Distinct characteristics of the gut virome in patients with osteoarthritis and gouty arthritis.

BACKGROUND/PURPOSE(S): The gut microbiota and its metabolites play crucial roles in pathogenesis of arthritis, highlighting gut microbiota as a promising avenue for modulating autoimmunity. However, the characterization of the gut virome in arthritis patients, including osteoarthritis (OA) and gouty arthritis (GA), requires further investigation. METHODS: We employed virus-like particle (VLP)-based metagenomic sequencing to analyze gut viral community in 20 OA patients, 26 GA patients, and 31 healthy controls, encompassing a total of 77 fecal samples. RESULTS: Our analysis generated 6819 vOTUs, with a considerable proportion of viral genomes differing from existing catalogs. The gut virome in OA and GA patients differed significantly from healthy controls, showing variations in diversity and viral family abundances. We identified 157 OA-associated and 94 GA-associated vOTUs, achieving high accuracy in patient-control discrimination with random forest models. OA-associated viruses were predicted to infect pro-inflammatory bacteria or bacteria associated with immunoglobulin A production, while GA-associated viruses were linked to Bacteroidaceae or Lachnospiraceae phages. Furthermore, several viral functional orthologs displayed significant differences in frequency between OA-enriched and GA-enriched vOTUs, suggesting potential functional roles of these viruses. Additionally, we trained classification models based on gut viral signatures to effectively discriminate OA or GA patients from healthy controls, yielding AUC values up to 0.97, indicating the clinical utility of the gut virome in diagnosing OA or GA. CONCLUSION: Our study highlights distinctive alterations in viral diversity and taxonomy within gut virome of OA and GA patients, offering insights into arthritis etiology and potential treatment and prevention strategies.

Assessment of microorganisms in drinking water disinfected by catalytic ozonation with fluorinated ceramic honeycomb and NaClO disinfectants under laboratory and pilot conditions.

While sodium hypochlorite (NaClO) has long been used to disinfect drinking water, concerns have risen over its use due to causing potentially hazardous byproducts. Catalytic ozonation with metal-free catalysts has attracted increasing attention to eliminate the risk of secondary pollution of byproducts in water treatment. Here, we compared the disinfection efficiency and microbial community of catalytic ozone with a type of metal-free catalyst fluorinated ceramic honeycomb (FCH) and NaClO disinfectants under laboratory- and pilot-scale conditions. Under laboratory conditions, the disinfection rate of catalytic ozonation was 3∼6-fold that of ozone when the concentration of Escherichia coli was 1 × 106 CFU/ml, and all E. coli were killed within 15 s. However, 0.65 mg/L NaClO retained E. coli after 30 min using the traditional culturable approach. The microorganism inactivation results of raw reservoir water disinfected by catalytic ozonation and ozonation within 15 s were incomparable based on the cultural method. In pilot-scale testing, catalytic ozonation inactivated all environmental bacteria within 4 min, while 0.65 mg/L NaClO could not achieve this success. Both catalytic ozonation and NaClO-disinfected methods significantly reduced the number of microorganisms but did not change the relative abundances of different species, i.e., bacteria, viruses, eukaryotes, and archaea, based on metagenomic analyses. The abundance of virulence factors (VFs) and antimicrobial resistance genes (ARGs) was detected few in catalytic ozonation, as determined by metagenomic sequencing. Some VFs or ARGs, such as virulence gene 'FAS-II' which was hosted by Mycobacterium_tuberculosis, were detected solely by the NaClO-disinfected method. The enriched genes and pathways of cataO3-disinfected methods exhibited an opposite trend, especially in human disease, compared with NaClO disinfection. These results indicated that the disinfection effect of catalytic ozone is superior to NaClO, this finding contributed to the large-scale application of catalytic ozonation with FCH in practical water treatment.

Similarity-guided graph contrastive learning for lncRNA-disease association prediction.

