Predicting rRNA-, RNA-, and DNA-binding proteins from primary structure with support vector machines

In the post-genome era, the prediction of protein function is one of the most demanding tasks in the study of bioinformatics. Machine learning methods, such as the support vector machines (SVMs), greatly help to improve the classification of protein function. In this work, we integrated SVMs, protein sequence amino acid composition, and associated physicochemical properties into the study of nucleic-acid-binding proteins prediction. We developed the binary classifications for rRNA-, RNA-, DNA-binding proteins that play an important role in the control of many cell processes. Each SVM predicts whether a protein belongs to rRNA-, RNA-, or DNA-binding protein class. Self-consistency and jackknife tests were performed on the protein data sets in which the sequences identity was < 25%. Test results show that the accuracies of rRNA-, RNA-, DNA-binding SVMs predictions are approximately 84%, approximately 78%, approximately 72%, respectively. The predictions were also performed on the ambiguous and negative data set. The results demonstrate that the predicted scores of proteins in the ambiguous data set by RNA- and DNA-binding SVM models were distributed around zero, while most proteins in the negative data set were predicted as negative scores by all three SVMs. The score distributions agree well with the prior knowledge of those proteins and show the effectiveness of sequence associated physicochemical properties in the protein function prediction. The software is available from the author upon request.     

利用伪氨基酸组分和支持向量机预测抗冻蛋白

抗冻蛋白是一类具有提高生物抗冻能力的蛋白质。抗冻蛋白能够特异性的与冰晶相结合,进而阻止体液内冰核的形成与生长。因此,对抗冻蛋白的生物信息学研究对生物工程发展。提高作物抗冻性有重要的推动作用。本文采用由400条抗冻蛋白序列和400条非抗冻蛋白序列构成数据集,以伪氨基酸组分为特征,利用支持向量机分类算法预测抗冻蛋白,对训练集预测精度达到91．3％,对测试集预测精度达到78．8％。该结果证明伪氨基酸组分能够很好的反映抗冻蛋白特性,并能够用于预测抗冻蛋白。     

Predict prokaryotic proteins through detecting N-formylmethionine residues in protein sequences using support vector machine

Identifying prokaryotes in silico is commonly based on DNA sequences. In experiments where DNA sequences may not be immediately available, we need to have a different approach to detect prokaryotes based on RNA or protein sequences. N-formylmethionine (fMet) is known as a typical characteristic of prokaryotes. A web tool has been implemented here for predicting prokaryotes through detecting the N-formylmethionine residues in protein sequences. The predictor is constructed using support vector machine. An online predictor has been implemented using Python. The implemented predictor is able to achieve the total prediction accuracy 80% with the specificity 80% and the sensitivity 81%.     

Predicting homo-oligomers and hetero-oligomers by pseudo-amino acid composition: an approach from discrete wavelet transformation

Many proteins exist in vivo as oligomers with different quaternary structural attributes rather than as individual chains. These proteins are the structural components of various biological functions, including cooperative effects, allosteric mechanisms and ion-channel gating. With the dramatic increase in the number of protein sequences submitted to the public databank, it is important for both basic research and drug discovery research to acquire the knowledge about possible quaternary structural attributes of their interested proteins in a timely manner. A high-throughput method (DWT_SVM), fusing discrete wavelet transform (DWT) and support vector machine (SVM) classifier algorithm with various physicochemical features, has been developed to predict protein quaternary structure. The accuracy in distinguishing candidate proteins as homo-oligomer or hetero-oligomer using the dataset R₂₇₂₀ was 85.95% and 85.49% respectively by jackknife, showing that DWT_SVM is guide promising in predicting protein quaternary structures. The online service is available at http://bioinfo.ncu.edu.cn/Services.aspx. Protein sequences in FASTA format can be directly fed to the system OligoPred. The processed results will be presented in a diagram that includes the information of feature extraction and the classification error rate.     

