Predicting miRNA-disease Associations Based on Spectral Graph Transformer with Dynamic Attention and Regularization.

Extensive research indicates that microRNAs (miRNAs) play a crucial role in the analysis of complex human diseases. Recently, numerous methods utilizing graph neural networks have been developed to investigate the complex relationships between miRNAs and diseases. However, these methods often face challenges in terms of overall effectiveness and are sensitive to node positioning. To address these issues, the researchers introduce DARSFormer, an advanced deep learning model that integrates dynamic attention mechanisms with a spectral graph Transformer effectively. In the DARSFormer model, a miRNA-disease heterogeneous network is constructed initially. This network undergoes spectral decomposition into eigenvalues and eigenvectors, with the eigenvalue scalars being mapped into a vector space subsequently. An orthogonal graph neural network is employed to refine the parameter matrix. The enhanced features are then input into a graph Transformer, which utilizes a dynamic attention mechanism to amalgamate features by aggregating the enhanced neighbor features of miRNA and disease nodes. A projection layer is subsequently utilized to derive the association scores between miRNAs and diseases. The performance of DARSFormer in predicting miRNA-disease associations is exemplary. It achieves an AUC of 94.18% in a five-fold cross-validation on the HMDD v2.0 database. Similarly, on HMDD v3.2, it records an AUC of 95.27%. Case studies involving colorectal, esophageal, and prostate tumors confirm 27, 28, and 26 of the top 30 associated miRNAs against the dbDEMC and miR2Disease databases, respectively. The code and data for DARSFormer are accessible at https://github.com/baibaibaialone/DARSFormer.

Global research states and trends of micro RNA in irritable bowel syndrome: a bibliometric analysis.

Irritable bowel syndrome (IBS) is a common chronic gastrointestinal disorder, but its diagnosis and treatment remain obscure. Non-coding RNAs (ncRNAs), as potential biomarkers, have attracted increasing attention in digestive diseases. Here, we present a comprehensive research status, development trends, and valuable insights in this subject area. The literature search was performed using Web of Science Core Collection. VOSviewer 1.6.20, Citespace 6.2.R4, and Microsoft Excel 2021 were used for bibliometric analysis. A total of 124 articles were included in the analysis. Overall, publication patterns fluctuated. Globally, People's Republic of China, the USA, and Germany were the top three contributors of publications. Guangzhou University of Chinese Medicine, University of California, Mayo Clinic, and University of California, Los Angeles contributed the highest number of publications. The pathways and specific mechanisms by which ncRNAs regulate transcription and translation and thus regulate the pathophysiological processes of IBS are the main research hotspots in this field. We found that microRNA (miRNAs) are intricately involved in the regulation of key pathologies such as viscera sensitivity, intestinal permeability, intestinal mucosal barrier, immunoinflammatory response, and brain-gut axis in the IBS, and these topics have garnered significant attention in research community. Notably, microecological disorders are also associated with IBS pathogenesis, and ncRNA may play an important role in the interactions between host and intestinal flora. This is the first bibliometric study to comprehensively summarize the research hotspots and trends related to IBS and ncRNAs (especially miRNAs). Our findings will help understand the role of ncRNAs in IBS and provide guidance to future studies.

LMGATCDA: Graph Neural Network With Labeling Trick for Predicting circRNA-Disease Associations.

Previous studies have proven that circular RNAs (circRNAs) are inextricably connected to the etiology and pathophysiology of complicated diseases. Since conventional biological research are frequently small-scale, expensive, and time-consuming, it is essential to establish an efficient and reasonable computation-based method to identify disease-related circRNAs. In this article, we proposed a novel ensemble model for predicting probable circRNA-disease associations based on multi-source similarity information(LMGATCDA). In particular, LMGATCDA first incorporates information on circRNA functional similarity, disease semantic similarity, and the Gaussian interaction profile (GIP) kernel similarity as explicit features, along with node-labeling of the three-hop subgraphs extracted from each linked target node as graph structural features. After that, the fused features are used as input, and further implied features are extracted by graph sampling aggregation (GraphSAGE) and multi-hop attention graph neural network (MAGNA). Finally, the prediction scores are obtained through a fully connected layer. With five-fold cross-validation, LMGATCDA demonstrated excellent competitiveness against gold standard data, reaching 95.37% accuracy and 91.31% recall with an AUC of 94.25% on the circR2Disease benchmark dataset. Collectively, the noteworthy findings from these case studies support our conclusion that the LMGATCDA model can provide reliable circRNA-disease associations for clinical research while helping to mitigate experimental uncertainties in wet-lab investigations.

