PRFold-TNN: Protein Fold Recognition With an Ensemble Feature Selection Method Using PageRank Algorithm Based on Transformer.

Understanding the tertiary structures of proteins is of great benefit to function in many aspects of human life. Protein fold recognition is a vital and salient means to know protein structure. Until now, researchers have successively proposed a variety of methods to realize protein fold recognition, but the novel and effective computational method is still needed to handle this problem with the continuous updating of protein structure databases. In this study, we develop a new protein structure dataset named AT and propose the PRFold-TNN model for protein fold recognition. Firstly, different types of feature extraction methods including AAC, HMM, HMM-Bigram and ACC are selected to extract corresponding features for protein sequences. Then an ensemble feature selection method based on PageRank algorithm integrating various tree-based algorithms is used to screen the fusion features. Ultimately, the classifier based on the Transformer model achieves the final prediction. Experiments show that the prediction accuracy is 86.27% on the AT dataset and 88.91% on the independent test set, indicating that the model can demonstrate superior performance and generalization ability in the problem of protein fold recognition. Furthermore, we also carry out research on the DD, EDD and TG benchmark datasets, and make them achieve prediction accuracy of 88.41%, 97.91% and 95.16%, which are at least 3.0%, 0.8% and 2.5% higher than those of the state-of-the-art methods. It can be concluded that the PRFold-TNN model is more prominent.

GSB: GNGS and SAG-BiGRU network for malware dynamic detection.

With the rapid development of the Internet, the continuous increase of malware and its variants have brought greatly challenges for cyber security. Due to the imbalance of the data distribution, the research on malware detection focuses on the accuracy of the whole data sample, while ignoring the detection rate of the minority categories' malware. In the dataset sample, the normal data samples account for the majority, while the attacks' malware accounts for the minority. However, the minority categories' attacks will bring great losses to countries, enterprises, or individuals. For solving the problem, this study proposed the GNGS algorithm to construct a new balance dataset for the model algorithm to pay more attention to the feature learning of the minority attacks' malware to improve the detection rate of attacks' malware. The traditional malware detection method is highly dependent on professional knowledge and static analysis, so we used the Self-Attention with Gate mechanism (SAG) based on the Transformer to carry out feature extraction between the local and global features and filter irrelevant noise information, then extracted the long-distance dependency temporal sequence features by the BiGRU network, and obtained the classification results through the SoftMax classifier. In the study, we used the Alibaba Cloud dataset for malware multi-classification. Compared the GSB deep learning network model with other current studies, the experimental results showed that the Gaussian noise generation strategy (GNGS) could solve the unbalanced distribution of minority categories' malware and the SAG-BiGRU algorithm obtained the accuracy rate of 88.7% on the eight-classification, which has better performance than other existing algorithms, and the GSB model also has a good effect on the NSL-KDD dataset, which showed the GSB model is effective for other network intrusion detection.

Network pharmacology-based approach to investigate the molecular targets of essential oil obtained from lavender for treating breast cancer.

Lavender essential oil (LEO) is known for its medicinal use in the development of pharmaceuticals. Further investigations were demonstrated that LEO has many biological properties including apoptosis. However, The anti-breast cancer activity and mechanism of LEO are still unclear. we aim to elucidate the elusive anti-breast cancer activity and mechanism of LEO by unveiling the intricate molecular targets that it engages with, thereby priming it for effective therapeutic intervention against breast carcinoma. In this paper, we extracted LEO from lavender and analyzed it's chemical constituents by using hydro-distillation and gas chromatography-mass spectrometry (GS-MS/MS) method, respectively. The active components against breast cancer and it's molecular targets were selected and biological process, molecular function, cellular component and involving pathways were evaluated via network pharmacology approach. Cell viability, apoptosis and cell cycle assay were used to evaluate anti-breast cancer effect of LEO. Employing the western blotting method to validate target protein expression following LEO treatment in vitro. We found the 21 effective components and 213 drug-disease common targets of LEO. Amoung them, 7 active components and 19 targets were identified as potential therapeutic targets. Gene ontology results revealed that the drug-disease common targets of LEO were mainly distributed in membrane region, involved in peptide-tyrosine phosphorylation, and primarily associated with protein tyrosine kinase. We also found that drug-disease common targets might contribute to the regulation of PI3K-AKT signaling pathway by using KEGG pathway analysis. Besides, our study demonstrated reduced cell viability, induced apoptosis in MCF-7 and MDA-MB-231 treated with LEO while cell cycle arrest was not altered. The AKT1 expression down-regulated while PIK3CA expression was increased in both cell lines. Our findings indicate that LEO has the ability to induce apoptosis by modulating the expression of PI3K-AKT signaling pathway in these cell lines.

