Homosalate and ERK Knockdown in the Modulation of Aurelia coerulea Metamorphosis by Regulating the PI3K Pathway and ERK Pathway.

Metamorphosis control is pivotal in preventing the outbreak of jellyfish, and it is often studied using common model organisms. The widespread use of the ultraviolet blocking agent homosalate in cosmetics poses a threat to marine ecosystems. Although the impact of homosalate on marine organisms has been extensively examined, there is a notable absence of research on its effects on jellyfish metamorphosis and the underlying mechanisms, warranting further investigation. In this study, we first established a study model by using 5-methoxy-2-methylindole to induce Aurelia coerulea metamorphosis, and selected homosalate as a PI3K agonist and an ERK agonist, while we used YS-49 as a specific PI3K agonist, as well as ERK knockdown, to observe their effect on the metamorphosis of Aurelia coerulea. The results showed that an Aurelia coerulea metamorphosis model was established successfully, and the PI3K agonist homosalate, YS-49, and the knockdown of ERK molecules could significantly delay the metamorphosis development of Aurelia coerulea. We propose that activating PI3K/Akt and inhibiting the ERK pathway are involved in the delayed development of Aurelia coerulea, which provides a new strategy for the prevention and control of jellyfish blooms.

Pre-exposure to mRNA-LNP inhibits adaptive immune responses and alters innate immune fitness in an inheritable fashion.

Hundreds of millions of SARS-CoV-2 mRNA-LNP vaccine doses have already been administered to humans. However, we lack a comprehensive understanding of the immune effects of this platform. The mRNA-LNP-based SARS-CoV-2 vaccine is highly inflammatory, and its synthetic ionizable lipid component responsible for the induction of inflammation has a long in vivo half-life. Since chronic inflammation can lead to immune exhaustion and non-responsiveness, we sought to determine the effects of pre-exposure to the mRNA-LNP on adaptive immune responses and innate immune fitness. We found that pre-exposure to mRNA-LNPs or LNP alone led to long-term inhibition of the adaptive immune response, which could be overcome using standard adjuvants. On the other hand, we report that after pre-exposure to mRNA-LNPs, the resistance of mice to heterologous infections with influenza virus increased while resistance to Candida albicans decreased. The diminished resistance to Candida albicans correlated with a general decrease in blood neutrophil percentages. Interestingly, mice pre-exposed to the mRNA-LNP platform can pass down the acquired immune traits to their offspring, providing better protection against influenza. In summary, the mRNA-LNP vaccine platform induces long-term unexpected immunological changes affecting both adaptive immune responses and heterologous protection against infections. Thus, our studies highlight the need for more research to determine this platform's true impact on human health.

Langerhans cells and cDC1s play redundant roles in mRNA-LNP induced protective anti-influenza and anti-SARS-CoV-2 immune responses.

Nucleoside modified mRNA combined with Acuitas Therapeutics' lipid nanoparticles (LNPs) has been shown to support robust humoral immune responses in many preclinical animal vaccine studies and later in humans with the SARS-CoV-2 vaccination. We recently showed that this platform is highly inflammatory due to the LNPs' ionizable lipid component. The inflammatory property is key to support the development of potent humoral immune responses. However, the mechanism by which this platform drives T follicular helper (Tfh) cells and humoral immune responses remains unknown. Here we show that lack of Langerhans cells or cDC1s neither significantly affected the induction of PR8 HA and SARS-CoV-2 RBD-specific Tfh cells and humoral immune responses, nor susceptibility towards the lethal challenge of influenza and SARS-CoV-2. However, the combined deletion of these two DC subsets led to a significant decrease in the induction of PR8 HA and SARS-CoV-2 RBD-specific Tfh cell and humoral immune responses. Despite these observed defects, these mice remained protected from lethal influenza and SARS-CoV-2 challenges. We further found that IL-6, unlike neutrophils, was required to generate normal Tfh cells and antibody responses, but not for protection from influenza challenge. In summary, here we bring evidence that the mRNA-LNP platform can support the induction of protective immune responses in the absence of certain innate immune cells and cytokines.

Large-range two-dimensional sub-nano-misalignment sensing for lithography with a piecewise frequency regression network.

