Flavone inhibits Staphylococcus aureus virulence via inhibiting the sae two component system.

The rising prevalence of antibiotic resistance in Staphylococcus aureus calls for the development of innovative antimicrobial agents targeting novel pathways. S. aureus generates various virulence factors that compromise host defense mechanisms. Flavone, a core structure of flavonoids, has been shown to diminish the production of staphyloxanthin and alpha-hemolysin. Nonetheless, the influence of flavone on the majority of other virulence factors in S. aureus and its underlying molecular mechanism remain elusive. In this study, we examined the impact of flavone on the transcriptional profile of S. aureus using transcriptome sequencing. Our findings revealed that flavone substantially downregulated the expression of over 30 virulence factors implicated in immune evasion by the pathogen. Gene set enrichment analysis of the fold change-ranked gene list in relation to the Sae regulon indicated a robust association between flavone-induced downregulation and membership in the Sae regulon. Through the analysis of Sae target promoter-gfp fusion expression patterns, we observed a dose-dependent inhibition of Sae target promoter activity by flavone. Moreover, we discovered that flavone protected human neutrophils from S. aureus-mediated killing. Flavone also decreased the expression of alpha-hemolysin and other hemolytic toxins, resulting in a reduction in S. aureus' hemolytic capacity. Additionally, our data suggested that the inhibitory effect of flavone on the Sae system operates independently of its capacity to lower staphyloxanthin levels. In conclusion, our study proposes that flavone exhibits a broad inhibitory action on multiple virulence factors of S. aureus by targeting the Sae system, consequently diminishing the bacterium's pathogenicity.

Combination effect between gut microbiota and traditional potentially modifiable risk factors for first-ever ischemic stroke in Tujia, Miao and Han populations in China.

China has had explosive growth in ischemic stroke (IS) burden with significant ethnic and geographic disparities. The aim of this study was to explore the possible combination effect between gut microbiota and traditional potentially modifiable risk factors for IS among two ethnic minorities (Tujia and Miao) and the Han population. Herein, we first used the 16 S rRNA sequencing to compare the gut microbial compositions of 82 patients with first-ever IS vs. 82 normal controls (NCs) among Han, Tujia, and Miao people between 1 May 2018 and 30 April 2019, from Xiangxi Tujia and Miao Autonomous Prefecture in China. An additive model was used to study the interaction between traditional risk factors and gut microbiota with R software. Linear discriminant analysis (LDA) and LDA effect size (LEfSe) results showed that the identified key gut microbiota's taxonomic composition varied in different ethnicity between the IS patients and NCs. Furthermore, families Lactobacillaceae, Enterococcaceae, Streptococcaceae, and Enterobacteriaceae were found to be positively correlated with high-risk factors and negatively correlated with preventive factors in the IS patients, but families Ruminococcaceae and Lachnospiraceae were just the opposite in the NCs. There were additive interactions between traditional risk factors (systolic blood pressure, diastolic blood pressure, and high-sensitive C-reactive protein) and family Enterococcaceae for first-ever IS with the attributable proportion due to the interaction was 0.74, 0.71, and 0.85, respectively; and the synergy index was 4.45, 3.78, and 7.01, respectively. This preliminary but promising study showed that the gut microbiota disturbances may potentially interact to IS with different ethnic host's traditional risk factors.

Spatial transcriptome profiling of normal human liver.

The comprehensive study of the spatial-cellular anatomy of the human liver is critical to addressing the cellular origins of liver disease. Here we conducted spatial transcriptomics on normal human liver tissue sections, providing detailed information of liver zonation at the transcriptional level. We present 6581 high-quality spots from normal livers of two human donors. In this dataset, cells were mainly hepatocytes, and we classified them into four sub-groups. Collectively, these data provide a reliable reference for studies on spatial heterogeneity of liver lobules.

Significance of Liver Zonation in Hepatocellular Carcinoma.

Liver zonation is fundamental to normal liver function, and numerous studies have investigated the microstructure of normal liver lobules. However, only a few studies have explored the zonation signature in hepatocellular carcinoma (HCC). In this study, we investigated the significance of liver zonation in HCC with the help of single-cell RNA sequencing (scRNA-seq) and multicolor immunofluorescence staining. Liver zonation-related genes were extracted from the literature, and a three-gene model was established for HCC prognosis. The model reliability was validated using bulk RNA and single-cell RNA-level data, and the underlying biological mechanism was revealed by a functional enrichment analysis. The results showed that the signaling pathways of high-risk groups were similar to those of perivenous zones in the normal liver, indicating the possible regulating role of hypoxia in HCC zonation. Furthermore, the co-staining results showed that the low-grade tumors lost their zonation features whereas the high-grade tumors lost the expression of zonation-related genes, which supported the results obtained from the sequencing data.

