GCFMCL: predicting miRNA-drug sensitivity using graph collaborative filtering and multi-view contrastive learning.

Studies have shown that the mechanism of action of many drugs is related to miRNA. In-depth research on the relationship between miRNA and drugs can provide theoretical foundations and practical approaches for various areas, such as drug target discovery, drug repositioning and biomarker research. Traditional biological experiments to test miRNA-drug susceptibility are costly and time-consuming. Thus, sequence- or topology-based deep learning methods are recognized in this field for their efficiency and accuracy. However, these methods have limitations in dealing with sparse topologies and higher-order information of miRNA (drug) feature. In this work, we propose GCFMCL, a model for multi-view contrastive learning based on graph collaborative filtering. To the best of our knowledge, this is the first attempt that incorporates contrastive learning strategy into the graph collaborative filtering framework to predict the sensitivity relationships between miRNA and drug. The proposed multi-view contrastive learning method is divided into topological contrastive objective and feature contrastive objective: (1) For the homogeneous neighbors of the topological graph, we propose a novel topological contrastive learning method via constructing the contrastive target through the topological neighborhood information of nodes. (2) The proposed model obtains feature contrastive targets from high-order feature information according to the correlation of node features, and mines potential neighborhood relationships in the feature space. The proposed multi-view comparative learning effectively alleviates the impact of heterogeneous node noise and graph data sparsity in graph collaborative filtering, and significantly enhances the performance of the model. Our study employs a dataset derived from the NoncoRNA and ncDR databases, encompassing 2049 experimentally validated miRNA-drug sensitivity associations. Five-fold cross-validation shows that the Area Under the Curve (AUC), Area Under the Precision-Recall Curve (AUPR) and F1-score (F1) of GCFMCL reach 95.28%, 95.66% and 89.77%, which outperforms the state-of-the-art (SOTA) method by the margin of 2.73%, 3.42% and 4.96%, respectively. Our code and data can be accessed at https://github.com/kkkayle/GCFMCL.

Perceived stress and influencing factors for the people at high risk to COVID-19 in centralized quarantine camps in Wenzhou, China.

BACKGROUND: This study was designed to assess stress levels and related factors during the coronavirus disease 2019 (COVID-19) epidemic among individuals in centralized quarantine camps in Wenzhou, China. METHODS: The survey was conducted using a questionnaire. The questionnaire included questions on sociodemographic characteristics, life events related to the COVID-19 and stressful situations, as well as Perceived Stress Scale-14. Participants included close contacts of patients with COVID-19 or at-risk individuals in quarantine camps. Multivariate logistic regression was used to analyze different factors affecting perceived stress. RESULTS: The prevalence of high stress among quarantine camp participants was 37.45%. Of the 881 respondents, 51.99% were concerned about the difficulty of controlling the epidemic, 46.20% were concerned about the health of themselves and their family members and 39.61% were concerned about not being able to leave their homes. Multivariate logistic regression analysis revealed statistically significant differences in the prevalence of stress among different groups for certain variables, including occupation, education level and knowledge of COVID-19 (all P < 0.05). Our study found that at-risk individuals and close contacts experienced high levels of stress in quarantine camps during the COVID-19 pandemic. CONCLUSIONS: These findings suggest that centralized quarantine policies should be adapted and optimized to minimize negative psychological effects on quarantined individuals.

Reliability assessment of permanent magnet brake based on accelerated bivariate Wiener degradation process.

Permanent magnet brake (PMB) is a safe and effective braking mechanism used to stop and hold the load in place. Due to its complex structure and high reliability, assessing the reliability of PMB remains a challenge. The main difficulty lies in that there are several performance indicators reflecting the health state of PMB, and they are correlated with each other. In order to assess the reliability of PMB more accurately, a constant stress accelerated degradation test (ADT) is carried out to collect degradation data of two main performance indicators in PMB. An accelerated bivariate Wiener degradation model is proposed to analyse the ADT data. In the proposed model, the relationship between degradation rate and stress levels is described by Arrhenius model, and a common random effect is introduced to describe the unit-to-unit variation and correlation between the two performance indicators. The Markov Chain Monte Carlo (MCMC) algorithm is performed to obtain the point and interval estimates of the model parameters. Finally, the proposed model and method are applied to analyse the accelerated degradation data of PMB, and the results show that the reliability of PMB at the used condition can be quantified quite well.

