Bridging the Diagnostic Gap between Histopathologic and Hysteroscopic Chronic Endometritis with Deep Learning Models.

Chronic endometritis (CE) is an inflammatory pathologic condition of the uterine mucosa characterized by unusual infiltration of CD138(+) endometrial stromal plasmacytes (ESPCs). CE is often identified in infertile women with unexplained etiology, tubal factors, endometriosis, repeated implantation failure, and recurrent pregnancy loss. Diagnosis of CE has traditionally relied on endometrial biopsy and histopathologic/immunohistochemistrical detection of ESPCs. Endometrial biopsy, however, is a somewhat painful procedure for the subjects and does not allow us to grasp the whole picture of this mucosal tissue. Meanwhile, fluid hysteroscopy has been recently adopted as a less-invasive diagnostic modality for CE. We launched the ARCHIPELAGO (ARChival Hysteroscopic Image-based Prediction for histopathologic chronic Endometritis in infertile women using deep LeArninG mOdel) study to construct the hysteroscopic CE finding-based prediction tools for histopathologic CE. The development of these deep learning-based novel models and computer-aided detection/diagnosis systems potentially benefits infertile women suffering from this elusive disease.

Elucidation of Anti-Obesity Mechanisms of Phenolics in Artemisiae argyi Folium (Aiye) by Integrating LC-MS, Network Pharmacology, and Molecular Docking.

The global prevalence of obesity is a pressing health issue, increasing the medical burden and posing significant health risks to humans. The side effects and complications associated with conventional medication and surgery have spurred the search for anti-obesity drugs from plant resources. Previous studies have suggested that Artemisiae argyi Folium (Aiye) water extracts could inhibit pancreatic lipase activities, control body weight increase, and improve the plasma lipids profile. However, the exact components and mechanisms were not precisely understood. Therefore, this research aims to identify the chemical profile of Aiye and provide a comprehensive prediction of its anti-obesity mechanisms. The water extract of Aiye was subjected to LC-MS analysis, which identified 30 phenolics. The anti-obesity mechanisms of these phenolics were then predicted, employing network pharmacology and molecular docking. Among the 30 phenolics, 21 passed the drug-likeness screening and exhibited 486 anti-obesity targets. The enrichment analysis revealed that these phenolics may combat obesity through PI3K-Akt signaling and MAPK, prolactin, and cAMP signaling pathways. Eight phenolics and seven central targets were selected for molecular docking, and 45 out of 56 docking had a binding affinity of less than -5 kcal/mol. This research has indicated the potential therapy targets and signaling pathways of Aiye in combating obesity.

Predictive Prognostic Factors in Non-Calcific Supraspinatus Tendinopathy Treated with Focused Extracorporeal Shock Wave Therapy: An Artificial Neural Network Approach.

The supraspinatus tendon is one of the most involved tendons in the development of shoulder pain. Extracorporeal shockwave therapy (ESWT) has been recognized as a valid and safe treatment. Sometimes the symptoms cannot be relieved, or a relapse develops, affecting the patient's quality of life. Therefore, a prediction protocol could be a powerful tool aiding our clinical decisions. An artificial neural network was run, in particular a multilayer perceptron model incorporating input information such as the VAS and Constant-Murley score, administered at T0 and at T1 after six months. It showed a model sensitivity of 80.7%, and the area under the ROC curve was 0.701, which demonstrates good discrimination. The aim of our study was to identify predictive factors for minimal clinically successful therapy (MCST), defined as a reduction of ≥40% in VAS score at T1 following ESWT for chronic non-calcific supraspinatus tendinopathy (SNCCT). From the male gender, we expect greater and more frequent clinical success. The more severe the patient's initial condition, the greater the possibility that clinical success will decrease. The Constant and Murley score, Roles and Maudsley score, and VAS are not just evaluation tools to verify an improvement; they are also prognostic factors to be taken into consideration in the assessment of achieving clinical success. Due to the lower clinical improvement observed in older patients and those with worse clinical and functional scales, it would be preferable to also provide these patients with the possibility of combined treatments. The ANN predictive model is reasonable and accurate in studying the influence of prognostic factors and achieving clinical success in patients with chronic non-calcific tendinopathy of the supraspinatus treated with ESWT.