Circular gratings have been traditionally used as coarse alignment markers rather than fine ones for carrying out two-dimensional (2D) large-range misalignment measurements. This is primarily due to its complex phase distribution, which renders the extraction of information from high-precision alignment challenging using conventional frequency filtering methods. Along these lines, in this work, a novel, to the best of our knowledge, convolutional regression filter capable of achieving a 2D misalignment measurement with an impressive accuracy of 0.82 nm across a 3 mm range was introduced. Importantly, the proposed approach exhibited robustness against system errors and noise. It is anticipated that this strategy will provide an effective solution for similar misalignment sensing applications and hold promise for addressing future challenges in these fields.

Development of inducible promoters for regulating gene expression in Clostridium tyrobutyricum for biobutanol production.

Clostridium tyrobutyricum is an anaerobe known for its ability to produce short-chain fatty acids, alcohols, and esters. We aimed to develop inducible promoters for fine-tuning gene expression in C. tyrobutyricum. Synthetic inducible promoters were created by employing an Escherichia coli lac operator to regulate the thiolase promoter (PCathl) from Clostridium acetobutylicum, with the best one (LacI-Pto4s) showing a 5.86-fold dynamic range with isopropyl ß- d-thiogalactoside (IPTG) induction. A LT-Pt7 system with a dynamic range of 11.6-fold was then created by combining LacI-Pto4s with a T7 expression system composing of RNA polymerase (T7RNAP) and Pt7lac promoter. Furthermore, two inducible expression systems BgaR-PbgaLA and BgaR-PbgaLB with a dynamic range of ~40-fold were developed by optimizing a lactose-inducible expression system from Clostridium perfringens with modified 5' untranslated region (5' UTR) and ribosome-binding site (RBS). BgaR-PbgaLB was then used to regulate the expressions of a bifunctional aldehyde/alcohol dehydrogenase encoded by adhE2 and butyryl-CoA/acetate Co-A transferase encoded by cat1 in C. tyrobutyricum wild type and Δcat1::adhE2, respectively, demonstrating its efficient inducible gene regulation. The regulated cat1 expression also confirmed that the Cat1-catalyzed reaction was responsible for acetate assimilation in C. tyrobutyricum. The inducible promoters offer new tools for tuning gene expression in C. tyrobutyricum for industrial applications.

The application status of sequencing technology in global respiratory infectious disease diagnosis.

Next-generation sequencing (NGS) has revolutionized clinical microbiology, particularly in diagnosing respiratory infectious diseases and conducting epidemiological investigations. This narrative review summarizes conventional methods for routine respiratory infection diagnosis, including culture, smear microscopy, immunological assays, image techniques as well as polymerase chain reaction(PCR). In contrast to conventional methods, there is a new detection technology, sequencing technology, and here we mainly focus on the next-generation sequencing NGS, especially metagenomic NGS(mNGS). NGS offers significant advantages over traditional methods. Firstly, mNGS eliminates assumptions about pathogens, leading to faster and more accurate results, thus reducing diagnostic time. Secondly, it allows unbiased identification of known and novel pathogens, offering broad-spectrum coverage. Thirdly, mNGS not only identifies pathogens but also characterizes microbiomes, analyzes human host responses, and detects resistance genes and virulence factors. It can complement targeted sequencing for bacterial and fungal classification. Unlike traditional methods affected by antibiotics, mNGS is less influenced due to the extended survival of pathogen DNA in plasma, broadening its applicability. However, barriers to full integration into clinical practice persist, primarily due to cost constraints and limitations in sensitivity and turnaround time. Despite these challenges, ongoing advancements aim to improve cost-effectiveness and efficiency, making NGS a cornerstone technology for global respiratory infection diagnosis.

Copper-catalyzed syn-hydroformylation of alkynes with silanes and N,N-dimethylformamide dimethylacetal.

A copper-catalyzed syn-hydrocarbonization of internal alkynes with N,N-dimethylformamide dimethylacetal and silanes has been disclosed that offers an efficient and expedient access to (E)-α,ß-unsaturated aldehydes. This highly selective process, which can be performed at gram-scale, enjoys operational simplicity, as well as syngas-free conditions.

Improved deep neural network (EnhanceNet) for real-time detection of some publicly prohibited items.

