Boosting classifier for predicting protein domain structural class

A novel classifier, the so-called “LogitBoost” classifier, was introduced to predict the structural class of a protein domain according to its amino acid sequence. LogitBoost is featured by introducing a log-likelihood loss function to reduce the sensitivity to noise and outliers, as well as by performing classification via combining many weak classifiers together to build up a very strong and robust classifier. It was demonstrated thru jackknife cross-validation tests that LogitBoost outperformed other classifiers including “support vector machine,” a very powerful classifier widely used in biological literatures. It is anticipated that LogitBoost can also become a useful vehicle in classifying other attributes of proteins according to their sequences, such as subcellular localization and enzyme family class, among many others.     

Using pseudo-amino acid composition and support vector machine to predict protein structural class

As a result of genome and other sequencing projects, the gap between the number of known protein sequences and the number of known protein structural classes is widening rapidly. In order to narrow this gap, it is vitally important to develop a computational prediction method for fast and accurately determining the protein structural class. In this paper, a novel predictor is developed for predicting protein structural class. It is featured by employing a support vector machine learning system and using a different pseudo-amino acid composition (PseAA), which was introduced to, to some extent, take into account the sequence-order effects to represent protein samples. As a demonstration, the jackknife cross-validation test was performed on a working dataset that contains 204 non-homologous proteins. The predicted results are very encouraging, indicating that the current predictor featured with the PseAA may play an important complementary role to the elegant covariant discriminant predictor and other existing algorithms.     

Reduced amino acid alphabet is sufficient to accurately recognize intrinsically disordered protein

Intrinsically disordered proteins are an important class of proteins with unique functions and properties. Here, we have applied a support vector machine (SVM) trained on naturally occurring disordered and ordered proteins to examine the contribution of various parameters (vectors) to recognizing proteins that contain disordered regions. We find that a SVM that incorporates only amino acid composition has a recognition accuracy of 87+/-2%. This result suggests that composition alone is sufficient to accurately recognize disorder. Interestingly, SVMs using reduced sets of amino acids based on chemical similarity preserve high recognition accuracy. A set as small as four retains an accuracy of 84+/-2%; this suggests that general physicochemical properties rather than specific amino acids are important factors contributing to protein disorder.     

Predicting protein structural class with pseudo-amino acid composition and support vector machine fusion network

Because a priori knowledge of a protein structural class can provide useful information about its overall structure, the determination of protein structural class is a quite meaningful topic in protein science. However, with the rapid increase in newly found protein sequences entering into databanks, it is both time-consuming and expensive to do so based solely on experimental techniques. Therefore, it is vitally important to develop a computational method for predicting the protein structural class quickly and accurately. To deal with the challenge, this article presents a dual-layer support vector machine (SVM) fusion network that is featured by using a different pseudo-amino acid composition (PseAA). The PseAA here contains much information that is related to the sequence order of a protein and the distribution of the hydrophobic amino acids along its chain. As a showcase, the rigorous jackknife cross-validation test was performed on the two benchmark data sets constructed by Zhou. A significant enhancement in success rates was observed, indicating that the current approach may serve as a powerful complementary tool to other existing methods in this area.     

Using supervised fuzzy clustering to predict protein structural classes

Prediction of protein classification is both an important and a tempting topic in protein science. This is because of not only that the knowledge thus obtained can provide useful information about the overall structure of a query protein, but also that the practice itself can technically stimulate the development of novel predictors that may be straightforwardly applied to many other relevant areas. In this paper, a novel approach, the so-called "supervised fuzzy clustering approach" is introduced that is featured by utilizing the class label information during the training process. Based on such an approach, a set of "if-then" fuzzy rules for predicting the protein structural classes are extracted from a training dataset. It has been demonstrated through two different working datasets that the overall success prediction rates obtained by the supervised fuzzy clustering approach are all higher than those by the unsupervised fuzzy c-means introduced by the previous investigators [C.T. Zhang, K.C. Chou, G.M. Maggiora. Protein Eng. (1995) 8, 425-435]. It is anticipated that the current predictor may play an important complementary role to other existing predictors in this area to further strengthen the power in predicting the structural classes of proteins and their other characteristic attributes.     

A novel protein structural classes prediction method based on predicted secondary structure

Knowledge of structural classes plays an important role in understanding protein folding patterns. In this paper, features based on the predicted secondary structure sequence and the corresponding E–H sequence are extracted. Then, an 11-dimensional feature vector is selected based on a wrapper feature selection algorithm and a support vector machine (SVM). Among the 11 selected features, 4 novel features are newly designed to model the differences between α/β class and α + β class, and other 7 rational features are proposed by previous researchers. To examine the performance of our method, a total of 5 datasets are used to design and test the proposed method. The results show that competitive prediction accuracies can be achieved by the proposed method compared to existing methods (SCPRED, RKS-PPSC and MODAS), and 4 new features are demonstrated essential to differentiate α/β and α + β classes. Standalone version of the proposed method is written in JAVA language and it can be downloaded from http://web.xidian.edu.cn/slzhang/paper.html.     

