RESUMO
OBJECTIVE: To investigate the association of coronary plaque burden variables derived from coronary computed tomography angiography (CCTA) before patients underwent their first percutaneous coronary intervention (PCI) procedure and major adverse cardiovascular events (MACEs) after PCI. METHODS: Patients who underwent CCTA before their first PCI were included retrospectively. A radiologist and a cardiologist analyzed CCTA images on a dedicated workstation. The coronary plaque burden variables included total plaque volume, total percent atheroma volume, volumes and fractions of total low-attenuation plaque, total fibrous plaque, and total calcified plaque. The primary outcomes were MACEs, a composite of all-cause death, nonfatal myocardial infarction, nonfatal stroke, and unscheduled coronary revascularization. RESULTS: A total of 230 patients were included in the final analysis. During a median follow-up of 4.8 years, 67 MACEs occurred. Total plaque volume, total percent atheroma volume, volumes of total low-attenuation plaque and total fibrous plaque but not their fractions were independent predictors for MACEs. Compared with the first tertiles, the hazard ratio of the third tertile of total plaque volume, total percent atheroma volume, total low-attenuation plaque volume, and total fibrous plaque volume were 2.06 (95% CI: 1.03-4.15), 2.15 (95% CI: 1.02-4.51), 3.04 (95% CI: 1.45-6.36), and 2.23 (95% CI: 1.11-4.46), respectively. Neither total calcified plaque volume nor fraction was associated with MACEs independently. CONCLUSION: Selected pre-PCI CCTA-derived variables, including total percent atheroma volume, volumes of total plaque, total low-attenuation plaque and total fibrous plaque, were significantly associated with MACEs after PCI, suggesting that CCTA before PCI reveals the residual risk after revascularization. CLINICAL RELEVANCE STATEMENT: The coronary plaque burden variables derived from coronary computed tomography angiography before percutaneous coronary intervention are independently associated with major adverse cardiovascular events, which could be instrumental in optimizing patient management. KEY POINTS: Coronary plaque burden is associated with cardiovascular events in patients with coronary artery disease. Selected total plaque burden variables derived from coronary computed tomography angiography before percutaneous coronary intervention were associated with poor prognosis. Routine coronary computed tomography angiography before percutaneous coronary intervention might be helpful in reducing future risks.
RESUMO
BACKGROUND: An increasing body of observational studies have indicated an association between gut microbiota and endometriosis. However, the causal relationship between them is not yet clear. In this study, we employed Mendelian randomization method to investigate the causal relationship between 211 gut microbiota taxa and endometriosis. METHODS: Independent genetic loci significantly associated with the relative abundance of 211 gut microbiota taxa, based on predefined thresholds, were extracted as instrumental variables. The primary analytical approach employed was the IVW method. Effect estimates were assessed primarily using the odds ratio and 95% confidence intervals. Supplementary analyses were conducted using MR-Egger regression, the weighted median method, the simple mode and the weighted mode method to complement the IVW results. In addition, we conducted tests for heterogeneity, horizontal pleiotropy, sensitivity analysis, and MR Steiger to assess the robustness of the results and the strength of the causal relationships. RESULTS: Based on the IVW method, we found that the family Prevotellaceae, genus Anaerotruncus, genus Olsenella, genus Oscillospira, and order Bacillales were identified as risk factors for endometriosis, while class Melainabacteria and genus Eubacterium ruminantium group were protective factors. Additionally, no causal relationship was observed between endometriosis and gut microbiota. Heterogeneity tests, pleiotropy tests, and leave-one-out sensitivity analyses did not detect any significant heterogeneity or pleiotropic effects. CONCLUSIONS: Our MR study has provided evidence supporting a potential causal relationship between gut microbiota and endometriosis, and it suggests the absence of bidirectional causal effects. These findings could potentially offer new insights for the development of novel strategies for the prevention and treatment of endometriosis.