Public safety is a critical concern, typically addressed through security checks at entrances of public places, involving trained officers or X-ray scanning machines to detect prohibited items. However, many places like hospitals, schools, and event centres lack such resources, risking security breaches. Even with X-ray scanners or manual checks, gaps can be exploited by individuals with malicious intent, posing significant security risks. Additionally, traditional methods, relying on manual inspections and conventional image processing techniques, are often inefficient and prone to high error rates. To mitigate these risks, we propose a real-time detection model - EnhanceNet using a customized Scale-Enhanced Pooling Network (SEP-Net) integrated into the YOLOv4. The innovative SEP-Net enhances feature representation and localization accuracy, significantly contributing to the model's efficacy in detecting prohibited items. We annotated a custom dataset of nine classes and evaluated our models using different input sizes (608 and 416). The 608 input size achieved a mean Average Precision (mAP) of 74.10% with a detection speed of 22.3 Frames per Second (FPS). The 416 input size showed superior performance, achieving a mAP of 76.75% and a detection speed of 27.1 FPS. These demonstrate that our models are accurate and efficient, making them suitable for real-time applications.

Comparative performance analysis of Boruta, SHAP, and Borutashap for disease diagnosis: A study with multiple machine learning algorithms.

Interpretable machine learning models are instrumental in disease diagnosis and clinical decision-making, shedding light on relevant features. Notably, Boruta, SHAP (SHapley Additive exPlanations), and BorutaShap were employed for feature selection, each contributing to the identification of crucial features. These selected features were then utilized to train six machine learning algorithms, including LR, SVM, ETC, AdaBoost, RF, and LR, using diverse medical datasets obtained from public sources after rigorous preprocessing. The performance of each feature selection technique was evaluated across multiple ML models, assessing accuracy, precision, recall, and F1-score metrics. Among these, SHAP showcased superior performance, achieving average accuracies of 80.17%, 85.13%, 90.00%, and 99.55% across diabetes, cardiovascular, statlog, and thyroid disease datasets, respectively. Notably, the LGBM emerged as the most effective algorithm, boasting an average accuracy of 91.00% for most disease states. Moreover, SHAP enhanced the interpretability of the models, providing valuable insights into the underlying mechanisms driving disease diagnosis. This comprehensive study contributes significant insights into feature selection techniques and machine learning algorithms for disease diagnosis, benefiting researchers and practitioners in the medical field. Further exploration of feature selection methods and algorithms holds promise for advancing disease diagnosis methodologies, paving the way for more accurate and interpretable diagnostic models.

Enhanced Cardiovascular Disease Prediction Modelling using Machine Learning Techniques: A Focus on CardioVitalnet.

Aiming at early detection and accurate prediction of cardiovascular disease (CVD) to reduce mortality rates, this study focuses on the development of an intelligent predictive system to identify individuals at risk of CVD. The primary objective of the proposed system is to combine deep learning models with advanced data mining techniques to facilitate informed decision-making and precise CVD prediction. This approach involves several essential steps, including the preprocessing of acquired data, optimized feature selection, and disease classification, all aimed at enhancing the effectiveness of the system. The chosen optimal features are fed as input to the disease classification models and into some Machine Learning (ML) algorithms for improved performance in CVD classification. The experiment was simulated in the Python platform and the evaluation metrics such as accuracy, sensitivity, and F1_score were employed to assess the models' performances. The ML models (Extra Trees (ET), Random Forest (RF), AdaBoost, and XG-Boost) classifiers achieved high accuracies of 94.35%, 97.87%, 96.44%, and 99.00%, respectively, on the test set, while the proposed CardioVitalNet (CVN) achieved 87.45% accuracy. These results offer valuable insights into the process of selecting models for medical data analysis, ultimately enhancing the ability to make more accurate diagnoses and predictions.

Carbon dioxide production index (VCO2i) predicts hyperlactatemia during cardiopulmonary bypass in pediatric carDiac surGery (pGDP- VCO2i): Study protocol for a nested case-control trial.

