Predicting disulfide connectivity from protein sequence using multiple sequence feature vectors and secondary structure

MOTIVATION: Disulfide bonds are primary covalent crosslinks between two cysteine residues in proteins that play critical roles in stabilizing the protein structures and are commonly found in extracy-toplasmatic or secreted proteins. In protein folding prediction, the localization of disulfide bonds can greatly reduce the search in conformational space. Therefore, there is a great need to develop computational methods capable of accurately predicting disulfide connectivity patterns in proteins that could have potentially important applications. RESULTS: We have developed a novel method to predict disulfide connectivity patterns from protein primary sequence, using a support vector regression (SVR) approach based on multiple sequence feature vectors and predicted secondary structure by the PSIPRED program. The results indicate that our method could achieve a prediction accuracy of 74.4% and 77.9%, respectively, when averaged on proteins with two to five disulfide bridges using 4-fold cross-validation, measured on the protein and cysteine pair on a well-defined non-homologous dataset. We assessed the effects of different sequence encoding schemes on the prediction performance of disulfide connectivity. It has been shown that the sequence encoding scheme based on multiple sequence feature vectors coupled with predicted secondary structure can significantly improve the prediction accuracy, thus enabling our method to outperform most of other currently available predictors. Our work provides a complementary approach to the current algorithms that should be useful in computationally assigning disulfide connectivity patterns and helps in the annotation of protein sequences generated by large-scale whole-genome projects. AVAILABILITY: The prediction web server and Supplementary Material are accessible at http://foo.maths.uq.edu.au/~huber/disulfide     

Disulfide connectivity prediction using recursive neural networks and evolutionary information

MOTIVATION: We focus on the prediction of disulfide bridges in proteins starting from their amino acid sequence and from the knowledge of the disulfide bonding state of each cysteine. The location of disulfide bridges is a structural feature that conveys important information about the protein main chain conformation and can therefore help towards the solution of the folding problem. Existing approaches based on weighted graph matching algorithms do not take advantage of evolutionary information. Recursive neural networks (RNN), on the other hand, can handle in a natural way complex data structures such as graphs whose vertices are labeled by real vectors, allowing us to incorporate multiple alignment profiles in the graphical representation of disulfide connectivity patterns. RESULTS: The core of the method is the use of machine learning tools to rank alternative disulfide connectivity patterns. We develop an ad-hoc RNN architecture for scoring labeled undirected graphs that represent connectivity patterns. In order to compare our algorithm with previous methods, we report experimental results on the SWISS-PROT 39 dataset. We find that using multiple alignment profiles allows us to obtain significant prediction accuracy improvements, clearly demonstrating the important role played by evolutionary information. AVAILABILITY: The Web interface of the predictor is available at http://neural.dsi.unifi.it/cysteines     

Disulfide connectivity prediction with 70% accuracy using two-level models

Disulfide bridges stabilize protein structures covalently and play an important role in protein folding. Predicting disulfide connectivity precisely helps towards the solution of protein structure prediction. Previous methods for disulfide connectivity prediction either infer the bonding potential of cysteine pairs or rank alternative disulfide bonding patterns. As a result, these methods encode data according to cysteine pairs (pair-wise) or disulfide bonding patterns (pattern-wise). However, using either encoding scheme alone cannot fully utilize the local and global information of proteins, so the accuracies of previous methods are limited. In this work, we propose a novel two-level framework to predict disulfide connectivity. With this framework, both the pair-wise and pattern-wise encoding schemes are considered. Our models were validated on the datasets derived from SWISS-PROT 39 and 43, and the results demonstrate that our models can combine both local and global information. Compared to previous methods, significant improvements were obtained by our models. Our work may also provide insights to further improvements of disulfide connectivity prediction and increase its applicability in protein structure analysis and prediction.     

Prediction of disulfide connectivity in proteins.

MOTIVATION: A major problem in protein structure prediction is the correct location of disulfide bridges in cysteine-rich proteins. In protein-folding prediction, the location of disulfide bridges can strongly reduce the search in the conformational space. Therefore the correct prediction of the disulfide connectivity starting from the protein residue sequence may also help in predicting its 3D structure. RESULTS: In this paper we equate the problem of predicting the disulfide connectivity in proteins to a problem of finding the graph matching with the maximum weight. The graph vertices are the residues of cysteine-forming disulfide bridges, and the weight edges are contact potentials. In order to solve this problem we develop and test different residue contact potentials. The best performing one, based on the Edmonds-Gabow algorithm and Monte-Carlo simulated annealing reaches an accuracy significantly higher than that obtained with a general mean force contact potential. Significantly, in the case of proteins with four disulfide bonds in the structure, the accuracy is 17 times higher than that of a random predictor. The method presented here can be used to locate putative disulfide bridges in protein-folding. AVAILABILITY: The program is available upon request from the authors. CONTACT: Casadio@alma.unibo.it; Piero@biocomp.unibo.it.     