The increasing research evidence indicates that long non-coding RNAs (lncRNAs) play important roles in regulating biological processes and are closely associated with many human diseases. Computational methods have emerged as indispensable tools for identifying associations between long non-coding RNA (lncRNA) and diseases, primarily due to the time-consuming and costly nature of traditional biological experiments. Given the scarcity of verified lncRNA-disease associations, the intensifying focus on deep learning is playing a crucial role in refining the accuracy of predictive models. Moreover, the contrastive learning method exhibits a clear advantage in situations where data is scarce or annotation costs are high. In this paper, we leverage the advantages of graph neural networks and contrastive learning to innovatively propose a similarity-guided graph contrastive learning (SGGCL) model for predicting lncRNA-disease associations. In the SGGCL model, we employ a novel similarity-guided graph data augmentation method to generate high-quality positive and negative sample pairs, addressing the scarcity of verified data. Additionally, we utilize the RWR algorithm and a graph convolutional neural network for contrastive learning, facilitating the capture of global topology and high-level node embeddings. The experimental results on several datasets demonstrate the superior predictive performance and scalability of our method in lncRNA-disease association prediction compared to state-of-the-art methods.

Profiling the Gut Microbiota in Obese Children with Formula Feeding in Early Life and Selecting Strains against Obesity.

Formula feeding, obesity and the gut microbiota are closely related. The present investigation explored the profiles of the intestinal microbiota in obese children over 5 years old with formula feeding in early life. We identified functional bacteria with anti-obesity potential through in vitro and in vivo experiments, elucidating their mechanisms. The results indicated that, in the group of children over 5 years old who were fed formula in early life, obese children exhibited distinct gut microbiota, which were characterized by diminished species diversity and reduced Bifidobacterium levels compared to normal-weight children. As a result, Lactobacillus acidophilus H-68 (H-68) was isolated from the feces of the N-FF group and recognized as a promising candidate. H-68 demonstrated the ability to stimulate cholecystokinin (CCK) secretion in STC-1 cells and produce bile salt hydrolase. In vivo, H-68 promoted CCK secretion, suppressing food intake, and regulated bile acid enterohepatic circulation, leading to increased deoxycholic acid and lithocholic acid levels in the ileum and liver. This regulation effectively inhibited the diet-induced body weight and body fat gain, along with the liver fat deposition. In conclusion, H-68 was recognized for its prospective anti-obesity impact, signifying an auspicious pathway for forthcoming interventions targeted at averting pediatric obesity in formula-fed children.

Artificial Intelligence-Assisted Prescription Determination for Orthokeratology Lens Fitting: From Algorithm to Clinical Practice.

OBJECTIVES: To explore the potential of artificial intelligence (AI) to assist prescription determination for orthokeratology (OK) lenses. METHODS: Artificial intelligence algorithm development followed by a real-world trial. A total of 11,502 OK lenses fitting records collected from seven clinical environments covering major brands. Records were randomly divided in a three-way data split. Cross-validation was used to identify the most accurate algorithm, followed by an evaluation using an independent test data set. An online AI-assisted system was implemented and assessed in a real-world trial involving four junior and three senior clinicians. RESULTS: The primary outcome measure was the algorithm's accuracy (ACC). The ACC of the best performance of algorithms to predict the targeted reduction amplitude, lens diameter, and alignment curve of the prescription was 0.80, 0.82, and 0.83, respectively. With the assistance of the AI system, the number of trials required to determine the final prescription significantly decreased for six of the seven participating clinicians (all P <0.01). This reduction was more significant among junior clinicians compared with consultants (0.76±0.60 vs. 0.32±0.60, P <0.001). Junior clinicians achieved clinical outcomes comparable to their seniors, as 93.96% (140/149) and 94.44% (119/126), respectively, of the eyes fitted achieved unaided visual acuity no worse than 0.8 ( P =0.864). CONCLUSIONS: AI can improve prescription efficiency and reduce discrepancies in clinical outcomes among clinicians with differing levels of experience. Embedment of AI in practice should ultimately help lessen the medical burden and improve service quality for myopia boom emerging worldwide.