BACKGROUND: Hyperlactatemia (HL) during cardiopulmonary bypass (CPB) is relatively frequent in infants and associates with increased morbidity and mortality. Studies on adults have shown that carbon dioxide production index (VCO2i) during CPB is linked to the occurrence of HL, with 'critical thresholds' for VCO2i reported to be 60 mL/min/m2. However, considering infants have a higher metabolic rate and lower tolerance to hypoxia, the critical threshold of VCO2i in infants cannot be replied to the existing adults' standards. The objective of this study is to investigate the association of VCO2i during CPB and HL, and explore the critical VCO2i threshold during CPB in infants. METHODS: VCO2i predicts hyperlactatemia during cardiopulmonary bypass in pediatric cardiac surgery (pGDP-VCO2i) is a nested case-control study. A cohort of consecutive pediatric patients of less than 3 years of age, undergoing congenital cardiac surgeries between May 2021 and December 2023 in West China Hospital will be enrolled. The VCO2i levels of each patient will be recorded every 5 min during CPB. The primary outcome is the rate of HL. The infants will be divided into two groups based on the presence or not of HL. Pre- and intraoperative factors will be tested for independent association with HL. Then, we will make an analysis, and the critical value of VCO2i will be obtained. The postoperative outcome of patients with or without HL will be compared. DISCUSSION: This will be the first trial to investigate the association of VCO2i during CPB and HL, and explore the critical VCO2i threshold during CPB in pediatrics. The results of this study are expected to lay a foundation for clinical application of goal-directed perfusion (GDP) management strategy, and optimize the perfusion strategy and improve the prognosis of pediatric patients undergoing cardiac surgery. TRIAL REGISTRATION: Chictr.org.cn, ChiCTR2100044296 on 16 March 2021.

Stereoselective Solid-State Synthesis of Biologically Active Cyclobutane and Dicyclobutane Isomers via Conformation Blocking and Transference.

Conformations in the solid state are typically fixed during crystallization. Transference of "frozen" C=C conformations in 3,5-bis((E)-2-(pyridin-4-yl)vinyl)methylbenzene (CH3-3,5-bpeb) by photodimerization selectively yielded cyclobutane and dicyclobutane isomers, one of which (Isomer 2) exhibited excellent in vitro anti-cancer activity towards T-24, 7402, MGC803, HepG-2, and HeLa cells.

Sirtuin 3 ameliorates inflammatory bowel disease via inhibiting intestinal inflammation and oxidative stress.

Sirtuin 3 involved in development of various diseases, but its role in inflammatory bowel disease is still unknown. We used inflammatory bowel disease biopsies, colitis animal model, and vitro cells RAW264.7 to study the role of Sirtuin 3 in the pathophysiology of inflammatory bowel disease. Sirtuin 3 negatively correlated with intestinal TNF-α. Sirt3 was less pronounced in pediatric and adult inflammatory bowel disease patients compared with corresponding control group. Sirtuin 3 activator Honokiol suppressed dextran sulfate sodium induced colonic manifestations, while Sirt3 inhibitor caused opposite results. Honokiol inhibited colonic oxidative stress by and reduced intestinal permeability. Honokiol repressed inflammatory response by reducing macrophage infiltration, pro-inflammatory cytokines TNF-α, IL-1ß, and IL-6 levels, and inhibiting activation of NF-κB p65 in the colitis mice. However, Sirt3 inhibitor amplified colonic oxidative stress and inflammatory response. In vitro study, Sirt3 inhibitor or siRNA Sirtuin 3 activated NF-κB p65 and enhanced TNF-α, IL-1ß, and IL-6 secretion from LPS stimulated RAW264.7, while Honokiol remarkably attenuated these pro-inflammatory cytokines secretion. Finally, knockdown of Sirt3 in Caco-2 cells enhanced TNF-α induced intestinal barrier integrity injury. Sirtuin 3 negatively regulates inflammatory bowel disease progression via reducing colonic inflammation and oxidative stress. Sirtuin 3 is a promising therapeutic target in clinical application for inflammatory bowel disease therapy.

Differential expression profiles of plasma exosomal microRNAs in dilated cardiomyopathy with chronic heart failure.

As one of the most prevalent heritable cardiovascular diseases, dilated cardiomyopathy (DCM) induces cardiac insufficiency and dysfunction. Although genetic mutation has been identified one of the causes of DCM, the usage of genetic biomarkers such as RNAs for DCM early diagnosis is still being overlooked. In addition, the alternation of RNAs could reflect the progression of the diseases, as an indicator for the prognosis of patients. Therefore, it is beneficial to develop genetic based diagnostic tool for DCM. RNAs are often unstable within circulatory system, leading to the infeasibility for clinical application. Recently discovered exosomal miRNAs have the stability that is then need for diagnostic purpose. Hence, fully understanding of the exosomal miRNA within DCM patients is vital for clinical translation. In this study, we employed the next generation sequencing based on the plasma exosomal miRNAs to comprehensively characterize the miRNAs expression in plasma exosomes from DCM patients exhibiting chronic heart failure (CHF) compared to healthy individuals. A complex landscape of differential miRNAs and target genes in DCM with CHF patients were identified. More importantly, we discovered that 92 differentially expressed miRNAs in DCM patients undergoing CHF were correlated with several enriched pathways, including oxytocin signalling pathway, circadian entrainment, hippo signalling pathway-multiple species, ras signalling pathway and morphine addiction. This study reveals the miRNA expression profiles in plasma exosomes in DCM patients with CHF, and further reveal their potential roles in the pathogenesis of it, presenting a new direction for clinical diagnosis and management of DCM patients with CHF.

