Monte Carlo simulation studies on the prediction of protein folding types from amino acid composition.

In the methodology development for statistical prediction of protein structures, the founders of different methods usually selected different sets of proteins to test their predicted results. Therefore, it is hard to make a fair comparison according to the results they reported. Even if the predictions by different methods are performed for the same set of proteins, there is still such a problem: a method better that the other for one set of proteins would not necessarily remain so when applied to another set of proteins. To tackle this problem, a Monte Carlo simulation method is proposed to establish an objective criterion to measure the accuracy of prediction for the protein folding type. Such an objective accuracy is actually corresponding to the asymptotical limit genereated during the Monte Carlo simulation process. Based on that, it has been found that the average objective accuracy for predicting the all-alpha, all-beta, alpha + beta, and alpha/beta proteins by the least Euclid's distance method (Nakashima, H., K. Nishikawa, and T. Ooi. 1986. J. Biochem. 99:152-162) is 73.0% and that by the least Minkowski's distance method (Chou, P.Y. 1989. Prediction in Protein Structure and the Principles of Protein Conformation. Plenum Press. New York. 549-586) is 70.9%, indicating that the former is better than the latter. However, according to the original reports, the latter claimed a rate of correct prediction with 79.7% but the former with only 70.2%, leading to a completely opposite conclusion. This indicates the necessity of establishing an objective criterion, and a comparison is meaningful only when it is based on the objective criterion. The simulation method and the idea developed here also can be applied to examine any other statistical prediction methods.     

Neural networks for secondary structure and structural class predictions

A pair of neural network-based algorithms is presented for predicting the tertiary structural class and the secondary structure of proteins. Each algorithm realizes improvements in accuracy based on information provided by the other. Structural class prediction of proteins nonhomologous to any in the training set is improved significantly, from 62.3% to 73.9%, and secondary structure prediction accuracy improves slightly, from 62.26% to 62.64%. A number of aspects of neural network optimization and testing are examined. They include network overtraining and an output filter based on a rolling average. Secondary structure prediction results vary greatly depending on the particular proteins chosen for the training and test sets; consequently, an appropriate measure of accuracy reflects the more unbiased approach of “jackknife” cross-validation (testing each protein in the database individually).     

Swfoldrate: Predicting protein folding rates from amino acid sequence with sliding window method

Protein folding is the process by which a protein processes from its denatured state to its specific biologically active conformation. Understanding the relationship between sequences and the folding rates of proteins remains an important challenge. Most previous methods of predicting protein folding rate require the tertiary structure of a protein as an input. In this study, the long‐range and short‐range contact in protein were used to derive extended version of the pseudo amino acid composition based on sliding window method. This method is capable of predicting the protein folding rates just from the amino acid sequence without the aid of any structural class information. We systematically studied the contributions of individual features to folding rate prediction. The optimal feature selection procedures are adopted by means of combining the forward feature selection and sequential backward selection method. Using the jackknife cross validation test, the method was demonstrated on the large dataset. The predictor was achieved on the basis of multitudinous physicochemical features and statistical features from protein using nonlinear support vector machine (SVM) regression model, the method obtained an excellent agreement between predicted and experimentally observed folding rates of proteins. The correlation coefficient is 0.9313 and the standard error is 2.2692. The prediction server is freely available at http://www.jci‐bioinfo.cn/swfrate/input.jsp . Proteins 2013. © 2012 Wiley Periodicals, Inc.     

A neural-network based method for prediction of gamma-turns in proteins from multiple sequence alignment

In the present study, an attempt has been made to develop a method for predicting gamma-turns in proteins. First, we have implemented the commonly used statistical and machine-learning techniques in the field of protein structure prediction, for the prediction of gamma-turns. All the methods have been trained and tested on a set of 320 nonhomologous protein chains by a fivefold cross-validation technique. It has been observed that the performance of all methods is very poor, having a Matthew's Correlation Coefficient (MCC) 相似文献   

Additive method for the prediction of protein-peptide binding affinity. Application to the MHC class I molecule HLA-A*0201