Predicting protein structural class based on multi-features fusion

Structural class characterizes the overall folding type of a protein or its domain and the prediction of protein structural class has become both an important and a challenging topic in protein science. Moreover, the prediction itself can stimulate the development of novel predictors that may be straightforwardly applied to many other relational areas. In this paper, 10 frequently used sequence-derived structural and physicochemical features, which can be easily computed by the PROFEAT (Protein Features) web server, were taken as inputs of support vector machines to develop statistical learning models for predicting the protein structural class. More importantly, a strategy of merging different features, called best-first search, was developed. It was shown through the rigorous jackknife cross-validation test that the success rates by our method were significantly improved. We anticipate that the present method may also have important impacts on boosting the predictive accuracies for a series of other protein attributes, such as subcellular localization, membrane types, enzyme family and subfamily classes, among many others.     

Prediction of thermophilic proteins using feature selection technique

The thermostability of proteins is particularly relevant for enzyme engineering. Developing a computational method to identify mesophilic proteins would be helpful for protein engineering and design. In this work, we developed support vector machine based method to predict thermophilic proteins using the information of amino acid distribution and selected amino acid pairs. A reliable benchmark dataset including 915 thermophilic proteins and 793 non-thermophilic proteins was constructed for training and testing the proposed models. Results showed that 93.8% thermophilic proteins and 92.7% non-thermophilic proteins could be correctly predicted by using jackknife cross-validation. High predictive successful rate exhibits that this model can be applied for designing stable proteins.     

Prediction of protein structural class for low-similarity sequences using support vector machine and PSI-BLAST profile

Knowledge of structural class plays an important role in understanding protein folding patterns. In this study, a simple and powerful computational method, which combines support vector machine with PSI-BLAST profile, is proposed to predict protein structural class for low-similarity sequences. The evolution information encoding in the PSI-BLAST profiles is converted into a series of fixed-length feature vectors by extracting amino acid composition and dipeptide composition from the profiles. The resulting vectors are then fed to a support vector machine classifier for the prediction of protein structural class. To evaluate the performance of the proposed method, jackknife cross-validation tests are performed on two widely used benchmark datasets, 1189 (containing 1092 proteins) and 25PDB (containing 1673 proteins) with sequence similarity lower than 40% and 25%, respectively. The overall accuracies attain 70.7% and 72.9% for 1189 and 25PDB datasets, respectively. Comparison of our results with other methods shows that our method is very promising to predict protein structural class particularly for low-similarity datasets and may at least play an important complementary role to existing methods.     

Prediction of membrane protein types from sequences and position-specific scoring matrices

Membrane protein plays an important role in some biochemical process such as signal transduction, transmembrane transport, etc. Membrane proteins are usually classified into five types [Chou, K.C., Elrod, D.W., 1999. Prediction of membrane protein types and subcellular locations. Proteins: Struct. Funct. Genet. 34, 137-153] or six types [Chou, K.C., Cai, Y.D., 2005. J. Chem. Inf. Modelling 45, 407-413]. Designing in silico methods to identify and classify membrane protein can help us understand the structure and function of unknown proteins. This paper introduces an integrative approach, IAMPC, to classify membrane proteins based on protein sequences and protein profiles. These modules extract the amino acid composition of the whole profiles, the amino acid composition of N-terminal and C-terminal profiles, the amino acid composition of profile segments and the dipeptide composition of the whole profiles. In the computational experiment, the overall accuracy of the proposed approach is comparable with the functional-domain-based method. In addition, the performance of the proposed approach is complementary to the functional-domain-based method for different membrane protein types.     

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.     

High-accuracy prediction of protein structural class for low-similarity sequences based on predicted secondary structure

Information on the structural classes of proteins has been proven to be important in many fields of bioinformatics. Prediction of protein structural class for low-similarity sequences is a challenge problem. In this study, 11 features (including 8 re-used features and 3 newly-designed features) are rationally utilized to reflect the general contents and spatial arrangements of the secondary structural elements of a given protein sequence. To evaluate the performance of the proposed method, jackknife cross-validation tests are performed on two widely used benchmark datasets, 1189 and 25PDB with sequence similarity lower than 40% and 25%, respectively. Comparison of our results with other methods shows that our proposed method is very promising and may provide a cost-effective alternative to predict protein structural class in particular for low-similarity datasets.     