LGCDA: Predicting CircRNA-Disease Association Based on Fusion of Local and Global Features.

CircRNA has been shown to be involved in the occurrence of many diseases. Several computational frameworks have been proposed to identify circRNA-disease associations. Despite the existing computational methods have obtained considerable successes, these methods still require to be improved as their performance may degrade due to the sparsity of the data and the problem of memory overflow. We develop a novel computational framework called LGCDA to predict circRNA-disease associations by fusing local and global features to solve the above mentioned problems. First, we construct closed local subgraphs by using k-hop closed subgraph and label the subgraphs to obtain rich graph pattern information. Then, the local features are extracted by using graph neural network (GNN). In addition, we fuse Gaussian interaction profile (GIP) kernel and cosine similarity to obtain global features. Finally, the score of circRNA-disease associations is predicted by using the multilayer perceptron (MLP) based on local and global features. We perform five- fold cross validation on five datasets for model evaluation and our model surpasses other advanced methods. The code is available at https://github.com/lanbiolab/LGCDA.

Deep Imputation Bi-stochastic Graph Regularized Matrix Factorization for Clustering Single-cell RNA-sequencing Data.

By generating massive gene transcriptome data and analyzing transcriptomic variations at the cell level, single-cell RNA-sequencing (scRNA-seq) technology has provided new way to explore cellular heterogeneity and functionality. Clustering scRNA-seq data could discover the hidden diversity and complexity of cell populations, which can aid to the identification of the disease mechanisms and biomarkers. In this paper, a novel method (DSINMF) is presented for single cell RNA sequencing data by using deep matrix factorization. Our proposed method comprises four steps: first, the feature selection is utilized to remove irrelevant features. Then, the dropout imputation is used to handle missing value problem. Further, the dimension reduction is employed to preserve data characteristics and reduce noise effects. Finally, the deep matrix factorization with bi-stochastic graph regularization is used to obtain cluster results from scRNA-seq data. We compare DSINMF with other state-of-the-art algorithms on nine datasets and the results show our method outperformances than other methods.

In Situ Fabrication of Hierarchical CuO@CoNi-LDH Composite Structures for High-Performance Supercapacitors.

Layered double hydroxide (LDH) materials, despite their high theoretical capacity, exhibit significant performance degradation with increasing load due to their low conductivity. Simultaneously achieving both high capacity and high rate performance is challenging. Herein, we fabricated vertically aligned CuO nanowires in situ on the copper foam (CF) substrate by alkali-etching combined with the annealing process. Using this as a skeleton, electrochemical deposition technology was used to grow the amorphous α-phase CoNi-LDH nanosheets on its surface. Thanks to the high specific surface area of the CuO skeleton, ultrahigh loading (̃16.36 mg cm-2) was obtained in the fabricated CF/CuO@CoNi-LDH electrode with the cactus-like hierarchical structure, which enhanced the charge transfer and ion diffusion dynamics. The CF/CuO@CoNi-LDH electrode achieved a good combination of high areal capacitance (33.5 F cm-2) and high rate performance (61% capacitance retention as the current density increases 50 times). The assembled asymmetric supercapacitor device demonstrated a maximum potential window of 0-1.6 V and an energy density of 1.7 mWh cm-2 at a power density of 4 mW cm-2. This work provides a feasible strategy for the design and fabrication of high-mass-loading LDH composites for electrochemical energy storage applications.

Desmoplastic fibroma in a child: a 9-year follow-up case report.