ResCNNT-fold: Combining residual convolutional neural network and Transformer for protein fold recognition from language model embeddings.

A comprehensive understanding of protein functions holds significant promise for disease research and drug development, and proteins with analogous tertiary structures tend to exhibit similar functions. Protein fold recognition stands as a classical approach in the realm of protein structure investigation. Despite significant advancements made by researchers in this field, the continuous updating of protein databases presents an ongoing challenge in accurately identifying protein fold types. In this study, we introduce a predictor, ResCNNT-fold, for protein fold recognition and employ the LE dataset for testing purpose. ResCNNT-fold leverages a pre-trained language model to obtain embedding representations for protein sequences, which are then processed by the ResCNNT feature extractor, a combination of residual convolutional neural network and Transformer, to derive fold-specific features. Subsequently, the query protein is paired with each protein whose structure is known in the template dataset. For each pair, the similarity score of their fold-specific features is calculated. Ultimately, the query protein is identified as the fold type of the template protein in the pair with the highest similarity score. To further validate the utility and efficacy of the proposed ResCNNT-fold predictor, we conduct a 2-fold cross-validation experiment on the fold level of the LE dataset. Remarkably, this rigorous evaluation yields an exceptional accuracy of 91.57%, which surpasses the best result among other state-of-the-art protein fold recognition methods by an approximate margin of 10%. The excellent performance unequivocally underscores the compelling advantages inherent to our proposed ResCNNT-fold predictor in the realm of protein fold recognition. The source code and data of ResCNNT-fold can be downloaded from https://github.com/Bioinformatics-Laboratory/ResCNNT-fold.

Vericiguat reduces electrical and structural remodeling in a rabbit model of atrial fibrillation.

Purpose: The molecular etiology of atrial fibrillation (AF) and its treatment are poorly understood. AF involves both electrical and structural features. Vericiguat can ameliorate cardiac remodeling in heart failure. The effects of vericiguat on AF, however, are unclear. Here, the actions of vericiguat on atrial structural and electrical remodeling in AF and its possible mechanisms were investigated. Methods and Results: Thirty-six rabbits were randomly allocated to four groups, namely, sham, RAP (pacing with 600 beats/min over three weeks), vericiguat-treated (three weeks' pacing plus daily oral dose of 1.5 mg/kg of vericiguat), and vericiguat-treated only. HL-1 cells received rapid pacing with or without vericiguat. Parameters including electrophysiology, echocardiography, histology, Ca2+ levels, and ICaL density, as well as levels of TRPC6, CaN, NFAT4, p-NFAT4, Cav1.2, collagen I, collagen III, and ST2 were measured. Significant changes of above proteins expression level, circulating biochemical indices, Ca2+ concentrations, and ICaL density in both animals and cell models, these effects were significantly restored by vericiguat. Vericiguat also reversed the enlarged atrium and significantly reduced myocardial fibrosis, together with preventing reduced atrial effective refractory periods (AERPs) and AF induction rate. Conclusion: Vericiguat thus ameliorated AF-associated structural and electrical remodeling. These findings suggest the potential of vericiguat for treating AF.

Ticagrelor versus clopidogrel in reducing inflammatory cell infiltration of thrombus aspirated in patients with ST-elevation myocardial infarction.