Assuntos
Endometriose , Microbioma Gastrointestinal , Feminino , Humanos , Endometriose/genética , Análise da Randomização Mendeliana , Microbioma Gastrointestinal/genética , Fatores de Risco , Razão de ChancesRESUMO
BACKGROUND: Post-anesthetic emergence agitation is common after general anesthesia and may cause adverse consequences, such as injury as well as respiratory and circulatory complications. Emergence agitation after general anesthesia occurs more frequently in nasal surgery than in other surgical procedures. This study aimed to assess the occurrence of emergence agitation in patients undergoing nasal surgery who were extubated under deep anesthesia or when fully awake. METHODS: A total of 202 patients (18-60 years, American Society of Anesthesiologists classification: I-II) undergoing nasal surgery under general anesthesia were randomized 1:1 into two groups: a deep extubation group (group D) and an awake extubation group (group A). The primary outcome was the incidence of emergence agitation. The secondary outcomes included number of emergence agitations, sedation score, vital signs, and incidence of adverse events. RESULTS: The incidence of emergence agitation was lower in group D than in group A (34.7% vs. 72.8%; p < 0.001). Compared to group A, patients in group D had lower Richmond Agitation-Sedation Scale scores, higher Ramsay sedation scores, fewer agitation episodes, and lower mean arterial pressure when extubated and 30 min after surgery, whereas these indicators did not differ 90 min after surgery. There was no difference in the incidence of adverse events between the two groups. CONCLUSIONS: Extubation under deep anesthesia can significantly reduce emergence agitation after nasal surgery under general anesthesia without increasing the incidence of adverse events. TRIAL REGISTRATION: Registered in Clinicaltrials.gov (NCT04844333) on 14/04/2021.
Assuntos
Extubação , Anestesia Geral , Delírio do Despertar , Procedimentos Cirúrgicos Nasais , Humanos , Extubação/métodos , Feminino , Masculino , Adulto , Pessoa de Meia-Idade , Delírio do Despertar/prevenção & controle , Delírio do Despertar/epidemiologia , Delírio do Despertar/etiologia , Anestesia Geral/métodos , Procedimentos Cirúrgicos Nasais/métodos , Procedimentos Cirúrgicos Nasais/efeitos adversos , Adulto Jovem , Adolescente , Vigília , Período de Recuperação da AnestesiaRESUMO
Objective: Some colorectal cancer patients still face high recurrence rates and poor prognoses even after they have undergone the surgical treatment of radical resection. Identifying potential biochemical markers and therapeutic targets for the prognostic evaluation of patients undergoing radical resection of colorectal cancer is crucial for improving their clinical outcomes. Recently, it has been reported that the T cell immunoglobulin and mucin domain protein 3 (Tim-3) and its ligand galactose lectin 9 (galectin-9) play crucial roles in immune dysfunction caused by various tumors, such as colorectal cancer. However, their expressions, biological functions, and prognostic value in colorectal cancer are still unclear. This study aims to investigate the relationship between Tim-3 and galectin-9 expression levels and the clinicopathological characteristics and prognosis of patients undergoing radical resection of colorectal cancer. Methods: A total of 171 patients who underwent radical resection of colorectal cancer at Chengdu Fifth People's Hospital between February 2018 and March 2019 were selected. Immunohistochemistry was performed to assess the expression levels of Tim-3 and galectin-9 in the cancer tissue samples and the paracancerous tissue samples of the patients. The relationship between Tim-3 and galectin-9 expression levels and the baseline clinical parameters of the patients was analyzed accordingly. Kaplan-Meier analysis was performed to assess the association between Tim-3 and galectin-9 expression levels and the relapse-free survival (RFS) and the overall survival (OS) of colorectal cancer patients. Cox regression analysis was conducted to identify factors associated with adverse prognosis in the patients. Results: The immunohistochemical results showed that the high expression levels of Tim-3 and galectin-9 were observed in 70.18% (120/171) and 32.16% (55/171), respectively, of the colorectal