The Kinase IKKß Regulates a STING- and NF-κB-Dependent Antiviral Response Pathway in Drosophila.

Antiviral immunity in Drosophila involves RNA interference and poorly characterized inducible responses. Here, we showed that two components of the IMD pathway, the kinase dIKKß and the transcription factor Relish, were required to control infection by two picorna-like viruses. We identified a set of genes induced by viral infection and regulated by dIKKß and Relish, which included an ortholog of STING. We showed that dSTING participated in the control of infection by picorna-like viruses, acting upstream of dIKKß to regulate expression of Nazo, an antiviral factor. Our data reveal an antiviral function for STING in an animal model devoid of interferons and suggest an evolutionarily ancient role for this molecule in antiviral immunity.

CHP1 Regulates Compartmentalized Glycerolipid Synthesis by Activating GPAT4.

Cells require a constant supply of fatty acids to survive and proliferate. Fatty acids incorporate into membrane and storage glycerolipids through a series of endoplasmic reticulum (ER) enzymes, but how these enzymes are regulated is not well understood. Here, using a combination of CRISPR-based genetic screens and unbiased lipidomics, we identified calcineurin B homologous protein 1 (CHP1) as a major regulator of ER glycerolipid synthesis. Loss of CHP1 severely reduces fatty acid incorporation and storage in mammalian cells and invertebrates. Mechanistically, CHP1 binds and activates GPAT4, which catalyzes the initial rate-limiting step in glycerolipid synthesis. GPAT4 activity requires CHP1 to be N-myristoylated, forming a key molecular interface between the two proteins. Interestingly, upon CHP1 loss, the peroxisomal enzyme, GNPAT, partially compensates for the loss of ER lipid synthesis, enabling cell proliferation. Thus, our work identifies a conserved regulator of glycerolipid metabolism and reveals plasticity in lipid synthesis of proliferating cells.

Chemical Proteomics Reveals Nε-Fatty-Acylation of Septins by Rho Inactivation Domain (RID) of the Vibrio MARTX Toxin to Alter Septin Localization and Organization.

Vibrio species, the Gram-negative bacterial pathogens causing cholera and sepsis, produce multiple secreted virulence factors for infection and pathogenesis. Among these is the multifunctional-autoprocessing repeats-in-toxin (MARTX) toxin that releases several critical effector domains with distinct functions inside eukaryotic host cells. One such effector domain, the Rho inactivation domain (RID), has been discovered to catalyze long-chain Nε-fatty-acylation on lysine residues of Rho GTPases, causing inactivation of Rho GTPases and disruption of the host actin cytoskeleton. However, whether RID modifies other host proteins to exert additional functions remains to be determined. Herein, we describe the integration of bioorthogonal chemical labeling and quantitative proteomics to globally profile the target proteins modified by RID in living cells. More than 246 proteins are identified as new RID substrates, including many involved in GTPase regulation, cytoskeletal organization, and cell division. We demonstrate that RID extensively Nε-fatty-acylates septin proteins, the fourth cytoskeletal component of mammalian cells with important roles in diverse cellular processes. While affinity purification and mass spectrometry analysis show that RID-mediated Nε-fatty-acylation does not affect septin-septin interactions, this modification increases the membrane association of septins and confers localization to detergent-resistant membrane rafts. As a result, the filamentous assembly and organization of septins are disrupted by RID-mediated Nε-fatty-acylation, further contributing to cytoskeletal and mitotic defects that phenocopy the effects of septin depletion. Overall, our work greatly expands the substrate scope and function of RID and demonstrates the role of RID-mediated Nε-fatty-acylation in manipulating septin localization and organization.

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.

Rice kinase OsMRLK63 contributes to drought tolerance by regulating reactive oxygen species production.