Predicting disulfide connectivity patterns

Disulfide bonds play an important role in stabilizing protein structure and regulating protein function. Therefore, the ability to infer disulfide connectivity from protein sequences will be valuable in structural modeling and functional analysis. However, to predict disulfide connectivity directly from sequences presents a challenge to computational biologists due to the nonlocal nature of disulfide bonds, i.e., the close spatial proximity of the cysteine pair that forms the disulfide bond does not necessarily imply the short sequence separation of the cysteine residues. Recently, Chen and Hwang (Proteins 2005;61:507-512) treated this problem as a multiple class classification by defining each distinct disulfide pattern as a class. They used multiple support vector machines based on a variety of sequence features to predict the disulfide patterns. Their results compare favorably with those in the literature for a benchmark dataset sharing less than 30% sequence identity. However, since the number of disulfide patterns grows rapidly when the number of disulfide bonds increases, their method performs unsatisfactorily for the cases of large number of disulfide bonds. In this work, we propose a novel method to represent disulfide connectivity in terms of cysteine pairs, instead of disulfide patterns. Since the number of bonding states of the cysteine pairs is independent of that of disulfide bonds, the problem of class explosion is avoided. The bonding states of the cysteine pairs are predicted using the support vector machines together with the genetic algorithm optimization for feature selection. The complete disulfide patterns are then determined from the connectivity matrices that are constructed from the predicted bonding states of the cysteine pairs. Our approach outperforms the current approaches in the literature.     

Predicting disulfide bond connectivity in proteins by correlated mutations analysis

MOTIVATION: Prediction of disulfide bond connectivity facilitates structural and functional annotation of proteins. Previous studies suggest that cysteines of a disulfide bond mutate in a correlated manner. RESULTS: We developed a method that analyzes correlated mutation patterns in multiple sequence alignments in order to predict disulfide bond connectivity. Proteins with known experimental structures and varying numbers of disulfide bonds, and that spanned various evolutionary distances, were aligned. We observed frequent variation of disulfide bond connectivity within members of the same protein families, and it was also observed that in 99% of the cases, cysteine pairs forming non-conserved disulfide bonds mutated in concert. Our data support the notion that substitution of a cysteine in a disulfide bond prompts the substitution of its cysteine partner and that oxidized cysteines appear in pairs. The method we developed predicts disulfide bond connectivity patterns with accuracies of 73, 69 and 61% for proteins with two, three and four disulfide bonds, respectively.     

Prediction of cystine connectivity using SVM

One of the major contributors to protein structures is the formation of disulphide bonds between selected pairs of cysteines at oxidized state. Prediction of such disulphide bridges from sequence is challenging given that the possible combination of cysteine pairs as the number of cysteines increases in a protein. Here, we describe a SVM (support vector machine) model for the prediction of cystine connectivity in a protein sequence with and without a priori knowledge on their bonding state. We make use of a new encoding scheme based on physico-chemical properties and statistical features (probability of occurrence of each amino acid residue in different secondary structure states along with PSI-blast profiles). We evaluate our method in SPX (an extended dataset of SP39 (swiss-prot 39) and SP41 (swiss-prot 41) with known disulphide information from PDB) dataset and compare our results with the recursive neural network model described for the same dataset.     

支持向量机方法预测蛋白质结构中的二硫键

在蛋白质结构预测的研究中,一个重要的问题就是正确预测二硫键的连接,二硫键的准确预测可以减少蛋白质构像的搜索空间,有利于蛋白质3D结构的预测,本文将预测二硫键的连接问题转化成对连接模式的分类问题,并成功地将支持向量机方法引入到预测工作中。通过对半胱氨酸局域序列连接模式的分类预测,可以由蛋白质的一级结构序列预测该蛋白质的二硫键的连接。结果表明蛋白质的二硫键的连接与半胱氨酸局域序列连接模式有重要联系,应用支持向量机方法对蛋白质结构的二硫键预测取得了良好的结果。     

