Search

X-ray crystallography is the most popular approach for analyzing protein 3D structure. However, the success rate of protein crystallization is very low (2-10 percent). To reduce the cost of time and resources, lots of computation-based methods are developed to detect the protein crystallization. Improving the accuracy of predicting protein crystallization is very important for the determination of protein structure by X-ray crystallography. At present, many machine learning methods are used to predict protein crystallization. In this article, we propose a Fuzzy Support Vector Machine based on Linear Neighborhood Representation (FSVM-LNR) to predict the crystallization propensity of proteins. Proteins are represented by three types of features (PsePSSM, PSSM-DWT, MMI-PS), and these features are serially combined and fed into FSVM-LNR. FSVM-LNR can filter outliers by membership score, which is calculated via reconstruction residuals of $k$ k nearest samples. To evaluate the performance of our predictive model, we test FSVM-LNR on the datasets of TRAIN3587, TEST3585 and TEST500. Our method achieves better Mathew’s correlation coefficient (MCC) on TRAIN3587 (MCC: 0.56) and TEST3585 (MCC: 0.58). Although the performance of independent test is not the best on TEST500, FSVM-LNR also has a certain predictability (MCC: 0.70) in the identification of protein crystallization. The good performance on the datasets proves the effectiveness of our method and the better performance on large datasets further demonstrates the stability and superiority of our method. [ABSTRACT FROM AUTHOR]

RNA-binding proteins play an important role in the biological process. However, the traditional experiment technology to predict RNA-binding residues is time-consuming and expensive, so the development of an effective computational approach can provide a strategy to solve this issue. In recent years, most of the computational approaches are constructed on protein sequence information, but the protein structure has not been considered. In this paper, we use a novel computational model of RNA-binding residues prediction, using protein sequence and structure information. Our hybrid features are encoded by local sequence and structure feature extraction models. Our predictor is built by employing the Granular Multiple Kernel Support Vector Machine with Repetitive Under-sampling (GMKSVM-RU). In order to evaluate our method, we use fivefold cross-validation on the RBP129, our method achieves better experimental performance with MCC of 0.3367 and accuracy of 88.84%. In order to further evaluate our model, an independent data set (RBP60) is employed, and our method achieves MCC of 0.3921 and accuracy of 87.52%. Above results demonstrate that integrating sequence and structure information is beneficial to improve the prediction ability of RNA-binding residues. [ABSTRACT FROM AUTHOR]

Background: DNA-Binding Proteins (DBP) plays a pivotal role in biological system. A mounting number of researchers are studying the mechanism and detection methods. To detect DBP, the tradition experimental method is time-consuming and resource-consuming. In recent years, Machine Learning methods have been used to detect DBP. However, it is difficult to adequately describe the information of proteins in predicting DNA-binding proteins. In this study, we extract six features from protein sequence and use Multiple Kernel Learning-based on Centered Kernel Alignment to integrate these features. The integrated feature is fed into Support Vector Machine to build predictive model and detect new DBP. Results: In our work, date sets of PDB1075 and PDB186 are employed to test our method. From the results, our model obtains better results (accuracy) than other existing methods on PDB1075 ( 84.19 % ) and PDB186 ( 83.7 % ), respectively. Conclusion: Multiple kernel learning could fuse the complementary information between different features. Compared with existing methods, our method achieves comparable and best results on benchmark data sets. [ABSTRACT FROM AUTHOR]

Background: Biological functions of biomolecules rely on the cellular compartments where they are located in cells. Importantly, RNAs are assigned in specific locations of a cell, enabling the cell to implement diverse biochemical processes in the way of concurrency. However, lots of existing RNA subcellular localization classifiers only solve the problem of single-label classification. It is of great practical significance to expand RNA subcellular localization into multi-label classification problem. Results: In this study, we extract multi-label classification datasets about RNA-associated subcellular localizations on various types of RNAs, and then construct subcellular localization datasets on four RNA categories. In order to study Homo sapiens, we further establish human RNA subcellular localization datasets. Furthermore, we utilize different nucleotide property composition models to extract effective features to adequately represent the important information of nucleotide sequences. In the most critical part, we achieve a major challenge that is to fuse the multivariate information through multiple kernel learning based on Hilbert-Schmidt independence criterion. The optimal combined kernel can be put into an integration support vector machine model for identifying multi-label RNA subcellular localizations. Our method obtained excellent results of 0.703, 0.757, 0.787, and 0.800, respectively on four RNA data sets on average precision. Conclusion: To be specific, our novel method performs outstanding rather than other prediction tools on novel benchmark datasets. Moreover, we establish user-friendly web server with the implementation of our method. [ABSTRACT FROM AUTHOR]