Adversarial dense graph convolutional networks for single-cell classification.

MOTIVATION: In single-cell transcriptomics applications, effective identification of cell types in multicellular organisms and in-depth study of the relationships between genes has become one of the main goals of bioinformatics research. However, data heterogeneity and random noise pose significant difficulties for scRNA-seq data analysis. RESULTS: We have proposed an adversarial dense graph convolutional network architecture for single-cell classification. Specifically, to enhance the representation of higher-order features and the organic combination between features, dense connectivity mechanism and attention-based feature aggregation are introduced for feature learning in convolutional neural networks. To preserve the features of the original data, we use a feature reconstruction module to assist the goal of single-cell classification. In addition, HNNVAT uses virtual adversarial training to improve the generalization and robustness. Experimental results show that our model outperforms the existing classical methods in terms of classification accuracy on benchmark datasets. AVAILABILITY AND IMPLEMENTATION: The source code of HNNVAT is available at https://github.com/DisscLab/HNNVAT. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Predicting Mirna-Disease Associations Based on Neighbor Selection Graph Attention Networks.

Numerous experiments have shown that the occurrence of complex human diseases is often accompanied by abnormal expression of microRNA (miRNA). Identifying the associations between miRNAs and diseases is of great significance in the development of clinical medicine. However, traditional experimental methods are often time-consuming and inefficient. To this end, we proposed a deep learning method based on neighbor selection graph attention networks for predicting miRNA-disease associations (NSAMDA). Specifically, we firstly fused miRNA sequence similarity information and miRNA integrated similarity information to enrich miRNA feature information. Secondly, we used the fused miRNA feature information and disease integrated similarity information to construct a miRNA-disease heterogeneous graph. Thirdly, we introduced a neighbor selection method based on graph attention networks to select k-most important neighbors for aggregation. Finally, we used the inner product decoder to score miRNA-disease pairs. The results of five-fold cross-validation show that the mean AUC of NSAMDA is 93.69% on HMDD v2.0 dataset. In addition, case studies on the esophageal neoplasm, lung neoplasm and lymphoma were carried out to further confirm the effectiveness of the NSAMDA model. The results showed that the NSAMDA method achieves satisfactory performance on predicting miRNA-disease associations and is superior to the most advanced model.

GCMCDTI: Graph convolutional autoencoder framework for predicting drug-target interactions based on matrix completion.

Identification of potential drug-target interactions (DTIs) plays a pivotal role in the development of drug and target discovery in the public healthcare sector. However, biological experiments for predicting interactions between drugs and targets are still expensive, complicated, and time-consuming. Thus, computational methods are widely applied for aiding drug-target interaction prediction. In this paper, we propose a novel model, named GCMCDTI, for DTIs prediction which adopts a graph convolutional network based on matrix completion. We regard the association prediction between drugs and targets as link prediction and treat the process as matrix completion, and then a graph convolutional auto-encoder framework is employed to construct the drug and target embeddings. Then, a bilinear decoder is applied to reconstruct the DTI matrix. We conduct our experiments on four benchmark datasets consisting of enzymes, G protein-coupled receptors (GPCRs), ion channels, and nuclear receptors. The five-fold cross-validation results achieve the high average AUC values of 95.78%, 95.31%, 93.90%, and 91.77%, respectively. To further evaluate our method, we compare our proposed method with other state-of-the-art approaches. The comparison results illustrate that our proposed method obtains improvement in performance on DTI prediction. The proposed method will be a good choice in the field of DTI prediction.

Hierarchical graph attention network for miRNA-disease association prediction.

Many biological studies show that the mutation and abnormal expression of microRNAs (miRNAs) could cause a variety of diseases. As an important biomarker for disease diagnosis, miRNA is helpful to understand pathogenesis, and could promote the identification, diagnosis and treatment of diseases. However, the pathogenic mechanism how miRNAs affect these diseases has not been fully understood. Therefore, predicting the potential miRNA-disease associations is of great importance for the development of clinical medicine and drug research. In this study, we proposed a novel deep learning model based on hierarchical graph attention network for predicting miRNA-disease associations (HGANMDA). Firstly, we constructed a miRNA-disease-lncRNA heterogeneous graph based on known miRNA-disease associations, miRNA-lncRNA associations and disease-lncRNA associations. Secondly, the node-layer attention was applied to learn the importance of neighbor nodes based on different meta-paths. Thirdly, the semantic-layer attention was applied to learn the importance of different meta-paths. Finally, a bilinear decoder was employed to reconstruct the connections between miRNAs and diseases. The extensive experimental results indicated that our model achieved good performance and satisfactory results in predicting miRNA-disease associations.