Generative Adversarial Networks (GANs) in the Field of Head and Neck Surgery: Current Evidence and Prospects for the Future-A Systematic Review.

Background: Generative Adversarial Networks (GANs) are a class of artificial neural networks capable of generating content such as images, text, and sound. For several years already, artificial intelligence algorithms have shown promise as tools in the medical field, particularly in oncology. Generative Adversarial Networks (GANs) represent a new frontier of innovation, as they are revolutionizing artificial content generation, opening opportunities in artificial intelligence and deep learning. Purpose: This systematic review aims to investigate what the stage of development of such technology is in the field of head and neck surgery, offering a general overview of the applications of such algorithms, how they work, and the potential limitations to be overcome in the future. Methods: The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines were followed in conducting this study, and the PICOS framework was used to formulate the research question. The following databases were evaluated: MEDLINE, Embase, Cochrane Central Register of Controlled Trials (CENTRAL), Scopus, ClinicalTrials.gov, ScienceDirect, and CINAHL. Results: Out of 700 studies, only 9 were included. Eight applications of GANs in the head and neck region were summarized, including the classification of craniosynostosis, recognition of the presence of chronic sinusitis, diagnosis of radicular cysts in panoramic X-rays, segmentation of craniomaxillofacial bones, reconstruction of bone defects, removal of metal artifacts from CT scans, prediction of the postoperative face, and improvement of the resolution of panoramic X-rays. Conclusions: Generative Adversarial Networks may represent a new evolutionary step in the study of pathology, oncological and otherwise, making the approach to the disease much more precise and personalized.

Bioactive Phyto-Compounds with Antimicrobial Effects and AI: Results of a Desk Research Study.

Resistance of microorganisms to antibiotics represents a formidable global challenge, manifesting in intricate public health ramifications including escalated mortality rates and augmented healthcare costs. The current efforts to manage antimicrobial resistance (AMR) are limited mainly to the standard therapeutic approaches. The aim of this study is to present and analyze the role of artificial intelligence (AI) in the search for new phyto-compounds and novel interactions with antimicrobial effects. The ambition of the current research study is to support researchers by providing summarized information and ideas for future research in the battle with AMR. Inevitably, the AI role in healthcare is growing exponentially. The reviewed AI models reveal new data on essential oils (EOs) as potential therapeutic agents. In terms of antibacterial activity, EOs show activity against MDR bacteria, reduce resistance by sensitizing bacteria to the action of antibiotics, and improve therapeutic efficiency when combined with antibiotics. AI models can also serve for the detailed study of other therapeutic applications of EOs such as respiratory diseases, immune diseases, neurodegenerative diseases, and oncological diseases. The last 5 years have seen an increasing application of AI in the search for potential plant sources to control AMR. For the time being, the application of machine-learning (ML) models is greater in the studies of EOs. Future attention of research teams may also be directed toward a more efficient search for plant antimicrobial peptides (PAMPs). Of course, investments in this direction are a necessary preface, but the excitement of new possibilities should not override the role of human intelligence in directing research processes. In this report, tradition meets innovation to address the "silent pandemic" of AMR.

Bidirectional Optical Neural Networks Based on Free-Space Optics Using Lens Arrays and Spatial Light Modulator.

This paper introduces a novel architecture-bidirectional optical neural network (BONN)-for providing backward connections alongside forward connections in artificial neural networks (ANNs). BONN incorporates laser diodes and photodiodes and exploits the properties of Köhler illumination to establish optical channels for backward directions. Thus, it has bidirectional functionality that is crucial for algorithms such as the backpropagation algorithm. BONN has a scaling limit of 96 × 96 for input and output arrays, and a throughput of 8.5 × 1015 MAC/s. While BONN's throughput may rise with additional layers for continuous input, limitations emerge in the backpropagation algorithm, as its throughput does not scale with layer count. The successful BONN-based implementation of the backpropagation algorithm requires the development of a fast spatial light modulator to accommodate frequent data flow changes. A two-mirror-like BONN and its cascaded extension are alternatives for multilayer emulation, and they help save hardware space and increase the parallel throughput for inference. An investigation into the application of the clustering technique to BONN revealed its potential to help overcome scaling limits and to provide full interconnections for backward directions between doubled input and output ports. BONN's bidirectional nature holds promise for enhancing supervised learning in ANNs and increasing hardware compactness.