BACKGROUND: Desmoplastic fibroma is an extremely rare primary bone tumor. Its characteristic features include bone destruction accompanied by the formation of soft tissue masses. This condition predominantly affects individuals under the age of 30. Since its histology is similar to desmoid-type fibromatosis, an accurate diagnosis before operation is difficult. Desmoplastic fibroma is resistant to chemotherapy, and the efficacy of radiotherapy is uncertain. Surgical excision is preferred for treatment, but it entails high recurrence. Further, skeletal reconstruction post-surgery is challenging, especially in pediatric cases. CASE PRESENTATION: Nine years ago, a 14-year-old male patient presented with a 4-year history of progressive pain in his left wrist. Initially diagnosed as fibrous dysplasia by needle biopsy, the patient underwent tumor resection followed by free vascularized fibular proximal epiphyseal transfer for wrist reconstruction. However, a histological examination confirmed a diagnosis of desmoplastic fibroma. The patient achieved bone union and experienced a recurrence in the ipsilateral ulna 5 years later, accompanied by a wrist deformity. He underwent a second tumor resection and wrist arthrodesis in a single stage. The most recent annual follow-up was in September 2023; the patient had no recurrence and was satisfied with the surgery. CONCLUSIONS: Desmoplastic fibroma is difficult to diagnose and treat, and reconstruction surgery after tumor resection is challenging. Close follow-up by experienced surgeons may be beneficial for prognosis.

Fungal biomineralization of toxic metals accelerates organic pollutant removal.

Fungal biomineralization plays an important role in the biogeochemical cycling of metals in the environment and has been extensively explored for bioremediation and element biorecovery. However, the cellular and metabolic responses of fungi in the presence of toxic metals during biomineralization and their impact on organic matter transformations are unclear. This is an important question because co-contamination by toxic metals and organic pollutants is a common phenomenon in the natural environment. In this research, the biomineralization process and oxidative stress response of the geoactive soil fungus Aspergillus niger were investigated in the presence of toxic metals (Co, Cu, Mn, and Fe) and the azo dye orange II (AO II). We have found that the co-existence of toxic metals and AO II not only enhanced the fungal biomineralization of toxic metals but also accelerated the removal of AO II. We hypothesize that the fungus and in situ mycogenic biominerals (toxic metal oxalates) constituted a quasi-bioreactor, where the biominerals removed organic pollutants by catalyzing reactive oxygen species (ROS) generation resulting from oxidative stress. We have therefore demonstrated that a fungal/biomineral system can successfully achieve the goal of toxic metal immobilization and organic pollutant decomposition. Such findings inform the potential development of fungal-biomineral hybrid systems for mixed pollutant bioremediation as well as provide further understanding of fungal organic-inorganic pollutant transformations in the environment and their importance in biogeochemical cycles.

IBPGNET: lung adenocarcinoma recurrence prediction based on neural network interpretability.

Lung adenocarcinoma (LUAD) is the most common histologic subtype of lung cancer. Early-stage patients have a 30-50% probability of metastatic recurrence after surgical treatment. Here, we propose a new computational framework, Interpretable Biological Pathway Graph Neural Networks (IBPGNET), based on pathway hierarchy relationships to predict LUAD recurrence and explore the internal regulatory mechanisms of LUAD. IBPGNET can integrate different omics data efficiently and provide global interpretability. In addition, our experimental results show that IBPGNET outperforms other classification methods in 5-fold cross-validation. IBPGNET identified PSMC1 and PSMD11 as genes associated with LUAD recurrence, and their expression levels were significantly higher in LUAD cells than in normal cells. The knockdown of PSMC1 and PSMD11 in LUAD cells increased their sensitivity to afatinib and decreased cell migration, invasion and proliferation. In addition, the cells showed significantly lower EGFR expression, indicating that PSMC1 and PSMD11 may mediate therapeutic sensitivity through EGFR expression.

DeepKEGG: a multi-omics data integration framework with biological insights for cancer recurrence prediction and biomarker discovery.