A method has been developed for prediction of binding affinities between proteins and peptides. We exemplify the method through its application to binding predictions of peptides with affinity to major histocompatibility complex class I molecule HLA-A*0201. The method is named "additive" because it is based on the assumption that the binding affinity of a peptide could be presented as a sum of the contributions of the amino acids at each position and the interactions between them. The amino acid contributions and the contributions of the interactions between adjacent side chains and every second side chain were derived using a partial least squares (PLS) statistical methodology using a training set of 420 experimental IC50 values. The predictive power of the method was assessed using rigorous cross-validation and using an independent test set of 89 peptides. The mean value of the residuals between the experimental and predicted pIC50 values was 0.508 for this test set. The additive method was implemented in a program for rapid T-cell epitope search. It is universal and can be applied to any peptide-protein interaction where binding data is known.     

How good is prediction of protein structural class by the component-coupled method?

Proteins of known structures are usually classified into four structural classes: all-alpha, all-beta, alpha+beta, and alpha/beta type of proteins. A number of methods to predicting the structural class of a protein based on its amino acid composition have been developed during the past few years. Recently, a component-coupled method was developed for predicting protein structural class according to amino acid composition. This method is based on the least Mahalanobis distance principle, and yields much better predicted results in comparison with the previous methods. However, the success rates reported for structural class prediction by different investigators are contradictory. The highest reported accuracies by this method are near 100%, but the lowest one is only about 60%. The goal of this study is to resolve this paradox and to determine the possible upper limit of prediction rate for structural classes. In this paper, based on the normality assumption and the Bayes decision rule for minimum error, a new method is proposed for predicting the structural class of a protein according to its amino acid composition. The detailed theoretical analysis indicates that if the four protein folding classes are governed by the normal distributions, the present method will yield the optimum predictive result in a statistical sense. A non-redundant data set of 1,189 protein domains is used to evaluate the performance of the new method. Our results demonstrate that 60% correctness is the upper limit for a 4-type class prediction from amino acid composition alone for an unknown query protein. The apparent relatively high accuracy level (more than 90%) attained in the previous studies was due to the preselection of test sets, which may not be adequately representative of all unrelated proteins.     

New joint prediction algorithm (Q7-JASEP) improves the prediction of protein secondary structure

The classical problem of secondary structure prediction is approached by a new joint algorithm (Q7-JASEP) that combines the best aspects of six different methods. The algorithm includes the statistical methods of Chou-Fasman, Nagano, and Burgess-Ponnuswamy-Scheraga, the homology method of Nishikawa, the information theory method of Garnier-Osgurthope-Robson, and the artificial neural network approach of Qian-Sejnowski. Steps in the algorithm are (i) optimizing each individual method with respect to its correlation coefficient (Q7) for assigning a structural type from the predictive score of the method, (ii) weighting each method, (iii) combining the scores from different methods, and (iv) comparing the scores for alpha-helix, beta-strand, and coil conformational states to assign the secondary structure at each residue position. The present application to 45 globular proteins demonstrates good predictive power in cross-validation testing (with average correlation coefficients per test protein of Q7, alpha = 0.41, Q7, beta = 0.47, Q7,c = 0.41 for alpha-helix, beta-strand, and coil conformations). By the criterion of correlation coefficient (Q7) for each type of secondary structure, Q7-JASEP performs better than any of the component methods. When all protein classes are included for training and testing (by cross-validation), the results here equal the best in the literature, by the Q7 criterion. More generally, the basic algorithm can be applied to any protein class and to any type of structure/sequence or function/sequence correlation for which multiple predictive methods exist.     

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.     