BACKGROUND: Ticagrelor provides more rapid, potent, and consistent anti-platelet efficacy than clopidogrel. This randomized trial aimed to evaluate the anti-inflammation effects of ticagrelor versus clopidogrel on thrombus aspirated from the ST-elevation myocardial infarction (STEMI) patients. METHOD: A total of 98 patients with STEMI and intended percutaneous coronary intervention (PCI) were randomly assigned to receive clopidogrel (600-mg loading dose) or ticagrelor (180-mg loading dose), of whom 55 with large thrombus burden underwent thrombus aspiration during PCI. Thrombus specimens were successfully aspirated from 49 patients. Finally, 24 patients in the clopidogrel group and 23 in the ticagrelor group completed the study. Inflammatory cells within thrombi were assessed by hematoxylin-eosin and immunohistochemistry stainings. RESULTS: Compared with the clopidogrel group, the number of total inflammatory cells per mm2 thrombus area in the ticagrelor group was decreased by 28% (P = 0.009). The numbers of neutrophils and myeloperoxidase-positive cells per mm2 thrombus area in the ticagrelor group were respectively decreased by 35% (P = 0.016) and 28% (P = 0.047), as compared with those in the clopidogrel group. Moreover, ticagrelor treatment reduced the ratio of monocytes number higher than 250 per mm2 thrombus area compared with clopidogrel treatment (4% versus 29%, P = 0.048). CONCLUSION: In patients with undergoing PCI for STEMI, the loading dose ticagrelor regimen was associated with a reduction in inflammatory cell infiltration within thrombus compared with the loading dose clopidogrel regimen.

Effects of ticagrelor monotherapy vs. clopidogrel monotherapy on platelet reactivity: a randomized, crossover clinical study (SINGLE study).

Increasing clinical trials demonstrated that the discontinuation of aspirin while maintaining a P2Y12 inhibitor monotherapy could decrease the risk of bleeding without losing the antithrombotic effect. However, no data are available on the platelet reactivity of patients undergoing ticagrelor monotherapy vs. clopidogrel. Therefore, we performed this study to observe the efficacy of ticagrelor monotherapy vs. clopidogrel in Chinese patients with chronic coronary syndrome. This randomized, single-blinded, crossover trial enrolled 50 patients who were administered with ticagrelor (90 mg twice daily for 2 weeks) or clopidogrel (75 mg once daily for 2 weeks). Followed by a 2-week washout period, the two groups of patients underwent a crossover trial. Light transmission aggregometry (LTA) and thromboelastography (TEG) assays were used to test platelet reactivity. The platelet aggregation rate (PAgR) of ADP and AA was significantly lower with ticagrelor than clopidogrel (PAgR of ADP, 27.30% (7.30%-42.635%) vs. 35.55% (12.03%-69.25%), P = .0254; PAgR of AA, 77.80% (21.60%-86.43%) vs. 83.10% (67.13%-87.20%), P = .0400). There was no significant difference in PAgR of collagen and epinephrine between the two groups. The TEG assay showed that ADP and AA, which induced the inhibition of platelet aggregation, were significantly higher in the ticagrelor group than those in the clopidogrel group [ADP%, 69.00% (59.68%-88.95%) vs. 60.55% (35.98%-78.35%), P = .0020; AA%, 53.65% (22.75%-79.28%) vs. 15.15% (5.75%-70.25%), P = .0127]. High on-treatment platelet reactivity (HTPR) on ADP was 2.17% with ticagrelor and 19.57% with clopidogrel. HTPR on AA was 50.00% with ticagrelor and 69.57% with clopidogrel. Ticagrelor and clopidogrel caused the inhibition of ADP and AA-induced platelet aggregation. Moreover, ticagrelor monotherapy had a stronger inhibitory effect than clopidogrel monotherapy (except on collagen and epinephrine).

ASFold-DNN: Protein Fold Recognition Based on Evolutionary Features With Variable Parameters Using Full Connected Neural Network.

Protein fold recognition contribute to comprehend the function of proteins, which is of great help to the gene therapy of diseases and the development of new drugs. Researchers have been working in this direction and have made considerable achievements, but challenges still exist on low sequence similarity datasets. In this study, we propose the ASFold-DNN framework for protein fold recognition research. Above all, four groups of evolutionary features are extracted from the primary structures of proteins, and a preliminary selection of variable parameter is made for two groups of features including ACC _HMM and SXG _HMM, respectively. Then several feature selection algorithms are selected for comparison and the best feature selection scheme is obtained by changing their internal threshold values. Finally, multiple hyper-parameters of Full Connected Neural Network are fully optimized to construct the best model. DD, EDD and TG datasets with low sequence similarities are chosen to evaluate the performance of the models constructed by the framework, and the final prediction accuracy are 85.28, 95.00 and 88.84 percent, respectively. Furthermore, the ASTRAL186 and LE datasets are introduced to further verify the generalization ability of our proposed framework. Comprehensive experimental results prove that the ASFold-DNN framework is more prominent than the state-of-the-art studies on protein fold recognition. The source code and data of ASFold-DNN can be downloaded from https://github.com/Bioinformatics-Laboratory/project/tree/master/ASFold.