Drought is a major adverse environmental factor that plants face in nature but the molecular mechanism by which plants transduce stress signals and further endow themselves with tolerance remains unclear. Malectin/malectin-like domains containing receptor-like kinases (MRLKs) have been proposed to act as receptors in multiple biological signaling pathways, but limited studies show their roles in drought-stress signaling and tolerance. In this study, we demonstrate OsMRLK63 in rice (Oryza sativa L.) functions in drought tolerance by acting as the receptor of 2 rapid alkalization factors, OsRALF45 and OsRALF46. We show OsMRLK63 is a typical receptor-like kinase that positively regulates drought tolerance and reactive oxygen species (ROS) production. OsMRLK63 interacts with and phosphorylates several nicotinamide adenine dinucleotide phosphate (NADPH) oxidases with the primarily phosphorylated site at Ser26 in the N-terminal of RESPIRATORY BURST OXIDASE HOMOLOGUE A (OsRbohA). The application of the 2 small signal peptides (OsRALF45/46) on rice can greatly alleviate the dehydration of plants induced by mimic drought. This function depends on the existence of OsMRLK63 and the NADPH oxidase-dependent ROS production. The 2 RALFs interact with OsMRLK63 by binding to its extracellular domain, suggesting they may act as drought/dehydration signal sensors for the OsMRLK63-mediated process. Our study reveals a OsRALF45/46-OsMRLK63-OsRbohs module which contributes to drought-stress signaling and tolerance in rice.

Tolerogenic CD11c+dendritic cells regulate CD4+Tregs in replacing delayed ischemic preconditioning to alleviate ischemia-reperfusion acute kidney injury.

Ischemia-reperfusion injury (IRI) is one of the primary clinical causes of acute kidney injury (AKI). The key to IRI lies in immune-inflammatory damage, where dendritic cells (DCs) play a central role in eliciting immune responses within the context of inflammation induced by ischemia-reperfusion. Our previous study has confirmed that delayed ischemic preconditioning (DIPC) can reduce the kidney injury by mediating DCs to regulate T-cells. However, the clinical feasibility of DIPC is limited, as pre-clamping of the renal artery is not applicable for the prevention and treatment of ischemia-reperfusion acute kidney injury (I/R-AKI) in clinical patients. Therefore, the infusion of DCs as a substitute for DIPC presents a more viable strategy for preventing renal IRI. In this study, we further evaluated the impact and mechanism of infused tolerogenic CD11c+DCs on the kidneys following IRI by isolating bone marrow-derived dendritic cells and establishing an I/R-AKI model after pre-infusion of DCs. Renal function was significantly improved in the I/R-AKI mouse model after pre-infused with CD11c+DCs. The pro-inflammatory response and oxidative damage were reduced, and the levels of T helper 2 (Th2) cells and related anti-inflammatory cytokines were increased, which was associated with the reduction of autologous DCs maturation mediated by CD11c+DCs and the increase of regulatory T-cells (Tregs). Next, knocking out CD11c+DCs, we found that the reduced immune protection of tolerogenic CD11c+DCs reinfusion was related to the absence of own DCs. Together, pre-infusion of tolerogenic CD11c+DCs can replace the regulatory of DIPC on DCs and T-cells to alleviate I/R-AKI. DC vaccine is expected to be a novel avenue to prevent and treat I/R-AKI.

Epstein-Barr virus envelope glycoprotein 110 inhibits NF-κB activation by interacting with NF-κB subunit p65.