Identification of Context-Specific Fitness Genes Associated With Metabolic Rearrangements for Prognosis and Potential Treatment Targets for Liver Cancer.

Liver cancer is the most frequent fatal malignancy. Furthermore, there is a lack of effective therapeutics for this cancer type. To construct a prognostic model for potential beneficiary screens and identify novel treatment targets, we used an adaptive daisy model (ADaM) to identify context-specific fitness genes from the CRISPR-Cas9 screens database, DepMap. Functional analysis and prognostic significance were assessed using data from TCGA and ICGC cohorts, while drug sensitivity analysis was performed using data from the Liver Cancer Model Repository (LIMORE). Finally, a 25-gene prognostic model was established. Patients were then divided into high- and low-risk groups; the high-risk group had a higher stemness index and shorter overall survival time than the low-risk group. The C-index, time-dependent ROC curves, and multivariate Cox regression analysis confirmed the excellent prognostic ability of this model. Functional enrichment analysis revealed the importance of metabolic rearrangements and serine/threonine kinase activity, which could be targeted by trametinib and is the key pathway in regulating liver cancer cell viability. In conclusion, the present study provides a prognostic model for patients with liver cancer and might help in the exploration of novel therapeutic targets to ultimately improve patient outcomes.

Seek for Success: A Visualization Approach for Understanding the Dynamics of Academic Careers.

How to achieve academic career success has been a long-standing research question in social science research. With the growing availability of large-scale well-documented academic profiles and career trajectories, scholarly interest in career success has been reinvigorated, which has emerged to be an active research domain called the Science of Science (i.e., SciSci). In this study, we adopt an innovative dynamic perspective to examine how individual and social factors will influence career success over time. We propose ACSeeker, an interactive visual analytics approach to explore the potential factors of success and how the influence of multiple factors changes at different stages of academic careers. We first applied a Multi-factor Impact Analysis framework to estimate the effect of different factors on academic career success over time. We then developed a visual analytics system to understand the dynamic effects interactively. A novel timeline is designed to reveal and compare the factor impacts based on the whole population. A customized career line showing the individual career development is provided to allow a detailed inspection. To validate the effectiveness and usability of ACSeeker, we report two case studies and interviews with a social scientist and general researchers.

The Prognostic Model Based on Tumor Cell Evolution Trajectory Reveals a Different Risk Group of Hepatocellular Carcinoma.

Hepatocellular carcinoma (HCC) is one of the leading causes of cancer-related death worldwide, and heterogeneity of HCC is the major barrier in improving patient outcome. To stratify HCC patients with different degrees of malignancy and provide precise treatment strategies, we reconstructed the tumor evolution trajectory with the help of scRNA-seq data and established a 30-gene prognostic model to identify the malignant state in HCC. Patients were divided into high-risk and low-risk groups. C-index and receiver operating characteristic (ROC) curve confirmed the excellent predictive value of this model. Downstream analysis revealed the underlying molecular and functional characteristics of this model, including significantly higher genomic instability and stronger proliferation/progression potential in the high-risk group. In summary, we established a novel prognostic model to overcome the barriers caused by HCC heterogeneity and provide the possibility of better clinical management for HCC patients to improve their survival outcomes.

MSCs enhances the protective effects of valsartan on attenuating the doxorubicin-induced myocardial injury via AngII/NOX/ROS/MAPK signaling pathway.