Using cross-validation to evaluate predictive accuracy of survival risk classifiers based on high-dimensional data

Developments in whole genome biotechnology have stimulated statistical focus on prediction methods. We review here methodology for classifying patients into survival risk groups and for using cross-validation to evaluate such classifications. Measures of discrimination for survival risk models include separation of survival curves, time-dependent ROC curves and Harrell's concordance index. For high-dimensional data applications, however, computing these measures as re-substitution statistics on the same data used for model development results in highly biased estimates. Most developments in methodology for survival risk modeling with high-dimensional data have utilized separate test data sets for model evaluation. Cross-validation has sometimes been used for optimization of tuning parameters. In many applications, however, the data available are too limited for effective division into training and test sets and consequently authors have often either reported re-substitution statistics or analyzed their data using binary classification methods in order to utilize familiar cross-validation. In this article we have tried to indicate how to utilize cross-validation for the evaluation of survival risk models; specifically how to compute cross-validated estimates of survival distributions for predicted risk groups and how to compute cross-validated time-dependent ROC curves. We have also discussed evaluation of the statistical significance of a survival risk model and evaluation of whether high-dimensional genomic data adds predictive accuracy to a model based on standard covariates alone.     

Accuracy improvement for identifying translation initiation sites in microbial genomes

MOTIVATION: At present the computational gene identification methods in microbial genomes have a high prediction accuracy of verified translation termination site (3' end), but a much lower accuracy of the translation initiation site (TIS, 5' end). The latter is important to the analysis and the understanding of the putative protein of a gene and the regulatory machinery of the translation. Improving the accuracy of prediction of TIS is one of the remaining open problems. RESULTS: In this paper, we develop a four-component statistical model to describe the TIS of prokaryotic genes. The model incorporates several features with biological meanings, including the correlation between translation termination site and TIS of genes, the sequence content around the start codon; the sequence content of the consensus signal related to ribosomal binding sites (RBSs), and the correlation between TIS and the upstream consensus signal. An entirely non-supervised training system is constructed, which takes as input a set of annotated coding open reading frames (ORFs) by any gene finder, and gives as output a set of organism-specific parameters (without any prior knowledge or empirical constants and formulas). The novel algorithm is tested on a set of reliable datasets of genes from Escherichia coli and Bacillus subtillis. MED-Start may correctly predict 95.4% of the start sites of 195 experimentally confirmed E.coli genes, 96.6% of 58 reliable B.subtillis genes. Moreover, the test results indicate that the algorithm gives higher accuracy for more reliable datasets, and is robust to the variation of gene length. MED-Start may be used as a postprocessor for a gene finder. After processing by our program, the improvement of gene start prediction of gene finder system is remarkable, e.g. the accuracy of TIS predicted by MED 1.0 increases from 61.7 to 91.5% for 854 E.coli verified genes, while that by GLIMMER 2.02 increases from 63.2 to 92.0% for the same dataset. These results show that our algorithm is one of the most accurate methods to identify TIS of prokaryotic genomes. AVAILABILITY: The program MED-Start can be accessed through the website of CTB at Peking University: http://ctb.pku.edu.cn/main/SheGroup/MED_Start.htm.     

Prediction of maize single-cross hybrid performance: support vector machine regression versus best linear prediction

Accurate prediction of the phenotypic performance of a hybrid plant based on the molecular fingerprints of its parents should lead to a more cost-effective breeding programme as it allows to reduce the number of expensive field evaluations. The construction of a reliable prediction model requires a representative sample of hybrids for which both molecular and phenotypic information are accessible. This phenotypic information is usually readily available as typical breeding programmes test numerous new hybrids in multi-location field trials on a yearly basis. Earlier studies indicated that a linear mixed model analysis of this typically unbalanced phenotypic data allows to construct ɛ-insensitive support vector machine regression and best linear prediction models for predicting the performance of single-cross maize hybrids. We compare these prediction methods using different subsets of the phenotypic and marker data of a commercial maize breeding programme and evaluate the resulting prediction accuracies by means of a specifically designed field experiment. This balanced field trial allows to assess the reliability of the cross-validation prediction accuracies reported here and in earlier studies. The limits of the predictive capabilities of both prediction methods are further examined by reducing the number of training hybrids and the size of the molecular fingerprints. The results indicate a considerable discrepancy between prediction accuracies obtained by cross-validation procedures and those obtained by correlating the predictions with the results of a validation field trial. The prediction accuracy of best linear prediction was less sensitive to a reduction of the number of training examples compared with that of support vector machine regression. The latter was, however, better at predicting hybrid performance when the size of the molecular fingerprints was reduced, especially if the initial set of markers had a low information content.     

