Prediction of functional class of the SARS coronavirus proteins by a statistical learning method

The complete genome of severe acute respiratory syndrome coronavirus (SARS-CoV) reveals the existence of putative proteins unique to SARS-CoV. Identification of their function facilitates a mechanistic understanding of SARS infection and drug development for its treatment. The sequence of the majority of these putative proteins has no significant similarity to those of known proteins, which complicates the task of using sequence analysis tools to probe their function. Support vector machines (SVM), useful for predicting the functional class of distantly related proteins, is employed to ascribe a possible functional class to SARS-CoV proteins. Testing results indicate that SVM is able to predict the functional class of 73% of the known SARS-CoV proteins with available sequences and 67% of 18 other novel viral proteins. A combination of the sequence comparison method BLAST and SVMProt can further improve the prediction accuracy of SMVProt such that the functional class of two additional SARS-CoV proteins is correctly predicted. Our study suggests that the SARS-CoV genome possibly contains a putative voltage-gated ion channel, structural proteins, a carbon-oxygen lyase, oxidoreductases acting on the CH-OH group of donors, and an ATP-binding cassette transporter. A web version of our software, SVMProt, is accessible at http://jing.cz3.nus.edu.sg/cgi-bin/svmprot.cgi .     

Prediction of functional class of novel bacterial proteins without the use of sequence similarity by a statistical learning method

A substantial percentage of the putative protein-encoding open reading frames (ORFs) in bacterial genomes have no homolog of known function, and their function cannot be confidently assigned on the basis of sequence similarity. Methods not based on sequence similarity are needed and being developed. One method, SVMProt (http://jing.cz3.nus.edu.sg/cgi-bin/svmprot.cgi), predicts protein functional family irrespective of sequence similarity (Nucleic Acids Res. 2003;31:3692-3697). While it has been tested on a large number of proteins, its capability for non-homologous proteins has so far been evaluated for a relatively small number of proteins, and additional tests are needed to more fully assess SVMProt. In this work, 90 novel bacterial proteins (non-homologous to known proteins) are used to evaluate the capability of SVMProt. These proteins are such that none of their homologs are in the Swiss-Prot database, their functions not clearly described in the literature, and they themselves and their homologs are not included in the training sets of SVMProt. They represent proteins whose function cannot be confidently predicted by sequence similarity methods at present. The predicted functional class of 76.7% of each of these proteins shows various levels of consistency with the literature-described function, compared to the overall accuracy of 87% for the SVMProt functional class assignment of 34,582 proteins that have at least one homolog of known function. Our study suggests that SVMProt is capable of assigning functional class for novel bacterial proteins at a level not too much lower than that of sequence alignment methods for homologous proteins.     

Structural bioinformatics prediction of membrane-binding proteins

Membrane-binding peripheral proteins play important roles in many biological processes, including cell signaling and membrane trafficking. Unlike integral membrane proteins, these proteins bind the membrane mostly in a reversible manner. Since peripheral proteins do not have canonical transmembrane segments, it is difficult to identify them from their amino acid sequences. As a first step toward genome-scale identification of membrane-binding peripheral proteins, we built a kernel-based machine learning protocol. Key features of known membrane-binding proteins, including electrostatic properties and amino acid composition, were calculated from their amino acid sequences and tertiary structures, which were then incorporated into the support vector machine to perform the classification. A data set of 40 membrane-binding proteins and 230 non-membrane-binding proteins was used to construct and validate the protocol. Cross-validation and holdout evaluation of the protocol showed that the accuracy of the prediction reached up to 93.7% and 91.6%, respectively. The protocol was applied to the prediction of membrane-binding properties of four C2 domains from novel protein kinases C. Although these C2 domains have 50% sequence identity, only one of them was predicted to bind the membrane, which was verified experimentally with surface plasmon resonance analysis. These results suggest that our protocol can be used for predicting membrane-binding properties of a wide variety of modular domains and may be further extended to genome-scale identification of membrane-binding peripheral proteins.     

Prediction of protein relative solvent accessibility with a two-stage SVM approach

Information on relative solvent accessibility (RSA) of amino acid residues in proteins provides valuable clues to the prediction of protein structure and function. A two-stage approach with support vector machines (SVMs) is proposed, where an SVM predictor is introduced to the output of the single-stage SVM approach to take into account the contextual relationships among solvent accessibilities for the prediction. By using the position-specific scoring matrices (PSSMs) generated by PSI-BLAST, the two-stage SVM approach achieves accuracies up to 90.4% and 90.2% on the Manesh data set of 215 protein structures and the RS126 data set of 126 nonhomologous globular proteins, respectively, which are better than the highest published scores on both data sets to date. A Web server for protein RSA prediction using a two-stage SVM method has been developed and is available (http://birc.ntu.edu.sg/~pas0186457/rsa.html).     