OBJECTIVE: To verify if AngII/NOX/ROS/MAPK signaling pathway is involved in Doxorubicin (DOX)-induced myocardial injury and if mesenchymal stem cells (MSCs) could enhance the protective effects of valsartan (Val) on attenuating DOX-induced injury in vitro. METHODS: Reactive oxygen species (ROS) formation and the protein expression of AT1R, NOX2, NOX4, caspase-3, caspase-9 and MAPK signaling were assessed in H9c2 cardiomyocytes exposed to DOX for 24 h in the absence or presence of Val, NADPH oxidase inhibitor DPI or knockdown and overexpression of NADPH oxidase subunit: NOX2 and NOX4, co-culture with MSCs, respectively. Finally, MTT assay was used to determine the cell viability of H9c2 cells, MDA-MB-231 breast cancer cells and A549 pulmonary cancer cells under Val, DOX and Val+ DOX treatments. RESULTS: DOX increased ROS formation and upregulated proteins expression of AT1R, NOX2, NOX4, caspase-3, caspase-9 and MAPK signaling including p-p38, p-JNK, p-ERK in H9c2 cells. These effects could be attenuated by Val, DPI, NOX2 siRNA and NOX4 siRNA. Meanwhile, overexpression of NOX2 and NOX4 could significantly increase DOX-induced ROS formation and further upregulate apoptotic protein expressions and protein expressions of MAPK signaling. MSCs on top of Val further enhanced the protective effects of Val on reducing the DOX-induced ROS formation and downregulating the expression of apoptotic proteins and MAPK signaling as compared with Val alone in DOX-treated H9c2 cells. Simultaneous Val and DOX treatment did not affect cell viability of DOX-treated MDA-MB-231 breast cancer cells or A549 pulmonary cancer cells but significantly improved cell viability of DOX-treated H9c2 cardiomyocytes. CONCLUSIONS: AT1R/NOX/ROS/MAPK signaling pathway is involved in DOX-induced cardiotoxicity. Val treatment significantly attenuated DOX-induced cardiotoxicity, without affecting the anti-tumor effect of DOX. MSCs enhance the protective effects of Val on reducing the DOX-induced toxicity in H9c2 cells.

Ecological risk, health risk assessment, and pollution source analysis of Xinli Lake wetland based on triangular fuzzy number.

Wetland environmental pollution has become a global problem involving the ecological environment and human health. This study measured the concentration of seven potentially toxic elements (PTEs Hg, Cd, Zn, Cu, Cr, Pb, and As) in the soil upstream of the Xinli Lake wetland in China. Based on the fuzzy theory, the sources, spatial distribution, ecological risks, and health risks of pollutants are studied. The result shows that the concentrations of the seven potentially toxic elements are close to or exceed the background value, and their spatial distribution showed irregular changes. The soil upstream of the wetland has not been seriously polluted, and Cd, which has higher bioavailability, is the priority element for ecological risk. Pollutants do not harm human health; children face higher health risks; Pb and As have the highest carcinogenic and non-carcinogenic risks, respectively. Zn, Cu, Cr, Pb, and As in the study area are derived from agricultural activities, while Hg and Cd are mainly affected by soil-forming parent materials. Attention should be paid to controlling the intensity of agricultural activities to avoid excessive input and accumulation of pollutants that would harm the ecological environment and human health.

Protective effects of valsartan administration on doxorubicin­induced myocardial injury in rats and the role of oxidative stress and NOX2/NOX4 signaling.

Clinical application of doxorubicin (DOX) is hampered by its potential cardiotoxicity, however angiotensin receptor blockers could attenuate DOX­induced cardiomyopathy. The present study tested the hypothesis that simultaneous administration of valsartan (Val) with DOX could prevent DOX­induced myocardial injury by modulating myocardial NAD(P)H oxidase (NOX) expression in rats. Eight­week­old male Sprague­Dawley rats were randomly divided into control (CON), DOX, and DOX+Val groups. After 10 weeks, surviving rats underwent echocardiography examination, myocardial mRNA and protein expression detection of NOX1, NOX2 and NOX4. H9C2 cells were used to perform in vitro experiments, reactive oxygen species (ROS) production and apoptosis were observed under the conditions of down­ or upregulation of NOX2 and NOX4 in DOX­ and DOX+Val­treated H9C2 cells. Cardiac function was significantly improved, pathological lesion and collagen volume fraction were significantly reduced in the DOX+Val group compared with the DOX group (all P<0.05). Myocardial protein and mRNA expression of NOX2 and NOX4 was significantly downregulated in DOX+Val group compared with in the DOX group (all P<0.05). In vitro, ROS production and apoptosis in DOX­treated H9C2 cells was significantly reduced by NOX2­small interfering (si)RNA and NOX4­siRNA, and significantly increased by overexpressing NOX2 and NOX4. To conclude, Val applied simultaneously with DOX could prevent DOX­induced myocardial injury and reduce oxidative stress by downregulating the myocardial expression of NOX2 and NOX4 in rats.

Identification of key genes for type 1 diabetes mellitus by network-based guilt by association.