Deep learning-based multi-omics data integration methods have the capability to reveal the mechanisms of cancer development, discover cancer biomarkers and identify pathogenic targets. However, current methods ignore the potential correlations between samples in integrating multi-omics data. In addition, providing accurate biological explanations still poses significant challenges due to the complexity of deep learning models. Therefore, there is an urgent need for a deep learning-based multi-omics integration method to explore the potential correlations between samples and provide model interpretability. Herein, we propose a novel interpretable multi-omics data integration method (DeepKEGG) for cancer recurrence prediction and biomarker discovery. In DeepKEGG, a biological hierarchical module is designed for local connections of neuron nodes and model interpretability based on the biological relationship between genes/miRNAs and pathways. In addition, a pathway self-attention module is constructed to explore the correlation between different samples and generate the potential pathway feature representation for enhancing the prediction performance of the model. Lastly, an attribution-based feature importance calculation method is utilized to discover biomarkers related to cancer recurrence and provide a biological interpretation of the model. Experimental results demonstrate that DeepKEGG outperforms other state-of-the-art methods in 5-fold cross validation. Furthermore, case studies also indicate that DeepKEGG serves as an effective tool for biomarker discovery. The code is available at https://github.com/lanbiolab/DeepKEGG.

Chinese herb ultrafine powder supplementation improves egg nutritional value and quality in laying hens.

This study evaluates the effects of dietary Chinese herb ultrafine powder (CHUP) supplementation in late-phase laying hens on the quality and nutritional values of eggs. A total of 576 Xinyang black-feather laying hens (300-day-old) were randomly allocated into eight groups for a 120-day feeding trial. Each group contained eight replicates with nine hens per replicate. The experimental groups included the control (basal diet) and different levels of CHUP groups (details in 'Materials and methods'). The results showed that the eggshell strength was increased (p < 0.05) in the L, LF, L-LF, L-T, and LF-T groups on day 60 of the trial. In addition, the plasma estradiol level in the L-LF, LF-T, and L-LF-T groups and unsaturated fatty acids concentrations in egg yolk of the CHUP groups (except LF-T group) were increased, whereas total cholesterol (T, L-LF, L-T, and L-LF-T groups) in egg yolk and the atherogenicity (T, L-T, and L-LF-T groups) and thrombogenicity (T, L-LF, L-T, and L-LF-T groups) indexes were decreased (p < 0.05) on day 60 of the trial compared with the control group. Moreover, bitter amino acids in egg albumen were decreased (p < 0.05) in the L-LF group on day 60 and the L-LF-T group on day 120 of the trial. Collectively, these findings indicate that dietary CHUP supplementation could improve eggshell quality and increase plasma reproductive hormone, fatty acid and amino acid composition, and nutritional values of eggs, especially L-LF and L-LF-T.

Right ventricular dyssynchrony for the prediction of prognosis in patients with systemic lupus erythematosus-aaociated pulmonary arterial hypertension: a study with two-dimensional speckle tracking.

Pulmonary arterial hypertension (PAH) is a common complication of systemic lupus erythematosus (SLE), and PAH can cause right ventricle (RV) remodel and dyssynchrony. The aim of this study was to explore the value of RV dyssynchrony in predicting adverse clinical events in patients with systemic lupus erythematosus-aaociated pulmonary arterial hypertension (SLE-PAH) using two-dimensional speckle tracking echocardiography (2D-STE). A total of 53 patients with SLE-PAH were enrolled in this study. The dyssynchrony of the RV (RV-SD6) was evaluated by 2D-STE. The clinical data of all participants were collected, and routine cardiac function parameters were measured by two-dimensional echocardiography, and analyzed for their correlation with RV-SD6. The predictive value of RV-SD6 in clinical adverse event was evaluated. RV-SD6 was negatively correlated with RV-FLS, RV-FAC, and TAPSE (r = - 0.788, r = - 0.363 and r = - 0.325, respectively, all P < 0.01), while the correlation with RV-FLS was the strongest. linear regression analysis showed that RV-FLS was an independent risk factor for RV-SD6 (ß = - 1.40, 95% CI - 1.65 ~ - 1.14, P < 0.001). Cox regression analysis showed that RV-SD6 was a predictor with clinical adverse events (HR = 1.03, 95% CI 1 ~ 1.06, P < 0.05). RV-SD6 was highly discriminative in predicting clinical adverse events (AUC = 0.764), at a cutoff of 51.10 ms with a sensitivity of 83.3% and specificity of 68.3%. RV-FLS was negatively correlated with RV-SD6 and was an independent risk factor for it. RV-SD6 can serve as an indicator for predicting the occurrence of adverse clinical events in SLE-PAH patients, with high sensitivity and specificity.

