Search

Motivation Anticancer peptides (ACPs) have natural cationic properties and can act on the anionic cell membrane of cancer cells to kill cancer cells. Therefore, ACPs have become a potential anticancer drug with good research value and prospect. Results In this article, we propose AACFlow, an end-to-end model for identification of ACPs based on deep learning. End-to-end models have more room to automatically adjust according to the data, making the overall fit better and reducing error propagation. The combination of attention augmented convolutional neural network (AAConv) and multi-layer convolutional neural network (CNN) forms a deep representation learning module, which is used to obtain global and local information on the sequence. Based on the concept of flow network, multi-head flow-attention mechanism is introduced to mine the deep features of the sequence to improve the efficiency of the model. On the independent test dataset, the ACC, Sn, Sp, and AUC values of AACFlow are 83.9%, 83.0%, 84.8%, and 0.892, respectively, which are 4.9%, 1.5%, 8.0%, and 0.016 higher than those of the baseline model. The MCC value is 67.85%. In addition, we visualize the features extracted by each module to enhance the interpretability of the model. Various experiments show that our model is more competitive in predicting ACPs. [ABSTRACT FROM AUTHOR]

Highlights • A feature design model named MACC-PSSM is proposed by integrating Moran autocorrelation and cross correlation with PSSM. • The principal component analysis is successfully applied to predict apoptosis protein subcellular localization. • The MACC–PSSM model achieves the satisfying performance. Abstract The prediction of subcellular localization of an apoptosis protein is still a challenging task, and existing methods mainly based on protein primary sequences. In this study, we propose a novel model called MACC–PSSM by integrating Moran autocorrelation and cross correlation with PSSM. Then a 3600-dimensional feature vector is constructed to predict apoptosis protein subcellular localization. Finally, 210 features are selected using principal component analysis (PCA) on the ZW 225 dataset, and support vector machine is adopted as classifier. To evaluate the performance of the proposed method, jackknife cross-validation tests are performed on two widely used benchmark datasets: ZW 225 and CL 317. Our model achieves competitive performance on prediction accuracies, especially for the overall prediction accuracies for datasets ZW 225 and CL 317, which reach 84.9% and 90.5%, respectively. Comparison of our results with other methods demonstrates that MACC–PSSM model can be used as a potential candidate for the accurate prediction of apoptosis protein subcellular localization. [ABSTRACT FROM AUTHOR]

Gram-negative bacterial secreted proteins are crucial for bacterial pathogenesis by making bacteria interact with their environments. Therefore, identification of bacterial secreted proteins becomes a significant process for the research of various diseases and the corresponding drugs. In this paper, we develop a feature design model named ACCP-KL-NMF by fusing PSSM-based auto-cross correlation analysis for features extraction and nonnegative matrix factorization algorithm based on Kullback–Leibler divergence for dimensionality reduction. Hence, a 150-dimensional feature vector is constructed on the training set. Then support vector machine is adopted as the classifier, and the most objective jackknife test is chosen for evaluating the accuracy. The ACCP-KL-NMF model yields the approving performance of the overall accuracy on the test set, and also outperforms the other three existing models. The numerical experimental results show that our model is effective and reliable for identification of Gram-negative bacterial secreted protein types. Moreover, it is anticipated that the proposed model could be beneficial for other biology sequence in future research. [ABSTRACT FROM AUTHOR]

Structural class is an important attribute of protein, which plays an important role in both the experiment and theoretical research of protein science. Prediction of protein structural classes has been a challenging task, specifically for low-similarity datasets. In this paper, we develop a feature extraction method PSSS-SOMA-PSSM by incorporating two different modes of evolutionary information into Chou's general pseudo amino acid composition (PseAAC) based on predicted secondary structure sequence (PSSS) and position-specific scoring matrix (PSSM). We construct a 170-dimensional (170D) feature vector for each protein sequence sample, which contains 10D PSSS features that reflect content, alternating word frequency and novel position information, and contains 160D PSSM features that are calculated by second-order moving average (SOMA) algorithm. The SVM classifier with RBF kernel function and the jackknife test are used to predict and evaluate on 1189, 25PDB and 640 datasets with sequence similarity lower than 40%, 25%, and 25%, respectively. Comparison of our results with other methods shows that the proposed method provides the state-of-the-art performance and a cost-effective alternative to structural classes prediction for low-similarity datasets. [ABSTRACT FROM AUTHOR]

