Prediction of protein binding sites in protein structures using hidden Markov support vector machine

Background  

Predicting the binding sites between two interacting proteins provides important clues to the function of a protein. Recent research on protein binding site prediction has been mainly based on widely known machine learning techniques, such as artificial neural networks, support vector machines, conditional random field, etc. However, the prediction performance is still too low to be used in practice. It is necessary to explore new algorithms, theories and features to further improve the performance.     

Improved prediction of protein-protein binding sites using a support vector machines approach

MOTIVATION: Structural genomics projects are beginning to produce protein structures with unknown function, therefore, accurate, automated predictors of protein function are required if all these structures are to be properly annotated in reasonable time. Identifying the interface between two interacting proteins provides important clues to the function of a protein and can reduce the search space required by docking algorithms to predict the structures of complexes. RESULTS: We have combined a support vector machine (SVM) approach with surface patch analysis to predict protein-protein binding sites. Using a leave-one-out cross-validation procedure, we were able to successfully predict the location of the binding site on 76% of our dataset made up of proteins with both transient and obligate interfaces. With heterogeneous cross-validation, where we trained the SVM on transient complexes to predict on obligate complexes (and vice versa), we still achieved comparable success rates to the leave-one-out cross-validation suggesting that sufficient properties are shared between transient and obligate interfaces. AVAILABILITY: A web application based on the method can be found at http://www.bioinformatics.leeds.ac.uk/ppi_pred. The dataset of 180 proteins used in this study is also available via the same web site. CONTACT: westhead@bmb.leeds.ac.uk SUPPLEMENTARY INFORMATION: http://www.bioinformatics.leeds.ac.uk/ppi-pred/supp-material.     

Prediction of siRNA functionality using generalized string kernel and support vector machine

Small interfering RNAs (siRNAs) are becoming widely used for sequence-specific gene silencing in mammalian cells, but designing an effective siRNA is still a challenging task. In this study, we developed an algorithm for predicting siRNA functionality by using generalized string kernel (GSK) combined with support vector machine (SVM). With GSK, siRNA sequences were represented as vectors in a multi-dimensional feature space according to the numbers of subsequences in each siRNA, and subsequently classified with SVM into effective or ineffective siRNAs. We applied this algorithm to published siRNAs, and could classify effective and ineffective siRNAs with 90.6%, 86.2% accuracy, respectively.     

Prediction of mitochondrial proteins using support vector machine and hidden Markov model

Mitochondria are considered as one of the core organelles of eukaryotic cells hence prediction of mitochondrial proteins is one of the major challenges in the field of genome annotation. This study describes a method, MitPred, developed for predicting mitochondrial proteins with high accuracy. The data set used in this study was obtained from Guda, C., Fahy, E. & Subramaniam, S. (2004) Bioinformatics 20, 1785-1794. First support vector machine-based modules/methods were developed using amino acid and dipeptide composition of proteins and achieved accuracy of 78.37 and 79.38%, respectively. The accuracy of prediction further improved to 83.74% when split amino acid composition (25 N-terminal, 25 C-terminal, and remaining residues) of proteins was used. Then BLAST search and support vector machine-based method were combined to get 88.22% accuracy. Finally we developed a hybrid approach that combined hidden Markov model profiles of domains (exclusively found in mitochondrial proteins) and the support vector machine-based method. We were able to predict mitochondrial protein with 100% specificity at a 56.36% sensitivity rate and with 80.50% specificity at 98.95% sensitivity. The method estimated 9.01, 6.35, 4.84, 3.95, and 4.25% of proteins as mitochondrial in Saccharomyces cerevisiae, Drosophila melanogaster, Caenorhabditis elegans, mouse, and human proteomes, respectively. MitPred was developed on the above hybrid approach.     

Prediction of methylated CpGs in DNA sequences using a support vector machine

DNA methylation plays a key role in the regulation of gene expression. The most common type of DNA modification consists of the methylation of cytosine in the CpG dinucleotide. At the present time, there is no method available for the prediction of DNA methylation sites. Therefore, in this study we have developed a support vector machine (SVM)-based method for the prediction of cytosine methylation in CpG dinucleotides. Initially a SVM module was developed from human data for the prediction of human-specific methylation sites. This module achieved a MCC and AUC of 0.501 and 0.814, respectively, when evaluated using a 5-fold cross-validation. The performance of this SVM-based module was better than the classifiers built using alternative machine learning and statistical algorithms including artificial neural networks, Bayesian statistics, and decision trees. Additional SVM modules were also developed based on mammalian- and vertebrate-specific methylation patterns. The SVM module based on human methylation patterns was used for genome-wide analysis of methylation sites. This analysis demonstrated that the percentage of methylated CpGs is higher in UTRs as compared to exonic and intronic regions of human genes. This method is available on line for public use under the name of Methylator at http://bio.dfci.harvard.edu/Methylator/.     