cancer tissues, whereas the low expression levels were 29.82% (51/171) and 67.84% (116/171), respectively. Furthermore, the expression score of Tim-3 was significantly higher in colorectal cancer tissues than that in the paracancerous tissues, while the expression score of galectin-9 was lower than that in the paracancerous tissues (P<0.05). Further analysis revealed that the expression of Tim-3 and galectin-9 was associated with the depth of tumor infiltration, vascular infiltration, and clinical staging (P<0.05). During the follow-up period of 14-63 months, 7 out of 171 patients were lost to follow-up. Among the remaining patients, 49 and 112 cases presented abnormally low expression of Tim-3 and galectin-9, respectively, whereas 115 and 52 cases presented high expression of Tim-3 and galectin-9, respectively. Kaplan-Meier survival analysis demonstrated that patients with high Tim-3 expression in colorectal cancer tissues had significantly lower RFS and OS than those with low expression did (RFS: log-rank=22.66, P<0.001; OS: log-rank=19.71, P<0.001). Conversely, patients with low galectin-9 expression had significantly lower RFS and OS than those with high expression did (RFS: log-rank=19.45, P<0.001; OS: log-rank=22.24, P<0.001). Cox multivariate analysis indicated that TNM stage â ¢ (HR=2.26, 95% CI: 1.20-5.68), high expression of Tim-3 (HR=0.80, 95% CI: 0.33-0.91), and low expression of galectin-9 (HR=1.80, 95% CI: 1.33-4.70) were independent risk factors affecting RFS and OS in patients (P<0.05). Conclusion: Aberrant expression of Tim-3 and galectin-9 is observed in colorectal cancer tissues. High expression of Tim-3 and low expression of galectin-9 are closely associated with adverse clinico-pathological characteristics and prognosis. They are identified as independent influencing factors that may trigger adverse prognostic events in patients. These findings suggest that Tim-3 and galectin-9 have potential as new therapeutic targets and clinical indicators.
Assuntos
Neoplasias Colorretais , Galectinas , Receptor Celular 2 do Vírus da Hepatite A , Humanos , Galectinas/metabolismo , Receptor Celular 2 do Vírus da Hepatite A/metabolismo , Neoplasias Colorretais/metabolismo , Neoplasias Colorretais/patologia , Neoplasias Colorretais/cirurgia , Prognóstico , Masculino , Feminino , Pessoa de Meia-Idade , Recidiva Local de Neoplasia/metabolismo , Biomarcadores Tumorais/metabolismo , IdosoRESUMO
Background and Aims: Epicardial adipose tissue, exosomes, and miRNAs have important activities in atherosclerosis. The purpose of this study was to establish miRNA expression profiles of epicardial adipose tissue-derived exosomes in patients with coronary atherosclerosis. Methods: Biopsies of epicardial adipose tissue were obtained from patients with and without coronary artery disease (CAD, n = 12 and NCAD, n = 12) during elective open-heart surgeries. Tissue was incubated with DMEM-F12 for 24 hours. Exosomes were isolated, then nanoparticle tracking analysis, transmission electron microscopy, and immunoblotting were performed to confirm the existence of exosomes. Total RNA in exosomes was subjected to high-throughput sequencing to identify differentially expressed miRNAs. MicroRNA target gene prediction was performed, and target genes were analyzed by Gene Ontology (GO), the Kyoto Encyclopedia of Genes and Genomes (KEGG), and mirPath to identify function. Reverse transcription quantitative PCR was performed to confirm the differentially expressed miRNAs. Results: Fifty-three unique miRNAs were identified (adjusted p < 0.05, fold of change > 2), among which 32 miRNAs were upregulated and 21 miRNAs were downregulated in coronary artery disease patients. Reverse transcription quantitative PCR validated the results for seven miRNAs including miR-141-3p, miR-183-5p, miR-200a-5p, miR-205-5p, miR-429, miR-382-5p and miR-485-3p, with the last two downregulated. GO and KEGG analysis by mirPath indicated that these differentially expressed miRNAs were enriched in cell survival, apoptosis, proliferation, and differentiation. Conclusions: Coronary artery disease patients showed differential epicardial adipose tissue exosomal miRNA expression compared with patients without coronary artery disease. The results provide clues for further studies of mechanisms of atherosclerosis.