Apoptosis is a fundamental process controlling normal tissue homeostasis by regulating a balance between cell proliferation and death. Predicting subcellular location of apoptosis proteins is very helpful for understanding its mechanism of programmed cell death. Prediction of apoptosis protein subcellular location is still a challenging and complicated task, and existing methods mainly based on protein primary sequences. In this paper, we propose a new position-specific scoring matrix (PSSM)-based model by using Geary autocorrelation function and detrended cross-correlation coefficient (DCCA coefficient). Then a 270-dimensional (270D) feature vector is constructed on three widely used datasets: ZD98, ZW225 and CL317, and support vector machine is adopted as classifier. The overall prediction accuracies are significantly improved by rigorous jackknife test. The results show that our model offers a reliable and effective PSSM-based tool for prediction of apoptosis protein subcellular localization. [ABSTRACT FROM AUTHOR]

In this paper, the authors first prove an upper bound of fractal dimension of kernel sections for the discrete Zakharov equations for plasmas with a quantum correction. Then they establish the upper semicontinuity of the kernel sections when the infinite lattice system is approximated by finite ordinary differential equations. [ABSTRACT FROM AUTHOR]

Prediction of protein structural classes for low-similarity sequences is useful for understanding fold patterns, regulation, functions, and interactions of proteins. It is well known that feature extraction is significant to prediction of protein structural class and it mainly uses protein primary sequence, predicted secondary structure sequence, and position-specific scoring matrix (PSSM). Currently, prediction solely based on the PSSM has played a key role in improving the prediction accuracy. In this paper, we propose a novel method called CSP-SegPseP-SegACP by fusing consensus sequence (CS), segmented PsePSSM, and segmented autocovariance transformation (ACT) based on PSSM. Three widely used low-similarity datasets (1189, 25PDB, and 640) are adopted in this paper. Then a 700-dimensional (700D) feature vector is constructed and the dimension is decreased to 224D by using principal component analysis (PCA). To verify the performance of our method, rigorous jackknife cross-validation tests are performed on 1189, 25PDB, and 640 datasets. Comparison of our results with the existing PSSM-based methods demonstrates that our method achieves the favorable and competitive performance. This will offer an important complementary to other PSSM-based methods for prediction of protein structural classes for low-similarity sequences. [ABSTRACT FROM AUTHOR]

• The intravascular blood pressure of common carotid artery can be used to estimate CrCP and RAP. • For patients undergoing brain DSA examination, invasive common carotid blood pressure monitoring can be used for personalized blood pressure management. • This study expanded on the current knowledge of the role of critical closing pressure and cerebrovascular disease. Radial artery, femoral artery, and aortic arterial blood pressures (ABPs) can be used to estimate cerebral critical closing pressure (CrCP) and resistance−area product (RAP). However, the use of the common carotid artery (CCA) intravascular blood pressure to estimate CrCP is unclear. Thus, using continuous ABP monitoring, we compared the CrCP and RAP estimated from CCA measurements with the corresponding values acquired from the radial artery. In this retrospective cross−sectional study, we analyzed CrCP and RAP estimations from 21 patients with normal cerebral blood vessels between July 23, 2010, and February 9, 2011, using linear regression of the cerebral blood flow velocity–ABP relationship. Bland–Altman analysis showed that the average differences (95% limits of agreement) between the radial artery and the left CCA were −6.3 (−53.1 – 40.6) mmHg and −0.08 (−0.41 – 0.25) mmHg s cm−1 for CrCP and RAP, respectively. The CrCP and RAP estimated from the CCA measurements are consistent with the corresponding values obtained from the radial artery. [ABSTRACT FROM AUTHOR]

Abstract: Prediction of protein structural class for low-similarity sequences remains a challenging problem. In this study, the new computational method has been developed to predict protein structural class by incorporating alternating word frequency and normalized Lempel–Ziv complexity. To evaluate the performance of the proposed method, jackknife cross-validation tests are performed on three widely used benchmark datasets, 25PDB, 1189 and 640, respectively. We report 83.6%, 81.8% and 83.6% prediction accuracies for 25PDB, 1189 and 640 benchmarks, respectively. Comparison of our results with other methods shows that the proposed method is very promising and may provide a cost-effective alternative to predict protein structural class in particular for low-similarity datasets and may at least play an important complementary role to existing methods. [Copyright &y& Elsevier]