Functional Evaluation of Intermediate Coronary Lesions with Integrated Computed Tomography Angiography and Invasive Angiography in Patients with Stable Coronary Artery Disease.

Background and objectives: The hemodynamic evaluation of coronary stenoses undergoes a transition from wire-based invasive measurements to image-based computational assessments. However, fractional flow reserve (FFR) values derived from coronary CT angiography (CCTA) and angiography-based quantitative flow ratio have certain limitations in accuracy and efficiency, preventing their widespread use in routine practice. Hence, we aimed to investigate the diagnostic performance of FFR derived from the integration of CCTA and invasive angiography (FFRCT-angio) with artificial intelligence assistance in patients with stable coronary artery disease (CAD). Methods: Forty stable CAD patients with 67 target vessels (50%-90% diameter stenosis) were included in this single-center retrospective study. All patients underwent CCTA followed by coronary angiography with FFR measurement within 30 days. Both CCTA and angiographic images were combined to generate a three-dimensional reconstruction of the coronary arteries using artificial intelligence. Subsequently, functional assessment was performed through a deep learning algorithm. FFR was used as the reference. Results: FFRCT-angio values were significantly correlated with FFR values (r = 0.81, P < 0.001, Spearman analysis). Per-vessel diagnostic accuracy of FFRCT-angio was 92.54%. Sensitivity and specificity in identifying ischemic lesions were 100% and 88.10%, respectively. Positive predictive value and negative predictive value were 83.33% and 100%, respectively. Moreover, the diagnostic performance of FFRCT-angio was satisfactory in different target vessels and different segment lesions. Conclusions: FFRCT-angio exhibits excellent diagnostic performance of identifying ischemic lesions in patients with stable CAD. Combining CCTA and angiographic imaging, FFRCT-angio may represent an effective and practical alternative to invasive FFR in selected patients.

Effects of Sacubitril/Valsartan on the Expression of CaMKII/Cav1.2 in Atrial Fibrillation Stimulation Rabbit Model.

Methods: Overall, 18 rabbits were randomly divided into control, pacing (600 beats/min), and pacing+sac/val groups. The rabbits in the pacing+sac/val cohort received oral sac/val (10 mg/kg twice daily) across the 21-day investigation period. After three weeks, the atrial effective refractory period (AERP) and AF induction rate were compared. HL-1 cultures were exposed to fast pacing (24 h) with and without LBQ657 (active sacubitril form)/valsartan. Western blots were used for detecting Cav1.2 and CaMKII expression within atrial muscles of the rabbits and HL-1 cultures of AF model. Results: In comparison to the sham cohort, the AF induction rate was markedly increased together with AERP reduction within pacing cohort. Such changes were markedly rescued through sac/val treatment in pacing+sac/val cohort. The proteomic expression profiles of CaMKII and Cav1.2 showed that the CaMKII expression was markedly upregulated, while Cav1.2 expression was downregulated in the pacing cohort. Importantly, these effects were absent in pacing+sac/val cohort. Conclusion: Results of this study show that sac/val treatment regulates the expression of CaMKII/Cav1.2 and could alter this pathway in atrial rapid electrical stimulation models. Therefore, this investigation could contribute to a novel strategy in AF therapeutics in clinical settings.

BERT-m7G: A Transformer Architecture Based on BERT and Stacking Ensemble to Identify RNA N7-Methylguanosine Sites from Sequence Information.

As one of the most prevalent posttranscriptional modifications of RNA, N7-methylguanosine (m7G) plays an essential role in the regulation of gene expression. Accurate identification of m7G sites in the transcriptome is invaluable for better revealing their potential functional mechanisms. Although high-throughput experimental methods can locate m7G sites precisely, they are overpriced and time-consuming. Hence, it is imperative to design an efficient computational method that can accurately identify the m7G sites. In this study, we propose a novel method via incorporating BERT-based multilingual model in bioinformatics to represent the information of RNA sequences. Firstly, we treat RNA sequences as natural sentences and then employ bidirectional encoder representations from transformers (BERT) model to transform them into fixed-length numerical matrices. Secondly, a feature selection scheme based on the elastic net method is constructed to eliminate redundant features and retain important features. Finally, the selected feature subset is input into a stacking ensemble classifier to predict m7G sites, and the hyperparameters of the classifier are tuned with tree-structured Parzen estimator (TPE) approach. By 10-fold cross-validation, the performance of BERT-m7G is measured with an ACC of 95.48% and an MCC of 0.9100. The experimental results indicate that the proposed method significantly outperforms state-of-the-art prediction methods in the identification of m7G modifications.

