Drug repositioning based on weighted local information augmented graph neural network.

Drug repositioning, the strategy of redirecting existing drugs to new therapeutic purposes, is pivotal in accelerating drug discovery. While many studies have engaged in modeling complex drug-disease associations, they often overlook the relevance between different node embeddings. Consequently, we propose a novel weighted local information augmented graph neural network model, termed DRAGNN, for drug repositioning. Specifically, DRAGNN firstly incorporates a graph attention mechanism to dynamically allocate attention coefficients to drug and disease heterogeneous nodes, enhancing the effectiveness of target node information collection. To prevent excessive embedding of information in a limited vector space, we omit self-node information aggregation, thereby emphasizing valuable heterogeneous and homogeneous information. Additionally, average pooling in neighbor information aggregation is introduced to enhance local information while maintaining simplicity. A multi-layer perceptron is then employed to generate the final association predictions. The model's effectiveness for drug repositioning is supported by a 10-times 10-fold cross-validation on three benchmark datasets. Further validation is provided through analysis of the predicted associations using multiple authoritative data sources, molecular docking experiments and drug-disease network analysis, laying a solid foundation for future drug discovery.

A weighted bilinear neural collaborative filtering approach for drug repositioning.

Drug repositioning is an efficient and promising strategy for traditional drug discovery and development. Many research efforts are focused on utilizing deep-learning approaches based on a heterogeneous network for modeling complex drug-disease associations. Similar to traditional latent factor models, which directly factorize drug-disease associations, they assume the neighbors are independent of each other in the network and thus tend to be ineffective to capture localized information. In this study, we propose a novel neighborhood and neighborhood interaction-based neural collaborative filtering approach (called DRWBNCF) to infer novel potential drugs for diseases. Specifically, we first construct three networks, including the known drug-disease association network, the drug-drug similarity and disease-disease similarity networks (using the nearest neighbors). To take the advantage of localized information in the three networks, we then design an integration component by proposing a new weighted bilinear graph convolution operation to integrate the information of the known drug-disease association, the drug's and disease's neighborhood and neighborhood interactions into a unified representation. Lastly, we introduce a prediction component, which utilizes the multi-layer perceptron optimized by the α-balanced focal loss function and graph regularization to model the complex drug-disease associations. Benchmarking comparisons on three datasets verified the effectiveness of DRWBNCF for drug repositioning. Importantly, the unknown drug-disease associations predicted by DRWBNCF were validated against clinical trials and three authoritative databases and we listed several new DRWBNCF-predicted potential drugs for breast cancer (e.g. valrubicin and teniposide) and small cell lung cancer (e.g. valrubicin and cytarabine).

Drug repositioning based on the heterogeneous information fusion graph convolutional network.

In silico reuse of old drugs (also known as drug repositioning) to treat common and rare diseases is increasingly becoming an attractive proposition because it involves the use of de-risked drugs, with potentially lower overall development costs and shorter development timelines. Therefore, there is a pressing need for computational drug repurposing methodologies to facilitate drug discovery. In this study, we propose a new method, called DRHGCN (Drug Repositioning based on the Heterogeneous information fusion Graph Convolutional Network), to discover potential drugs for a certain disease. To make full use of different topology information in different domains (i.e. drug-drug similarity, disease-disease similarity and drug-disease association networks), we first design inter- and intra-domain feature extraction modules by applying graph convolution operations to the networks to learn the embedding of drugs and diseases, instead of simply integrating the three networks into a heterogeneous network. Afterwards, we parallelly fuse the inter- and intra-domain embeddings to obtain the more representative embeddings of drug and disease. Lastly, we introduce a layer attention mechanism to combine embeddings from multiple graph convolution layers for further improving the prediction performance. We find that DRHGCN achieves high performance (the average AUROC is 0.934 and the average AUPR is 0.539) in four benchmark datasets, outperforming the current approaches. Importantly, we conducted molecular docking experiments on DRHGCN-predicted candidate drugs, providing several novel approved drugs for Alzheimer's disease (e.g. benzatropine) and Parkinson's disease (e.g. trihexyphenidyl and haloperidol).

[Effect of underground work on cardiovascular system in coal miners].

OBJECTIVE: To study the effect of underground work on cardiovascular system health in coal miners.
 METHODS: Male coal miners, who received electrocardiographic examinations between June, 2013 and August, 2014 in Hunan Prevention and Treatment Institute for Occupational Diseases to exclude pneumoconiosis, were enrolled for this study (n=3 134). Miners with 2 years or more underground work experience were selected as the exposed group (n=2 370), while miners without underground work experience were selected as the control group (n=764). The prevalence of electrocardiographic abnormalities and the influential factors were compared between the 2 groups.
 RESULTS: The prevalences of electrocardiographic abnormalities, hypertension, heart rate abnormalities and cardiovascular system abnormalities in the exposed group vs the control group were 37.6% vs 25.4%, 20.5% vs 13.4%, 5.7% vs 6.0%, 49.8% vs 35.2%, respectively. The cardiovascular system abnormalities were correlated with the underground work (OR=3.128, 95% CI: 1.969-4.970), the underground work experience (OR=1.205, 95% CI: 1.070-1.358) and the type of works (mining worker OR=1.820, 95% CI: 1.527-2.169; auxiliary worker OR=1.937, 95% CI: 1.511-2.482; other worker OR=3.291, 95%CI: 2.120-5.109).
 CONCLUSION: Underground work may increase the prevalence of cardiovascular system abnormalities for coal miners. The longer the coal miners work in underground, the higher the risk of the cardiovascular system abnormalities they are.