Epstein-Barr virus (EBV) is a member of the lymphotropic virus family and is highly correlated with some human malignant tumors. It has been reported that envelope glycoprotein 110 (gp110) plays an essential role in viral fusion, DNA replication, and nucleocapsid assembly of EBV. However, it has not been established whether gp110 is involved in regulating the host's innate immunity. In this study, we found that gp110 inhibits tumor necrosis factor α-mediated NF- κB promoter activity and the downstream production of NF- κB-regulated cytokines under physiological conditions. Using dual-luciferase reporter assays, we showed that gp110 might impede the NF-κB promoter activation downstream of NF-κB transactivational subunit p65. Subsequently, we used coimmunoprecipitation assays to demonstrate that gp110 interacts with p65 during EBV lytic infection, and that the C-terminal cytoplasmic region of gp110 is the key interaction domain with p65. Furthermore, we determined that gp110 can bind to the N-terminal Rel homologous and C-terminal domains of p65. Alternatively, gp110 might not disturb the association of p65 with nontransactivational subunit p50, but we showed it restrains activational phosphorylation (at Ser536) and nuclear translocation of p65, which we also found to be executed by the C-terminal cytoplasmic region of gp110. Altogether, these data suggest that the surface protein gp110 may be a vital component for EBV to antagonize the host's innate immune response, which is also helpful for revealing the infectivity and pathogenesis of EBV.

The systematic identification of survival-related alternative splicing events and splicing factors in glioblastoma.

Glioblastoma multiforme (GBM) is the most common and aggressive primary brain tumor, making it one of the most life-threatening human cancers. Nevertheless, research on the mechanism of action between alternative splicing (AS) and splicing factor (SF) or biomarkers in GBM is limited. AS is a crucial post-transcriptional regulatory mechanism. More than 95% of human genes undergo AS events. AS can diversify the expression patterns of genes, thereby increasing the diversity of proteins and playing a significant role in the occurrence and development of tumors. In this study, we downloaded 599 clinical data and 169 transcriptome analysis data from The Cancer Genome Atlas (TCGA) database. Besides, we collected AS data about GBM from TCGA-SpliceSeq. The overall survival (OS) related AS events in GBM were determined through least absolute shrinkage and selection operator (Lasso) and Cox analysis. Subsequently, the association of these 1825 OS-related AS events with patient survival was validated using the Kaplan-Meier survival analysis, receiver operating characteristic curve, risk curve analysis, and independent prognostic analysis. Finally, we depicted the AS-SF regulatory network, illustrating the interactions between splicing factors and various AS events in GBM. Additionally, we identified three splicing factors (RNU4-1, SEC31B, and CLK1) associated with patient survival. In conclusion, based on AS occurrences, we developed a predictive risk model and constructed an interaction network between GBM-related AS events and SFs, aiming to shed light on the underlying mechanisms of GBM pathogenesis and progression.

A Multifunctional Herb-Derived Glycopeptide Hydrogel for Chronic Wound Healing.

Chronic wounds constitute an increasingly prevalent global healthcare issue, characterized by recurring bacterial infections, pronounced oxidative stress, compromised functionality of immune cells, unrelenting inflammatory reactions, and deficits in angiogenesis. In response to these multifaceted challenges, the study introduced a stimulus-responsive glycopeptide hydrogel constructed by oxidized Bletilla striata polysaccharide (OBSP), gallic acid-grafted ε-Polylysine (PLY-GA), and paeoniflorin-loaded micelles (MIC@Pae), called OBPG&MP. The hydrogel emulates the structure of glycoprotein fibers of the extracellular matrix (ECM), exhibiting exceptional injectability, self-healing, and biocompatibility. It adapts responsively to the inflammatory microenvironment of chronic wounds, sequentially releasing therapeutic agents to eradicate bacterial infection, neutralize reactive oxygen species (ROS), modulate macrophage polarization, suppress inflammation, and encourage vascular regeneration and ECM remodeling, playing a critical role across the inflammatory, proliferative, and remodeling phases of wound healing. Both in vitro and in vivo studies confirmed the efficacy of OBPG&MP hydrogel in regulating the wound microenvironment and enhancing the regeneration and remodeling of chronic wound skin tissue. This research supports the vast potential for herb-derived multifunctional hydrogels in tissue engineering and regenerative medicine.

A study on whether deep learning models based on CT images for bone density classification and prediction can be used for opportunistic osteoporosis screening.