Detection of circRNA Biomarker for Acute Myocardial Infarction Based on System Biological Analysis of RNA Expression.

Acute myocardial infarction (AMI) is myocardial necrosis caused by the persistent interruption of myocardial blood supply, which has high incidence rate and high mortality in middle-aged and elderly people in the worldwide. Biomarkers play an important role in the early diagnosis and treatment of AMI. Recently, more and more researches confirmed that circRNA may be a potential diagnostic biomarker and therapeutic target for cardiovascular diseases. In this paper, a series of biological analyses were performed to find new effective circRNA biomarkers for AMI. Firstly, the expression levels of circRNAs in blood samples of patients with AMI and those with mild coronary stenosis were compared to reveal circRNAs which were involved in AMI. Then, circRNAs which were significant expressed abnormally in the blood samples of patients with AMI were selected from those circRNAs. Next, a ceRNA network was constructed based on interactions of circRNA, miRNA and mRNA through biological analyses to detect crucial circRNA associated with AMI. Finally, one circRNA was selected as candidate biomarker for AMI. To validate effectivity and efficiency of the candidate biomarker, fluorescence in situ hybridization, hypoxia model of human cardiomyocytes, and knockdown and overexpression analyses were performed on candidate circRNA biomarker. In conclusion, experimental results demonstrated that the candidate circRNA was an effective biomarker for diagnosis and therapy of AMI.

DNN-m6A: A Cross-Species Method for Identifying RNA N6-Methyladenosine Sites Based on Deep Neural Network with Multi-Information Fusion.

As a prevalent existing post-transcriptional modification of RNA, N6-methyladenosine (m6A) plays a crucial role in various biological processes. To better radically reveal its regulatory mechanism and provide new insights for drug design, the accurate identification of m6A sites in genome-wide is vital. As the traditional experimental methods are time-consuming and cost-prohibitive, it is necessary to design a more efficient computational method to detect the m6A sites. In this study, we propose a novel cross-species computational method DNN-m6A based on the deep neural network (DNN) to identify m6A sites in multiple tissues of human, mouse and rat. Firstly, binary encoding (BE), tri-nucleotide composition (TNC), enhanced nucleic acid composition (ENAC), K-spaced nucleotide pair frequencies (KSNPFs), nucleotide chemical property (NCP), pseudo dinucleotide composition (PseDNC), position-specific nucleotide propensity (PSNP) and position-specific dinucleotide propensity (PSDP) are employed to extract RNA sequence features which are subsequently fused to construct the initial feature vector set. Secondly, we use elastic net to eliminate redundant features while building the optimal feature subset. Finally, the hyper-parameters of DNN are tuned with Bayesian hyper-parameter optimization based on the selected feature subset. The five-fold cross-validation test on training datasets show that the proposed DNN-m6A method outperformed the state-of-the-art method for predicting m6A sites, with an accuracy (ACC) of 73.58%-83.38% and an area under the curve (AUC) of 81.39%-91.04%. Furthermore, the independent datasets achieved an ACC of 72.95%-83.04% and an AUC of 80.79%-91.09%, which shows an excellent generalization ability of our proposed method.

Structural protein fold recognition based on secondary structure and evolutionary information using machine learning algorithms.

Understanding the function of protein is conducive to research in advanced fields such as gene therapy of diseases, the development and design of new drugs, etc. The prerequisite for understanding the function of a protein is to determine its tertiary structure. The realization of protein structure classification is indispensable for this problem and fold recognition is a commonly used method of protein structure classification. Protein sequences of 40% identity in the ASTRAL protein classification database are used for fold recognition research in current work to predict 27 folding types which mostly belong to four protein structural classes: α, ß, α/ß and α + ß. We extract features from primary structure of protein using methods covering DSSP, PSSM and HMM which are based on secondary structure and evolutionary information to convert protein sequences into feature vectors that can be recognized by machine learning algorithm and utilize the combination of LightGBM feature selection algorithm and incremental feature selection method (IFS) to find the optimal classifiers respectively constructed by machine learning algorithms on the basis of tree structure including Random Forest, XGBoost and LightGBM. Bayesian optimization method is used for hyper-parameter adjustment of machine learning algorithms to make the accuracy of fold recognition reach as high as 93.45% at last. The result obtained by the model we propose is outstanding in the study of protein fold recognition.