Noninvasive Assessment of hiPSC Differentiation toward Cardiomyocytes Using Pretrained Convolutional Neural Networks and the Channel Pruning Algorithm.

Human induced pluripotent stem cell (hiPSC)-derived cardiomyocytes (hiPSC-CMs) offer versatile applications in tissue engineering and drug screening. To facilitate the monitoring of hiPSC cardiac differentiation, a noninvasive approach using convolutional neural networks (CNNs) was explored. HiPSCs were differentiated into cardiomyocytes and analyzed using the quantitative real-time polymerase chain reaction (qRT-PCR). The bright-field images of the cells at different time points were captured to create the dataset. Six pretrained models (AlexNet, GoogleNet, ResNet 18, ResNet 50, DenseNet 121, VGG 19-BN) were employed to identify different stages in differentiation. VGG 19-BN outperformed the other five CNNs and exhibited remarkable performance with 99.2% accuracy, recall, precision, and F1 score and 99.8% specificity. The pruning process was then applied to the optimal model, resulting in a significant reduction of model parameters while maintaining high accuracy. Finally, an automation application using the pruned VGG 19-BN model was developed, facilitating users in assessing the cell status during the myocardial differentiation of hiPSCs.

SSLDTI: A novel method for drug-target interaction prediction based on self-supervised learning.

Many computational methods have been proposed to identify potential drug-target interactions (DTIs) to expedite drug development. Graph neural network (GNN) methods are considered to be one of the most effective approaches. However, shallow GNN methods can only aggregate local information from nodes. Also, deep GNN methods may result in over-smoothing while obtaining long-distance neighbourhood information. As a result, existing GNN methods struggle to extract the complete features of the graph. Additionally, the number of known DTIs is insufficient, and there are far more unknown drug-target pairs than known DTIs, leading to class imbalance. This article proposes a model that combines graph autoencoder and self-supervised learning to accurately encode multilevel features of graphs using only a small number of labelled samples. We introduce a positive sample compensation coefficient to the objective function to mitigate the impact of class imbalance. Experiments on two datasets demonstrated that our model outperforms the four baseline methods, and the new DTIs predicted by the SSLDTI model were verified by the DrugBank database.

Adult-onset congenital cholesteatoma in the hypotympanum initially presenting as Bell's palsy: A case report.

INTRODUCTION: Cholesteatoma is a rare disease characterized by the accumulation of keratinized squamous epithelial cells in the middle ear or mastoid cavity. Vertigo and facial palsy, which are rare complications, may indicate erosion into the semicircular canals or the fallopian canal. PATIENT CONCERNS: A 40-year-old woman presented to our clinic with progressive right-sided hearing loss over 5 years (primary concern). Approximately 10 years ago, the patient had developed acute right-sided facial weakness with no additional symptoms. A neurologist at another hospital had diagnosed her condition as Bell's palsy and treated it accordingly. DIAGNOSIS: Adult-onset congenital cholesteatoma in the hypotympanum. INTERVENTION: Combined endoscopic and microscopic removal of the cholesteatoma. OUTCOMES: Physical examination revealed slight improvement in right-sided peripheral facial palsy. LESSON: Routine eardrum examination is recommended for patients presenting with isolated peripheral facial palsy. If necessary, a patient should be referred to an otologist for further evaluation and treatment.

Preclinical systolic dysfunction relating to ankle-brachial index among high-risk PAD population with preserved left ventricular ejection fraction.