Using Bagging classifier to predict protein domain structural class

Classification and prediction of protein domain structural class is one of the important topics in the molecular biology. We introduce the Bagging (Bootstrap aggregating), one of the bootstrap methods, for classifying and predicting protein structural classes. By a bootstrap aggregating procedure, the Bagging can improve a weak classifier, for instance the random tree method, to a significant step towards optimality. In this research, it is demonstrated that the Bagging performed at least as well as LogitBoost and Support vector machines in predicting the structural classes for a given protein domain dataset by 10 cross-validation test, which indicate that the Bagging method is promising and anticipated that it could be potentially further improved on predicting protein structural classes as well as other bio-macromolecular attributes, if the bagging method and other existing methods can be effectively complemented with each other.     

Using core hydrophobicity to identify phosphorylation sites of human G protein-coupled receptors

As the most frequent drug target, G protein-coupled receptors (GPCRs) are a large family of seven trans-membrane receptors that sense molecules outside the cell and activate inside signal transduction pathways. The activity and lifetime of activated receptors are regulated by receptor phosphorylation. Therefore, investigating the exact positions of phosphorylation sites in GPCRs sequence could provide useful clues for drug design and other biotechnology applications. Experimental identification of phosphorylation sites is expensive and laborious. Hence, there is significant interest in the development of computational methods for reliable prediction of phosphorylation sites from amino acid sequences. In this article, we presented a simple and effective method to recognize phosphorylation sites of human GPCRs by combining amino acid hydrophobicity and support vector machine. The prediction accuracy, sensitivity, specificity, Matthews correlation coefficient and area under the curve values for phosphoserine, phosphothreonine, and phosphotyrosine were 0.964, 0.790, 0.999, 0.866, 0.941; 0.954, 0.800, 0.985, 0.828, 0.958; and 0.976, 0.820, 0.993, 0.861, 0.959, respectively. The establishment of such a fast and accurate prediction method will speed up the pace of identifying proper GPCRs sites to facilitate drug discovery.     

Prediction of protein structural classes using support vector machines

Summary. The support vector machine, a machine-learning method, is used to predict the four structural classes, i.e. mainly α, mainly β, α–β and fss, from the topology-level of CATH protein structure database. For the binary classification, any two structural classes which do not share any secondary structure such as α and β elements could be classified with as high as 90% accuracy. The accuracy, however, will decrease to less than 70% if the structural classes to be classified contain structure elements in common. Our study also shows that the dimensions of feature space 20² = 400 (for dipeptide) and 20³ = 8 000 (for tripeptide) give nearly the same prediction accuracy. Among these 4 structural classes, multi-class classification gives an overall accuracy of about 52%, indicating that the multi-class classification technique in support of vector machines may still need to be further improved in future investigation.     

Using stacked generalization to predict membrane protein types based on pseudo-amino acid composition

Membrane proteins are vitally important for many biological processes and have become an attractive target for both basic research and drug design. Knowledge of membrane protein types often provides useful clues in deducing the functions of uncharacterized membrane proteins. With the unprecedented increasing of newly found protein sequences in the post-genomic era, it is highly demanded to develop an automated method for fast and accurately identifying the types of membrane proteins according to their amino acid sequences. Although quite a few identifiers have been developed in this regard through various approaches, such as covariant discriminant (CD), support vector machine (SVM), artificial neural network (ANN), and K-nearest neighbor (KNN), classifier the way they operate the identification is basically individual. As is well known, wise persons usually take into account the opinions from several experts rather than rely on only one when they are making critical decisions. Likewise, a sophisticated identifier should be trained by several different modes. In view of this, based on the frame of pseudo-amino acid that can incorporate a considerable amount of sequence-order effects, a novel approach called "stacked generalization" or "stacking" has been introduced. Unlike the "bagging" and "boosting" approaches which only combine the classifiers of a same type, the stacking approach can combine several different types of classifiers through a meta-classifier to maximize the generalization accuracy. The results thus obtained were very encouraging. It is anticipated that the stacking approach may also hold a high potential to improve the identification quality for, among many other protein attributes, subcellular location, enzyme family class, protease type, and protein-protein interaction type. The stacked generalization classifier is available as a web-server named "SG-MPt_Pred" at: http://202.120.37.186/bioinf/wangsq/service.htm.     