This study utilized deep learning to classify osteoporosis and predict bone density using opportunistic CT scans and independently tested the models on data from different hospitals and equipment. Results showed high accuracy and strong correlation with QCT results, showing promise for expanding osteoporosis screening and reducing unnecessary radiation and costs. PURPOSE: To explore the feasibility of using deep learning to establish a model for osteoporosis classification and bone density value prediction based on opportunistic CT scans and to verify its generalization and diagnostic ability using an independent test set. METHODS: A total of 1219 cases of opportunistic CT scans were included in this study, with QCT results as the reference standard. The training set: test set: independent test set ratio was 703: 176: 340, and the independent test set data of 340 cases were from 3 different hospitals and 4 different CT scanners. The VB-Net structure automatic segmentation model was used to segment the trabecular bone, and DenseNet was used to establish a three-classification model and bone density value prediction regression model. The performance parameters of the models were calculated and evaluated. RESULTS: The ROC curves showed that the mean AUCs of the three-category classification model for categorizing cases into "normal," "osteopenia," and "osteoporosis" for the training set, test set, and independent test set were 0.999, 0.970, and 0.933, respectively. The F1 score, accuracy, precision, recall, precision, and specificity of the test set were 0.903, 0.909, 0.899, 0.908, and 0.956, respectively, and those of the independent test set were 0.798, 0.815, 0.792, 0.81, and 0.899, respectively. The MAEs of the bone density prediction regression model in the training set, test set, and independent test set were 3.15, 6.303, and 10.257, respectively, and the RMSEs were 4.127, 8.561, and 13.507, respectively. The R-squared values were 0.991, 0.962, and 0.878, respectively. The Pearson correlation coefficients were 0.996, 0.981, and 0.94, respectively, and the p values were all < 0.001. The predicted values and bone density values were highly positively correlated, and there was a significant linear relationship. CONCLUSION: Using deep learning neural networks to process opportunistic CT scan images of the body can accurately predict bone density values and perform bone density three-classification diagnosis, which can reduce the radiation risk, economic consumption, and time consumption brought by specialized bone density measurement, expand the scope of osteoporosis screening, and have broad application prospects.

Fabrication of a MXene-based shape-memory hydrogel and its application in the wound repair of skin.

Wound dressings can generally complete hemostasis and provide temporary protection after skin damage. Herein, a MXene-based hydrogel was prepared from MXene, gelatin, poly(ethylene glycol)diacrylate (PEGDA) and N,N'-methylenebis(acrylamide) (HEAA) to prepare wound-dressing hydrogels for skin repair. HEAA and PEGDA crosslink polymerization formed the first layer of the network. Hydrogen bonds between MXene, PHEAA, and gelatin formed the second layer of the network. To make the hydrogel more suitable for skin repair, the mechanical properties of the hybrid hydrogel were adjusted. The MXene-based hydrogel could recover its original shape in 16 s upon immersion in water or for a few minutes under light irradiation. The obtained hydrogel showed good photothermal properties upon light irradiation (808 nm, 1 W cm-2) for 20 s, and its temperature on the surface could reach 86.4 °C. Due to its good photothermal properties, this MXene-based hydrogel was suitable for skin repair.

Establishment of a multi-line immunochromatography based on magnetic nanoparticles for simultaneous screening of multiple biomarkers.

Biomarkers screening is a benefit approach for early diagnosis of major diseases. In this study, magnetic nanoparticles (MNPs) have been utilized as labels to establish a multi-line immunochromatography (MNP-MLIC) for simultaneous detection of carcinoembryonic antigen (CEA), carbohydrate antigen 199 (CA 19-9), and alpha-fetoprotein (AFP) in a single serum sample. Under the optimal parameters, the three biomarkers can be rapidly and simultaneously qualitative screening within 15 min by naked eye. As for quantitative detection, the MNP-MLIC test strips were precisely positioned and captured by a smartphone, and signals on the test and control lines were extracted by ImageJ software. The signal ratio of test and control lines has been calculated and used to plot quantitative standard curves with the logarithmic concentration, of which the correlation coefficients are more than 0.99, and the limit of detection for CEA, CA 19-9, and AFP were 0.60 ng/mL, 1.21 U/mL, and 0.93 ng/mL, respectively. The recoveries of blank serum were 75.0 ~ 112.5% with the relative standard deviation ranging from 2.5 to 15.3%, and the specificity investigation demonstrated that the MNP-MLIC is highly specific to the three biomarkers. In conclusion, the developed MNP-MLIC offers a rapid, simple, accurate, and highly specific method for simultaneously detecting multiple biomarkers in serum samples, which provides an efficient and accurate approach for the early diagnosis of diseases.