OBJECTIVE This study aimed to propose a co-expression-network (CEN) based gene functional inference by extending the "Guilt by Association" (GBA) principle to predict candidate gene functions for type 1 diabetes mellitus (T1DM). METHODS Firstly, transcriptome data of T1DM were retrieved from the genomics data repository for differentially expressed gene (DEGs) analysis, and a weighted differential CEN was generated. The area under the receiver operating characteristics curve (AUC) was chosen to determine the performance metric for each Gene Ontology (GO) term. Differential expression analysis identified 325 DEGs in T1DM, and co-expression analysis generated a differential CEN of edge weight > 0.8. RESULTS A total of 282 GO annotations with DEGs > 20 remained for functional inference. By calculating the multifunctionality score of genes, gene function inference was performed to identify the optimal gene functions for T1DM based on the optimal ranking gene list. Considering an AUC > 0.7, six optimal gene functions for T1DM were identified, such as regulation of immune system process and receptor activity. CONCLUSIONS CEN-based gene functional inference by extending the GBA principle predicted 6 optimal gene functions for T1DM. The results may be potential paths for therapeutic or preventive treatments of T1DM.

Identification of key genes for type 1 diabetes mellitus by network-based guilt by association

SUMMARY OBJECTIVE This study aimed to propose a co-expression-network (CEN) based gene functional inference by extending the "Guilt by Association" (GBA) principle to predict candidate gene functions for type 1 diabetes mellitus (T1DM). METHODS Firstly, transcriptome data of T1DM were retrieved from the genomics data repository for differentially expressed gene (DEGs) analysis, and a weighted differential CEN was generated. The area under the receiver operating characteristics curve (AUC) was chosen to determine the performance metric for each Gene Ontology (GO) term. Differential expression analysis identified 325 DEGs in T1DM, and co-expression analysis generated a differential CEN of edge weight > 0.8. RESULTS A total of 282 GO annotations with DEGs > 20 remained for functional inference. By calculating the multifunctionality score of genes, gene function inference was performed to identify the optimal gene functions for T1DM based on the optimal ranking gene list. Considering an AUC > 0.7, six optimal gene functions for T1DM were identified, such as regulation of immune system process and receptor activity. CONCLUSIONS CEN-based gene functional inference by extending the GBA principle predicted 6 optimal gene functions for T1DM. The results may be potential paths for therapeutic or preventive treatments of T1DM.

RESUMO OBJETIVO O objetivo deste estudo é realizar uma inferência funcional genética baseada na rede de coexpressão (CEN), expandindo o escopo do princípio de "Culpa por Associação" (GBA - Guilt by Association) para prever as funções genéticas do diabetes mellitus tipo 1 (T1DM). MÉTODOS Primeiro, os dados transcritos do T1DM foram recuperados do repositório de dados genômicos para a análise dos genes diferenciais (DEGs), e foi gerada uma CEN diferencial ponderada. A área sob a curva ROC (AUC) foi escolhida para determinar a métrica de desempenho para cada termo de Ontologia Genética (GO). A análise da expressão diferencial identificou 325 DEGs no T1DM, e a análise de coexpressão gerou uma CEN diferencial com aresta de peso >0,8. RESULTADOS Um total de 282 anotações de GO com DEGs >20 foram mantidas para inferência funcional. Ao calcular a pontuação de multifuncionalidade dos genes, a inferência da função genética foi realizada para identificar as funções genéticas ideais para T1DM com base na lista de classificação genética ideal. Considerando um valor de AUC >0,7, foram identificadas seis funções genéticas ideais para a T1DM, tais como a regulação do processo imunológico e da atividade dos receptores. CONCLUSÕES A inferência funcional genética baseada em CEN, ao expandir o princípio de GBA, previu seis funções genéticas ideais para o T1DM. Os resultados podem ser caminhos potenciais para tratamentos terapêuticos ou preventivos do T1DM.

Phase Mapping in EBSD Using Convolutional Neural Networks.

The emergence of commercial electron backscatter diffraction (EBSD) equipment ushered in an era of information rich maps produced by determining the orientation of user-selected crystal structures. Since then, a technological revolution has occurred in the quality, rate detection, and analysis of these diffractions patterns. The next revolution in EBSD is the ability to directly utilize the information rich diffraction patterns in a high-throughput manner. Aided by machine learning techniques, this new methodology is, as demonstrated herein, capable of accurately separating phases in a material by crystal symmetry, chemistry, and even lattice parameters with fewer human decisions. This work is the first demonstration of such capabilities and addresses many of the major challenges faced in modern EBSD. Diffraction patterns are collected from a variety of samples, and a convolutional neural network, a type of machine learning algorithm, is trained to autonomously recognize the subtle differences in the diffraction patterns and output phase maps of the material. This study offers a path to machine learning coupled phase mapping as databases of EBSD patterns encompass an increasing number of the possible space groups, chemistry changes, and lattice parameter variations.