Synchrotron Protein Footprinting: A Technique to Investigate Protein-Protein Interactions

Abstract

Traditional approaches for macromolecular structure elucidation, including NMR, crystallography and cryo-EM have made significant progress in defining the structures of protein-protein complexes. A substantial number of macromolecular structures, however, have not been examined with atomic detail due to sample size and heterogeneity, or resolution limitations of the technique; therefore, the general applicability of each method is greatly reduced. Synchrotron footprinting attempts to bridge the gap in these methods by monitoring changes in accessible surface areas of discrete macromolecular moieties. As evidenced by our previous studies on RNA folding and DNA-protein interactions, the three-dimensional structure is probed by examining the reactions of these moieties with hydroxyl radicals generated by synchrotron X-rays. Here we report the application of synchrotron foot- printing to the investigation of protein-protein interactions, as the novel technique has been utilized to successfully map the contact sites of gelsolin segment-1 in the gelsolin segment 1/actin complex. Footprinting results demonstrate that phenylalanine 104, located on the actin binding helix of gelsolin segment 1, is protected from hydroxyl radical modification in the presence of actin. This change in reactivity results from the specific protection of gel- solin segment-1, consistent with the substantial decrease in solvent accessibility of F104 upon actin binding, as calculated from the crystal structural of the gelsolin segment 1/actin complex. The results presented here establish synchrotron footprinting as a broadly applicable method to probe structural features of macromolecular complexes that are not amenable to conventional approaches.     

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%。     

Predicting secondary structures of membrane proteins with neural networks

Back-propagation, feed-forward neural networks are used to predict the secondary structures of membrane proteins whose structures are known to atomic resolution. These networks are trained on globular proteins and can predict globular protein structures having no homology to those of the training set with correlation coefficients (C) of 0.45, 0.32 and 0.43 for a-helix, -strand and random coil structures, respectively. When tested on membrane proteins, neural networks trained on globular proteins do, on average, correctly predict (Q_i) 62%, 38% and 69% of the residues in the -helix, -strand and random coil structures. These scores rank higher than those obtained with the currently used statistical methods and are comparable to those obtained with the joint approaches tested so far on membrane proteins. The lower success score for -strand as compared to the other structures suggests that the sample of -strand patterns contained in the training set is less representative than those of a-helix and random coil. Our analysis, which includes the effects of the network parameters and of the structural composition of the training set on the prediction, shows that regular patterns of secondary structures can be successfully extrapolated from globular to membrane proteins. Correspondence to: R. Casadio     

结合支持向量机和贝叶斯方法进行蛋白质二级结构预测

组建一个分两个阶段的分类器来进行蛋白质二级结构预测。第一阶段由支持向量机分类器组成,在第二阶段中使用第一阶段已预测的结果来进行贝叶斯判别。预测性能的改进表明了结合支持向量机和贝叶斯方法预测性能优越于单独使用支持向量机的预测性能。同时也证明残基在形成二级结构时是相互影响的。     

基于添加模体信息和功率谱密度的组合向量预测27类蛋白质折叠子

以序列相似性低于40%的1895条蛋白质序列构建涵盖27个折叠类型的蛋白质折叠子数据库,从蛋白质序列出发,用模体频数值、低频功率谱密度值、氨基酸组分、预测的二级结构信息和自相关函数值构成组合向量表示蛋白质序列信息,采用支持向量机算法,基于整体分类策略,对27类蛋白质折叠子的折叠类型进行预测,独立检验的预测精度达到了66.67%。同时,以同样的特征参数和算法对27类折叠子的4个结构类型进行了预测,独立检验的预测精度达到了89.24%。将同样的方法用于前人使用过的27类折叠子数据库,得到了好于前人的预测结果。     

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.     