Novel hybrid method for the evaluation of parameters contributing in determination of protein structural classes

Due to the increasing gap between structure-determined and sequenced proteins, prediction of protein structural classes has been an important problem. It is very important to use efficient sequential parameters for developing class predictors because of the close sequence-structure relationship. The multinomial logistic regression model was used for the first time to evaluate the contribution of sequence parameters in determining the protein structural class. An in-house program generated parameters including single amino acid and all dipeptide composition frequencies. Then, the most effective parameters were selected by a multinomial logistic regression. Selected variables in the multinomial logistic model were Valine among single amino acid composition frequencies and Ala-Gly, Cys-Arg, Asp-Cys, Glu-Tyr, Gly-Glu, His-Tyr, Lys-Lys, Leu-Asp, Leu-Arg, Pro-Cys, Gln-Met, Gln-Thr, Ser-Trp, Val-Asn and Trp-Asn among dipeptide composition frequencies. Also a neural network model was constructed and fed by the parameters selected by multinomial logistic regression to build a hybrid predictor. In this study, self-consistency and jackknife tests on a database constructed by Zhou [1998. An intriguing controversy over protein structural class prediction. J. Protein Chem. 17(8), 729-738] containing 498 proteins are used to verify the performance of this hybrid method, and are compared with some of prior works. The results showed that our two-stage hybrid model approach is very promising and may play a complementary role to the existing powerful approaches.     

Classifying G-protein-coupled receptors to the finest subtype level

G-protein-coupled receptors (GPCRs) constitute a remarkable protein family of receptors that are involved in a broad range of biological processes. A large number of clinically used drugs elicit their biological effect via a GPCR. Thus, developing a reliable computational method for predicting the functional roles of GPCRs would be very useful in the pharmaceutical industry. Nowadays, researchers are more interested in functional roles of GPCRs at the finest subtype level. However, with the accumulation of many new protein sequences, none of the existing methods can completely classify these GPCRs to their finest subtype level. In this paper, a pioneer work was performed trying to resolve this problem by using a hierarchical classification method. The first level determines whether a query protein is a GPCR or a non-GPCR. If it is considered as a GPCR, it will be finally classified to its finest subtype level. GPCRs are characterized by 170 sequence-derived features encapsulating both amino acid composition and physicochemical features of proteins, and support vector machines are used as the classification engine. To test the performance of the present method, a non-redundant dataset was built which are organized at seven levels and covers more functional classes of GPCRs than existing datasets. The number of protein sequences in each level is 5956, 2978, 8079, 8680, 6477, 1580 and 214, respectively. By 5-fold cross-validation test, the overall accuracy of 99.56%, 93.96%, 82.81%, 85.93%, 94.1%, 95.38% and 92.06% were observed at each level. When compared with some previous methods, the present method achieved a consistently higher overall accuracy. The results demonstrate the power and effectiveness of the proposed method to accomplish the classification of GPCRs to the finest subtype level.     

基于支持向量机识别亚高尔基体蛋白质的定位

研究表明,许多神经退行性疾病都与蛋白质在高尔基体中的定位有关,因此,正确识别亚高尔基体蛋白质对相关疾病药物的研制有一定帮助,本文建立了两类亚高尔基体蛋白质数据集,提取了氨基酸组分信息、联合三联体信息、平均化学位移、基因本体注释信息等特征信息,利用支持向量机算法进行预测,基于5-折交叉检验下总体预测成功率为87.43%。     

Using support vector machines to distinguish enzymes: Approached by incorporating wavelet transform

The enzymatic attributes of newly found protein sequences are usually determined either by biochemical analysis of eukaryotic and prokaryotic genomes or by microarray chips. These experimental methods are both time-consuming and costly. With the explosion of protein sequences registered in the databanks, it is highly desirable to develop an automated method to identify whether a given new sequence belongs to enzyme or non-enzyme. The discrete wavelet transform (DWT) and support vector machine (SVM) have been used in this study for distinguishing enzyme structures from non-enzymes. The networks have been trained and tested on two datasets of proteins with different wavelet basis functions, decomposition scales and hydrophobicity data types. Maximum accuracy has been obtained using SVM with a wavelet function of Bior2.4, a decomposition scale j=5, and Kyte-Doolittle hydrophobicity scales. The results obtained by the self-consistency test, jackknife test and independent dataset test are encouraging, which indicates that the proposed method can be employed as a useful assistant technique for distinguishing enzymes from non-enzymes.     

Accurate prediction of protein structural classes using functional domains and predicted secondary structure sequences

Protein structural class prediction is one of the challenging problems in bioinformatics. Previous methods directly based on the similarity of amino acid (AA) sequences have been shown to be insufficient for low-similarity protein data-sets. To improve the prediction accuracy for such low-similarity proteins, different methods have been recently proposed that explore the novel feature sets based on predicted secondary structure propensities. In this paper, we focus on protein structural class prediction using combinations of the novel features including secondary structure propensities as well as functional domain (FD) features extracted from the InterPro signature database. Our comprehensive experimental results based on several benchmark data-sets have shown that the integration of new FD features substantially improves the accuracy of structural class prediction for low-similarity proteins as they capture meaningful relationships among AA residues that are far away in protein sequence. The proposed prediction method has also been tested to predict structural classes for partially disordered proteins with the reasonable prediction accuracy, which is a more difficult problem comparing to structural class prediction for commonly used benchmark data-sets and has never been done before to the best of our knowledge. In addition, to avoid overfitting with a large number of features, feature selection is applied to select discriminating features that contribute to achieve high prediction accuracy. The selected features have been shown to achieve stable prediction performance across different benchmark data-sets.     