An incremental learning system for atrial fibrillation detection based on transfer learning and active learning.

BACKGROUND AND OBJECTIVE: Atrial fibrillation (AF) is a type of arrhythmia with high incidence. Automatic AF detection methods have been studied in previous works. However, a model cannot be used all the time without any improvement. And updating model requires adequate data and cost. Therefore, this study aims at finding a low-cost way to choose learning samples and developing an incremental learning system for AF detection. METHODS: Based on transfer learning and active learning, this paper proposed a loop-locked framework integrating AF diagnose, label query, and model fine-tuning. In the pre-training stage, a novel multiple-input deep neural network (MIDNN) is pre-trained using labeled samples from an original training set. In practical application, the model can be used for AF detection. Meanwhile, continuous data is collected to form the candidate set. In the incremental learning stage, the model was fine-tuned continuously by the most informative samples in the candidate set. These samples are selected from the candidate set based on the pre-trained model and a new active learning strategy. The strategy combines the features and the uncertainty of the predicted results. RESULTS: In order to evaluate the method, the MIT-BIH atrial fibrillation database was used for pre-training and samples of the MIT-BIH arrhythmia database were taken as candidate set. The initial values of Acc, Sen, and PPV were 87.40%, 97.46%, and 81.11%. These indexes reached to the top values of 97.53%, 100.00%, and 95.29% after 14 iterations. Hence, the number of queries was saved by 90.67%. CONCLUSIONS: The proposed system is able to update the model continuously and reduce the labeling cost over 90%. The comparisons demonstrated the effectiveness of MIDNN model and the suitability of novel learning strategy for AF. Moreover, this framework can be extended to other biomedical applications.

An Improved Convolutional Neural Network Based Approach for Automated Heartbeat Classification.

With age, our blood vessels are prone to aging, which induces cardiovascular disease. As an important basis for diagnosing heart disease and evaluating heart function, the electrocardiogram (ECG) records cardiac physiological electrical activity. Abnormalities in cardiac physiological activity are directly reflected in the ECG. Thus, ECG research is conducive to heart disease diagnosis. Considering the complexity of arrhythmia detection, we present an improved convolutional neural network (CNN) model for accurate classification. Compared with the traditional machine learning methods, CNN requires no additional feature extraction steps due to the automatic feature processing layers. In this paper, an improved CNN is proposed to automatically classify the heartbeat of arrhythmia. Firstly, all the heartbeats are divided from the original signals. After segmentation, the ECG heartbeats can be inputted into the first convolutional layers. In the proposed structure, kernels with different sizes are used in each convolution layer, which takes full advantage of the features in different scales. Then a max-pooling layer followed. The outputs of the last pooling layer are merged and as the input to fully-connected layers. Our experiment is in accordance with the AAMI inter-patient standard, which included normal beats (N), supraventricular ectopic beats (S), ventricular ectopic beats (V), fusion beats (F), and unknown beats (Q). For verification, the MIT arrhythmia database is introduced to confirm the accuracy of the proposed method, then, comparative experiments are conducted. The experiment demonstrates that our proposed method has high performance for arrhythmia detection, the accuracy is 99.06%. When properly trained, the proposed improved CNN model can be employed as a tool to automatically detect different kinds of arrhythmia from ECG.

A High Precision Real-time Premature Ventricular Contraction Assessment Method based on the Complex Feature Set.

This paper presents a high precision and low computational complexity premature ventricular contraction (PVC) assessment method for the ECG human-machine interface device. The original signals are preprocessed by integrated filters. Then, R points and surrounding feature points are determined by corresponding detection algorithms. On this basis, a complex feature set and feature matrices are obtained according to the position feature points. Finally, an exponential Minkowski distance method is proposed for PVC recognition. Both public dataset and clinical experiments were utilized to verify the effectiveness and superiority of the proposed method. The results show that our R peak detection algorithm can substantially reduce the error rate, and obtained 98.97% accuracy for QRS complexes. Meanwhile, the accuracy of PVC recognition was 98.69% for the MIT-BIH database and 98.49% for clinical tests. Moreover, benefiting from the lightweight of our model, it can be easily applied to portable healthcare devices for human-computer interaction.