Predicting miRNA-disease associations based on graph random propagation network and attention network.

Numerous experiments have demonstrated that abnormal expression of microRNAs (miRNAs) in organisms is often accompanied by the emergence of specific diseases. The research of miRNAs can promote the prevention and drug research of specific diseases. However, there are still many undiscovered links between miRNAs and diseases, which greatly limits the research of miRNAs. Therefore, for exploring the unknown miRNA-disease associations, we combine the graph random propagation network based on DropFeature with attention network to propose a novel deep learning model to predict the miRNA-disease associations (GRPAMDA). Specifically, we firstly construct the miRNA-disease heterogeneous graph based on miRNA-disease association information. Secondly, we adopt DropFeature to randomly delete the features of nodes in the graph and then perform propagation operations to enhance the features of miRNA and disease nodes. Thirdly, we employ the attention mechanism to fuse the features of random propagation by aggregating the enhanced neighbor features of miRNA and disease nodes. Finally, miRNA-disease association scores are generated by a fully connected layer. The average area under the curve of GRPAMDA model based on 5-fold cross-validation is 93.46% on HMDD v2.0. Case studies of esophageal tumors, lymphomas and prostate tumors show that 48, 47 and 46 of the top 50 miRNAs associated with these diseases are confirmed by dbDEMC and miR2Disease database, respectively. In short, the GRPAMDA model can be used as a valuable method to study miRNA-disease associations.

Efficient framework for predicting MiRNA-disease associations based on improved hybrid collaborative filtering.

BACKGROUND: Accumulating studies indicates that microRNAs (miRNAs) play vital roles in the process of development and progression of many human complex diseases. However, traditional biochemical experimental methods for identifying disease-related miRNAs cost large amount of time, manpower, material and financial resources. METHODS: In this study, we developed a framework named hybrid collaborative filtering for miRNA-disease association prediction (HCFMDA) by integrating heterogeneous data, e.g., miRNA functional similarity, disease semantic similarity, known miRNA-disease association networks, and Gaussian kernel similarity of miRNAs and diseases. To capture the intrinsic interaction patterns embedded in the sparse association matrix, we prioritized the predictive score by fusing three types of information: similar disease associations, similar miRNA associations, and similar disease-miRNA associations. Meanwhile, singular value decomposition was adopted to reduce the impact of noise and accelerate predictive speed. RESULTS: We then validated HCFMDA with leave-one-out cross-validation (LOOCV) and two types of case studies. In the LOOCV, we achieved 0.8379 of AUC (area under the curve). To evaluate the performance of HCFMDA on real diseases, we further implemented the first type of case validation over three important human diseases: Colon Neoplasms, Esophageal Neoplasms and Prostate Neoplasms. As a result, 44, 46 and 44 out of the top 50 predicted disease-related miRNAs were confirmed by experimental evidence. Moreover, the second type of case validation on Breast Neoplasms indicates that HCFMDA could also be applied to predict potential miRNAs towards those diseases without any known associated miRNA. CONCLUSIONS: The satisfactory prediction performance demonstrates that our model could serve as a reliable tool to guide the following research for identifying candidate miRNAs associated with human diseases.

A graph auto-encoder model for miRNA-disease associations prediction.