Abstract: This paper discusses the large time behaviors of solutions for a class of incompressible third grade fluid equations in . Using the Fourier splitting method of Schonbek, the authors prove the upper and lower bounds of the time decay rate in for the weak solutions. The upper and lower bounds of decay rate are optimal in the sense that they coincide with the upper and lower bounds of the decay rate of solutions to the heat equation. [Copyright &y& Elsevier]

Promoter is a region of DNA that determines the transcription of a particular gene. There are several σ factors in the RNA polymerase, which has the function of identifying the promoter and facilitating the binding of the RNA polymerase to the promoter. Owing to the importance of promoter in genome research, it is an urgent task to develop computational tool for effectively identifying promoters and their strength facing the avalanche of DNA sequences discovered in the post-genomic age. In this paper, we develop a model named iPromoter-ET using the k -mer nucleotide composition, binary encoding and dinucleotide property matrix-based distance transformation for features extraction, and extremely randomized trees (extra trees) for feature selection. Its 1st layer is used to identify whether a DNA sequence is of promoter or not, while its 2nd layer is to identify promoter samples as being strong or weak promoter. Support vector machine and the five cross-validation are used to perform identification and assess performance, respectively. The results indicate that our model remarkably outperforms the existing models in both the 1st and 2nd layers for accuracy and stability. We anticipate that our proposed model will become a very effective intelligent tool, or at the least, a complementary tool to the existing modes of identifying promoters and their strength. Moreover, the datasets and codes for iPromoter-ET are freely available at https://github.com/shengli0201/iPromoter-ET. [Display omitted] • A novel identifying model named iPromoter-ET is proposed based on extremely randomized trees for feature selection. • Our iPromoter-ET model achieves remarkably higher accuracy for identifying promoters and their strength. • The performance of iPromoter-ET model outperforms those of existing related models. [ABSTRACT FROM AUTHOR]

Electrical stimulation (ES) with conductive polymers can dramatically enhance neurite outgrowth and promote neural regeneration. However, besides ES, the practical applications of neural repair is also highly dependent on the nerve cell functionality and response to substrate conductivity. Therefore, the combination of the ES and suitable materials, such as tissue scaffolds, has been applied to facilitate treatment of neural injuries and demonstrated great potential in peripheral nerve regeneration. In this study, polypyrrole/silk fibroin (PPy/SF) conductive composite scaffold was fabricated by 3D bioprinting and electrospinning. Schwann cells seeded on these scaffolds were electrically stimulated and hence demonstrated enhanced viability, proliferation and migration, as well as upregulated expression of neurotrophic factors. Furthermore, the constructed PPy/SF conductive nerve guidance conduits accompanying with ES could effectively promote axonal regeneration and remyelination in vivo. Moreover, we found that the MAPKs signal transduction pathway was activated by ES at the conductive conduit. Our findings demonstrate that the PPy/SF conductive composite scaffolds with longitudinal guidance exhibit favorable properties for clinical use and promotes nerve regeneration and functional recovery. [ABSTRACT FROM AUTHOR]

DNase I hypersensitive sites (DHSs) are regarded as those regions of chromatin that are sensitive to cleavage by the DNase I enzyme. Identification of DNase I hypersensitive sites will provide useful insights for discovering DNA's functional elements from the non-coding sequences in the biomedical research. Because of the significance for DNase I hypersensitive sites, it is indispensable to develop an accurate, fast, robust, and high-throughput automated computational model. In this paper, we develop a model named iDHSs-MFF by combining multiple fusion features and F-score features selection approach. The multiple fusion features include three auto-correlation descriptors based on the dinucleotide property matrix and the trinucleotide property matrix (TPM), Pseudo-DPM and Pseudo-TPM. Evaluation by the jackknife cross-validation indicates that the selected features by F-score are effective in the identification of DNase I hypersensitive sites. Experimental results on two benchmark datasets demonstrate that the proposed model outperforms some highly related models. Systematic application of this computational approach will greatly facilitate the analysis of transcriptional regulatory elements. The datasets and Matlab source codes are freely available at: https://github.com/shengli0201/Datasets. Unlabelled Image • A novel identifying model named iDHSs-MFF is proposed based on dinucleotide and trinucleotide property matrixs. • F-score approach is performed for features selection. • iDHSs-MFF model outperforms some highly related models. [ABSTRACT FROM AUTHOR]