Improving the accuracy of predicting protein crystallization is very important for protein crystallization projects, which is a critical step for the determination of protein structure by X-ray crystallography. At present, many machine learning methods are used to predict protein crystallization. Here, we use a novel feature combination to construct a SVM model in the prediction of protein crystallization, called as CrystalM. In this work, we extract six features to represent protein sequences, namely Average Block-Position specific scoring matrix (AVBlock-PSSM), Average Block-Secondary Structure (AVBlock-SS), Global Encoding (GE), Pseudo-Position specific scoring matrix (PsePSSM), Protscale, and Discrete Wavelet Transform-Position specific scoring matrix (DWT-PSSM). Moreover, we employ two training datasets (TRAIN3587 and TRAIN1500) and their corresponding independent test datasets (TEST3585 and TEST500) to evaluate CrystalM by feeding multi-view features into Support Vector Machine (SVM) classifier. Two training datasets are employed for five-fold cross validation, and two test datasets are separately used to test the corresponding datasets. Finally, we compare CrystalM with other existing methods in the performance. For the datasets of TRAIN3587 and TEST3585, CrystalM achieves best Accuracy (ACC), best Specificity (SP), and the same Mathew's correlation coefficient (MCC) as the previous outperforming methods in the five-fold cross validation. In particular, ACC, SP, and MCC have surpassed the existing methods in independent test, which proves the effectiveness of CrystalM. Meanwhile, ACC, SP, and MCC are higher than existing methods in the five-fold cross validation for TRAIN1500. Although the performance of independent test for TEST500 is not the best, CrystalM also has a certain predictability in the prediction of protein crystallization. In addition, we find that only choosing the first four features can improve the performance of prediction for TRAIN1500 and TEST500, not only in independent tests but also in five-fold cross validation. This phenomenon indicates that the latter two features can not effectively represent proteins of TRAIN1500 and TEST500. CrystalM is a sequence-based protein crystallization prediction method. The good performance on the datasets proves the effectiveness of CrystalM and the better performance on large datasets further demonstrates the stability and superiority of CrystalM. [ABSTRACT FROM AUTHOR]

With the emergence of large-scale experimental data on genes and proteins, drug discovery and repositioning will be more difficult in the field of biomedical research. More and more resources are needed for detecting drug–target interactions (DTIs) in the experimental works. The interactions between drugs and targets could been seen as a bipartite network. Many computational methods have been developed to identify DTIs. However, most of them did not integrate multiple information and filter noise or outlier points. In this paper, we develop a fuzzy bipartite local model (FBLM) based on fuzzy least squares support vector machine and multiple kernel learning (MKL) for predicting DTIs. First, multiple kernels are constructed in drug and target spaces, respectively. Then, all corresponding kernels are combined by MKL algorithm in two spaces. Finally, FBLM is employed to identify DTIs. Our proposed approach is tested on four benchmark datasets under three types of cross validation. Comparing with existing outstanding methods, our method is a useful tool for the DTIs prediction. [ABSTRACT FROM AUTHOR]

The functional magnetic resonance imaging (fMRI) data and brain network analysis have been widely applied to automated diagnosis of neural diseases or brain diseases. The fMRI time series data not only contains specific numerical information, but also involves rich dynamic temporal information, those previous graph theory approaches focus on local topology structure and lose contextual information and global fluctuation information. Here, we propose a novel multi-scale functional connectivity for identifying the brain disease via fMRI data. We calculate the discrete probability distribution of co-activity between different brain regions with various intervals. Also, we consider nonsynchronous information under different time dimensions, for analyzing the contextual information in the fMRI data. Therefore, our proposed method can be applied to more disease diagnosis and other fMRI data, particularly automated diagnosis of neural diseases or brain diseases. Finally, we adopt Support Vector Machine (SVM) on our proposed time-series features, which can be applied to do the brain disease classification and even deal with all time-series data. Experimental results verify the effectiveness of our proposed method compared with other outstanding approaches on Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset and Major Depressive Disorder (MDD) dataset. Therefore, we provide an efficient system via a novel perspective to study brain networks. [ABSTRACT FROM AUTHOR]