The Profile of Network Spontaneous Activity and Functional Organization Interplay in Hierarchically Connected Modular Neural Networks In Vitro.

Modern microtechnology methods are widely used to create neural networks on a chip with a connection architecture demonstrating properties of modularity and hierarchy similar to brain networks. Such in vitro networks serve as a valuable model for studying the interplay of functional architecture within modules, their activity, and the effectiveness of inter-module interaction. In this study, we use a two-chamber microfluidic platform to investigate functional connectivity and global activity in hierarchically connected modular neural networks. We found that the strength of functional connections within the module and the profile of network spontaneous activity determine the effectiveness of inter-modular interaction and integration activity in the network. The direction of intermodular activity propagation configures the different densities of inhibitory synapses in the network. The developed microfluidic platform holds the potential to explore function-structure relationships and efficient information processing in two- or multilayer neural networks, in both healthy and pathological states.

Combined Control for a Piezoelectric Actuator Using a Feed-Forward Neural Network and Feedback Integral Fast Terminal Sliding Mode Control.

In recent years, there has been significant interest in incorporating micro-actuators into industrial environments; this interest is driven by advancements in fabrication methods. Piezoelectric actuators (PEAs) have emerged as vital components in various applications that require precise control and manipulation of mechanical systems. These actuators play a crucial role in the micro-positioning systems utilized in nanotechnology, microscopy, and semiconductor manufacturing; they enable extremely fine movements and adjustments and contribute to vibration control systems. More specifically, they are frequently used in precision positioning systems for optical components, mirrors, and lenses, and they enhance the accuracy of laser systems, telescopes, and image stabilization devices. Despite their numerous advantages, PEAs exhibit complex dynamics characterized by phenomena such as hysteresis, which can significantly impact accuracy and performance. The characterization of these non-linearities remains a challenge for PEA modeling. Recurrent artificial neural networks (ANNs) may simplify the modeling of the hysteresis dynamics for feed-forward compensation. To address these challenges, robust control strategies such as integral fast terminal sliding mode control (IFTSMC) have been proposed. Unlike traditional fast terminal sliding mode control methods, IFTSMC includes integral action to minimize steady-state errors, improving the tracking accuracy and disturbance rejection capabilities. However, accurate modeling of the non-linear dynamics of PEAs remains a challenge. In this study, we propose an ANN-based IFTSMC controller to address this issue and to enhance the precision and reliability of PEA positioning systems. We implement and validate the proposed controller in a real-time setup and compare its performance with that of a PID controller. The results obtained from real PEA experiments demonstrate the stability of the novel control structure, as corroborated by the theoretical analysis. Furthermore, experimental validation reveals a notable reduction in error compared to the PID controller.

Maize Leaf Disease Recognition Based on Improved Convolutional Neural Network ShuffleNetV2.

The occurrence of maize diseases is frequent but challenging to manage. Traditional identification methods have low accuracy and complex model structures with numerous parameters, making them difficult to implement on mobile devices. To address these challenges, this paper proposes a corn leaf disease recognition model SNMPF based on convolutional neural network ShuffleNetV2. In the down-sampling module of the ShuffleNet model, the max pooling layer replaces the deep convolutional layer to perform down-sampling. This improvement helps to extract key features from images, reduce the overfitting of the model, and improve the model's generalization ability. In addition, to enhance the model's ability to express features in complex backgrounds, the Sim AM attention mechanism was introduced. This mechanism enables the model to adaptively adjust focus and pay more attention to local discriminative features. The results on a maize disease image dataset demonstrate that the SNMPF model achieves a recognition accuracy of 98.40%, representing a 4.1 percentage point improvement over the original model, while its size is only 1.56 MB. Compared with existing convolutional neural network models such as EfficientNet, MobileViT, EfficientNetV2, RegNet, and DenseNet, this model offers higher accuracy and a more compact size. As a result, it can automatically detect and classify maize leaf diseases under natural field conditions, boasting high-precision recognition capabilities. Its accurate identification results provide scientific guidance for preventing corn leaf disease and promote the development of precision agriculture.