Computational Prediction of Human Salivary Proteins from Blood Circulation and Application to Diagnostic Biomarker Identification

Proteins can move from blood circulation into salivary glands through active transportation, passive diffusion or ultrafiltration, some of which are then released into saliva and hence can potentially serve as biomarkers for diseases if accurately identified. We present a novel computational method for predicting salivary proteins that come from circulation. The basis for the prediction is a set of physiochemical and sequence features we found to be discerning between human proteins known to be movable from circulation to saliva and proteins deemed to be not in saliva. A classifier was trained based on these features using a support-vector machine to predict protein secretion into saliva. The classifier achieved 88.56% average recall and 90.76% average precision in 10-fold cross-validation on the training data, indicating that the selected features are informative. Considering the possibility that our negative training data may not be highly reliable (i.e., proteins predicted to be not in saliva), we have also trained a ranking method, aiming to rank the known salivary proteins from circulation as the highest among the proteins in the general background, based on the same features. This prediction capability can be used to predict potential biomarker proteins for specific human diseases when coupled with the information of differentially expressed proteins in diseased versus healthy control tissues and a prediction capability for blood-secretory proteins. Using such integrated information, we predicted 31 candidate biomarker proteins in saliva for breast cancer.     

Secondary structure prediction with support vector machines

MOTIVATION: A new method that uses support vector machines (SVMs) to predict protein secondary structure is described and evaluated. The study is designed to develop a reliable prediction method using an alternative technique and to investigate the applicability of SVMs to this type of bioinformatics problem. METHODS: Binary SVMs are trained to discriminate between two structural classes. The binary classifiers are combined in several ways to predict multi-class secondary structure. RESULTS: The average three-state prediction accuracy per protein (Q(3)) is estimated by cross-validation to be 77.07 +/- 0.26% with a segment overlap (Sov) score of 73.32 +/- 0.39%. The SVM performs similarly to the 'state-of-the-art' PSIPRED prediction method on a non-homologous test set of 121 proteins despite being trained on substantially fewer examples. A simple consensus of the SVM, PSIPRED and PROFsec achieves significantly higher prediction accuracy than the individual methods.     

Predicting protein folding cores by empirical potential functions

Theoretical and in vitro experiments suggest that protein folding cores form early in the process of folding, and that proteins may have evolved to optimize both folding speed and native-state stability. In our previous work (Chen et al., Structure, 14 (2006) 1401), we developed a set of empirical potential functions and used them to analyze interaction energies among secondary-structure elements in two β-sandwich proteins. Our work on this group of proteins demonstrated that the predicted folding core also harbors residues that form native-like interactions early in the folding reaction. In the current work, we have tested our empirical potential functions on structurally-different proteins for which the folding cores have been revealed by protein hydrogen-deuterium exchange experiments. Using a set of 29 unrelated proteins, which have been extensively studied in the literature, we demonstrate that the average prediction result from our method is significantly better than predictions based on other computational methods. Our study is an important step towards the ultimate goal of understanding the correlation between folding cores and native structures.     

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

In this paper a systematic attempt has been made to develop a better method for predicting alpha-turns in proteins. Most of the commonly used approaches in the field of protein structure prediction have been tried in this study, which includes statistical approach "Sequence Coupled Model" and machine learning approaches; i) artificial neural network (ANN); ii) Weka (Waikato Environment for Knowledge Analysis) Classifiers and iii) Parallel Exemplar Based Learning (PEBLS). We have also used multiple sequence alignment obtained from PSIBLAST and secondary structure information predicted by PSIPRED. The training and testing of all methods has been performed on a data set of 193 non-homologous protein X-ray structures using five-fold cross-validation. It has been observed that ANN with multiple sequence alignment and predicted secondary structure information outperforms other methods. Based on our observations we have developed an ANN-based method for predicting alpha-turns in proteins. The main components of the method are two feed-forward back-propagation networks with a single hidden layer. The first sequence-structure network is trained with the multiple sequence alignment in the form of PSI-BLAST-generated position specific scoring matrices. The initial predictions obtained from the first network and PSIPRED predicted secondary structure are used as input to the second structure-structure network to refine the predictions obtained from the first net. The final network yields an overall prediction accuracy of 78.0% and MCC of 0.16. A web server AlphaPred (http://www.imtech.res.in/raghava/alphapred/) has been developed based on this approach.     