Evaluation of Graphene Oxide as a Thermal Ionization Enhancer for Plutonium in TIMS Measurement.

Thermal ionization mass spectrometry (TIMS) has been extensively employed for the assessment of plutonium (Pu) isotopes in nuclear forensics and environmental monitoring. Recently, great efforts have been made to improve the ionization efficiency (IE) of Pu to achieve better accuracy and precision for trace-level analysis. Herein, the thermal ionization enhancement effect for plutonium of graphene oxide (GO) was investigated and the corresponding mechanism was discussed. The GO layers were homogeneously mounted on the filament's central surface to promote pg-level Pu ion emission. With the excellent structural property of GO, a greatly promoted ionization efficiency of 0.44% for Pu was obtained, and the initial ionization temperature for Pu was remarkably reduced from 1610 to 1390 °C. Average boosts in IE compared to the classical double-filament mode and graphite-loaded single-filament mode were 1640 and 520%, respectively. The analytical accuracy and precision based on the GO-loaded single-filament mode were validated using Pu isotopic certified reference materials. This work demonstrates the excellent property of GO as an ion source additive for Pu ionization, as it provided an interface for the promotion of energy transfer and Pu carbide formation. The operation of GO loading is quite simple and can be finished within 5 min. This rapid filament carburization approach has great potential for improving the measurement precision of trace-level plutonium isotopes and can be applied in nuclear safeguards, nuclear forensics, and environmental monitoring.

Alternative splicing of TaHSFA6e modulates heat shock protein-mediated translational regulation in response to heat stress in wheat.

Heat stress greatly threatens crop production. Plants have evolved multiple adaptive mechanisms, including alternative splicing, that allow them to withstand this stress. However, how alternative splicing contributes to heat stress responses in wheat (Triticum aestivum) is unclear. We reveal that the heat shock transcription factor gene TaHSFA6e is alternatively spliced in response to heat stress. TaHSFA6e generates two major functional transcripts: TaHSFA6e-II and TaHSFA6e-III. TaHSFA6e-III enhances the transcriptional activity of three downstream heat shock protein 70 (TaHSP70) genes to a greater extent than does TaHSFA6e-II. Further investigation reveals that the enhanced transcriptional activity of TaHSFA6e-III is due to a 14-amino acid peptide at its C-terminus, which arises from alternative splicing and is predicted to form an amphipathic helix. Results show that knockout of TaHSFA6e or TaHSP70s increases heat sensitivity in wheat. Moreover, TaHSP70s are localized in stress granule following exposure to heat stress and are involved in regulating stress granule disassembly and translation re-initiation upon stress relief. Polysome profiling analysis confirms that the translational efficiency of stress granule stored mRNAs is lower at the recovery stage in Tahsp70s mutants than in the wild types. Our finding provides insight into the molecular mechanisms by which alternative splicing improves the thermotolerance in wheat.

The zinc finger and BTB domain containing protein ZBTB20 regulates plasma triglyceride metabolism by repressing lipoprotein lipase gene transcription in hepatocytes.