Implementation and Evaluation of Spatial Attention Mechanism in Apricot Disease Detection Using Adaptive Sampling Latent Variable Network.

In this study, an advanced method for apricot tree disease detection is proposed that integrates deep learning technologies with various data augmentation strategies to significantly enhance the accuracy and efficiency of disease detection. A comprehensive framework based on the adaptive sampling latent variable network (ASLVN) and the spatial state attention mechanism was developed with the aim of enhancing the model's capability to capture characteristics of apricot tree diseases while ensuring its applicability on edge devices through model lightweighting techniques. Experimental results demonstrated significant improvements in precision, recall, accuracy, and mean average precision (mAP). Specifically, precision was 0.92, recall was 0.89, accuracy was 0.90, and mAP was 0.91, surpassing traditional models such as YOLOv5, YOLOv8, RetinaNet, EfficientDet, and DEtection TRansformer (DETR). Furthermore, through ablation studies, the critical roles of ASLVN and the spatial state attention mechanism in enhancing detection performance were validated. These experiments not only showcased the contributions of each component for improving model performance but also highlighted the method's capability to address the challenges of apricot tree disease detection in complex environments. Eight types of apricot tree diseases were detected, including Powdery Mildew and Brown Rot, representing a technological breakthrough. The findings provide robust technical support for disease management in actual agricultural production and offer broad application prospects.

Based on Network Pharmacology and Molecular Docking, the Active Components, Targets, and Mechanisms of Flemingia philippinensis in Improving Inflammation Were Excavated.

Flemingia philippinensis, a polyphenol-rich plant, holds potential for improving inflammation, but its mechanisms are not well understood. Therefore, this study employed network pharmacology and molecular docking to explore the mechanism by which Flemingia philippinensis ameliorates inflammation. In this study, 29 kinds of active ingredients were obtained via data mining. Five main active components were screened out for improving inflammation, which were flemichin D, naringenin, chrysophanol, genistein and orobol. In total, 52 core targets were identified, including AKT serine/threonine kinase 1 (AKT1), tumor necrosis factor (TNF), B-cell lymphoma-2 (BCL2), serum albumin (ALB), and estrogen receptor 1 (ESR1). Gene ontology (GO) enrichment analysis identified 2331 entries related to biological processes, 98 entries associated with cellular components, and 203 entries linked to molecular functions. Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analysis yielded 149 pathways, including those involved in EGFR tyrosine kinase inhibitor resistance, endocrine resistance, and the PI3K-Akt signaling pathway. Molecular docking results showed strong binding effects between the main active components and the core targets, with binding energies less than -5 kcal/mol. In summary, this study preliminarily elucidated the underlying mechanisms by which Flemingia philippinensis, through a multi-component, multi-target, and multi-pathway approach, ameliorates inflammation. This provides a theoretical foundation for the subsequent application of Flemingia philippinensis in inflammation amelioration.

Bioactive Compounds in Citrus reticulata Peel Are Potential Candidates for Alleviating Physical Fatigue through a Triad Approach of Network Pharmacology, Molecular Docking, and Molecular Dynamics Modeling.

Physical fatigue (peripheral fatigue), which affects a considerable portion of the world population, is a decline in the ability of muscle fibers to contract effectively due to alterations in the regulatory processes of muscle action potentials. However, it lacks an efficacious therapeutic intervention. The present study explored bioactive compounds and the mechanism of action of Citrus reticulata peel (CR-P) in treating physical fatigue by utilizing network pharmacology (NP), molecular docking, and simulation-based molecular dynamics (MD). The bioactive ingredients of CR-P and prospective targets of CR-P and physical fatigue were obtained from various databases. A PPI network was generated by the STRING database, while the key overlapping targets were analyzed for enrichment by adopting KEGG and GO. The binding affinities of bioactive ingredients to the hub targets were determined by molecular docking. The results were further validated by MD simulation. Five bioactive compounds were screened, and 56 key overlapping targets were identified for CR-P and physical fatigue, whereas the hub targets with a greater degree in the PPI network were AKT1, TP53, STAT3, MTOR, KRAS, HRAS, JAK2, IL6, EGFR, and ESR1. The findings of the enrichment analysis indicated significant enrichment of the targets in three key signaling pathways, namely PI3K-AKT, MAPK, and JAK-STAT. The molecular docking and MD simulation results revealed that the bioactive compounds of CR-P exhibit a stronger affinity for interacting with the hub targets. The present work suggests that bioactive compounds of CR-P, specifically Hesperetin and Sitosterol, may ameliorate physical fatigue via the PI3K-AKT signaling pathway by targeting AKT1, KRAS, and MTOR proteins.