Clinical domain knowledge-derived template improves post hoc AI explanations in pneumothorax classification.

OBJECTIVE: Pneumothorax is an acute thoracic disease caused by abnormal air collection between the lungs and chest wall. Recently, artificial intelligence (AI), especially deep learning (DL), has been increasingly employed for automating the diagnostic process of pneumothorax. To address the opaqueness often associated with DL models, explainable artificial intelligence (XAI) methods have been introduced to outline regions related to pneumothorax. However, these explanations sometimes diverge from actual lesion areas, highlighting the need for further improvement. METHOD: We propose a template-guided approach to incorporate the clinical knowledge of pneumothorax into model explanations generated by XAI methods, thereby enhancing the quality of the explanations. Utilizing one lesion delineation created by radiologists, our approach first generates a template that represents potential areas of pneumothorax occurrence. This template is then superimposed on model explanations to filter out extraneous explanations that fall outside the template's boundaries. To validate its efficacy, we carried out a comparative analysis of three XAI methods (Saliency Map, Grad-CAM, and Integrated Gradients) with and without our template guidance when explaining two DL models (VGG-19 and ResNet-50) in two real-world datasets (SIIM-ACR and ChestX-Det). RESULTS: The proposed approach consistently improved baseline XAI methods across twelve benchmark scenarios built on three XAI methods, two DL models, and two datasets. The average incremental percentages, calculated by the performance improvements over the baseline performance, were 97.8% in Intersection over Union (IoU) and 94.1% in Dice Similarity Coefficient (DSC) when comparing model explanations and ground-truth lesion areas. We further visualized baseline and template-guided model explanations on radiographs to showcase the performance of our approach. CONCLUSIONS: In the context of pneumothorax diagnoses, we proposed a template-guided approach for improving model explanations. Our approach not only aligns model explanations more closely with clinical insights but also exhibits extensibility to other thoracic diseases. We anticipate that our template guidance will forge a novel approach to elucidating AI models by integrating clinical domain expertise.

Icariin Regulates EMT and Stem Cell-Like Character in Breast Cancer through Modulating lncRNA NEAT1/TGFß/SMAD2 Signaling Pathway.

Metastases and drug resistance are the major risk factors associated with breast cancer (BC), which is the most common type of tumor affecting females. Icariin (ICA) is a traditional Chinese medicine compound that possesses significant anticancer properties. Long non-coding RNAs (lncRNAs) are involved in a wide variety of biological and pathological processes and have been shown to modulate the effectiveness of certain drugs in cancer. The purpose of this study was to examine the potential effect of ICA on epithelial mesenchymal transition (EMT) and stemness articulation in BC cells, as well as the possible relationship between its inhibitory action on EMT and stemness with the NEAT1/transforming growth factor ß (TGFß)/SMAD2 pathway. The effect of ICA on the proliferation (3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyltetrazolium bromide (MTT) and colony assays), EMT (Western blotting, immunofluorescence, and wound healing), and stemness (mammosphere formation assays, Western blotting) of BC cells were examined. According to the findings, ICA suppressed the proliferation, EMT, and stem cell-like in MDA-MB-231 cells, and exerted its inhibitory impact by downregulating the TGFß/SMAD2 signaling pathway. ICA could significantly downregulate the expression of lncRNA NEAT1, and silencing NEAT1 enhanced the effect of ICA in suppressing EMT and expression of different stem cell markers. In addition, silencing NEAT1 was found to attenuate the TGFß/SMAD2 signaling pathway, thereby improving the inhibitory impact of ICA on stemness and EMT in BC cells. In conclusion, ICA can potentially inhibit the metastasis of BC via affecting the NEAT1/TGFß/SMAD2 pathway, which provides a theoretical foundation for understanding the mechanisms involved in potential application of ICA for BC therapy.