RESUMO
Many scientific phenomena are linked to wave problems. This paper presents an effective and suitable technique for generating approximation solutions to multi-dimensional problems associated with wave propagation. We adopt a new iterative strategy to reduce the numerical work with minimum time efficiency compared to existing techniques such as the variational iteration method (VIM) and homotopy analysis method (HAM) have some limitations and constraints within the development of recurrence relation. To overcome this drawback, we present a Sawi integral transform ( S T) for constructing a suitable recurrence relation. This recurrence relation is solved to determine the coefficients of the homotopy perturbation strategy (HPS) that leads to the convergence series of the precise solution. This strategy derives the results in algebraic form that are independent of any discretization. To demonstrate the performance of this scheme, several mathematical frameworks and visual depictions are shown.
RESUMO
Diabetes mellitus (DM) is one of the most prevalent diseases worldwide, greatly impacting patients' quality of life. This article reviews the progress in Salvia miltiorrhiza, an ancient Chinese plant, for the treatment of DM and its associated complications. Extensive studies have been conducted on the chemical composition and pharmacological effects of S miltiorrhiza, including its anti-inflammatory and antioxidant activities. It has demonstrated potential in preventing and treating diabetes and its consequences by improving peripheral nerve function and increasing retinal thickness in diabetic individuals. Moreover, S miltiorrhiza has shown effectiveness when used in conjunction with angiotensin-converting enzyme inhibitors, angiotensin receptor blockers (ARBs), and statins. The safety and tolerability of S miltiorrhiza have also been thoroughly investigated. Despite the established benefits of managing DM and its complications, further research is needed to determine appropriate usage, dosage, long-term health benefits, and safety.
Assuntos
Diabetes Mellitus , Salvia miltiorrhiza , Humanos , Salvia miltiorrhiza/química , Antagonistas de Receptores de Angiotensina/uso terapêutico , Qualidade de Vida , Inibidores da Enzima Conversora de Angiotensina/uso terapêutico , Diabetes Mellitus/tratamento farmacológicoRESUMO
Ovarian cancer stands as a prevalent malignancy within the realm of gynecology, and the emergence of resistance to chemotherapeutic agents remains a pivotal impediment to both prognosis and treatment. Through a single-cell level investigation, we scrutinize the drug resistance and mitotic activity of the core tumor cells in ovarian cancer. Our study revisits the interrelationships and temporal trajectories of distinct epithelial cells (EPCs) subpopulations, while identifying genes associated with ovarian cancer prognosis. Notably, our findings establish a strong association between the drug resistance of EPCs and oxidative phosphorylation pathways. Subsequently, through subpopulation and temporal trajectory analysis, we confirm the intermediate position of EPCs subpopulation C0. Furthermore, we delve into the immunological functions and differentially expressed genes associated with the prognosis of C0, shedding light on the potential for constructing novel ovarian cancer prognosis models and identifying new therapeutic targets.
Assuntos
Resistencia a Medicamentos Antineoplásicos , Neoplasias Ovarianas , Humanos , Feminino , Resistencia a Medicamentos Antineoplásicos/genética , Neoplasias Ovarianas/tratamento farmacológico , Neoplasias Ovarianas/genética , Neoplasias Ovarianas/patologia , Prognóstico , Células Epiteliais/metabolismo , Análise de Sequência de RNARESUMO
Biological research has demonstrated the significance of identifying miRNA-disease associations in the context of disease prevention, diagnosis, and treatment. However, the utilization of experimental approaches involving biological subjects to infer these associations is both costly and inefficient. Consequently, there is a pressing need to devise novel approaches that offer enhanced accuracy and effectiveness. Presently, the predominant methods employed for predicting disease associations rely on Graph Convolutional Network (GCN) techniques. However, the Graph Convolutional Network algorithm, which is locally aggregated, solely incorporates information from the immediate neighboring nodes of a given node at each layer. Consequently, GCN cannot simultaneously aggregate information from multiple nodes. This constraint significantly impacts the predictive efficacy of the model. To tackle this problem, we propose a novel approach, based on HyperGCN and Sørensen-Dice loss (HGSMDA), for predicting associations between miRNAs and diseases. In the initial phase, we developed multiple networks to represent the similarity between miRNAs and diseases and employed GCNs to extract information from diverse perspectives. Subsequently, we draw into HyperGCN to construct a miRNA-disease heteromorphic hypergraph using hypernodes and train GCN on the graph to aggregate information. Finally, we utilized the Sørensen-Dice loss function to evaluate the degree of similarity between the predicted outcomes and the ground truth values, thereby enabling the prediction of associations between miRNAs and diseases. In order to assess the soundness of our methodology, an extensive series of experiments was conducted employing the Human MicroRNA Disease Database (HMDD v3.2) as the dataset. The experimental outcomes unequivocally indicate that HGSMDA exhibits remarkable efficacy when compared to alternative methodologies. Furthermore, the predictive capacity of HGSMDA was corroborated through a case study focused on colon cancer. These findings strongly imply that HGSMDA represents a dependable and valid framework, thereby offering a novel avenue for investigating the intricate association between miRNAs and diseases.