Prediction of prostate cancer using hair trace element concentration and support vector machine method

A change in the normal concentration of essential trace elements in the human body might lead to major health disturbances. In this study, hair samples were collected from 115 human subject, including 55 healthy people and 60 patients with prostate cancer. The concentrations of 20 trace elements (TEs) in these samples were measured by inductively coupled plasma-mass spectrometry. A support vector machine was used to investigate the relationship between TEs and prostate cancer. It is found that, among the 20 TEs, 10 (Mg P, K, Ca, Cr, Mn, Fe. Cu, Zn, and Se) are related to the risk of prostate cancer. These 10 TEs were used to build the prediction model for prostate cancer. The model obtained can satisfactorily distinguish the healthy samples from the cancer samples. Furthermore, the cross-validation by leaving-one method proved that the prediction ability of this model reaches as high as 95.8%. It is practical to predict the risk of prostate cancer using this model in the clinics     

Effect of training datasets on support vector machine prediction of protein-protein interactions

Knowledge of protein-protein interaction is useful for elucidating protein function via the concept of 'guilt-by-association'. A statistical learning method, Support Vector Machine (SVM), has recently been explored for the prediction of protein-protein interactions using artificial shuffled sequences as hypothetical noninteracting proteins and it has shown promising results (Bock, J. R., Gough, D. A., Bioinformatics 2001, 17, 455-460). It remains unclear however, how the prediction accuracy is affected if real protein sequences are used to represent noninteracting proteins. In this work, this effect is assessed by comparison of the results derived from the use of real protein sequences with that derived from the use of shuffled sequences. The real protein sequences of hypothetical noninteracting proteins are generated from an exclusion analysis in combination with subcellular localization information of interacting proteins found in the Database of Interacting Proteins. Prediction accuracy using real protein sequences is 76.9% compared to 94.1% using artificial shuffled sequences. The discrepancy likely arises from the expected higher level of difficulty for separating two sets of real protein sequences than that for separating a set of real protein sequences from a set of artificial sequences. The use of real protein sequences for training a SVM classification system is expected to give better prediction results in practical cases. This is tested by using both SVM systems for predicting putative protein partners of a set of thioredoxin related proteins. The prediction results are consistent with observations, suggesting that real sequence is more practically useful in development of SVM classification system for facilitating protein-protein interaction prediction.     

Conserved residue clusters at protein-protein interfaces and their use in binding site identification

Background  

Biological evolution conserves protein residues that are important for structure and function. Both protein stability and function often require a certain degree of structural co-operativity between spatially neighboring residues and it has previously been shown that conserved residues occur clustered together in protein tertiary structures, enzyme active sites and protein-DNA interfaces. Residues comprising protein interfaces are often more conserved compared to those occurring elsewhere on the protein surface. We investigate the extent to which conserved residues within protein-protein interfaces are clustered together in three-dimensions.     

Prediction of membrane proteins in Mycobacterium tuberculosis using a support vector machine algorithm.

We report our finding of linear clustering of signal sequences at the N-terminus of M.tb membrane proteins, directing membrane localization. Although it is widely accepted that membrane proteins have signal peptides at the N-terminus, statistical ensemble analysis of Support Vector Machine prediction results indicate that M.tb membrane proteins have embedded N-terminal sequence patterns beyond the signal peptides previously identified in E. coli. The additional patterns at the N-terminus of M.tb membrane proteins may have correlations to their unique enzymatic functions and unusual characteristics such as membrane interaction in pathogenes.     

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 protein structure class by coupling improved genetic algorithm and support vector machine

Structural class characterizes the overall folding type of a protein or its domain. Most of the existing methods for determining the structural class of a protein are based on a group of features that only possesses a kind of discriminative information for the prediction of protein structure class. However, different types of discriminative information associated with primary sequence have been completely missed, which undoubtedly has reduced the success rate of prediction. We present a novel method for the prediction of protein structure class by coupling the improved genetic algorithm (GA) with the support vector machine (SVM). This improved GA was applied to the selection of an optimized feature subset and the optimization of SVM parameters. Jackknife tests on the working datasets indicated that the prediction accuracies for the different classes were in the range of 97.8–100% with an overall accuracy of 99.5%. The results indicate that the approach has a high potential to become a useful tool in bioinformatics.     

Prediction of RNA-binding proteins from primary sequence by a support vector machine approach

Elucidation of the interaction of proteins with different molecules is of significance in the understanding of cellular processes. Computational methods have been developed for the prediction of protein-protein interactions. But insufficient attention has been paid to the prediction of protein-RNA interactions, which play central roles in regulating gene expression and certain RNA-mediated enzymatic processes. This work explored the use of a machine learning method, support vector machines (SVM), for the prediction of RNA-binding proteins directly from their primary sequence. Based on the knowledge of known RNA-binding and non-RNA-binding proteins, an SVM system was trained to recognize RNA-binding proteins. A total of 4011 RNA-binding and 9781 non-RNA-binding proteins was used to train and test the SVM classification system, and an independent set of 447 RNA-binding and 4881 non-RNA-binding proteins was used to evaluate the classification accuracy. Testing results using this independent evaluation set show a prediction accuracy of 94.1%, 79.3%, and 94.1% for rRNA-, mRNA-, and tRNA-binding proteins, and 98.7%, 96.5%, and 99.9% for non-rRNA-, non-mRNA-, and non-tRNA-binding proteins, respectively. The SVM classification system was further tested on a small class of snRNA-binding proteins with only 60 available sequences. The prediction accuracy is 40.0% and 99.9% for snRNA-binding and non-snRNA-binding proteins, indicating a need for a sufficient number of proteins to train SVM. The SVM classification systems trained in this work were added to our Web-based protein functional classification software SVMProt, at http://jing.cz3.nus.edu.sg/cgi-bin/svmprot.cgi. Our study suggests the potential of SVM as a useful tool for facilitating the prediction of protein-RNA interactions.     