Emerging evidence indicates that the abnormal expression of miRNAs involves in the evolution and progression of various human complex diseases. Identifying disease-related miRNAs as new biomarkers can promote the development of disease pathology and clinical medicine. However, designing biological experiments to validate disease-related miRNAs is usually time-consuming and expensive. Therefore, it is urgent to design effective computational methods for predicting potential miRNA-disease associations. Inspired by the great progress of graph neural networks in link prediction, we propose a novel graph auto-encoder model, named GAEMDA, to identify the potential miRNA-disease associations in an end-to-end manner. More specifically, the GAEMDA model applies a graph neural networks-based encoder, which contains aggregator function and multi-layer perceptron for aggregating nodes' neighborhood information, to generate the low-dimensional embeddings of miRNA and disease nodes and realize the effective fusion of heterogeneous information. Then, the embeddings of miRNA and disease nodes are fed into a bilinear decoder to identify the potential links between miRNA and disease nodes. The experimental results indicate that GAEMDA achieves the average area under the curve of $93.56\pm 0.44\%$ under 5-fold cross-validation. Besides, we further carried out case studies on colon neoplasms, esophageal neoplasms and kidney neoplasms. As a result, 48 of the top 50 predicted miRNAs associated with these diseases are confirmed by the database of differentially expressed miRNAs in human cancers and microRNA deregulation in human disease database, respectively. The satisfactory prediction performance suggests that GAEMDA model could serve as a reliable tool to guide the following researches on the regulatory role of miRNAs. Besides, the source codes are available at https://github.com/chimianbuhetang/GAEMDA.

Comparison of intravascular ultrasound-guided with angiography-guided double kissing crush stenting for patients with complex coronary bifurcation lesions: Rationale and design of a prospective, randomized, and multicenter DKCRUSH VIII trial.

BACKGROUND: Double kissing (DK) crush approach for patients with coronary bifurcation lesions, particularly localized at distal left main or lesions with increased complexity, is associated with significant reduction in clinical events when compared with provisional stenting. Recently, randomized clinical trial has demonstrated the net clinical benefits by intravascular ultrasound (IVUS)-guided implantation of drug-eluting stent in all-comers. However, the improvement in clinical outcome after DK crush treatment guided by IVUS over angiography guidance for patients with complex bifurcation lesions have never been studied in a randomized fashion. TRIAL DESIGN: DKCRUSH VIII study is a prospective, multicenter, randomized controlled trial designed to assess superiority of IVUS-guided vs angiography-guided DK crush stenting in patients with complex bifurcation lesions according to DEFINITION criteria. A total of 556 patients with complex bifurcation lesions will be randomly (1:1 of ratio) assigned to IVUS-guided or angiography-guided DK crush stenting group. The primary end point is the rate of 12-month target vessel failure, including cardiac death, target vessel myocardial infarction, or clinically driven target vessel revascularization. The secondary end points consist of the individual component of primary end point, all-cause death, myocardial infarction, and in-stent restenosis. The safety end point is the incidence of definite or probable stent thrombosis. An angiographic follow-up will be performed for all patients at 13 months and clinical follow-up will be continued annually until 3 years after the index procedure. CONCLUSIONS: DKCRUSH VIII trial is the first study designed to evaluate the differences in efficacy and safety between IVUS-guided and angiography-guided DK crush stenting in patients with complex true bifurcation lesions. This study will also provide IVUS-derived criteria to define optimal DK crush stenting for bifurcation lesions at higher complexity.

FCGCNMDA: predicting miRNA-disease associations by applying fully connected graph convolutional networks.

Growing evidence indicates that the development and progression of multiple complex diseases are influenced by microRNA (miRNA). Identifying more miRNAs as biomarkers for clinical diagnosis, treatment and prognosis is vital to promote the development of bioinformatics and medicine. Considering that the traditional biological experimental methods are generally time-consuming and expensive, high-efficient computational methods are encouraged to uncover potential disease-related miRNAs. In this paper, FCGCNMDA is presented to predict latent miRNA-disease associations by utilizing fully connected graph convolutional networks. Specially, our method first constructs a fully connected graph in which edge weights represent correlation coefficient between any two pairs of miRNA-disease pair, and then feeds this fully connected graph along with miRNA-disease pairs feature matrix into a two-layer graph convolutional networks (GCN) for training. At last, we utilize the trained network to predict the scores for unknown miRNA-disease pairs. As a result, FCGCNMDA achieves AUC value of [Formula: see text] and AUPRC value of [Formula: see text] in HMDD v2.0 based on five-fold cross validation. Moreover, case studies on Lymphoma, Breast Neoplasms and Prostate Neoplasms shown that 98%, 98%, 98% of the top 50 selected miRNAs were validated by recent experimental evidence. From above results, we can deduce that FCGCNMDA can be regarded as reliable method for potential miRNA-disease associations prediction.

Plasma D-dimer as a predictor of intraluminal thrombus burden and progression of abdominal aortic aneurysm.