Comparative Efficacy and Safety of Potassium-Competitive Acid Blockers vs. Proton Pump Inhibitors for Peptic Ulcer with or without Helicobacter pylori Infection: A Systematic Review and Network Meta-Analysis.

Novel potassium-competitive acid blockers (P-CABs) have emerged as effective acid-suppressive drugs in recent years, replacing proton pump inhibitors (PPIs). We aim to compare the efficacy and safety of P-CABs versus PPIs in the treatment of peptic ulcers with or without Helicobacter pylori (H. pylori) infection. We searched in PubMed, Embase, WOS, Cochrane Library, ClinicalTrials.gov, CNKI, and Wanfang databases (all years up to January 2024). Efficacy and safety outcomes were evaluated using odds ratio (OR) and 95% confidence intervals (CI). The Surface Under the Cumulative Ranking (SUCRA) probabilities were used to rank each intervention. Among 14,056 studies screened, 56 studies involving 9792 participants were analyzed. Vonoprazan demonstrated the best efficacy in ulcer healing rate and H. pylori eradication rate (SUCRA = 86.4% and 90.7%, respectively). Keverprazan ranked second in ulcer healing rates (SUCRA = 76.0%) and was more effective in pain remission rates (SUCRA = 91.7%). The risk of adverse events was low for keverprazan (SUCRA = 11.8%) and tegoprazan (SUCRA = 12.9%), and moderate risk for vonoprazan (SUCRA = 44.3%) was demonstrated. Compared to lansoprazole, vonoprazan exhibited a higher risk of drug-related adverse events (OR: 2.15; 95% CI: 1.60-2.89) and serious adverse events (OR: 2.22; 95% CI: 1.11-4.42). Subgroup analysis on patients with H. pylori-positive peptic ulcers showed that vonoprazan was at the top of the SUCRA rankings, followed by keverprazan. Vonoprazan showed superior performance in peptic ulcers, especially for patients with H. pylori-positive peptic ulcers. However, the risk of adverse events associated with vonoprazan should be noted. Keverprazan has also shown good therapeutic outcomes and has performed better in terms of safety.

The Bioactive Compounds of Epimedium and Their Potential Mechanism of Action in Treating Osteoporosis: A Network Pharmacology and Experimental Validation Study.

Osteoporosis is a global health challenge characterized by bone loss and microstructure deterioration, which urgently requires the development of safer and more effective treatments due to the significant adverse effects and limitations of existing drugs for long-term treatment. Traditional Chinese medicine, like Epimedium, offers fewer side effects and has been used to treat osteoporosis, yet its active compounds and pharmacological mechanisms remain unclear. In this study, 65 potential active compounds, 258 potential target proteins, and 488 pathways of Epimedium were identified through network pharmacology analysis. Further network analysis and review of the literature identified six potential active compounds and HIF-1α for subsequent experimental validation. In vitro experiments confirmed that 2″-O-RhamnosylIcariside II is the most effective compound among the six potential active compounds. It can promote osteoblast differentiation, bind with HIF-1α, and inhibit both HIF-1α gene and protein expression, as well as enhance COL1A1 protein expression under hypoxic conditions. In vivo experiments demonstrated its ability to improve bone microstructures and reduce bone loss by decreasing bone marrow adipose tissue, enhancing bone formation, and suppressing HIF-1α protein expression. This study is the first to describe the therapeutic effects of 2-O-RhamnosylIcariside II on osteoporosis, which was done, specifically, through a mechanism that targets and inhibits HIF-1α. This study provides a scientific basis for the clinical application of Epimedium and offers a new candidate drug for the treatment of osteoporosis. Additionally, it provides new evidence supporting HIF-1α as a therapeutic target for osteoporosis.