Prediction of seed gene function in progressive diabetic neuropathy by a network-based inference method.

Guilt by association (GBA) algorithm has been widely used to statistically predict gene functions, and network-based approach increases the confidence and veracity of identifying molecular signatures for diseases. This work proposed a network-based GBA method by integrating the GBA algorithm and network, to identify seed gene functions for progressive diabetic neuropathy (PDN). The inference of predicting seed gene functions comprised of three steps: i) Preparing gene lists and sets; ii) constructing a co-expression matrix (CEM) on gene lists by Spearman correlation coefficient (SCC) method and iii) predicting gene functions by GBA algorithm. Ultimately, seed gene functions were selected according to the area under the receiver operating characteristics curve (AUC) index. A total of 79 differentially expressed genes (DEGs) and 40 background gene ontology (GO) terms were regarded as gene lists and sets for the subsequent analyses, respectively. The predicted results obtained from the network-based GBA approach showed that 27.5% of all gene sets had a good classified performance with AUC >0.5. Most significantly, 3 gene sets with AUC >0.6 were denoted as seed gene functions for PDN, including binding, molecular function and regulation of the metabolic process. In summary, we predicted 3 seed gene functions for PDN compared with non-progressors utilizing network-based GBA algorithm. The findings provide insights to reveal pathological and molecular mechanism underlying PDN.

Combined Menin and EGFR Inhibitors Synergize to Suppress Colorectal Cancer via EGFR-Independent and Calcium-Mediated Repression of SKP2 Transcription.

Menin is a nuclear epigenetic regulator that can both promote and suppress tumor growth in a highly tissue-specific manner. The role of menin in colorectal cancer, however, remains unclear. Here, we demonstrate that menin was overexpressed in colorectal cancer and that inhibition of menin synergized with small-molecule inhibitors of EGFR (iEGFR) to suppress colorectal cancer cells and tumor xenografts in vivo in an EGFR-independent manner. Mechanistically, menin bound the promoter of SKP2, a pro-oncogenic gene crucial for colorectal cancer growth, and promoted its expression. Moreover, the iEGFR gefitinib activated endoplasmic reticulum calcium channel inositol trisphosphate receptor 3 (IP3R3)-mediated release of calcium, which directly bound menin. Combined inhibition of menin and iEGFR-induced calcium release synergistically suppressed menin-mediated expression of SKP2 and growth of colorectal cancer. Together, these findings uncover a molecular convergence of menin and the iEGFR-induced, IP3R3-mediated calcium release on SKP2 transcription and reveal opportunities to enhance iEGFR efficacy to improve treatments for colorectal cancer. SIGNIFICANCE: Menin acts as a calcium-responsive regulator of SKP2 expression, and small molecule EGFR inhibitors, which induce calcium release, synergize with Menin inhibition to reduce SKP2 expression and suppress colorectal cancer.

A hierarchical method based on weighted extreme gradient boosting in ECG heartbeat classification.

BACKGROUND AND OBJECTIVE: Electrocardiogram (ECG) is a useful tool for detecting heart disease. Automated ECG diagnosis allows for heart monitoring on small devices, especially on wearable devices. In order to recognize arrhythmias automatically, accurate classification method for electrocardiogram (ECG) heartbeats was studied in this paper. METHODS: Based on weighted extreme gradient boosting (XGBoost), a hierarchical classification method is proposed. A large number of features from 6 categories are extracted from the preprocessed heartbeats. Then recursive feature elimination is used for selecting features. Afterwards, a hierarchical classifier is constructed in classification stage. The hierarchical classifier is composed of threshold and XGBoost classifiers. And the XGBoost classifiers are improved with weights. RESULTS: The method was applied to an inter-patient experiment conforming AAMI standard. The obtained sensitivities for normal (N), supraventricular (S), ventricular (V), fusion (F), and Unknown beats (Q) were 92.1%, 91.7%, 95.1%, and 61.6%. Positive predictive values of 99.5%, 46.2%, 88.1%, and 15.2% were also provided for the four classes. CONCLUSIONS: XGBoost was improved and firstly introduced in single heartbeat classification. A comparison showed the effectiveness of the novel method. The method was more suitable for clinical application as both high positive predictive value for N class and high sensitivities for abnormal classes were provided.