Highlights • Multi-label protein subcellular localization prediction are focused on this paper. • PP matrix uses the physicochemical properties of proteins • PSSM matrix provides information about the evolution of proteins. • Multi-kernel SVM integrates multiple features to improve prediction accuracy. Abstract Identifying the location of proteins in a cell plays an important role in understanding their functions, such as drug design, therapeutic target discovery and biological research. However, the traditional subcellular localization experiments are time-consuming, laborious and small scale. With the development of next-generation sequencing technology, the number of proteins has grown exponentially, which lays the foundation of the computational method for identifying protein subcellular localization. Although many methods for predicting subcellular localization of proteins have been proposed, most of them are limited to single-location. In this paper, we propose a multi-kernel SVM to predict subcellular localization of both multi-location and single-location proteins. First, we make use of the evolutionary information extracted from position specific scoring matrix (PSSM) and physicochemical properties of proteins, by Chou's general PseAAC and other efficient functions. Then, we propose a multi-kernel support vector machine (SVM) model to identify multi-label protein subcellular localization. As a result, our method has a good performance on predicting subcellular localization of proteins. It achieves an average precision of 0.7065 and 0.6889 on two human datasets, respectively. All results are higher than those achieved by other existing methods. Therefore, we provide an efficient system via a novel perspective to study the protein subcellular localization. [ABSTRACT FROM AUTHOR]

DNA methylation is an important biochemical process, and it has a close connection with many types of cancer. Research about DNA methylation can help us to understand the regulation mechanism and epigenetic reprogramming. Therefore, it becomes very important to recognize the methylation sites in the DNA sequence. In the past several decades, many computational methods—especially machine learning methods—have been developed since the high-throughout sequencing technology became widely used in research and industry. In order to accurately identify whether or not a nucleotide residue is methylated under the specific DNA sequence context, we propose a novel method that overcomes the shortcomings of previous methods for predicting methylation sites. We use k-gram, multivariate mutual information, discrete wavelet transform, and pseudo amino acid composition to extract features, and train a sparse Bayesian learning model to do DNA methylation prediction. Five criteria—area under the receiver operating characteristic curve (AUC), Matthew’s correlation coefficient (MCC), accuracy (ACC), sensitivity (SN), and specificity—are used to evaluate the prediction results of our method. On the benchmark dataset, we could reach 0.8632 on AUC, 0.8017 on ACC, 0.5558 on MCC, and 0.7268 on SN. Additionally, the best results on two scBS-seq profiled mouse embryonic stem cells datasets were 0.8896 and 0.9511 by AUC, respectively. When compared with other outstanding methods, our method surpassed them on the accuracy of prediction. The improvement of AUC by our method compared to other methods was at least 0.0399. For the convenience of other researchers, our code has been uploaded to a file hosting service, and can be downloaded from: https://figshare.com/s/0697b692d802861282d3. [ABSTRACT FROM AUTHOR]

Since the importance of DNA-binding proteins in multiple biomolecular functions has been recognized, an increasing number of researchers are attempting to identify DNA-binding proteins. In recent years, the machine learning methods have become more and more compelling in the case of protein sequence data soaring, because of their favorable speed and accuracy. In this paper, we extract three features from the protein sequence, namely NMBAC (Normalized Moreau-Broto Autocorrelation), PSSM-DWT (Position-specific scoring matrix—Discrete Wavelet Transform), and PSSM-DCT (Position-specific scoring matrix—Discrete Cosine Transform). We also employ feature selection algorithm on these feature vectors. Then, these features are fed into the training SVM (support vector machine) model as classifier to predict DNA-binding proteins. Our method applys three datasets, namely PDB1075, PDB594 and PDB186, to evaluate the performance of our approach. The PDB1075 and PDB594 datasets are employed for Jackknife test and the PDB186 dataset is used for the independent test. Our method achieves the best accuracy in the Jacknife test, from 79.20% to 86.23% and 80.5% to 86.20% on PDB1075 and PDB594 datasets, respectively. In the independent test, the accuracy of our method comes to 76.3%. The performance of independent test also shows that our method has a certain ability to be effectively used for DNA-binding protein prediction. The data and source code are at . [ABSTRACT FROM AUTHOR]