AIM: Intraluminal thrombus (ILT) is presented in most abdominal aortic aneurysms (AAAs) and is suggested to promote AAA expansion. D-dimer, a breakdown product in the thrombus remodeling, may have prognostic value for AAA. This study investigated the interrelation between plasma D-dimer level, ILT volume, AAA size and progression. MAIN METHODS: This was a retrospective observational study that involved 181 patients with infra-renal AAA. They were divided into small and large AAA groups according to AAA diameter. 24 of them had repeated abdominal computed tomography angiography (CTA) scan and were divided into slow-growing and fast-growing AAA groups according to the median value of AAA growth rate. Baseline and follow-up plasma D-dimer level, maximum diameter of AAA, total infra-renal aortic volume and ILT volume were analyzed. KEY FINDINGS: Plasma D-dimer level was positively correlated with ILT volume (R = 0.382, P < 0.001) and maximum diameter of AAA (R = 0.442, P < 0.001). Increasing value of plasma D-dimer was positively associated with the accelerated growth rate of AAA (R = 0.720, P < 0.01). ILT volume showed positive correlation with maximum diameter (R = 0.859, P < 0.001) and growth rate of AAA (R = 0.490, P < 0.05). After adjusting the baseline ILT volume, the positive correlations remained to be statistically significant between plasma D-dimer level and AAA size (R = 0.200, P < 0.05), as well as increasing value of plasma D-dimer and growth rate of AAA (R = 0.642, P < 0.05). SIGNIFICANCE: Plasma D-dimer level reflected ILT burden in AAAs. Plasma D-dimer level and ILT volume were positively correlated with AAA size. Increasing value of plasma D-dimer and baseline ILT volume could be predictors of AAA progression.

Using discriminative vector machine model with 2DPCA to predict interactions among proteins.

BACKGROUND: The interactions among proteins act as crucial roles in most cellular processes. Despite enormous effort put for identifying protein-protein interactions (PPIs) from a large number of organisms, existing firsthand biological experimental methods are high cost, low efficiency, and high false-positive rate. The application of in silico methods opens new doors for predicting interactions among proteins, and has been attracted a great deal of attention in the last decades. RESULTS: Here we present a novelty computational model with the adoption of our proposed Discriminative Vector Machine (DVM) model and a 2-Dimensional Principal Component Analysis (2DPCA) descriptor to identify candidate PPIs only based on protein sequences. To be more specific, a 2DPCA descriptor is employed to capture discriminative feature information from Position-Specific Scoring Matrix (PSSM) of amino acid sequences by the tool of PSI-BLAST. Then, a robust and powerful DVM classifier is employed to infer PPIs. When applied on both gold benchmark datasets of Yeast and H. pylori, our model obtained mean prediction accuracies as high as of 97.06 and 92.89%, respectively, which demonstrates a noticeable improvement than some state-of-the-art methods. Moreover, we constructed Support Vector Machines (SVM) based predictive model and made comparison it with our model on Human benchmark dataset. In addition, to further demonstrate the predictive reliability of our proposed method, we also carried out extensive experiments for identifying cross-species PPIs on five other species datasets. CONCLUSIONS: All the experimental results indicate that our method is very effective for identifying potential PPIs and could serve as a practical approach to aid bioexperiment in proteomics research.

Pharmacodynamic changes of platelet reactivity status in patients with chronic kidney disease after coronary artery stenting.

OBJECTIVES: This study was to evaluate platelet reactivity over time among patients with chronic kidney disease (CKD) receiving standard dose of clopidogrel after percutaneous coronary intervention (PCI). The effect of CYP2C19 loss-of-function genotypes on platelet reactivity was also determined. METHODS: Patients with CKD (n = 138) on maintenance dose of clopidogrel after PCI were enrolled. Platelet reactivity was assessed by measuring P2Y12 reaction units (PRU) with VerifyNow P2Y12 assay, and platelet reactivity index (PRI) with flow cytometric using vasodilator-stimulated phosphoprotein (VASP) at baseline and 2 weeks later, respectively. The genotypes of CYP2C19 were also measured concurrently. RESULTS: The proportion of patients with high platelet reactivity (HPR) ranged from 23.2% to 59.4%, and almost 1 in 5 patients had a dual conversion between HPR and non-HPR status. Patients carrying CYP2C19 loss-of-function genotypes showed a higher platelet reactivity than non-carriers, but with an undetermined HPR status between the first and second visits. The individual switch of HPR to non-HPR status existed in both loss-of-function genotype carriers and non-carriers. CONCLUSIONS: HPR conversions occur in a significant proportion of CKD patients with maintenance doses of clopidogrel treatment post-PCI, and this conversion was not confined to CYP2C19 loss-of-function genotype carriers. Risk stratification for treatment adjustment in personalized antiplatelet therapy should be investigated in future research.