Prediction of protein subcellular localization

Because the protein's function is usually related to its subcellular localization, the ability to predict subcellular localization directly from protein sequences will be useful for inferring protein functions. Recent years have seen a surging interest in the development of novel computational tools to predict subcellular localization. At present, these approaches, based on a wide range of algorithms, have achieved varying degrees of success for specific organisms and for certain localization categories. A number of authors have noticed that sequence similarity is useful in predicting subcellular localization. For example, Nair and Rost (Protein Sci 2002;11:2836-2847) have carried out extensive analysis of the relation between sequence similarity and identity in subcellular localization, and have found a close relationship between them above a certain similarity threshold. However, many existing benchmark data sets used for the prediction accuracy assessment contain highly homologous sequences-some data sets comprising sequences up to 80-90% sequence identity. Using these benchmark test data will surely lead to overestimation of the performance of the methods considered. Here, we develop an approach based on a two-level support vector machine (SVM) system: the first level comprises a number of SVM classifiers, each based on a specific type of feature vectors derived from sequences; the second level SVM classifier functions as the jury machine to generate the probability distribution of decisions for possible localizations. We compare our approach with a global sequence alignment approach and other existing approaches for two benchmark data sets-one comprising prokaryotic sequences and the other eukaryotic sequences. Furthermore, we carried out all-against-all sequence alignment for several data sets to investigate the relationship between sequence homology and subcellular localization. Our results, which are consistent with previous studies, indicate that the homology search approach performs well down to 30% sequence identity, although its performance deteriorates considerably for sequences sharing lower sequence identity. A data set of high homology levels will undoubtedly lead to biased assessment of the performances of the predictive approaches-especially those relying on homology search or sequence annotations. Our two-level classification system based on SVM does not rely on homology search; therefore, its performance remains relatively unaffected by sequence homology. When compared with other approaches, our approach performed significantly better. Furthermore, we also develop a practical hybrid method, which combines the two-level SVM classifier and the homology search method, as a general tool for the sequence annotation of subcellular localization.     

Prediction of functional residues in water channels and related proteins.

In this paper, we present an updated classification of the ubiquitous MIP (Major Intrinsic Protein) family proteins, including 153 fully or partially sequenced members available in public databases. Presently, about 30 of these proteins have been functionally characterized, exhibiting essentially two distinct types of channel properties: (1) specific water transport by the aquaporins, and (2) small neutral solutes transport, such as glycerol by the glycerol facilitators. Sequence alignments were used to predict amino acids and motifs discriminant in channel specificity. The protein sequences were also analyzed using statistical tools (comparisons of means and correspondence analysis). Five key positions were clearly identified where the residues are specific for each functional subgroup and exhibit high dissimilar physico-chemical properties. Moreover, we have found that the putative channels for small neutral solutes clearly differ from the aquaporins by the amino acid content and the length of predicted loop regions, suggesting a substrate filter function for these loops. From these results, we propose a signature pattern for water transport.     

面向蛋白质功能位点识别的机器学习平台构建

有关蛋白质功能的研究是解析生命奥秘的基础,机器学习技术在该领域已有广泛应用。利用支持向量机(support vectormachine,SVM)方法,构建一个预测蛋白质功能位点的通用平台。该平台先提取非同源蛋白质序列,再对这些序列进行特征编码(包括序列的基本信息、物化特征、结构信息及序列保守性特征等),以编码好的样本作为训练数据,利用SVM进行训练,得到敏感性、特异性、Matthew相关系数、准确率及ROC曲线等评价指标,反复测试,得到评价指标最优的SVM模型后,便可以用来预测蛋白质序列上的功能位点。该平台除了应用在预测蛋白质功能位点之外,还可以应用于疾病相关单核苷酸多态性(SNP)预测分析、预测蛋白质结构域分析、生物分子间的相互作用等。     

Prediction of protein accessible surface areas by support vector regression

A novel support vector regression (SVR) approach is proposed to predict protein accessible surface areas (ASAs) from their primary structures. In this work, we predict the real values of ASA in squared angstroms for residues instead of relative solvent accessibility. Based on protein residues, the mean and median absolute errors are 26.0 A(2) and 18.87 A(2), respectively. The correlation coefficient between the predicted and observed ASAs is 0.66. Cysteine is the best predicted amino acid (mean absolute error is 13.8 A(2) and median absolute error is 8.37 A(2)), while arginine is the least predicted amino acid (mean absolute error is 42.7 A(2) and median absolute error is 36.31 A(2)). Our work suggests that the SVR approach can be directly applied to the ASA prediction where data preclassification has been used.     