A new approach to predicting protein folding types

A new method is proposed for predicting the folding type of a protein according to its amino acid composition based on the following physical picture: (1) a protein is characterized as a vector of 20-dimensional space, in which its 20 components are defined by the compositions of its 20 amino acids; and (2) the similarity of two proteins is proportional to the mutual projection of their characterized vectors, and hence inversely proportional to the size of their correlation angle. Thus, the prediction is performed by calculating the correlation angles of the vector for the predicted protein with a set of standard vectors representing the norms of four protein folding types (i.e., alla, all ,a+, anda/). In comparison with the existing methods, the new method has the merits of yielding a higher rate of correct prediction, displaying a more intuitive physical picture, and being convenient in application. For instance, in predicting the 64 proteins in the development set based on which the standard vectors are derived, the average accuracy rate is 83.6%, which is higher than that obtained for the same set of proteins by any of the existing methods. The average accuracy predicted for an independent set of 35 proteins of known X-ray structure is 91.4%, which is significantly higher than any of the reported accuracies so far, implying that the new method is of great value in practical application. All of these have demonstrated that the new method as proposed in this paper is characterized by an improved feature in both self-consistency and extrapolating-effectiveness.On sabbatical leave from Department of Physics, Tianjin University, Tianjin, China.     

The recognition of multi-class protein folds by adding average chemical shifts of secondary structure elements

The recognition of protein folds is an important step in the prediction of protein structure and function. Recently, an increasing number of researchers have sought to improve the methods for protein fold recognition. Following the construction of a dataset consisting of 27 protein fold classes by Ding and Dubchak in 2001, prediction algorithms, parameters and the construction of new datasets have improved for the prediction of protein folds. In this study, we reorganized a dataset consisting of 76-fold classes constructed by Liu et al. and used the values of the increment of diversity, average chemical shifts of secondary structure elements and secondary structure motifs as feature parameters in the recognition of multi-class protein folds. With the combined feature vector as the input parameter for the Random Forests algorithm and ensemble classification strategy, we propose a novel method to identify the 76 protein fold classes. The overall accuracy of the test dataset using an independent test was 66.69%; when the training and test sets were combined, with 5-fold cross-validation, the overall accuracy was 73.43%. This method was further used to predict the test dataset and the corresponding structural classification of the first 27-protein fold class dataset, resulting in overall accuracies of 79.66% and 93.40%, respectively. Moreover, when the training set and test sets were combined, the accuracy using 5-fold cross-validation was 81.21%. Additionally, this approach resulted in improved prediction results using the 27-protein fold class dataset constructed by Ding and Dubchak.     

An evaluation of beta-turn prediction methods

MOTIVATION: beta-turn is an important element of protein structure. In the past three decades, numerous beta-turn prediction methods have been developed based on various strategies. For a detailed discussion about the importance of beta-turns and a systematic introduction of the existing prediction algorithms for beta-turns and their types, please see a recent review (Chou, Analytical Biochemistry, 286, 1-16, 2000). However at present, it is still difficult to say which method is better than the other. This is because of the fact that these methods were developed on different sets of data. Thus, it is important to evaluate the performance of beta-turn prediction methods. RESULTS: We have evaluated the performance of six methods of beta-turn prediction. All the methods have been tested on a set of 426 non-homologous protein chains. It has been observed that the performance of the neural network based method, BTPRED, is significantly better than the statistical methods. One of the reasons for its better performance is that it utilizes the predicted secondary structure information. We have also trained, tested and evaluated the performance of all methods except BTPRED and GORBTURN, on new data set using a 7-fold cross-validation technique. There is a significant improvement in performance of all the methods when secondary structure information is incorporated. Moreover, after incorporating secondary structure information, the Sequence Coupled Model has yielded better results in predicting beta-turns as compared with other methods. In this study, both threshold dependent and independent (ROC) measures have been used for evaluation.