IL-33 promotes IL-10 production in macrophages: a role for IL-33 in macrophage foam cell formation.

We evaluated the role of IL-10- in IL-33-mediated cholesterol reduction in macrophage-derived foam cells (MFCs) and the mechanism by which IL-33 upregulates IL-10. Serum IL-33 and IL-10 levels in coronary artery disease patients were measured. The effects of IL-33 on intra-MFC cholesterol level, IL-10, ABCA1 and CD36 expression, ERK 1/2, Sp1, STAT3 and STAT4 activation, and IL-10 promoter activity were determined. Core sequences were identified using bioinformatic analysis and site-specific mutagenesis. The serum IL-33 levels positively correlated with those of IL-10. IL-33 decreased cellular cholesterol level and upregulated IL-10 and ABCA1 but had no effect on CD36 expression. siRNA-IL-10 partially abolished cellular cholesterol reduction and ABCA1 elevation by IL-33 but did not reverse the decreased CD36 levels. IL-33 increased IL-10 mRNA production but had little effect on its stability. IL-33 induced ERK 1/2 phosphorylation and increased the luciferase expression driven by the IL-10 promoter, with the highest extent within the -2000 to -1752 bp segment of the 5'-flank of the transcription start site; these effects were counteracted by U0126. IL-33 activated Sp1, STAT3 and STAT4, but only the STAT3 binding site was predicted in the above segment. Site-directed mutagenesis of the predicted STAT3-binding sites (CTGCTTCCTGGCAGCAGAA→︀CTGCCTGGCAGCAGAA) reduced luciferase activity, and a STAT3 inhibitor blocked the regulatory effects of IL-33 on IL-10 expression. Chromatin immunoprecipitation (CHIP) confirmed the STAT3-binding sequences within the -1997 to -1700 and -1091 to -811 bp locus regions. IL-33 increased IL-10 expression in MFCs via activating ERK 1/2 and STAT3, which subsequently promoted IL-10 transcription and thus contributed to the beneficial effects of IL-33 on MFCs.

In silico prediction of drug-target interaction networks based on drug chemical structure and protein sequences.

Analysis of drug-target interactions (DTIs) is of great importance in developing new drug candidates for known protein targets or discovering new targets for old drugs. However, the experimental approaches for identifying DTIs are expensive, laborious and challenging. In this study, we report a novel computational method for predicting DTIs using the highly discriminative information of drug-target interactions and our newly developed discriminative vector machine (DVM) classifier. More specifically, each target protein sequence is transformed as the position-specific scoring matrix (PSSM), in which the evolutionary information is retained; then the local binary pattern (LBP) operator is used to calculate the LBP histogram descriptor. For a drug molecule, a novel fingerprint representation is utilized to describe its chemical structure information representing existence of certain functional groups or fragments. When applying the proposed method to the four datasets (Enzyme, GPCR, Ion Channel and Nuclear Receptor) for predicting DTIs, we obtained good average accuracies of 93.16%, 89.37%, 91.73% and 92.22%, respectively. Furthermore, we compared the performance of the proposed model with that of the state-of-the-art SVM model and other previous methods. The achieved results demonstrate that our method is effective and robust and can be taken as a useful tool for predicting DTIs.

Accurate prediction of protein-protein interactions by integrating potential evolutionary information embedded in PSSM profile and discriminative vector machine classifier.