[Analysis of pulmonary dysfunction of 1 953 coal miners in Hunan Province].

OBJECTIVE: To explore the effect of dust exposure, type of work, age, length of service and duration of dust exposure on pulmonary function in coal miners by pulmonary function tests.
 METHODS: A total of 1 953 coal miners, who received occupational healthy examination and pulmonary function tests during June, 2013 and August, 2014 in Hunan Prevention and Treatment Institute, were enrolled for this study.
 RESULTS: A total of 1 302 miners (66.7%) displayed pulmonary dysfunction, including 1 139 with mild dysfunction (58.3%) and 163 with moderate or more serious dysfunction (8.3%). The risk factors for pulmonary dysfunction were age (OR=1.329, 95% CI: 1.196-1.620), dust exposure duration (OR=1.267, 95% CI: 1.136-1.413) and type of works (mining workers OR=1.156, 95% CI: 1.033-1.293; all P<0.05).
 CONCLUSION: The incidence rate of pulmonary dysfunction in coal miners is relatively high in Hunan Province. Most of them are mild dysfunction. The incidence rate of pulmonary dysfunction in mining works is statistically higher than that in other work types. Older workers and long duration-exposed workers are more likely to have pulmonary dysfunction.

Oxyimperatorin attenuates LPS-induced microglial activation in vitro and in vivo via suppressing NF-κB p65 signaling.

BACKGROUND: Microglia-mediated neuroinflammation is an important pathological feature in many neurological diseases; thus, suppressing microglial activation is considered a possible therapeutic strategy for reducing neuronal damage. Oxyimperatorin (OIMP) is a member of furanocoumarin, isolated from the medicinal herb Glehnia littoralis. However, it is unknown whether OIMP can suppress the neuroinflammation. PURPOSE: To investigate the neuroprotective activity of oxyimperatorin (OIMP) in LPS-induced neuroinflammation in vitro and in vivo models. METHODS: In vitro inflammation-related assays were performed with OIMP in LPS-induced BV-2 microglia. In addition, intraperitoneal injection of LPS-induced microglial activation in the mouse brain was used to validate the anti-neuroinflammatory activity of OIMP. RESULTS: OIMP was found to suppress LPS-induced neuroinflammation in vitro and in vivo. OIMP significantly attenuated LPS-induced the production of free radicals, inducible nitric oxide synthase, cyclooxygenase-2, and pro-inflammatory cytokines in BV-2 microglia without causing cytotoxicity. In addition, OIMP could reduce the M1 pro-inflammatory transition in LPS-stimulated BV-2 microglia. The mechanistic study revealed that OIMP inhibited LPS-induced NF-κB p65 phosphorylation and nuclear translocation. However, OIMP did not affect LPS-induced IκB phosphorylation and degradation. In addition, OIMP also was able to reduce LPS-induced microglial activation in mice brain. CONCLUSION: Our findings suggest that OIMP suppresses microglia activation and attenuates the production of pro-inflammatory mediators and cytokines via inhibition of NF-κB p65 signaling.

Graph embedding and Gaussian mixture variational autoencoder network for end-to-end analysis of single-cell RNA sequencing data.

Single-cell RNA sequencing (scRNA-seq) is a revolutionary technology to determine the precise gene expression of individual cells and identify cell heterogeneity and subpopulations. However, technical limitations of scRNA-seq lead to heterogeneous and sparse data. Here, we present autoCell, a deep-learning approach for scRNA-seq dropout imputation and feature extraction. autoCell is a variational autoencoding network that combines graph embedding and a probabilistic depth Gaussian mixture model to infer the distribution of high-dimensional, sparse scRNA-seq data. We validate autoCell on simulated datasets and biologically relevant scRNA-seq. We show that interpolation of autoCell improves the performance of existing tools in identifying cell developmental trajectories of human preimplantation embryos. We identify disease-associated astrocytes (DAAs) and reconstruct DAA-specific molecular networks and ligand-receptor interactions involved in cell-cell communications using Alzheimer's disease as a prototypical example. autoCell provides a toolbox for end-to-end analysis of scRNA-seq data, including visualization, clustering, imputation, and disease-specific gene network identification.

Enhancing Drug Repositioning through Local Interactive Learning with Bilinear Attention Networks.