Deletion of ArmPT, a LamB-like protein, increases cell membrane permeability and antibiotic sensitivity in Vibrio alginolyticus.

Vibrio bacterial species are dominant pathogens in mariculture animals. However, the extensive use of antibiotics and other chemicals has increased drug resistance in Vibrio bacteria. Despite rigorous investigative studies, the mechanism of drug resistance in Vibrio remains a mystery. In this study, we found that a gene encoding LamB-like outer membrane protein, named ArmPT, was upregulated in Va under antibiotic stress by RT-qPCR. We speculated that ArmPT might play a role in Va's drug resistance. Subsequently, using ArmPT gene knockout and gene complementation experiments, we confirmed its role in resistance against a variety of antibiotics, particularly kanamycin (KA). Transcriptomic and proteomic analyses identified 188 and 83 differentially expressed genes in the mutant strain compared with the wild-type (WT) before and after KA stress, respectively. Bioinformatic analysis predicted that ArmPT might control cell membrane permeability by changing cadaverine biosynthesis, thereby influencing the cell entry of antibiotics in Va. The higher levels of intracellular reactive oxygen species and the infused content of KA showed that antibiotics are more likely to enter the Va mutant strain. These results uncover the drug resistance mechanism of Va that can also exist in other similar pathogenic bacteria.

Baicalin protects against hepatocyte injury caused by aflatoxin B1 via the TP53-related ferroptosis Pathway.

OBJECTIVE: Baicalin has antioxidative, antiviral, and anti-inflammatory properties. However, its ability to alleviate oxidative stress (OS) and DNA damage in liver cells exposed to aflatoxin B1 (AFB1), a highly hepatotoxic compound, remains uncertain. In this study, the protective effects of baicalin on AFB1-induced hepatocyte injury and the mechanisms underlying those effects were investigated. METHODS: Stable cell lines expressing CYP3A4 were established using lentiviral vectors to assess oxidative stress levels by conducting assays to determine the content of reactive oxygen species (ROS), malondialdehyde (MDA), and superoxide dismutase (SOD). Additionally, DNA damage was evaluated by 8-hydroxy-2-deoxyguanosine (8-OHdG) and comet assays. Transcriptome sequencing, molecular docking, and in vitro experiments were conducted to determine the mechanisms underlying the effects of baicalin on AFB1-induced hepatocyte injury. In vivo, a rat model of hepatocyte injury induced by AFB1 was used to evaluate the effects of baicalin. RESULTS: In vitro, baicalin significantly attenuated AFB1-induced injury caused due to OS, as determined by a decrease in ROS, MDA, and SOD levels. Baicalin also considerably decreased AFB1-induced DNA damage in hepatocytes. This protective effect of baicalin was found to be closely associated with the TP53-mediated ferroptosis pathway. To elaborate, baicalin physically interacts with P53, leading to the suppression of the expression of GPX4 and SLC7A11, which in turn inhibits ferroptosis. In vivo findings showed that baicalin decreased DNA damage and ferroptosis in AFB1-treated rat liver tissues, as determined by a decrease in the expression of γ-H2AX and an increase in GPX4 and SLC7A11 levels. Overexpression of TP53 weakened the protective effects of baicalin. CONCLUSIONS: Baicalin can alleviate AFB1-induced OS and DNA damage in liver cells via the TP53-mediated ferroptosis pathway. In this study, a theoretical foundation was established for the use of baicalin in protecting the liver from the toxic effects of AFB1.

Rolling Bearing Remaining Useful Life Prediction Based on CNN-VAE-MBiLSTM.