Identification of protein-protein interactions (PPIs) is of critical importance for deciphering the underlying mechanisms of almost all biological processes of cell and providing great insight into the study of human disease. Although much effort has been devoted to identifying PPIs from various organisms, existing high-throughput biological techniques are time-consuming, expensive, and have high false positive and negative results. Thus it is highly urgent to develop in silico methods to predict PPIs efficiently and accurately in this post genomic era. In this article, we report a novel computational model combining our newly developed discriminative vector machine classifier (DVM) and an improved Weber local descriptor (IWLD) for the prediction of PPIs. Two components, differential excitation and orientation, are exploited to build evolutionary features for each protein sequence. The main characteristics of the proposed method lies in introducing an effective feature descriptor IWLD which can capture highly discriminative evolutionary information from position-specific scoring matrixes (PSSM) of protein data, and employing the powerful and robust DVM classifier. When applying the proposed method to Yeast and H. pylori data sets, we obtained excellent prediction accuracies as high as 96.52% and 91.80%, respectively, which are significantly better than the previous methods. Extensive experiments were then performed for predicting cross-species PPIs and the predictive results were also pretty promising. To further validate the performance of the proposed method, we compared it with the state-of-the-art support vector machine (SVM) classifier on Human data set. The experimental results obtained indicate that our method is highly effective for PPIs prediction and can be taken as a supplementary tool for future proteomics research.

Effect of Metabolic Syndrome on Risk Stratification for Left Atrial or Left Atrial Appendage Thrombus Formation in Patients with Nonvalvular Atrial Fibrillation.

BACKGROUND: Metabolic syndrome (MS) is a risk factor for stroke and thromboembolism event. Left atrial or LA appendage (LA/LAA) thrombus is a surrogate of potential stroke. The relationship between MS and atrial thrombus remains unclear. In this study, we sought to investigate the effect of MS on risk stratification of LA/LAA thrombus formation in patients with nonvalvular atrial fibrillation (NVAF). METHODS: This cross-sectional study enrolled 294 consecutive NVAF patients without prior anticoagulant and lipid-lowering therapies. LA/LAA thrombus was determined by transesophageal echocardiography. Risk assessment of LA/LAA thrombus was performed using the CHADS2 , CHA2DS2 -VASc, MS, CHADS2 -MS, and CHA2DS2 -VASc-MS scores. Logistic regression analyses were performed to determine which factors were significantly related to LA/LAA thrombus. Odds ratio (OR) including 95% confidence interval was also calculated. The predictive powers of different scores for the risk of LA/LAA thrombus were represented by C-statistics and compared by receiver operating characteristic (ROC) analysis. RESULTS: LA/LAA thrombi were identified in 56 patients (19.0%). Logistic analysis showed that MS was the strongest risk factor for LA/LAA thrombus in NVAF patients (OR = 14.698, P < 0.001). ROC curve analyses revealed that the C-statistics of CHADS2 -MS and CHA2DS2 -VASc-MS was significantly higher than those of CHADS2 and CHA2DS2 -VASc scores (CHADS2 -MS vs. CHADS2 , 0.807 vs. 0.726, P = 0.0019). Furthermore, MS was helpful for identifying individuals with a high risk of LA/LAA thrombus in the population with a low risk of stroke (CHADS2 or CHA2DS2 -VASc score = 0). CONCLUSIONS: MS is associated with LA/LAA thrombus risk in patients with NVAF. In addition to the CHADS2 and CHA2DS2 -VASc scores, the CHADS2 -MS and CHA2DS2 -VASc-MS scores provide additional information on stroke risk assessment.

Highly Accurate Prediction of Protein-Protein Interactions via Incorporating Evolutionary Information and Physicochemical Characteristics.

Protein-protein interactions (PPIs) occur at almost all levels of cell functions and play crucial roles in various cellular processes. Thus, identification of PPIs is critical for deciphering the molecular mechanisms and further providing insight into biological processes. Although a variety of high-throughput experimental techniques have been developed to identify PPIs, existing PPI pairs by experimental approaches only cover a small fraction of the whole PPI networks, and further, those approaches hold inherent disadvantages, such as being time-consuming, expensive, and having high false positive rate. Therefore, it is urgent and imperative to develop automatic in silico approaches to predict PPIs efficiently and accurately. In this article, we propose a novel mixture of physicochemical and evolutionary-based feature extraction method for predicting PPIs using our newly developed discriminative vector machine (DVM) classifier. The improvements of the proposed method mainly consist in introducing an effective feature extraction method that can capture discriminative features from the evolutionary-based information and physicochemical characteristics, and then a powerful and robust DVM classifier is employed. To the best of our knowledge, it is the first time that DVM model is applied to the field of bioinformatics. When applying the proposed method to the Yeast and Helicobacter pylori (H. pylori) datasets, we obtain excellent prediction accuracies of 94.35% and 90.61%, respectively. The computational results indicate that our method is effective and robust for predicting PPIs, and can be taken as a useful supplementary tool to the traditional experimental methods for future proteomics research.