Drug repositioning has emerged as a promising strategy for identifying new therapeutic applications for existing drugs. In this study, we present DRGBCN, a novel computational method that integrates heterogeneous information through a deep bilinear attention network to infer potential drugs for specific diseases. DRGBCN involves constructing a comprehensive drug-disease network by incorporating multiple similarity networks for drugs and diseases. Firstly, we introduce a layer attention mechanism to effectively learn the embeddings of graph convolutional layers from these networks. Subsequently, a bilinear attention network is constructed to capture pairwise local interactions between drugs and diseases. This combined approach enhances the accuracy and reliability of predictions. Finally, a multi-layer perceptron module is employed to evaluate potential drugs. Through extensive experiments on three publicly available datasets, DRGBCN demonstrates better performance over baseline methods in 10-fold cross-validation, achieving an average area under the receiver operating characteristic curve (AUROC) of 0.9399. Furthermore, case studies on bladder cancer and acute lymphoblastic leukemia confirm the practical application of DRGBCN in real-world drug repositioning scenarios. Importantly, our experimental results from the drug-disease network analysis reveal the successful clustering of similar drugs within the same community, providing valuable insights into drug-disease interactions. In conclusion, DRGBCN holds significant promise for uncovering new therapeutic applications of existing drugs, thereby contributing to the advancement of precision medicine.

The effects of bioactive components from the rhizome of gastrodia elata blume (Tianma) on the characteristics of Parkinson's disease.

Parkinson's disease (PD) is an age-related chronic neurodegenerative disease caused by the death and degeneration of dopaminergic neurons in the substantia nigra of the midbrain. The decrease of the neurotransmitter dopamine in the patient's brain leads to various motor symptoms. PD drugs mainly enhance dopamine levels but cannot prevent or slow down the loss of dopaminergic neurons. In addition, they exhibit significant side effects and addiction issues during long-term use. Therefore, it is particularly urgent to develop novel drugs that have fewer side effects, can improve PD symptoms, and prevent the death of dopaminergic neurons. The rhizome of Gastrodia elata Blume (Tianma) is a well-known medicinal herb and has long been used as a treatment of nervous system-related diseases in China. Several clinical studies showed that formula comprising Tianma could be used as an add-on therapy for PD patients. Pharmacological studies indicated that Tianma and its bioactive components can reduce the death of dopaminergic neurons, α-synuclein accumulation, and neuroinflammation in various PD models. In this review, we briefly summarize studies regarding the effects of Tianma and its bioactive components' effects on major PD features and explore the potential use of Tianma components for the treatment of PD.

Indicator Regularized Non-Negative Matrix Factorization Method-Based Drug Repurposing for COVID-19.

A novel coronavirus, named COVID-19, has become one of the most prevalent and severe infectious diseases in human history. Currently, there are only very few vaccines and therapeutic drugs against COVID-19, and their efficacies are yet to be tested. Drug repurposing aims to explore new applications of approved drugs, which can significantly reduce time and cost compared with de novo drug discovery. In this study, we built a virus-drug dataset, which included 34 viruses, 210 drugs, and 437 confirmed related virus-drug pairs from existing literature. Besides, we developed an Indicator Regularized non-negative Matrix Factorization (IRNMF) method, which introduced the indicator matrix and Karush-Kuhn-Tucker condition into the non-negative matrix factorization algorithm. According to the 5-fold cross-validation on the virus-drug dataset, the performance of IRNMF was better than other methods, and its Area Under receiver operating characteristic Curve (AUC) value was 0.8127. Additionally, we analyzed the case on COVID-19 infection, and our results suggested that the IRNMF algorithm could prioritize unknown virus-drug associations.

Dose-response study of spinal hyperbaric ropivacaine for cesarean section.

BACKGROUND: Spinal hyperbaric ropivacaine may produce more predictable and reliable anesthesia than plain ropivacaine for cesarean section. The dose-response relation for spinal hyperbaric ropivacaine is undetermined. This double-blind, randomized, dose-response study determined the ED50 (50% effective dose) and ED95 (95% effective dose) of spinal hyperbaric ropivacaine for cesarean section anesthesia. METHODS: Sixty parturients undergoing elective cesarean section delivery with use of combined spinal-epidural anesthesia were enrolled in this study. An epidural catheter was placed at the L1 approximately L2 vertebral interspace, then lumbar puncture was performed at the L3 approximately L4 vertebral interspace, and parturients were randomized to receive spinal hyperbaric ropivacaine in doses of 10.5 mg, 12 mg, 13.5 mg, or 15 mg in equal volumes of 3 ml. Sensory levels (pinprick) were assessed every 2.5 min until a T7 level was achieved and motor changes were assessed by modified Bromage Score. A dose was considered effective if an upper sensory level to pin prick of T7 or above was achieved and no intraoperative epidural supplement was required. ED50 and ED95 were determined with use of a logistic regression model. RESULTS: ED50 (95% confidence interval) of spinal hyperbaric ropivacaine was determined to be 10.37 (5.23 approximately 11.59) mg and ED95 (95% confidence interval) to be 15.39 (13.81approximately 23.59) mg. The maximum sensory block levels and the duration of motor block and the rate of hypotension, but not onset of anesthesia, were significantly related to the ropivacaine dose. CONCLUSION: The ED50 and ED95 of spinal hyperbaric ropivacaine for cesarean delivery under the conditions of this study were 10.37 mg and 15.39 mg, respectively. Ropivacaine is suitable for spinal anesthesia in cesarean delivery.