Peripheral artery disease (PAD) shares common clinical risk factors, for example, endothelial dysfunction, with preserved ejection fraction (LVEF) heart failure (HFpEF). Whether PAD is associated with preclinical systolic dysfunction and higher HF risk among individuals presenting preserved LVEF remains uncertain. We retrospectively included outpatients with at least one known or established cardiovascular (CV) risk factor with LVEF ≥ 50%. Patients were categorized into high risk and low risk of developing PAD (PAD vs Non-PAD) by ankle-brachial index (ABI) (≤ 0.90 or > 1.4) and further stratified based on their history of HFpEF (HFpEF vs. Non-HFpEF), resulting in the formation of four distinct strata. Preclinical systolic dysfunction was defined using dedicated speckle-tracking algorithm. A total of 2130 consecutive patients were enrolled in the study, with a median follow-up of 4.4 years. The analysis revealed a higher prevalence of high risk of developing PAD in patients with HFpEF compared to those without HFpEF (25.1% vs. 9.4%). Both high risk of developing PAD and HFpEF were independently associated with preclinical systolic dysfunction (global longitudinal strain, GLS ≥ - 18%) (odds ratio, OR: 1.38; 95% confidence interval, CI: 1.03-1.86). In comparison to patients at low risk of developing PAD without HFpEF (Non-PAD/Non-HFpEF group), those categorized as having a high risk of developing PAD with HFpEF (PAD/HFpEF group) exhibited the most impaired GLS and a heightened susceptibility to heart failure hospitalization (hazard ratio, HR: 6.51; 95% CI: 4.43-9.55), a twofold increased risk of all-cause mortality (HR: 2.01; 95% CI: 1.17-3.38), cardiovascular mortality (HR: 2.44; 95% CI: 1.08-5.51), and non-cardiovascular mortality (HR: 1.78; 95% CI: 0.82-3.84). A high risk of developing PAD was strongly linked to impaired preclinical systolic function and an increased likelihood for subsequent hospitalization for HF, all-cause mortality, CV mortality and non-CV mortality. There is a clear need for preventive strategies aimed at reducing hospitalizations for HF and mortality in this high-risk population.

NGCN: Drug-target interaction prediction by integrating information and feature learning from heterogeneous network.

Drug-target interaction (DTI) prediction is essential for new drug design and development. Constructing heterogeneous network based on diverse information about drugs, proteins and diseases provides new opportunities for DTI prediction. However, the inherent complexity, high dimensionality and noise of such a network prevent us from taking full advantage of these network characteristics. This article proposes a novel method, NGCN, to predict drug-target interactions from an integrated heterogeneous network, from which to extract relevant biological properties and association information while maintaining the topology information. It focuses on learning the topology representation of drugs and targets to improve the performance of DTI prediction. Unlike traditional methods, it focuses on learning the low-dimensional topology representation of drugs and targets via graph-based convolutional neural network. NGCN achieves substantial performance improvements over other state-of-the-art methods, such as a nearly 1.0% increase in AUPR value. Moreover, we verify the robustness of NGCN through benchmark tests, and the experimental results demonstrate it is an extensible framework capable of combining heterogeneous information for DTI prediction.

Natural Herbal Compounds Exerting an Antidepressant Effect through Hypothalamic-Pituitary-Adrenal Axis Regulation.

Depression is a common mental illness that damages the life and health of patients and causes economic burden, and HPA (hypothalamic-pituitary-adrenal) axis dysfunction is considered to be one of the important factors leading to depression. In this case, it is essential to explore possible treatment methods by using natural compounds with HPA axis regulating and antidepressant effects. However, no one has reviewed it so far. Therefore, the purpose of this review is to systematically sort out the related natural products that play an antidepressant role by regulating the function of the HPA axis. Natural products are divided into flavonoids, polyphenols, terpenoids, saponins, polysaccharides and so on according to their chemical structures, which play a variety of biological activities such as regulating the HPA axis, anti-inflammation and neuroprotection. These effects may provide a useful reference for the potential treatment of depression so as to develop new antidepressants.