Enzyme family classification by support vector machines

One approach for facilitating protein function prediction is to classify proteins into functional families. Recent studies on the classification of G-protein coupled receptors and other proteins suggest that a statistical learning method, Support vector machines (SVM), may be potentially useful for protein classification into functional families. In this work, SVM is applied and tested on the classification of enzymes into functional families defined by the Enzyme Nomenclature Committee of IUBMB. SVM classification system for each family is trained from representative enzymes of that family and seed proteins of Pfam curated protein families. The classification accuracy for enzymes from 46 families and for non-enzymes is in the range of 50.0% to 95.7% and 79.0% to 100% respectively. The corresponding Matthews correlation coefficient is in the range of 54.1% to 96.1%. Moreover, 80.3% of the 8,291 correctly classified enzymes are uniquely classified into a specific enzyme family by using a scoring function, indicating that SVM may have certain level of unique prediction capability. Testing results also suggest that SVM in some cases is capable of classification of distantly related enzymes and homologous enzymes of different functions. Effort is being made to use a more comprehensive set of enzymes as training sets and to incorporate multi-class SVM classification systems to further enhance the unique prediction accuracy. Our results suggest the potential of SVM for enzyme family classification and for facilitating protein function prediction. Our software is accessible at http://jing.cz3.nus.edu.sg/cgi-bin/svmprot.cgi.     

Prediction of the functional class of lipid binding proteins from sequence-derived properties irrespective of sequence similarity

Lipid binding proteins play important roles in signaling, regulation, membrane trafficking, immune response, lipid metabolism, and transport. Because of their functional and sequence diversity, it is desirable to explore additional methods for predicting lipid binding proteins irrespective of sequence similarity. This work explores the use of support vector machines (SVMs) as such a method. SVM prediction systems are developed using 14,776 lipid binding and 133,441 nonlipid binding proteins and are evaluated by an independent set of 6,768 lipid binding and 64,761 nonlipid binding proteins. The computed prediction accuracy is 78.9, 79.5, 82.2, 79.5, 84.4, 76.6, 90.6, 79.0, and 89.9% for lipid degradation, lipid metabolism, lipid synthesis, lipid transport, lipid binding, lipopolysaccharide biosynthesis, lipoprotein, lipoyl, and all lipid binding proteins, respectively. The accuracy for the nonmember proteins of each class is 99.9, 99.2, 99.6, 99.8, 99.9, 99.8, 98.5, 99.9, and 97.0%, respectively. Comparable accuracies are obtained when homologous proteins are considered as one, or by using a different SVM kernel function. Our method predicts 86.8% of the 76 lipid binding proteins nonhomologous to any protein in the Swiss-Prot database and 89.0% of the 73 known lipid binding domains as lipid binding. These findings suggest the usefulness of SVMs for facilitating the prediction of lipid binding proteins. Our software can be accessed at the SVMProt server (http://jing.cz3.nus.edu.sg/cgi-bin/svmprot.cgi).     

Gastrodianin-like mannose-binding proteins: a novel class of plant proteins with antifungal properties

The orchid Gastrodia elata depends on the fungus Armillaria mellea to complete its life cycle. In the interaction, fungal hyphae penetrate older, nutritive corms but not newly formed corms. From these corms, a protein fraction with in vitro activity against plant-pathogenic fungi has previously been purified. Here, the sequence of gastrodianin, the main constituent of the antifungal fraction, is reported. Four isoforms that encoded two different mature proteins were identified at the cDNA level. Another isoform was detected in sequenced peptides. Because the antifungal activity of gastrodianins produced in and purified from Escherichia coli and Nicotiana tabacum was comparable to that of gastrodianin purified from the orchid, gastrodianins are the active component of the antifungal fractions. Gastrodianin accumulation is probably an important part of the mechanism by which the orchid controls Armillaria penetration. Gastrodianin was found to be homologous to monomeric mannose-binding proteins of other orchids, of which at least one (Epipactis helleborine mannose-binding protein) also displayed in vitro antifungal activity. This establishes the gastrodianin-like proteins (GLIPs) as a novel class of antifungal proteins.     