Prediction of mitochondrial proteins of malaria parasite using bi-profile Bayes feature extraction

Mitochondrial proteins of Plasmodium falciparum are considered as attractive targets for anti-malarial drugs, but the experimental identification of these proteins is a difficult and time-consuming task. Computational prediction of mitochondrial proteins offers an alternative approach. However, the commonly used subcellular location prediction methods are unsuited for P. falciparum mitochondrial proteins whereas the organism and organelle-specific methods were constructed on the basis of a rather small dataset. In this study, a novel dataset termed PfM233, which included 108 mitochondrial and 125 non-mitochondrial proteins with sequence similarity below 25%, was established and the methods for predicting mitochondrial proteins of P. falciparum were described. Both bi-profile Bayes and split amino acid composition were applied to extract the features from the N- and C-terminal sequences of these proteins, which were then used to construct two SVM based classifiers (PfMP-N25 and PfMP-30). Using PfM233 as the dataset, PfMP-N25 and PfMP-30 achieved accuracies (MCCs) of 90.13% (0.80) and 90.99% (0.82). When tested with the commonly used 40 mitochondrial proteins in PfM175 and the 108 mitochondrial proteins in PfM233, these two methods obviously outperformed the existing general, organelle-specific and organism and organelle-specific methods.     

The evolution of proteins from random amino acid sequences. I. Evidence from the lengthwise distribution of amino acids in modern protein sequences

Summary We examine in this paper one of the expected consequences of the hypothesis that modern proteins evolved from random heteropeptide sequences. Specifically, we investigate the lengthwise distributions of amino acids in a set of 1,789 protein sequences with little sequence identity using the run test statistic (r _o) of Mood (1940,Ann. Math. Stat. 11, 367–392). The probability density ofr _o for a collection of random sequences has mean=0 and variance=1 [the N(0,1) distribution] and can be used to measure the tendency of amino acids of a given type to cluster together in a sequence relative to that of a random sequence. We implement the run test using binary representations of protein sequences in which the amino acids of interest are assigned a value of 1 and all others a value of 0. We consider individual amino acids and sets of various combinations of them based upon hydrophobicity (4 sets), charge (3 sets), volume (4 sets), and secondary structure propensity (3 sets). We find that any sequence chosen randomly has a 90% or greater chance of having a lengthwise distribution of amino acids that is indistinguishable from the random expectation regardless of amino acid type. We regard this as strong support for the random-origin hypothesis. However, we do observe significant deviations from the random expectation as might be expected after billions years of evolution. Two important global trends are found: (1) Amino acids with a strong α-helix propensity show a strong tendency to cluster whereas those with β-sheet or reverse-turn propensity do not. (2) Clustered rather than evenly distributed patterns tend to be preferred by the individual amino acids and this is particularly so for methionine. Finally, we consider the problem of reconciling the random nature of protein sequences with structurally meaningful periodic “patterns” that can be detected by sliding-window, autocorrelation, and Fourier analyses. Two examples, rhodopsin and bacteriorhodopsin, show that such patterns are a natural feature of random sequences.     

Cooperativity of the oxidization of cysteines in globular proteins

Based on the 639 non-homologous proteins with 2910 cysteine-containing segments of well-resolved three-dimensional structures, a novel approach has been proposed to predict the disulfide-bonding state of cysteines in proteins by constructing a two-stage classifier combining a first global linear discriminator based on their amino acid composition and a second local support vector machine classifier. The overall prediction accuracy of this hybrid classifier for the disulfide-bonding state of cysteines in proteins has scored 84.1% and 80.1%, when measured on cysteine and protein basis using the rigorous jack-knife procedure, respectively. It shows that whether cysteines should form disulfide bonds depends not only on the global structural features of proteins but also on the local sequence environment of proteins. The result demonstrates the applicability of this novel method and provides comparable prediction performance compared with existing methods for the prediction of the oxidation states of cysteines in proteins.     

Prediction of pi-turns in proteins using PSI-BLAST profiles and secondary structure information

Due to the structural and functional importance of tight turns, some methods have been proposed to predict gamma-turns, beta-turns, and alpha-turns in proteins. In the past, studies of pi-turns were made, but not a single prediction approach has been developed so far. It will be useful to develop a method for identifying pi-turns in a protein sequence. In this paper, the support vector machine (SVM) method has been introduced to predict pi-turns from the amino acid sequence. The training and testing of this approach is performed with a newly collected data set of 640 non-homologous protein chains containing 1931 pi-turns. Different sequence encoding schemes have been explored in order to investigate their effects on the prediction performance. With multiple sequence alignment and predicted secondary structure, the final SVM model yields a Matthews correlation coefficient (MCC) of 0.556 by a 7-fold cross-validation. A web server implementing the prediction method is available at the following URL: http://210.42.106.80/piturn/.