Tranilast prevents doxorubicin-induced myocardial hypertrophy and angiotensin II synthesis in rats.

An increase in oxidative stress is an important pathological mechanism of heart injury induced by doxorubicin (DOX). Tranilast is an anti-allergy drug that has been shown to possess good antioxidant activity in previous studies. The overexpression and secretion of chymase by mast cells (MCs) increase the pathological overexpression of angiotensin II (Ang II), which plays a crucial role in myocardial hypertrophy and the deterioration of heart disease. The MC stabilizer tranilast (N-(3,4-dimethoxycinnamoyl) anthranilic acid; tran) prevents mast cells from degranulating, which may reduce DOX-induced Ang II synthesis. Therefore, in the present study, we hypothesized that tranilast will protect rats from DOX-induced myocardial damage via its antioxidant activity, thereby inhibiting Ang II expression. Thirty male Wistar rats were divided into three groups (n = 10 in each group) that received DOX, a combination of DOX and tranilast or saline (the control group) to test this hypothesis. Tranilast suppressed chymase expression, reduced Ang II levels and prevented the myocardial hypertrophy and the deterioration of heart function induced by DOX. Based on the findings of the present study, the suppression of chymase-dependent Ang-II production and the direct effect of tranilast on the inhibition of apoptosis and fibrosis because of its antioxidant stress capacity may contribute to the protective effect of tranilast against DOX-induced myocardial hypertrophy.

Efficacy and safety of different ticagrelor regimens versus clopidogrel in patients with coronary artery disease: a retrospective multicenter study (SUPERIOR).

Current guidelines favor dual anti-platelet therapy with ticagrelor 90 mg BID (T90BID) over clopidogrel 75 mg QD (C75QD) in addition to aspirin for acute coronary syndrome. However, an increased risk of ticagrelor-related adverse events prompted the evaluation of low-dose regimens. This study (NCT03381742) retrospectively analyzed the data from 11 hospitals on 3,043 patients with coronary artery disease, who received C75QD, T90BID, ticagrelor 45 mg BID (T45BID), or ticagrelor 90 mg QD (T90QD). Compared with C75QD, both T45BID and T90QD showed significantly higher inhibition of platelet aggregation (P < .0001) and lower platelet-fibrin clot strength (P < .0001) induced by adenosine diphosphate. Furthermore, compared with T90BID, two low-dose regimens had a much lower minor bleeding rate and a significantly higher proportion of patients within the therapeutic window for P2Y12 receptor reactivity. There were no significant differences between T45BID and T90QD in the trough plasma concentrations of ticagrelor and its active metabolite. Similar efficacy and safety outcomes were observed in the propensity score-matched analysis. In conclusion, the low-dose ticagrelor regimen, either T45BID or T90QD, may provide a more attractive benefit-risk profile than C75QD or T90BID.

Succinylation Site Prediction Based on Protein Sequences Using the IFS-LightGBM (BO) Model.

Succinylation is an important posttranslational modification of proteins, which plays a key role in protein conformation regulation and cellular function control. Many studies have shown that succinylation modification on protein lysine residue is closely related to the occurrence of many diseases. To understand the mechanism of succinylation profoundly, it is necessary to identify succinylation sites in proteins accurately. In this study, we develop a new model, IFS-LightGBM (BO), which utilizes the incremental feature selection (IFS) method, the LightGBM feature selection method, the Bayesian optimization algorithm, and the LightGBM classifier, to predict succinylation sites in proteins. Specifically, pseudo amino acid composition (PseAAC), position-specific scoring matrix (PSSM), disorder status, and Composition of k-spaced Amino Acid Pairs (CKSAAP) are firstly employed to extract feature information. Then, utilizing the combination of the LightGBM feature selection method and the incremental feature selection (IFS) method selects the optimal feature subset for the LightGBM classifier. Finally, to increase prediction accuracy and reduce the computation load, the Bayesian optimization algorithm is used to optimize the parameters of the LightGBM classifier. The results reveal that the IFS-LightGBM (BO)-based prediction model performs better when it is evaluated by some common metrics, such as accuracy, recall, precision, Matthews Correlation Coefficient (MCC), and F-measure.