RESUMO
Advances in high-throughput single-cell RNA sequencing (scRNA-seq) technology have provided more comprehensive biological information on cell expression. Clustering analysis is a critical step in scRNA-seq research and provides clear knowledge of the cell identity. Unfortunately, the characteristics of scRNA-seq data and the limitations of existing technologies make clustering encounter a considerable challenge. Meanwhile, some existing methods treat different features equally and ignore differences in feature contributions, which leads to a loss of information. To overcome limitations, we introduce a weighted distance constraint into the construction of the similarity graph and combine the similarity constraint. We propose the Joint Automatic Weighting Similarity Graph and Low-rank Representation (JAGLRR) clustering method. Evaluating the contributions of each feature and assigning various weight values can increase the significance of valuable features while decreasing the interference of redundant features. The similarity constraint allows the model to generate a more symmetric affinity matrix. Benefitting from that affinity matrix, JAGLRR recovers the original linear relationship of the data more accurately and obtains more discriminative information. The results on simulated datasets and 8 real datasets show that JAGLRR outperforms 11 existing comparison methods in clustering experiments, with higher clustering accuracy and stability.
Assuntos
Algoritmos , Biologia Computacional , RNA-Seq , Análise de Célula Única , Análise por Conglomerados , Análise de Célula Única/métodos , Biologia Computacional/métodos , RNA-Seq/métodos , Humanos , Animais , Análise de Sequência de RNA/métodos , Camundongos , Análise da Expressão Gênica de Célula ÚnicaRESUMO
Numerous scientific studies have found a link between diverse microorganisms in the human body and complex human diseases. Because traditional experimental approaches are time-consuming and expensive, using computational methods to identify microbes correlated with diseases is critical. In this paper, a new microbe-disease association prediction model is proposed that combines a multi-view multi-modal network and a multi-scale feature fusion mechanism, called M3HOGAT. Firstly, a microbe-disease association network and multiple similarity views are constructed based on multi-source information. Then, consider that neighbor information from disparate orders might be more adept at learning node representations. Consequently, the higher-order graph attention network (HOGAT) is devised to aggregate neighbor information from disparate orders to extract microbe and disease features from different networks and views. Given that the embedding features of microbe and disease from different views possess varying importance, a multi-scale feature fusion mechanism is employed to learn their interaction information, thereby generating the final feature of microbes and diseases. Finally, an inner product decoder is used to reconstruct the microbe-disease association matrix. Compared with five state-of-the-art methods on the HMDAD and Disbiome datasets, the results of 5-fold cross-validations show that M3HOGAT achieves the best performance. Furthermore, case studies on asthma and obesity confirm the effectiveness of M3HOGAT in identifying potential disease-related microbes.