The Fokker–Planck (FP) equation provides a powerful tool for describing the state transition probability density function of complex dynamical systems governed by stochastic differential equations (SDEs). Unfortunately, the analytical solution of the FP equation can be found in very few special cases. Therefore, it has become an interest to find a numerical approximation method of the FP equation suitable for a wider range of nonlinear systems. In this paper, a machine learning method based on an adaptive Gaussian mixture model (AGMM) is proposed to deal with the general FP equations. Compared with previous numerical discretization methods, the proposed method seamlessly integrates data and mathematical models. The prior knowledge generated by the assumed mathematical model can improve the performance of the learning algorithm. Also, it yields more interpretability for machine learning methods. Numerical examples for one-dimensional and two-dimensional SDEs with one and/or two noises are given. The simulation results show the effectiveness and robustness of the AGMM technique for solving the FP equation. In addition, the computational complexity and the optimization algorithm of the model are also discussed. [ABSTRACT FROM AUTHOR]

The surface topographies of artificial implants including surface roughness, surface groove size and orientation, and surface pore size and distribution have a great influence on the adhesion, migration, proliferation, and differentiation of nerve cells in the nerve regeneration process. Optimizing the surface topographies of biomaterials can be a key strategy for achieving excellent cell performance in various applications such as nerve tissue engineering. In this review, we offer a comprehensive summary of the surface topographies of nerve implants and their effects on nerve cell behavior. This review also emphasizes the latest work progress of the layered structure of the natural extracellular matrix that can be imitated by the material surface topology. Finally, the future development of surface topographies on nerve regeneration was prospectively remarked. [ABSTRACT FROM AUTHOR]

Remyelination is a major therapeutic goal in peripheral nerve regeneration, serving to restore function of demyelinated axons and provide neuroprotection. In order to apply myelin biogenesis strategies to peripheral nerve defects, the tissue engineered substitutes might be amenable to the promotion of this repair process. Electrospun nanofibers are considered as promising scaffolds for tissue engineering due to extracellular matrix mimicking factor and enhanced electrostatic interaction resulting in a controllable 3 D nanofibrous membrane. In order to explore the role of electrospun silk fibroin (SF) membrane in myelination, co-culture of dorsal root ganglion (DRG) neurons and Schwann cells (SCs) in vitro was established and observed. Scanning electron microscopy was used to observe DRG adhesion to the membranes, the electrospinning SF membrane is more favorable to the adhesion of DRG. The immunofluorescence staining of MAG and NF showed considerable amount of myelin were formed, and the myelin was tightly wrapped around the axons of the neurons, which was confirmed under the scanning electron microscope observation. Real-time quantitative PCR technique was used to determine the gene expression level of DRG neurons cultured at different time points. The results showed that the mRNA levels of N-cadherin, laminin, fibronectin were higher than those in the control group. Our results showed that the electrospun SF nanofibers can provide topographical and chemical cues that mimic (to a certain extent) the extracellular matrix. [ABSTRACT FROM AUTHOR]

N4-methylcytosine (4 mC) is an important and common methylation which widely exists in prokaryotes. It plays a crucial role in correcting DNA replication errors and protecting host DNA against degradation by restrictive enzymes. Hence, the accurate identification for 4 mC sites is greatly significant for understanding biological functions and treating gene diseases. In this paper, a novel model is designed for identifying 4 mC sites. Firstly, we extract features from original sequences by multi-source feature representation methods, which are mono-nucleotide binary and k -mer frequency, dinucleotide binary and position-specific frequency, ring-function-hydrogen-chemical properties, dinucleotide-based DNA properties and trinucleotide-based DNA properties. Subsequently, gradient boosting decision tree is applied to select the optimal feature set and remove redundant information. Finally, support vector machine is employed to predict 4 mC or non-4mC sites. The accuracies of six datasets reach 0.851, 0.859, 0.801, 0.87, 0.859 and 0.901, respectively, which are superior to previous prediction methods. Therefore, the results show that our predictor is a feasible and effective tool for identifying 4 mC sites. Furthermore, an online web server is established at http://dnan4c.zhanglab.site. [Display omitted] • A predictor is designed to identify DNA N4-methylcytosine sites based on multi-source features and GBDT. • Extract features from original sequences by multi-source feature representation methods. • GBDT is applied to select the optimal feature set and remove redundant information. • An online web server is established at http://dnan4c.zhanglab.site. [ABSTRACT FROM AUTHOR]