半胱氨酸氧化还原状态的协同性

以2002年4月份的Culled Protein Data Bank数据库中的639条蛋白质多肽链为研究对象,统计分析了其含有的584条二硫键的形成特征,发现半胱氨酸氧化还原状态表现出明显的协同性现象：含有二硫键的蛋白质中几乎所有的半胱氨酸都以氧化态形式存在。这一协同性可以通过蛋白质全局水平上的20种氨基酸组分的百分含量很好地加以说明,由此来预测半胱氨酸的氧化还原状态准确率最高可达84．5％。结果表明半胱氨酸是否形成二硫键主要取决于蛋白质全局的而非局部的结构信息。     

Prediction of the disulfide-bonding state of cysteine in proteins

The bonding states of cysteine play important functional and structural roles in proteins. In particular, disulfide bond formation is one of the most important factors influencing the three-dimensional fold of proteins. Proteins of known structure were used to teach computer-simulated neural networks rules for predicting the disulfide-bonding state of a cysteine given only its flanking amino acid sequence. Resulting networks make accurate predictions on sequences different from those used in training, suggesting that local sequence greatly influences cysteines in disulfide bond formation. The average prediction rate after seven independent network experiments is 81.4% for disulfide-bonded and 80.0% for non-disulfide-bonded scenarios. Predictive accuracy is related to the strength of network output activities. Network weights reveal interesting position-dependent amino acid preferences and provide a physical basis for understanding the correlation between the flanking sequence and a cysteine's disulfide-bonding state. Network predictions may be used to increase or decrease the stability of existing disulfide bonds or to aid the search for potential sites to introduce new disulfide bonds.     

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.     

On the Relevance of Sophisticated Structural Annotations for Disulfide Connectivity Pattern Prediction

Disulfide bridges strongly constrain the native structure of many proteins and predicting their formation is therefore a key sub-problem of protein structure and function inference. Most recently proposed approaches for this prediction problem adopt the following pipeline: first they enrich the primary sequence with structural annotations, second they apply a binary classifier to each candidate pair of cysteines to predict disulfide bonding probabilities and finally, they use a maximum weight graph matching algorithm to derive the predicted disulfide connectivity pattern of a protein. In this paper, we adopt this three step pipeline and propose an extensive study of the relevance of various structural annotations and feature encodings. In particular, we consider five kinds of structural annotations, among which three are novel in the context of disulfide bridge prediction. So as to be usable by machine learning algorithms, these annotations must be encoded into features. For this purpose, we propose four different feature encodings based on local windows and on different kinds of histograms. The combination of structural annotations with these possible encodings leads to a large number of possible feature functions. In order to identify a minimal subset of relevant feature functions among those, we propose an efficient and interpretable feature function selection scheme, designed so as to avoid any form of overfitting. We apply this scheme on top of three supervised learning algorithms: k-nearest neighbors, support vector machines and extremely randomized trees. Our results indicate that the use of only the PSSM (position-specific scoring matrix) together with the CSP (cysteine separation profile) are sufficient to construct a high performance disulfide pattern predictor and that extremely randomized trees reach a disulfide pattern prediction accuracy of on the benchmark dataset SPX, which corresponds to improvement over the state of the art. A web-application is available at http://m24.giga.ulg.ac.be:81/x3CysBridges.     

Application of multiple sequence alignment profiles to improve protein secondary structure prediction

The effect of training a neural network secondary structure prediction algorithm with different types of multiple sequence alignment profiles derived from the same sequences, is shown to provide a range of accuracy from 70.5% to 76.4%. The best accuracy of 76.4% (standard deviation 8.4%), is 3.1% (Q(3)) and 4.4% (SOV2) better than the PHD algorithm run on the same set of 406 sequence non-redundant proteins that were not used to train either method. Residues predicted by the new method with a confidence value of 5 or greater, have an average Q(3) accuracy of 84%, and cover 68% of the residues. Relative solvent accessibility based on a two state model, for 25, 5, and 0% accessibility are predicted at 76.2, 79.8, and 86. 6% accuracy respectively. The source of the improvements obtained from training with different representations of the same alignment data are described in detail. The new Jnet prediction method resulting from this study is available in the Jpred secondary structure prediction server, and as a stand-alone computer program from: http://barton.ebi.ac.uk/. Proteins 2000;40:502-511.     