RESUMO
BACKGROUND: Observational studies have revealed associations between birth weight, childhood obesity, age at menarche, and ovarian dysfunction. However, these studies are susceptible to unavoidable confounding factors, leading to ongoing debates regarding their conclusions and making causal relationships challenging to infer. In light of these challenges, Mendelian randomization was employed in this study to investigate the causal relationships between birth weight, childhood obesity, age at menarche, and ovarian dysfunction. METHODS: This study employed a two-sample Mendelian randomization approach using genetic variation as instrumental variables to investigate causal relationships. Genetic variation data were sourced from summary data of genome-wide association studies in European populations. Instrumental variables were selected based on the principles of Mendel's three assumptions. The study utilized the inverse variance weighted method to assess the relationships between birth weight, childhood obesity, age at menarche, and ovarian dysfunction. Supplementary analyses were conducted using MR-Egger regression, the weighted median method, and the weighted median mode to complement the IVW results. Furthermore, the study conducted heterogeneity, horizontal pleiotropy, and sensitivity analyses to evaluate the robustness of the results. RESULTS: Based on the inverse variance weighted method, it was found that there exists a causal relationship between childhood obesity (OR = 1.378, 95% CI: 1.113â¼1.705, p = 0.003), age at menarche (OR = 0.639, 95% CI: 0.468â¼0.871, p = 0.005), and ovarian dysfunction, while no causal relationship was observed between birth weight and ovarian dysfunction. Heterogeneity tests, multiplicity tests, and leave-one-out sensitivity analyses did not detect any heterogeneity or multiplicity effects in the estimated impact of these three exposure factors on the risk of ovarian dysfunction. CONCLUSIONS: This study represents the first evidence suggesting a potential causal relationship between childhood obesity, age at menarche, and ovarian dysfunction. Childhood obesity was found to increase the risk of ovarian dysfunction, while a later age at menarche was associated with a reduced risk of ovarian dysfunction.
Assuntos
Peso ao Nascer , Menarca , Análise da Randomização Mendeliana , Obesidade Infantil , Humanos , Menarca/genética , Feminino , Obesidade Infantil/genética , Obesidade Infantil/epidemiologia , Peso ao Nascer/genética , Criança , Estudo de Associação Genômica Ampla , Fatores de Risco , Adolescente , Fatores EtáriosRESUMO
Accumulating scientific evidence highlights the pivotal role of miRNA-disease association research in elucidating disease pathogenesis and developing innovative diagnostics. Consequently, accurately identifying disease-associated miRNAs has emerged as a prominent research topic in bioinformatics. Advances in graph neural networks (GNNs) have catalyzed methodological breakthroughs in this field. However, existing methods are often plagued by data noise and struggle to effectively integrate local and global information, which hinders their predictive performance. To address this, we introduce HGTMDA, an innovative hypergraph learning framework that incorporates random walk with restart-based association masking and an enhanced GCN-Transformer model to infer miRNA-disease associations. HGTMDA starts by constructing multiple homogeneous similarity networks. A novel enhancement of our approach is the introduction of a restart-based random walk association masking strategy. By stochastically masking a subset of association data and integrating it with a GCN enhanced by an attention mechanism, this strategy enables better capture of key information, leading to improved information utilization and reduced impact of noisy data. Next, we build an miRNA-disease heterogeneous hypergraph and adopt an improved GCN-Transformer encoder to effectively solve the effective extraction of local and global information. Lastly, we utilize a combined Dice cross-entropy (DCE) loss function to guide the model training and optimize its performance. To evaluate the performance of HGTMDA, comprehensive comparisons were conducted with state-of-the-art methods. Additionally, in-depth case studies on lung cancer and colorectal cancer were performed. The results demonstrate HGTMDA's outstanding performance across various metrics and its exceptional effectiveness in real-world application scenarios, highlighting the advantages and value of this method.
RESUMO
Objective: Given lycopene's anti-inflammatory and antioxidant properties, we investigated its mortality impact in individuals with and without obesity, confirming distinct effects. Methods: This study analyzes the National Health and Nutrition Examination Survey (NHANES) data from 2003-2006 and 2017-2018, linking lycopene levels to all-cause and cardiovascular mortality. Using various statistical methods, three models are sequentially adjusted for confounders, investigating the lycopene-outcome relationship. Results: We studied 11 737 adults for 162 months and found 1537 all-cause deaths (13.1%) and 443 cardiovascular deaths (3.8%). For those without obesity, serum lycopene had an "L" shape relationship with all-cause mortality, being harmful at very low levels but protective above a certain threshold. It consistently protects against cardiovascular mortality. In individuals with obesity, the relationship with all-cause mortality formed a "U" shape, with increased risk at very low and very high lycopene levels and protection in the middle range. Cardiovascular mortality showed a similar pattern in individuals with obesity. Interestingly, dietary lycopene intake had protective effects in both groups. Conclusion: This study reveals that lycopene exhibits distinct associations with all-cause and cardiovascular mortality in populations with or without obesity, emphasizing the importance of considering individual health profiles when assessing its benefits.