Exploring the Underlying Mechanisms of Qingxing Granules Treating H1N1 Influenza Based on Network Pharmacology and Experimental Validation.

BACKGROUND: H1N1 is one of the major subtypes of influenza A virus (IAV) that causes seasonal influenza, posing a serious threat to human health. A traditional Chinese medicine combination called Qingxing granules (QX) is utilized clinically to treat epidemic influenza. However, its chemical components are complex, and the potential pharmacological mechanisms are still unknown. METHODS: QX's effective components were gathered from the TCMSP database based on two criteria: drug-likeness (DL ≥ 0.18) and oral bioavailability (OB ≥ 30%). SwissADME was used to predict potential targets of effective components, and Cytoscape was used to create a "Herb-Component-Target" network for QX. In addition, targets associated with H1N1 were gathered from the databases GeneCards, OMIM, and GEO. Targets associated with autophagy were retrieved from the KEGG, HAMdb, and HADb databases. Intersection targets for QX, H1N1 influenza, and autophagy were identified using Venn diagrams. Afterward, key targets were screened using Cytoscape's protein-protein interaction networks built using the database STRING. Biological functions and signaling pathways of overlapping targets were observed through GO analysis and KEGG enrichment analysis. The main chemical components of QX were determined by high-performance liquid chromatography (HPLC), followed by molecular docking. Finally, the mechanism of QX in treating H1N1 was validated through animal experiments. RESULTS: A total of 786 potential targets and 91 effective components of QX were identified. There were 5420 targets related to H1N1 and 821 autophagy-related targets. The intersection of all targets of QX, H1N1, and autophagy yielded 75 intersecting targets. Ultimately, 10 core targets were selected: BCL2, CASP3, NFKB1, MTOR, JUN, TNF, HSP90AA1, EGFR, HIF1A, and MAPK3. Identification of the main chemical components of QX by HPLC resulted in the separation of seven marker ingredients within 195 min, which are amygdalin, puerarin, baicalin, phillyrin, wogonoside, baicalein, and wogonin. Molecular docking results showed that BCL2, CASP3, NFKB1, and MTOR could bind well with the compounds. In animal studies, QX reduced the degenerative alterations in the lung tissue of H1N1-infected mice by upregulating the expression of p-mTOR/mTOR and p62 and downregulating the expression of LC3, which inhibited autophagy. CONCLUSIONS: According to this study's network pharmacology analysis and experimental confirmation, QX may be able to treat H1N1 infection by regulating autophagy, lowering the expression of LC3, and increasing the expression of p62 and p-mTOR/mTOR.

Remapping the Chemical Space and the Pharmacological Space of Drugs: What Can We Expect from the Road Ahead?

This work examines the current landscape of drug discovery and development, with a particular focus on the chemical and pharmacological spaces. It emphasizes the importance of understanding these spaces to anticipate future trends in drug discovery. The use of cheminformatics and data analysis enabled in silico exploration of these spaces, allowing a perspective of drugs, approved drugs after 2020, and clinical candidates, which were extracted from the newly released ChEMBL34 (March 2024). This perspective on chemical and pharmacological spaces enables the identification of trends and areas to be occupied, thereby creating opportunities for more effective and targeted drug discovery and development strategies in the future.

In Vitro and Randomized Controlled Clinical Study of Natural Constituents' Anti-HPV Potential for Treatment of Plantar Warts Supported with In Silico Studies and Network Analysis.

The aim of this study is to evaluate the anti-HPV potential of a Moringa olifera Lam seed, Nigella sativa L. seed, and Musa Acuminata peel herbal mixture in the form of polymer film-forming systems. A clinical trial conducted in outpatient clinics showed that the most significant outcome was wart size and quantity. Compared to the placebo group, the intervention group's size and number of warts were considerably better according to the results. Chemical profiling assisted by LC-HRMS led to the dereplication of 49 metabolites. Furthermore, network pharmacology was established for the mixture of three plants; each plant was studied separately to find out the annotated target genes, and then, we combined all annotated genes of all plants and filtered the genes to specify the genes related to human papilloma virus. In a backward step, the 24 configured genes related to HPV were used to specify only 30 compounds involved in HPV infection based on target genes. CA2 and EGFR were the top identified genes with 16 and 12 edges followed by PTGS2, CA9, and MMP9 genes with 11 edges each. A molecular docking study for the top active identified compounds of each species was conducted in the top target HPV genes, CA2 and EGFR, to investigate the mode of interaction between these compounds and the targets' active sites.

