CRPGCN: predicting circRNA-disease associations using graph convolutional network based on heterogeneous network

Background The existing studies show that circRNAs can be used as a biomarker of diseases and play a prominent role in the treatment and diagnosis of diseases. However, the relationships between the vast majority of circRNAs and diseases are still unclear, and more experiments are needed to study the mechanism of circRNAs. Nowadays, some scholars use the attributes between circRNAs and diseases to study and predict their associations. Nonetheless, most of the existing experimental methods use less information about the attributes of circRNAs, which has a certain impact on the accuracy of the final prediction results. On the other hand, some scholars also apply experimental methods to predict the associations between circRNAs and diseases. But such methods are usually expensive and time-consuming. Based on the above shortcomings, follow-up research is needed to propose a more efficient calculation-based method to predict the associations between circRNAs and diseases. Results In this study, a novel algorithm (method) is proposed, which is based on the Graph Convolutional Network (GCN) constructed with Random Walk with Restart (RWR) and Principal Component Analysis (PCA) to predict the associations between circRNAs and diseases (CRPGCN). In the construction of CRPGCN, the RWR algorithm is used to improve the similarity associations of the computed nodes with their neighbours. After that, the PCA method is used to dimensionality reduction and extract features, it makes the connection between circRNAs with higher similarity and diseases closer. Finally, The GCN algorithm is used to learn the features between circRNAs and diseases and calculate the final similarity scores, and the learning datas are constructed from the adjacency matrix, similarity matrix and feature matrix as a heterogeneous adjacency matrix and a heterogeneous feature matrix. Conclusions After 2-fold cross-validation, 5-fold cross-validation and 10-fold cross-validation, the area under the ROC curve of the CRPGCN is 0.9490, 0.9720 and 0.9722, respectively. The CRPGCN method has a valuable effect in predict the associations between circRNAs and diseases.

A 4-node quadrilateral element with center-point based discrete shear gap (CP-DSG4)

This work aims at presenting a novel four-node quadrilateral element, which is enhanced by integrating with discrete shear gap (DSG), for analysis of Reissner-Mindlin plates. In contrast to previous studies that are mainly based on three-node triangular elements, here we, for the first time, extend the DSG to four-node quadrilateral elements. We further integrate the fictitious point located at the center of element into the present formulation to eliminate the so-called anisotropy, leading to a simplified and efficient calculation of DSG, and that enhancement results in a novel approach named as "four-node quadrilateral element with center-point based discrete shear gap - CP-DSG4". The accuracy and efficiency of the CP-DSG4 are demonstrated through our numerical experiment, and its computed results are validated against those derived from the three-node triangular element using DSG, and other existing reference solutions.

Asymptotically accurate error estimates of exponential convergence for the trapezoidal rule

In many applied problems, efficient calculation of quadratures with high accuracy is required. The examples are: calculation of special functions of mathematical physics, calculation of Fourier coefficients of a given function, Fourier and Laplace transformations, numerical solution of integral equations, solution of boundary value problems for partial differential equations in integral form, etc. For grid calculation of quadratures, the trapezoidal, the mean and the Simpson methods are usually used. Commonly, the error of these methods depends quadratically on the grid step, and a large number of steps are required to obtain good accuracy. However, there are some cases when the error of the trapezoidal method depends on the step value not quadratically, but exponentially. Such cases are integral of a periodic function over the full period and the integral over the entire real axis of a function that decreases rapidly enough at infinity. If the integrand has poles of the first order on the complex plane, then the Trefethen-Weidemann majorant accuracy estimates are valid for such quadratures. In the present paper, new error estimates of exponentially converging quadratures from periodic functions over the full period are constructed. The integrand function can have an arbitrary number of poles of an integer order on the complex plane. If the grid is sufficiently detailed, i.e., it resolves the profile of the integrand function, then the proposed estimates are not majorant, but asymptotically sharp. Extrapolating, i.e., excluding this error from the numerical quadrature, it is possible to calculate the integrals of these classes with the accuracy of rounding errors already on extremely coarse grids containing only 10 steps.

On the Use of Cloud Analysis for Structural Glass Members under Seismic Events

Current standards for seismic-resistant buildings provide recommendations for various structural systems, but no specific provisions are given for structural glass. As such, the seismic design of joints and members could result in improper sizing and non-efficient solutions, or even non-efficient calculation procedures. An open issue is represented by the lack of reliable and generalized performance limit indicators (or “engineering demand parameters”, EDPs) for glass structures, which represent the basic input for seismic analyses or q-factor estimates. In this paper, special care is given to the q-factor assessment for glass frames under in-plane seismic loads. Major advantage is taken from efficient finite element (FE) numerical simulations to support the local/global analysis of mechanical behaviors. From extensive non-linear dynamic parametric calculations, numerical outcomes are discussed based on three different approaches that are deeply consolidated for ordinary structural systems. Among others, the cloud analysis is characterized by high computational efficiency, but requires the definition of specific EDPs, as well as the choice of reliable input seismic signals. In this regard, a comparative parametric study is carried out with the support of the incremental dynamic analysis (IDA) approach for the herein called “dynamic” (M1) and “mixed” (M2) procedures, towards the linear regression of cloud analysis data (M3). Potential and limits of selected calculation methods are hence discussed, with a focus on sample size, computational cost, estimated mechanical phenomena, and predicted q-factor estimates for a case study glass frame.

On IoT-Friendly Skewness Monitoring for Skewness-Aware Online Edge Learning

Machine learning techniques generally require or assume balanced datasets. Skewed data can make machine learning systems never function properly, no matter how carefully the parameter tuning is conducted. Thus, a common solution to the problem of high skewness is to pre-process data (e.g., log transformation) before applying machine learning to deal with real-world problems. Nevertheless, this pre-processing strategy cannot be employed for online machine learning, especially in the context of edge computing, because it is barely possible to foresee and store the continuous data flow on IoT devices on the edge. Thus, it will be crucial and valuable to enable skewness monitoring in real time. Unfortunately, there exists a surprising gap between practitioners’ needs and scientific research in running statistics for monitoring real-time skewness, not to mention the lack of suitable remedies for skewed data at runtime. Inspired by Welford’s algorithm, which is the most efficient approach to calculating running variance, this research developed efficient calculation methods for three versions of running skewness. These methods can conveniently be implemented as skewness monitoring modules that are affordable for IoT devices in different edge learning scenarios. Such an IoT-friendly skewness monitoring eventually acts a cornerstone for developing the research field of skewness-aware online edge learning. By initially validating the usefulness and significance of skewness awareness in edge learning implementations, we also argue that conjoint research efforts from relevant communities are needed to boost this promising research field.