Assuntos
Doenças Cardiovasculares , Carotenoides , Adulto , Humanos , Licopeno , Inquéritos Nutricionais , ObesidadeRESUMO
CircRNA has been proved to play an important role in the diseases diagnosis and treatment. Considering that the wet-lab is time-consuming and expensive, computational methods are viable alternative in these years. However, the number of circRNA-disease associations (CDAs) that can be verified is relatively few, and some methods do not take full advantage of dependencies between attributes. To solve these problems, this paper proposes a novel method based on Kernel Fusion and Deep Auto-encoder (KFDAE) to predict the potential associations between circRNAs and diseases. Firstly, KFDAE uses a non-linear method to fuse the circRNA similarity kernels and disease similarity kernels. Then the vectors are connected to make the positive and negative sample sets, and these data are send to deep auto-encoder to reduce dimension and extract features. Finally, three-layer deep feedforward neural network is used to learn features and gain the prediction score. The experimental results show that compared with existing methods, KFDAE achieves the best performance. In addition, the results of case studies prove the effectiveness and practical significance of KFDAE, which means KFDAE is able to capture more comprehensive information and generate credible candidate for subsequent wet-lab.
Assuntos
Algoritmos , Biologia Computacional , Redes Neurais de Computação , RNA Circular , Humanos , RNA Circular/genética , Biologia Computacional/métodos , Aprendizado ProfundoRESUMO
Feature selection is a critical component of data mining and has garnered significant attention in recent years. However, feature selection methods based on information entropy often introduce complex mutual information forms to measure features, leading to increased redundancy and potential errors. To address this issue, we propose FSCME, a feature selection method combining Copula correlation (Ccor) and the maximum information coefficient (MIC) by entropy weights. The FSCME takes into consideration the relevance between features and labels, as well as the redundancy among candidate features and selected features. Therefore, the FSCME utilizes Ccor to measure the redundancy between features, while also estimating the relevance between features and labels. Meanwhile, the FSCME employs MIC to enhance the credibility of the correlation between features and labels. Moreover, this study employs the Entropy Weight Method (EWM) to evaluate and assign weights to the Ccor and MIC. The experimental results demonstrate that FSCME yields a more effective feature subset for subsequent clustering processes, significantly improving the classification performance compared to the other six feature selection methods. The source codes of the FSCME are available online at https://github.com/CDMBlab/FSCME.
RESUMO
The pathogenesis of Alzheimer's disease (AD) is extremely intricate, which makes AD patients almost incurable. Recent studies have demonstrated that analyzing multi-modal data can offer a comprehensive perspective on the different stages of AD progression, which is beneficial for early diagnosis of AD. In this paper, we propose a deep self-reconstruction fusion similarity hashing (DS-FSH) method to effectively capture the AD-related biomarkers from the multi-modal data and leverage them to diagnose AD. Given that most existing methods ignore the topological structure of the data, a deep self-reconstruction model based on random walk graph regularization is designed to reconstruct the multi-modal data, thereby learning the nonlinear relationship between samples. Additionally, a fused similarity hash based on anchor graph is proposed to generate discriminative binary hash codes for multi-modal reconstructed data. This allows sample fused similarity to be effectively modeled by a fusion similarity matrix based on anchor graph while modal correlation can be approximated by Hamming distance. Especially, extracted features from the multi-modal data are classified using deep sparse autoencoders classifier. Finally, experiments conduct on the AD Neuroimaging Initiative database show that DS-FSH outperforms comparable methods of AD classification. To conclude, DS-FSH identifies multi-modal features closely associated with AD, which are expected to contribute significantly to understanding of the pathogenesis of AD.