HeadTailTransfer: An efficient sampling method to improve the performance of graph neural network method in predicting sparse ncRNA-protein interactions.

Noncoding RNA (ncRNA) is a functional RNA derived from DNA transcription, and most transcribed genes are transcribed into ncRNA. ncRNA is not directly involved in the translation of proteins, but it can participate in gene expression in cells and affect protein synthesis, thus playing an important role in biological processes such as growth, proliferation, metabolism, and information transmission. Therefore, understanding the interaction between ncRNA and protein is the basis for studying ncRNA regulation of protein-related biological activities. However, it is very expensive and time-consuming to verify ncRNA-protein interaction through biological experiments, and prediction methods based on machine learning have been developed rapidly. Recently, the graph neural network model (GNN) stands out for its excellent performance, but lacks a general framework for predicting ncRNA-protein interactions. We propose a GNN-based framework to predict ncRNA-protein interactions, which can utilize topological structure information to complete prediction tasks faster and more accurately. Meanwhile, for some smaller datasets, many ncRNA nodes lack neighbor information, resulting in lower prediction accuracy. For some larger datasets, the long-tail distribution causes the prediction of the tail nodes (sparse nodes linking few neighbors) to be affected. Therefore, we propose a new sampling method named HeadTailTransfer to mitigate these effects. Experimental results illustrate the effectiveness of this method. Especially for task-specific prediction on the RPI369 dataset in the Graphsage-based neural network framework, the AUC and ACC values increased from 56.8% and 52.2% to 80.2% and 71.8%, respectively. Our data and codes are available: https://github.com/kkkayle/HeadTailTransfer.

MHAM-NPI: Predicting ncRNA-protein interactions based on multi-head attention mechanism.

Non-coding RNA (ncRNA) is a functional RNA molecule that plays a key role in various fundamental biological processes, such as gene regulation. Therefore, studying the connection between ncRNA and proteins holds significant importance in exploring the function of ncRNA. Although many efficient and accurate methods have been developed by modern biological scientists, accurate predictions still pose a major challenge for various issues. In our approach, we utilize a multi-head attention mechanism to merge residual connections, allowing for the automatic learning of ncRNA and protein sequence features. Specifically, the proposed method projects node features into multiple spaces based on multi-head attention mechanism, thereby obtaining different feature interaction patterns in these spaces. By stacking interaction layers, higher-order interaction modes can be derived, while still preserving the initial feature information through the residual connection. This strategy effectively leverages the sequence information of ncRNA and protein, enabling the capture of hidden high-order features. The final experimental results demonstrate the effectiveness of our method, with AUC values of 97.4%, 98.5%, and 94.8% achieved on the NPInter v2.0, RPI807, and RPI488 datasets, respectively. These impressive results solidify our method as a powerful tool for exploring the connection between ncRNAs and proteins. We have uploaded the implementation code on GitHub: https://github.com/ZZCrazy00/MHAM-NPI.

DPB-NBFnet: Using neural Bellman-Ford networks to predict DNA-protein binding.

DNA is a hereditary material that plays an essential role in micro-organisms and almost all other organisms. Meanwhile, proteins are a vital composition and principal undertaker of microbe movement. Therefore, studying the bindings between DNA and proteins is of high significance from the micro-biological point of view. In addition, the binding affinity prediction is beneficial for the study of drug design. However, existing experimental methods to identifying DNA-protein bindings are extremely expensive and time consuming. To solve this problem, many deep learning methods (including graph neural networks) have been developed to predict DNA-protein interactions. Our work possesses the same motivation and we put the latest Neural Bellman-Ford neural networks (NBFnets) into use to build pair representations of DNA and protein to predict the existence of DNA-protein binding (DPB). NBFnet is a graph neural network model that uses the Bellman-Ford algorithms to get pair representations and has been proven to have a state-of-the-art performance when used to solve the link prediction problem. After building the pair representations, we designed a feed-forward neural network structure and got a 2-D vector output as a predicted value of positive or negative samples. We conducted our experiments on 100 datasets from ENCODE datasets. Our experiments indicate that the performance of DPB-NBFnet is competitive when compared with the baseline models. We have also executed parameter tuning with different architectures to explore the structure of our framework.