N4-methylcytosine (4mC) has a significant effect on altering protein interactions, DNA conformation, gene expression and genomic imprinting. Accurate recognition of the 4mC sites is helpful for in-depth study of biomedical research. Although there are experimental methods for detecting 4mC sites, these techniques are time-consuming and laborious, and cannot be applied to large-scale genome scanning. Therefore, supplementation with an efficient computational method is absolutely necessary. In this study, we propose a prediction tool, 4mCPred-FSVM, to solve the above problems. We use position-specific trinucleotide propensity (PSTNP) to construct feature vectors. Subsequently, the feature vector was used as the input of the fuzzy support vector machine (FSVM) and the final predictor was developed. We measure the performance of the model on six datasets. In comparison to the state-of-the-art predictor, our predictor has achieved much higher accuracies in predicting 4mC sites. • A fuzzy support vector machine is proposed. • The original feature space and kernelized self representation-membership functions are proposed. • The proposed model is robust in predicting 4mC. [ABSTRACT FROM AUTHOR]

In traditional wet experiments, fluorescent proteins are generally used to detect subcellular localization of protein. However, it is time consuming and expensive for detecting large-scale biological data. Many computational biological methods have been developed to identify various subcellular localizations of proteins. In the last ten years, machine learning methods have been widely used in many research issues in the field of bioinformatics. In this work, Fuzzy Support Vector Machine based on Kernelized Neighborhood Representation (FSVM-KNR) is proposed to predict the subcellular localization of protein. Proteins are represented via six types of features (PsePSSM, PSSM-DWT, PSSM-AB, PsePP, PP-DWT and PP-AB). These features are constructed kernels and combined with Kernel Target Alignment-based Multiple Kernel Learning (KTA-MKL). Then, Kernelized Neighborhood Representation (KNR) algorithm is proposed to filter outliers via fuzzy membership scores. At last, the membership scores (with KNR) and integrated kernel (with KTA-MKL) are used to built FSVM-KNR model. To evaluate the performance of FSVM-KNR model, we test it on two benchmark datasets of protein subcellular localization. Our method achieves better performance (average precision: 0.7108 and 0.6916) on two datasets, respectively. In addition, our model is also compared with other FSVM model on 8 UCI datasets and the performance of FSVM-KNR is better or comparable. • A neighborhood representation-based method is proposed to evaluate outliers. • KNR-based membership score assumes spherical data distribution in the feature space. • Heterogeneous information (kernels) is integrated via multiple kernel learning. [ABSTRACT FROM AUTHOR]

Membrane proteins perform a variety of functions vital to the survival of organisms, such as oxidoreductase, transferase or hydrolase. If the type of membrane protein can be detected, the function of protein can be quickly determined. Many existing computational methods not only use the autocorrelation function on the hydrophobicity index of amino acids, but also consider the evolutionary conservatism information of the primary protein sequences. In this study, we employ Average Blocks (AvBlock), Discrete Wavelet Transform (DWT), Discrete Cosine Transform (DCT), Histogram of Oriented Gradient (HOG) and Pseudo-PSSM (PsePSSM) to extract evolution characteristics from Position-Specific Score Matrix (PSSM). Then, we construct five kernels from above five corresponding feature sets. Finally, we propose a novel Multiple Kernel Support Vector Machine (MKSVM) classifier based on Hilbert Schmidt Independence Criterion (HSIC) to integrate five kernels for identifying membrane proteins. For the performance evaluation, our method is tested on four benchmark datasets of membrane proteins. The comparative results demonstrate that our prediction model achieves the best performance among all existing outstanding approaches. [ABSTRACT FROM AUTHOR]

Flow diagram of hypergraph regularized bipartite local model (HGBLM). • HGBLM approach builds more complex relationships between samples by hypergraph. • Heterogeneous information (similarity matrices) is integrated via CKA-MKL. • HGBLM is built via hypergraph embedded LapSVM to further improve the performance of prediction. MicroRNA (miRNA) plays an important role in life processes. In recent years, predicting the association between miRNAs and diseases has become a research hotspot. However, biological experiments take a lot of time and cost to identify pathogenic miRNAs. Computational biology-based methods can effectively improve accuracy of recognition. In our study, miRNAs-disease associations are predicted by a hypergraph regularized bipartite local model (HGBLM), which is based on hypergraph embedded Laplacian support vector machine (LapSVM). On benchmark dataset, the results of our method are comparable and even better than existing models. [ABSTRACT FROM AUTHOR]