Jingzhi Guanxin Oral Liquids Attenuate Atherosclerotic Coronary Heart Disease via Modulating Lipid Metabolism and PPAR-Related Targets.

Jingzhi Guanxin Oral Liquids (JZGX), a traditional Chinese medicine formulation prepared from the decoction of five herbs, has been utilized to relieve chest pain with coronary artery disease (CAD). However, the chemical composition and therapeutic mechanisms of JZGX remain obscured. In this research, the potential targets and pathways of JZGX against CAD were anticipated through network pharmacology based on analyzing its chemical constituents using UPLC-Q-TOF-MS/MS. One hundred seven ingredients in JZGX were identified. The 39 active chemicals and 37 key targets were screened, and CAD-related signaling pathways were clustered, mainly associated with lipid metabolism. Subsequently, the atherosclerotic CAD animal model employing 24 weeks of high-fat diet (HFD) ApoE-/- mice was constructed to investigate the JZGX efficacy and underlying mechanisms validating network forecasts. The histological staining examination and cardiovascular biomarker tests confirmed that JZGX reduced plaque formation in the aorta and decreased blood lipids in vivo. It featured anti-inflammatory, anti-thrombotic, and myocardial protective effects. JZGX prevented excessive lipid deposits and inflammation within the liver and exhibited hepatoprotective properties. Serum untargeted metabolomics analysis indicated that JZGX ameliorated metabolic abnormalities in atherosclerotic CAD mice and prompted lipid metabolism, especially linoleic acid. The PPARs and attached critical targets (SREBP1, FASN, PTGS2, and CYP3A), filtered from the networks and connected with lipid metabolism, were dramatically modulated through JZGX administration, as revealed by western blotting. The molecular docking outcomes showed that all 39 active ingredients in JZGX had good binding activity with PPARα and PPARγ. These findings illustrate that JZGX alleviates atherosclerotic CAD progression by remodeling the lipid metabolism and regulating PPAR-related proteins.

A Method for Predicting Inertial Navigation System Positioning Errors Using a Back Propagation Neural Network Based on a Particle Swarm Optimization Algorithm.

In order to reduce the position errors of the Global Positioning System/Strapdown Inertial Navigation System (GPS/SINS) integrated navigation system during GPS denial, this paper proposes a method based on the Particle Swarm Optimization-Back Propagation Neural Network (PSO-BPNN) to replace the GPS for positioning. The model relates the position information, velocity information, attitude information output by the SINS, and the navigation time to the position errors between the position information output by the SINS and the actual position information. The performance of the model is compared with the BPNN through an actual ship experiment. The results show that the PSO-BPNN can obviously reduce the position errors in the case of GPS signal denial.

Efficient Haze Removal from a Single Image Using a DCP-Based Lightweight U-Net Neural Network Model.

In this paper, we propose a lightweight U-net architecture neural network model based on Dark Channel Prior (DCP) for efficient haze (fog) removal with a single input. The existing DCP requires high computational complexity in its operation. These computations are challenging to accelerate, and the problem is exacerbated when dealing with high-resolution images (videos), making it very difficult to apply to general-purpose applications. Our proposed model addresses this issue by employing a two-stage neural network structure, replacing the computationally complex operations of the conventional DCP with easily accelerated convolution operations to achieve high-quality fog removal. Furthermore, our proposed model is designed with an intuitive structure using a relatively small number of parameters (2M), utilizing resources efficiently. These features demonstrate the effectiveness and efficiency of the proposed model for fog removal. The experimental results show that the proposed neural network model achieves an average Peak Signal-to-Noise Ratio (PSNR) of 26.65 dB and a Structural Similarity Index Measure (SSIM) of 0.88, indicating an improvement in the average PSNR of 11.5 dB and in SSIM of 0.22 compared to the conventional DCP. This shows that the proposed neural network achieves comparable results to CNN-based neural networks that have achieved SOTA-class performance, despite its intuitive structure with a relatively small number of parameters.