Assuntos
Doença de Alzheimer , Doença de Alzheimer/diagnóstico por imagem , Doença de Alzheimer/diagnóstico , Humanos , Algoritmos , Aprendizado Profundo , Imageamento por Ressonância Magnética/métodos , Interpretação de Imagem Assistida por Computador/métodos , Neuroimagem/métodos , Encéfalo/diagnóstico por imagem , Imagem Multimodal/métodosRESUMO
Neonatal epilepsy is a common emergency phenomenon in neonatal intensive care units (NICUs), which requires timely attention, early identification, and treatment. Traditional detection methods mostly use supervised learning with enormous labeled data. Hence, this study offers a semi-supervised hybrid architecture for detecting seizures, which combines the extracted electroencephalogram (EEG) feature dataset and convolutional autoencoder, called Fd-CAE. First, various features in the time domain and entropy domain are extracted to characterize the EEG signal, which helps distinguish epileptic seizures subsequently. Then, the unlabeled EEG features are fed into the convolutional autoencoder (CAE) for training, which effectively represents EEG features by optimizing the loss between the input and output features. This unsupervised feature learning process can better combine and optimize EEG features from unlabeled data. After that, the pre-trained encoder part of the model is used for further feature learning of labeled data to obtain its low-dimensional feature representation and achieve classification. This model is performed on the neonatal EEG dataset collected at the University of Helsinki Hospital, which has a high discriminative ability to detect seizures, with an accuracy of 92.34%, precision of 93.61%, recall rate of 98.74%, and F1-score of 95.77%, respectively. The results show that unsupervised learning by CAE is beneficial to the characterization of EEG signals, and the proposed Fd-CAE method significantly improves classification performance.
Assuntos
Eletroencefalografia , Convulsões , Humanos , Eletroencefalografia/métodos , Recém-Nascido , Convulsões/diagnóstico , Convulsões/fisiopatologia , Processamento de Sinais Assistido por Computador , Aprendizado Profundo , Aprendizado de Máquina não Supervisionado , Redes Neurais de ComputaçãoRESUMO
Genome-wide association study (GWAS) is essential for investigating the genetic basis of complex diseases; nevertheless, it usually ignores the interaction of multiple single nucleotide polymorphisms (SNPs). Genome-wide interaction studies provide crucial means for exploring complex genetic interactions that GWAS may miss. Although many interaction methods have been proposed, challenges still persist, including the lack of epistasis models and the inconsistency of benchmark datasets. SNP data simulation is a pivotal intermediary between interaction methods and real applications. Therefore, it is important to obtain epistasis models and benchmark datasets by simulation tools, which is helpful for further improving interaction methods. At present, many simulation tools have been widely employed in the field of population genetics. According to their basic principles, these existing tools can be divided into four categories: coalescent simulation, forward-time simulation, resampling simulation, and other simulation frameworks. In this paper, their basic principles and representative simulation tools are compared and analyzed in detail. Additionally, this paper provides a discussion and summary of the advantages and disadvantages of these frameworks and tools, offering technical insights for the design of new methods, and serving as valuable reference tools for researchers to comprehensively understand GWAS and genome-wide interaction studies.
RESUMO
Although the density peak clustering (DPC) algorithm can effectively distribute samples and quickly identify noise points, it lacks adaptability and cannot consider the local data structure. In addition, clustering algorithms generally suffer from high time complexity. Prior research suggests that clustering algorithms grounded in P systems can mitigate time complexity concerns. Within the realm of membrane systems (P systems), spiking neural P systems (SN P systems), inspired by biological nervous systems, are third-generation neural networks that possess intricate structures and offer substantial parallelism advantages. Thus, this study first improved the DPC by introducing the maximum nearest neighbor distance and K-nearest neighbors (KNN). Moreover, a method based on delayed spiking neural P systems (DSN P systems) was proposed to improve the performance of the algorithm. Subsequently, the DSNP-ANDPC algorithm was proposed. The effectiveness of DSNP-ANDPC was evaluated through comprehensive evaluations across four synthetic datasets and 10 real-world datasets. The proposed method outperformed the other comparison methods in most cases.