Ensuring precise prediction of the remaining useful life (RUL) for bearings in rolling machinery is crucial for preventing sudden machine failures and optimizing equipment maintenance strategies. Since the significant interference encountered in real industrial environments and the high complexity of the machining process, accurate and robust RUL prediction of rolling bearings is of tremendous research importance. Hence, a novel RUL prediction model called CNN-VAE-MBiLSTM is proposed in this paper by integrating advantages of convolutional neural network (CNN), variational autoencoder (VAE), and multiple bi-directional long short-term memory (MBiLSTM). The proposed approach includes a CNN-VAE model and a MBiLSTM model. The CNN-VAE model performs well for automatically extracting low-dimensional features from time-frequency spectrum of multi-axis signals, which simplifies the construction of features and minimizes the subjective bias of designers. Based on these features, the MBiLSTM model achieves a commendable performance in the prediction of RUL for bearings, which independently captures sequential characteristics of features in each axis and further obtains differences among multi-axis features. The performance of the proposed approach is validated through an industrial case, and the result indicates that it exhibits a higher accuracy and a better anti-noise capacity in RUL predictions than comparable methods.

Industrial Product Surface Anomaly Detection with Realistic Synthetic Anomalies Based on Defect Map Prediction.

The occurrence of anomalies on the surface of industrial products can lead to issues such as decreased product quality, reduced production efficiency, and safety hazards. Early detection and resolution of these problems are crucial for ensuring the quality and efficiency of production. The key challenge in applying deep learning to surface defect detection of industrial products is the scarcity of defect samples, which will make supervised learning methods unsuitable for surface defect detection problems. Therefore, it is a reasonable solution to use anomaly detection methods to deal with surface defect detection. Among image-based anomaly detection, reconstruction-based methods are the most commonly used. However, reconstruction-based approaches lack the involvement of defect samples in the training process, posing the risk of a perfect reconstruction of defects by the reconstruction network. In this paper, we propose a reconstruction-based defect detection algorithm that addresses these challenges by utilizing more realistic synthetic anomalies for training. Our model focuses on creating authentic synthetic defects and introduces an auto-encoder image reconstruction network with deep feature consistency constraints, as well as a defect separation network with a large receptive field. We conducted experiments on the challenging MVTec anomaly detection dataset and our trained model achieved an AUROC score of 99.70% and an average precision (AP) score of 99.87%. Our method surpasses recently proposed defect detection algorithms, thereby enhancing the accuracy of surface defect detection in industrial products.

A "Pincer" Type of Acridine-Triazole Fluorescent Dye for Iodine Detection by Both 'Naked-Eye' Colorimetric and Fluorometric Modes.

Iodine, primarily in the form of iodide (I-), is the bioavailable form for the thyroid in the human body. Both deficiency and excess intake of iodide can lead to serious health issues, such as thyroid disease. Selecting iodide ions among anions has been a significant challenge for decades due to interference from other anions. In this study, we designed and synthesized a new pincer-type acridine-triazole fluorescent probe (probe 1) with an acridine ring as a spacer and a triazole as a linking arm attached to two naphthol groups. This probe can selectively recognize iodide ions in a mixed solvent of THF/H2O (v/v, 9/1), changing its color from colorless to light yellow, making it suitable for highly sensitive and selective colorimetric and fluorescent detection in water systems. We also synthesized another molecular tweezer-type acridine-triazole fluorescent probe (probe 2) that exhibits uniform detection characteristics for iodide ions in the acetonitrile system. Interestingly, compared to probe 2, probe 1 can be detected by the naked eye due to its circulation effect, providing a simple method for iodine detection. The detection limit of probe 1 is determined to be 10-8 mol·L-1 by spectrometric titration and isothermal titration calorimetry measurements. The binding stoichiometry between probe 1 and iodide ions is calculated to be 1:1 by these methods, and the binding constant is 2 × 105 mol·L-1.