A classification of disulfide patterns and its relationship to protein structure and function

We report a detailed classification of disulfide patterns to further understand the role of disulfides in protein structure and function. The classification is applied to a unique searchable database of disulfide patterns derived from the SwissProt and Pfam databases. The disulfide database contains seven times the number of publicly available disulfide annotations. Each disulfide pattern in the database captures the topology and cysteine spacing of a protein domain. We have clustered the domains by their disulfide patterns and visualized the results using a novel representation termed the "classification wheel." The classification is applied to 40,620 protein domains with 2-10 disulfides. The effectiveness of the classification is evaluated by determining the extent to which proteins of similar structure and function are grouped together through comparison with the SCOP and Pfam databases, respectively. In general, proteins with similar disulfide patterns have similar structure and function, even in cases of low sequence similarity, and we illustrate this with specific examples. Using a measure of disulfide topology complexity, we find that there is a predominance of less complex topologies. We also explored the importance of loss or addition of disulfides to protein structure and function by linking classification wheels through disulfide subpattern comparisons. This classification, when coupled with our disulfide database, will serve as a useful resource for searching and comparing disulfide patterns, and understanding their role in protein structure, folding, and stability. Proteins in the disulfide clusters that do not contain structural information are prime candidates for structural genomics initiatives, because they may correspond to novel structures.     

Fold recognition by concurrent use of solvent accessibility and residue depth

Recognizing the structural similarity without significant sequence identity (called fold recognition) is the key for bridging the gap between the number of known protein sequences and the number of structures solved. Previously, we developed a fold-recognition method called SP(3) which combines sequence-derived sequence profiles, secondary-structure profiles and residue-depth dependent, structure-derived sequence profiles. The use of residue-depth-dependent profiles makes SP(3) one of the best automatic predictors in CASP 6. Because residue depth (RD) and solvent accessible surface area (solvent accessibility) are complementary in describing the exposure of a residue to solvent, we test whether or not incorporation of solvent-accessibility profiles into SP(3) could further increase the accuracy of fold recognition. The resulting method, called SP(4), was tested in SALIGN benchmark for alignment accuracy and Lindahl, LiveBench 8 and CASP7 blind prediction for fold recognition sensitivity and model-structure accuracy. For remote homologs, SP(4) is found to consistently improve over SP(3) in the accuracy of sequence alignment and predicted structural models as well as in the sensitivity of fold recognition. Our result suggests that RD and solvent accessibility can be used concurrently for improving the accuracy and sensitivity of fold recognition. The SP(4) server and its local usage package are available on http://sparks.informatics.iupui.edu/SP4.     

SP5: improving protein fold recognition by using torsion angle profiles and profile-based gap penalty model

How to recognize the structural fold of a protein is one of the challenges in protein structure prediction. We have developed a series of single (non-consensus) methods (SPARKS, SP(2), SP(3), SP(4)) that are based on weighted matching of two to four sequence and structure-based profiles. There is a robust improvement of the accuracy and sensitivity of fold recognition as the number of matching profiles increases. Here, we introduce a new profile-profile comparison term based on real-value dihedral torsion angles. Together with updated real-value solvent accessibility profile and a new variable gap-penalty model based on fractional power of insertion/deletion profiles, the new method (SP(5)) leads to a robust improvement over previous SP method. There is a 2% absolute increase (5% relative improvement) in alignment accuracy over SP(4) based on two independent benchmarks. Moreover, SP(5) makes 7% absolute increase (22% relative improvement) in success rate of recognizing correct structural folds, and 32% relative improvement in model accuracy of models within the same fold in Lindahl benchmark. In addition, modeling accuracy of top-1 ranked models is improved by 12% over SP(4) for the difficult targets in CASP 7 test set. These results highlight the importance of harnessing predicted structural properties in challenging remote-homolog recognition. The SP(5) server is available at http://sparks.informatics.iupui.edu.     

Predicting subcellular localization of mycobacterial proteins by using Chou's pseudo amino acid composition

The successful prediction of protein subcellular localization directly from protein primary sequence is useful to protein function prediction and drug discovery. In this paper, by using the concept of pseudo amino acid composition (PseAAC), the mycobacterial proteins are studied and predicted by support vector machine (SVM) and increment of diversity combined with modified Mahalanobis Discriminant (IDQD). The results of jackknife cross-validation for 450 non-redundant proteins show that the overall predicted successful rates of SVM and IDQD are 82.2% and 79.1%, respectively. Compared with other existing methods, SVM combined with PseAAC display higher accuracies.