A protein structural class prediction method based on novel features

In this study, a 12-dimensional feature vector is constructed to reflect the general contents and spatial arrangements of the secondary structural elements of a given protein sequence. Among the 12 features, 6 novel features are specially designed to improve the prediction accuracies for α/β and α + β classes based on the distributions of α-helices and β-strands and the characteristics of parallel β-sheets and anti-parallel β-sheets. To evaluate our method, the jackknife cross-validating test is employed on two widely-used datasets, 25PDB and 1189 datasets with sequence similarity lower than 40% and 25%, respectively. The performance of our method outperforms the recently reported methods in most cases, and the 6 newly-designed features have significant positive effect to the prediction accuracies, especially for α/β and α + β classes.     

Remote protein homology detection using recurrence quantification analysis and amino acid physicochemical properties

Remote homology detection refers to the detection of structure homology in evolutionarily related proteins with low sequence similarity. Supervised learning algorithms such as support vector machine (SVM) are currently the most accurate methods. In most of these SVM-based methods, efforts have been dedicated to developing new kernels to better use the pairwise alignment scores or sequence profiles. Moreover, amino acids’ physicochemical properties are not generally used in the feature representation of protein sequences. In this article, we present a remote homology detection method that incorporates two novel features: (1) a protein's primary sequence is represented using amino acid's physicochemical properties and (2) the similarity between two proteins is measured using recurrence quantification analysis (RQA). An optimization scheme was developed to select different amino acid indices (up to 10 for a protein family) that are best to characterize the given protein family. The selected amino acid indices may enable us to draw better biological explanation of the protein family classification problem than using other alignment-based methods. An SVM-based classifier will then work on the space described by the RQA metrics. The classification scheme is named as SVM-RQA. Experiments at the superfamily level of the SCOP1.53 dataset show that, without using alignment or sequence profile information, the features generated from amino acid indices are able to produce results that are comparable to those obtained by the published state-of-the-art SVM kernels. In the future, better prediction accuracies can be expected by combining the alignment-based features with our amino acids property-based features. Supplementary information including the raw dataset, the best-performing amino acid indices for each protein family and the computed RQA metrics for all protein sequences can be downloaded from http://ym151113.ym.edu.tw/svm-rqa.     

Using Chou's amphiphilic pseudo-amino acid composition and support vector machine for prediction of enzyme subfamily classes

With the rapid increment of protein sequence data, it is indispensable to develop automated and reliable predictive methods for protein function annotation. One approach for facilitating protein function prediction is to classify proteins into functional families from primary sequence. Being the most important group of all proteins, the accurate prediction for enzyme family classes and subfamily classes is closely related to their biological functions. In this paper, for the prediction of enzyme subfamily classes, the Chou's amphiphilic pseudo-amino acid composition [Chou, K.C., 2005. Using amphiphilic pseudo amino acid composition to predict enzyme subfamily classes. Bioinformatics 21, 10-19] has been adopted to represent the protein samples for training the 'one-versus-rest' support vector machine. As a demonstration, the jackknife test was performed on the dataset that contains 2640 oxidoreductase sequences classified into 16 subfamily classes [Chou, K.C., Elrod, D.W., 2003. Prediction of enzyme family classes. J. Proteome Res. 2, 183-190]. The overall accuracy thus obtained was 80.87%. The significant enhancement in the accuracy indicates that the current method might play a complementary role to the exiting methods.     

Novel two-stage hybrid neural discriminant model for predicting proteins structural classes

In order to establish novel hybrid neural discriminant model, linear discriminant analysis (LDA) was used at the first stage to evaluate the contribution of sequence parameters in determining the protein structural class. An in-house program generated parameters including single amino acid and all dipeptide composition frequencies for 498 proteins came from Zhou [An intriguing controversy over protein structural class prediction, J. Protein Chem. 17(8) (1998) 729-738]. Then, 127 statistically effective parameters were selected by stepwise LDA and were used as inputs of the artificial neural networks (ANNs) to build a two-stage hybrid predictor. In this study, self-consistency and jackknife tests were used to verify the performance of this hybrid model, and were compared with some of prior works. The results showed that our two-stage hybrid neural discriminant model approach is very promising and may play a complementary role to the existing powerful approaches.