Recognition and classification of histones using support vector machine.

Histones are DNA-binding proteins found in the chromatin of all eukaryotic cells. They are highly conserved and can be grouped into five major classes: H1/H5, H2A, H2B, H3, and H4. Two copies of H2A, H2B, H3, and H4 bind to about 160 base pairs of DNA forming the core of the nucleosome (the repeating structure of chromatin) and H1/H5 bind to its DNA linker sequence. Overall, histones have a high arginine/lysine content that is optimal for interaction with DNA. This sequence bias can make the classification of histones difficult using standard sequence similarity approaches. Therefore, in this paper, we applied support vector machine (SVM) to recognize and classify histones on the basis of their amino acid and dipeptide composition. On evaluation through a five-fold cross-validation, the SVM-based method was able to distinguish histones from nonhistones (nuclear proteins) with an accuracy around 98%. Similarly, we obtained an overall >95% accuracy in discriminating the five classes of histones through the application of 1-versus-rest (1-v-r) SVM. Finally, we have applied this SVM-based method to the detection of histones from whole proteomes and found a comparable sensitivity to that accomplished by hidden Markov motifs (HMM) profiles.     

Predictions of hot spot residues at protein-protein interfaces using support vector machines

Protein-protein interactions are critically dependent on just a few 'hot spot' residues at the interface. Hot spots make a dominant contribution to the free energy of binding and they can disrupt the interaction if mutated to alanine. Here, we present HSPred, a support vector machine(SVM)-based method to predict hot spot residues, given the structure of a complex. HSPred represents an improvement over a previously described approach (Lise et al, BMC Bioinformatics 2009, 10:365). It achieves higher accuracy by treating separately predictions involving either an arginine or a glutamic acid residue. These are the amino acid types on which the original model did not perform well. We have therefore developed two additional SVM classifiers, specifically optimised for these cases. HSPred reaches an overall precision and recall respectively of 61% and 69%, which roughly corresponds to a 10% improvement. An implementation of the described method is available as a web server at http://bioinf.cs.ucl.ac.uk/hspred. It is free to non-commercial users.     

Ecological footprint model using the support vector machine technique

The per capita ecological footprint (EF) is one of the most widely recognized measures of environmental sustainability. It aims to quantify the Earth's biological resources required to support human activity. In this paper, we summarize relevant previous literature, and present five factors that influence per capita EF. These factors are: National gross domestic product (GDP), urbanization (independent of economic development), distribution of income (measured by the Gini coefficient), export dependence (measured by the percentage of exports to total GDP), and service intensity (measured by the percentage of service to total GDP). A new ecological footprint model based on a support vector machine (SVM), which is a machine-learning method based on the structural risk minimization principle from statistical learning theory was conducted to calculate the per capita EF of 24 nations using data from 123 nations. The calculation accuracy was measured by average absolute error and average relative error. They were 0.004883 and 0.351078% respectively. Our results demonstrate that the EF model based on SVM has good calculation performance.     

Improved method for predicting beta-turn using support vector machine

MOTIVATION: Numerous methods for predicting beta-turns in proteins have been developed based on various computational schemes. Here, we introduce a new method of beta-turn prediction that uses the support vector machine (SVM) algorithm together with predicted secondary structure information. Various parameters from the SVM have been adjusted to achieve optimal prediction performance. RESULTS: The SVM method achieved excellent performance as measured by the Matthews correlation coefficient (MCC = 0.45) using a 7-fold cross validation on a database of 426 non-homologous protein chains. To our best knowledge, this MCC value is the highest achieved so far for predicting beta-turn. The overall prediction accuracy Qtotal was 77.3%, which is the best among the existing prediction methods. Among its unique attractive features, the present SVM method avoids overtraining and compresses information and provides a predicted reliability index.     

Prediction of biological activity of Aurora-A kinase inhibitors by multilinear regression analysis and support vector machine

Several QSAR (quantitative structure-activity relationships) models for predicting the inhibitory activity of 117 Aurora-A kinase inhibitors were developed. The whole dataset was split into a training set and a test set based on two different methods, (1) by a random selection; and (2) on the basis of a Kohonen’s self-organizing map (SOM). Then the inhibitory activity of 117 Aurora-A kinase inhibitors was predicted using multilinear regression (MLR) analysis and support vector machine (SVM) methods, respectively. For the two MLR models and the two SVM models, for the test sets, the correlation coefficients of over 0.92 were achieved.