Prediction of functional sites in proteins using conserved functional group analysis

A detailed knowledge of a protein's functional site is an absolute prerequisite for understanding its mode of action at the molecular level. However, the rapid pace at which sequence and structural information is being accumulated for proteins greatly exceeds our ability to determine their biochemical roles experimentally. As a result, computational methods are required which allow for the efficient processing of the evolutionary information contained in this wealth of data, in particular that related to the nature and location of functionally important sites and residues. The method presented here, referred to as conserved functional group (CFG) analysis, relies on a simplified representation of the chemical groups found in amino acid side-chains to identify functional sites from a single protein structure and a number of its sequence homologues. We show that CFG analysis can fully or partially predict the location of functional sites in approximately 96% of the 470 cases tested and that, unlike other methods available, it is able to tolerate wide variations in sequence identity. In addition, we discuss its potential in a structural genomics context, where automation, scalability and efficiency are critical, and an increasing number of protein structures are determined with no prior knowledge of function. This is exemplified by our analysis of the hypothetical protein Ydde_Ecoli, whose structure was recently solved by members of the North East Structural Genomics consortium. Although the proposed active site for this protein needs to be validated experimentally, this example illustrates the scope of CFG analysis as a general tool for the identification of residues likely to play an important role in a protein's biochemical function. Thus, our method offers a convenient solution to rapidly and automatically process the vast amounts of data that are beginning to emerge from structural genomics projects.     

N-terminal N-myristoylation of proteins: prediction of substrate proteins from amino acid sequence

Myristoylation by the myristoyl-CoA:protein N-myristoyltransferase (NMT) is an important lipid anchor modification of eukaryotic and viral proteins. Automated prediction of N-terminal N-myristoylation from the substrate protein sequence alone is necessary for large-scale sequence annotation projects but it requires a low rate of false positive hits in addition to a sufficient sensitivity.Our previous analysis of substrate protein sequence variability, NMT sequences and 3D structures has revealed motif properties in addition to the known PROSITE motif that are utilized in a new predictor described here. The composite prediction function (with separate ad hoc parameterization (a) for queries from non-fungal eukaryotes and their viruses and (b) for sequences from fungal species) consists of terms evaluating amino acid type preferences at sequences positions close to the N terminus as well as terms penalizing deviations from the physical property pattern of amino acid side-chains encoded in multi-residue correlation within the motif sequence. The algorithm has been validated with a self-consistency and two jack-knife tests for the learning set as well as with kinetic data for model substrates. The sensitivity in recognizing documented NMT substrates is above 95 % for both taxon-specific versions. The corresponding rate of false positive prediction (for sequences with an N-terminal glycine residue) is close to 0.5 %; thus, the technique is applicable for large-scale automated sequence database annotation. The predictor is available as public WWW-server with the URL http://mendel.imp.univie.ac.at/myristate/. Additionally, we propose a version of the predictor that identifies a number of proteolytic protein processing sites at internal glycine residues and that evaluates possible N-terminal myristoylation of the protein fragments.A scan of public protein databases revealed new potential NMT targets for which the myristoyl modification may be of critical importance for biological function. Among others, the list includes kinases, phosphatases, proteasomal regulatory subunit 4, kinase interacting proteins KIP1/KIP2, protozoan flagellar proteins, homologues of mitochondrial translocase TOM40, of the neuronal calcium sensor NCS-1 and of the cytochrome c-type heme lyase CCHL. Analyses of complete eukaryote genomes indicate that about 0.5 % of all encoded proteins are apparent NMT substrates except for a higher fraction in Arabidopsis thaliana ( approximately 0.8 %).     

Mimicking cellular sorting improves prediction of subcellular localization

Predicting the native subcellular compartment of a protein is an important step toward elucidating its function. Here we introduce LOCtree, a hierarchical system combining support vector machines (SVMs) and other prediction methods. LOCtree predicts the subcellular compartment of a protein by mimicking the mechanism of cellular sorting and exploiting a variety of sequence and predicted structural features in its input. Currently LOCtree does not predict localization for membrane proteins, since the compositional properties of membrane proteins significantly differ from those of non-membrane proteins. While any information about function can be used by the system, we present estimates of performance that are valid when only the amino acid sequence of a protein is known. When evaluated on a non-redundant test set, LOCtree achieved sustained levels of 74% accuracy for non-plant eukaryotes, 70% for plants, and 84% for prokaryotes. We rigorously benchmarked LOCtree in comparison to the best alternative methods for localization prediction. LOCtree outperformed all other methods in nearly all benchmarks. Localization assignments using LOCtree agreed quite well with data from recent large-scale experiments. Our preliminary analysis of a few entirely sequenced organisms, namely human (Homo sapiens), yeast (Saccharomyces cerevisiae), and weed (Arabidopsis thaliana) suggested that over 35% of all non-membrane proteins are nuclear, about 20% are retained in the cytosol, and that every fifth protein in the weed resides in the chloroplast.     

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.