Sacubitril/valsartan attenuates atrial electrical and structural remodelling in a rabbit model of atrial fibrillation.

Atrial structural and electrical remodelling play important roles in atrial fibrillation (AF). Sacubitril/valsartan attenuates cardiac remodelling in heart failure. However, the effect of sacubitril/valsartan on AF is unclear. The aim of this study was to evaluate the effect of sacubitril/valsartan on atrial electrical and structural remodelling in AF and investigate the underlying mechanism of action. Thirty-three rabbits were randomized into sham, RAP, and sac/val groups. HL-1 cells were subjected to control treatment or rapid pacing with or without LBQ657 and valsartan. Echocardiography, atrial electrophysiology, and histological examination were performed. The concentration of Ca2+ and expression levels of calcineurin, NFAT, p-NFAT, Cav1.2, collagen Ⅰ and Ⅲ, ANP, BNP, CNP, NT-proBNP, and ST2 in HL-1 cells, and IcaL in left atrial cells, were determined. We observed that compared to that in the sham group, the atrium and right ventricle were enlarged, myocardial fibrosis was markedly higher, AF inducibility was significantly elevated, and atrial effective refractory periods were shortened in the RAP group. These effects were significantly reversed by sacubitril/valsartan. Compared to that in the sham group, collagen Ⅰ and Ⅲ, NT-proBNP, ST2, calcineurin, and NFAT were significantly up-regulated, while p-NFAT and Cav1.2 were down-regulated in the RAP group, and sacubitril/valsartan inhibited these changes. Ca2+ concentration increased and ICaL density decreased in in vivo and in vitro AF models, reversed by sacubitril/valsartan. Sacubitril/valsartan attenuates atrial electrical remodelling and ameliorates structure remodelling in AF. This study paves the way for the possibility of clinical use of sacubitril/valsartan in AF patients.

Women Are at a Higher Risk of Chronic Metabolic Diseases Compared to Men With Increasing Body Mass Index in China.

Background: Chronic non-communicable diseases are the major causes of mortality in the world. However, few studies have investigated the association between multi-categories BMI and chronic diseases from perspective of sex stratification. This study aimed to investigate the risk of chronic diseases at different BMI levels, and to further explore whether BMI-health risk associations differ by sex. Methods: In total, 21,134 participants aged 19-65 years (60.4% men) from the Tianjin People's Hospital, Tianjin Union Medical Center-Health Management Center were recruited for this cross-sectional study. Sex-specific percentiles of BMI were calculated and divided into 11 categories according to the 2000 CDC growth charts. Health-related indicators, such as hyperglycemia, hypertension, non-alcoholic fatty liver diseases (NAFLD), hyperuricemia, etc., were used as dependent variables in this study. Statistical differences were tested by unpaired Mann-Whitney U-test and chi-squared test. Logistic regression models were used to examine the associations between BMI and health-related indicators. Results: The risk of hyperglycemia (OR: 1.67, 95%CI: 1.23-2.29), NAFLD (OR: 2.22, 95%CI: 1.74-2.85), hypertriglyceridemia (OR: 1.65, 95%CI: 1.28-2.12), and hyperuricemia (OR: 1.39, 95%CI: 1.12-1.72) in men began to increase significantly when BMI was in the range of 22.59-23.89 kg/m2. However, in women, the risk of hyperglycemia (OR: 3.02, 95%CI: 1.25-8.98) and hyperuricemia (OR: 1.94, 95%CI: 1.26-3.05) began to increase significantly when BMI was in the range of 22.76-23.62 kg/m2, and the risk of NAFLD (OR: 5.48, 95%CI: 2.49-14.47) began to increase significantly when BMI was in the range of 21.08-21.97 kg/m2. Besides, at the same BMI level, the risk of diseases in women were significantly higher than that in men, especially when BMI > 25 kg/m2. Conclusion: In the Chinese population, the risk of chronic diseases in women were significantly higher than that in men at the same BMI level, especially when BMI was >25 kg/m2. In addition, the risk of chronic diseases began to increase significantly when BMI was >21.97 kg/m2 in women and 23.89 kg/m2 in men. The results indicated that women should be more alert to the risk of chronic diseases caused by the increase of BMI than men.