BACKGROUND AND AIMS: Lipoprotein lipase (LPL) is responsible for the lipolytic processing of triglyceride-rich lipoproteins, the deficiency of which causes severe hypertriglyceridemia. Liver LPL expression is high in suckling rodents but relatively low at adulthood. However, the regulatory mechanism and functional significance of liver LPL expression are incompletely understood. We have established the zinc finger protein ZBTB20 as a critical factor for hepatic lipogenesis. Here, we evaluated the role of ZBTB20 in regulating liver Lpl gene transcription and plasma triglyceride metabolism. APPROACH AND RESULTS: Hepatocyte-specific inactivation of ZBTB20 in mice led to a remarkable increase in LPL expression at the mRNA and protein levels in adult liver, in which LPL protein was mainly localized onto sinusoidal epithelial cells and Kupffer cells. As a result, the LPL activity in postheparin plasma was substantially increased, and postprandial plasma triglyceride clearance was significantly enhanced, whereas plasma triglyceride levels were decreased. The dysregulated liver LPL expression and low plasma triglyceride levels in ZBTB20-deficient mice were normalized by inactivating hepatic LPL expression. ZBTB20 deficiency protected the mice against high-fat diet-induced hyperlipidemia without causing excessive triglyceride accumulation in the liver. Chromatin immunoprecipitation and gel-shift assay studies revealed that ZBTB20 binds to the LPL promoter in the liver. A luciferase reporter assay revealed that ZBTB20 inhibits the transcriptional activity of LPL promoter. The regulation of LPL expression by ZBTB20 is liver-specific under physiological conditions. CONCLUSIONS: Liver ZBTB20 serves as a key regulator of LPL expression and plasma triglyceride metabolism and could be a therapeutic target for hypertriglyceridemia.

Systemic lupus erythematosus with high disease activity identification based on machine learning.

OBJECTIVE: Clinical evaluation of systemic lupus erythematosus (SLE) disease activity is limited and inconsistent, and high disease activity significantly, seriously impacts on SLE patients. This study aims to generate a machine learning model to identify SLE patients with high disease activity. METHOD: A total of 1014 SLE patients with low disease activity and 453 SLE patients with high disease activity were included. A total of 94 clinical, laboratory data and 17 meteorological indicators were collected. After data preprocessing, we use mutual information and multisurf to evaluate and select the importance of features. The selected features are used for machine learning modeling. Performance of the model is evaluated and verified by a series of binary classification indicators. RESULTS: We screened out hematuria, proteinuria, pyuria, low complement, precipitation, sunlight and other features for model construction by integrated feature selection. After hyperparameter optimization, the LGB has the best performance (ROC: AUC = 0.930; PRC: AUC = 0.911, APS = 0.913; balance accuracy: 0.856), and the worst is the naive bayes (ROC: AUC = 0.849; PRC: AUC = 0.719, APS = 0.714; balance accuracy: 0.705). Finally, the selection of features has good consistency in the composite feature importance bar plot. CONCLUSION: We identify SLE patients with high disease activity by a simple machine learning pipeline, especially the LGB model based on the characteristics of proteinuria, hematuria, pyuria and other feathers screened out by collective feature selection.

Lupus nephritis or not? A simple and clinically friendly machine learning pipeline to help diagnosis of lupus nephritis.

OBJECTIVE: Diagnosis of lupus nephritis (LN) is a complex process, which usually requires renal biopsy. We aim to establish a machine learning pipeline to help diagnosis of LN. METHODS: A cohort of 681 systemic lupus erythematosus (SLE) patients without LN and 786 SLE patients with LN was established, and a total of 95 clinical, laboratory data and 17 meteorological indicators were collected. After tenfold cross-validation, the patients were divided into training set and test set. The features selected by collective feature selection method of mutual information (MI) and multisurf were used to construct the models of logistic regression, decision tree, random forest, naive Bayes, support vector machine (SVM), light gradient boosting (LGB), extreme gradient boosting (XGB), and artificial neural network (ANN), the models were compared and verified in post-analysis. RESULTS: Collective feature selection method screens out antistreptolysin (ASO), retinol binding protein (RBP), lupus anticoagulant 1 (LA1), LA2, proteinuria and other features, and the hyperparameter optimized XGB (ROC: AUC = 0.995; PRC: AUC = 1.000, APS = 1.000; balance accuracy: 0.990) has the best performance, followed by LGB (ROC: AUC = 0.992; PRC: AUC = 0.997, APS = 0.977; balance accuracy: 0.957). The worst performance is naive Bayes model (ROC: AUC = 0.799; PRC: AUC = 0.822, APS = 0.823; balance accuracy: 0.693). In the composite feature importance bar plots, ASO, RF, Up/Ucr, and other features play important roles in LN. CONCLUSION: We developed and validated a new and simple machine learning pathway for diagnosis of LN, especially the XGB model based on ASO, LA1, LA2, proteinuria, and other features screened out by collective feature selection.