work, we explore information geometry theoretic approach to analyzing EEG signals simulated by stochastic nonlinear coupled oscillator models for both healthy subjects and Alzheimer’s Disease (AD) patients with both eyes-closed and eyes-open conditions. In particular, we employ information rates to quantify the time evolution of probability density functions of simulated EEG signals, and employ causal information rates to quantify one signal’s instantaneous influence on another signal’s information rate. These two measures help us find significant and interesting distinctions between healthy subjects and AD patients when they change their eyes’ open/closed status. These distinctions may be further related to differences in neural information processing activities of the corresponding brain regions, and to differences in connectivities among these brain regions. In particular, a prominent distinction is that, when healthy subjects open their eyes, there is a directional change in net causal connectivities among brain regions (that generate EEG signals modeled by stochastic nonlinear coupled oscillators), as measured by net causal information rates, whereas this directional change in net causality does not present when AD patients open their eyes. Since these information geometry theoretic measures can be applied to experimental EEG signals in a modelfree manner, and they are capable of quantifying non-stationary time-varying effects, nonlinearity, and non-Gaussian stochasticity presented in real-world EEG signals, we believe that they can form an important and powerful tool-set for both understanding neural information processing in the brain and diagnosis of neurological disorders such as Alzheimer’s Disease.

In the midst of the COVID-19 pandemic, it was essential to accurately forecast the demand for hospitalisation resources to achieve an effective allocation of healthcare resources. This paper explores the potential of various Deep Learning (DL) models, namely basic Recurrent Neural Networks (RNNs), Long Short-Term Memory networks (LSTMs), Gated Recurrent Units (GRU), Bidirectional RNNs, and Sequence-to-Sequence architectures with the inclusion of attention mechanisms, to forecast the demand for hospitalisation resources (mechanical ventilators) in England during the COVID-19 pandemic. The implementation of simulated annealing (SA) as a hyperparameter tuning method produced certain model structures and good results in terms of prediction accuracy. Our findings show that the LSTM-based models (LSTM_SA), achieved the lowest mean average error (MAE), outperforming other architectures used in this study. The results of this study show the potential of DL models to forecast the demand for resources and could help inform the distribution of hospitalisation resources in England during the COVID-19 pandemic.

Alzheimer's disease (AD) is one of the most common neurodegenerative diseases, with around 50 million patients worldwide. Accessible and non-invasive methods of diagnosing and characterising AD are therefore urgently required. Electroencephalography (EEG) fulfils these criteria and is often used when studying AD. Several features derived from EEG were shown to predict AD with high accuracy, e.g. signal complexity and synchronisation. However, the dynamics of how the brain transitions between stable states have not been properly studied in the case of AD and EEG. Energy landscape analysis is a method that can be used to quantify these dynamics. This work presents the first application of this method to both AD and EEG. Energy landscape assigns energy value to each possible state, i.e. pattern of activations across brain regions. The energy is inversely proportional to the probability of occurrence. By studying the features of energy landscapes of 20 AD patients and 20 age-matched healthy counterparts (HC), significant differences are found. The dynamics of AD patients' EEG are shown to be more constrained - with more local minima, less variation in basin size, and smaller basins. We show that energy landscapes can predict AD with high accuracy, performing significantly better than baseline models. Moreover, these findings are replicated in a separate dataset including 9 AD and 10 HC above 70 years old.

MOTIVATION: Approximate Bayesian computation (ABC) is an important framework within which to infer the structure and parameters of a systems biology model. It is especially suitable for biological systems with stochastic and nonlinear dynamics, for which the likelihood functions are intractable. However, the associated computational cost often limits ABC to models that are relatively quick to simulate in practice. RESULTS: We here present a Julia package, GpABC, that implements parameter inference and model selection for deterministic or stochastic models using (i) standard rejection ABC or sequential Monte Carlo ABC or (ii) ABC with Gaussian process emulation. The latter significantly reduces the computational cost. AVAILABILITY AND IMPLEMENTATION: https://github.com/tanhevg/GpABC.jl.

BACKGROUND: Reverse engineering of gene regulatory networks from time series gene-expression data is a challenging problem, not only because of the vast sets of candidate interactions but also due to the stochastic nature of gene expression. We limit our analysis to nonlinear differential equation based inference methods. In order to avoid the computational cost of large-scale simulations, a two-step Gaussian process interpolation based gradient matching approach has been proposed to solve differential equations approximately. RESULTS: We apply a gradient matching inference approach to a large number of candidate models, including parametric differential equations or their corresponding non-parametric representations, we evaluate the network inference performance under various settings for different inference objectives. We use model averaging, based on the Bayesian Information Criterion (BIC), to combine the different inferences. The performance of different inference approaches is evaluated using area under the precision-recall curves. CONCLUSIONS: We found that parametric methods can provide comparable, and often improved inference compared to non-parametric methods; the latter, however, require no kinetic information and are computationally more efficient.

An important aspect of systems biology research is the so-called ldquoreverse engineeringrdquo of cellular metabolic dynamics from measured input-output data. This allows researchers to estimate and validate both the pathwaypsilas structure as well as the kinetic constants. In this paper, a regularization based method which performs model structure selection is developed and applied to the problem of analyzing how existing pathway knowledge can be used as a prior investigate the model change complexity/sensitivity trade-off. Specifically, a 1-norm prior on parameter deviations from an existing model of the IkappaB-NF-kappaB pathway is combined with new experimental data and an analysis is performed to determine which are the most relevant components to alter.

Due to the general lack of experimental data for biochemical pathway model identification, cell-level time series experimental design is particularly important in current systems biology research. This paper investigates the problem of experimental design for signal transduction pathway modeling, and in particular, focuses on methods for parametric feature selection. An important problem is the estimation of parametric uncertainty which is a function of the true (but unknown) parameters. In this paper, two “robust” feature selection strategies are investigated The first is a mini-max robust experimental design approach, the second is a sampled experimental design method inspired by the Morris global sensitivity analysis. The two approaches are analyzed and interpreted in terms of a generalized optimal experimental design criterion, and their performance has been compared via simulation on the IκB-NF-κB pathway feature selection problem.