SMpred: a support vector machine approach to identify structural motifs in protein structure without using evolutionary information

Knowledge of three dimensional structure is essential to understand the function of a protein. Although the overall fold is made from the whole details of its sequence, a small group of residues, often called as structural motifs, play a crucial role in determining the protein fold and its stability. Identification of such structural motifs requires sufficient number of sequence and structural homologs to define conservation and evolutionary information. Unfortunately, there are many structures in the protein structure databases have no homologous structures or sequences. In this work, we report an SVM method, SMpred, to identify structural motifs from single protein structure without using sequence and structural homologs. SMpred method was trained and tested using 132 proteins domains containing 581 motifs. SMpred method achieved 78.79% accuracy with 79.06% sensitivity and 78.53% specificity. The performance of SMpred was evaluated with MegaMotifBase using 188 proteins containing 1161 motifs. Out of 1161 motifs, SMpred correctly identified 1503 structural motifs reported in MegaMotifBase. Further, we showed that SMpred is useful approach for the length deviant superfamilies and single member superfamilies. This result suggests the usefulness of our approach for facilitating the identification of structural motifs in protein structure in the absence of sequence and structural homologs. The dataset and executable for the SMpred algorithm is available at http://www3.ntu.edu.sg/home/EPNSugan/index_files/SMpred.htm.     

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.     

Prediction of complex super-secondary structure βαβ motifs based on combined features

Prediction of a complex super-secondary structure is a key step in the study of tertiary structures of proteins. The strand-loop-helix-loop-strand (βαβ) motif is an important complex super-secondary structure in proteins. Many functional sites and active sites often occur in polypeptides of βαβ motifs. Therefore, the accurate prediction of βαβ motifs is very important to recognizing protein tertiary structure and the study of protein function. In this study, the βαβ motif dataset was first constructed using the DSSP package. A statistical analysis was then performed on βαβ motifs and non-βαβ motifs. The target motif was selected, and the length of the loop-α-loop varies from 10 to 26 amino acids. The ideal fixed-length pattern comprised 32 amino acids. A Support Vector Machine algorithm was developed for predicting βαβ motifs by using the sequence information, the predicted structure and function information to express the sequence feature. The overall predictive accuracy of 5-fold cross-validation and independent test was 81.7% and 76.7%, respectively. The Matthew’s correlation coefficient of the 5-fold cross-validation and independent test are 0.63 and 0.53, respectively. Results demonstrate that the proposed method is an effective approach for predicting βαβ motifs and can be used for structure and function studies of proteins.     

蛋白质序列中的关联规则发现及其应用

随着蛋白质序列-结构分析中使用的机器学习算法越来越复杂,其结果的解释和发现过程也随之复杂化,因此有必要寻找简单且理论上可靠的方法。通过引入原理简单、理论可靠、结果具有很强实际意义的关联规则发现算法,找到了蛋白质序列中数以万计的模式。结合实例演示了如何将这些模式应用于蛋白质序列分析中,如保守区域发现、二级结构预测等。同时根据这些结果构建了一个二级结构规则库和一种简单的二级结构预测算法,实验结果表明,约81%的二级结构可以由至少一条关联规则预测得到。     

TMBpro: secondary structure, beta-contact and tertiary structure prediction of transmembrane beta-barrel proteins

MOTIVATION: Transmembrane beta-barrel (TMB) proteins are embedded in the outer membranes of mitochondria, Gram-negative bacteria and chloroplasts. These proteins perform critical functions, including active ion-transport and passive nutrient intake. Therefore, there is a need for accurate prediction of secondary and tertiary structure of TMB proteins. Traditional homology modeling methods, however, fail on most TMB proteins since very few non-homologous TMB structures have been determined. Yet, because TMB structures conform to specific construction rules that restrict the conformational space drastically, it should be possible for methods that do not depend on target-template homology to be applied successfully. RESULTS: We develop a suite (TMBpro) of specialized predictors for predicting secondary structure (TMBpro-SS), beta-contacts (TMBpro-CON) and tertiary structure (TMBpro-3D) of transmembrane beta-barrel proteins. We compare our results to the recent state-of-the-art predictors transFold and PRED-TMBB using their respective benchmark datasets, and leave-one-out cross-validation. Using the transFold dataset TMBpro predicts secondary structure with per-residue accuracy (Q(2)) of 77.8%, a correlation coefficient of 0.54, and TMBpro predicts beta-contacts with precision of 0.65 and recall of 0.67. Using the PRED-TMBB dataset, TMBpro predicts secondary structure with Q(2) of 88.3% and a correlation coefficient of 0.75. All of these performance results exceed previously published results by 4% or more. Working with the PRED-TMBB dataset, TMBpro predicts the tertiary structure of transmembrane segments with RMSD <6.0 A for 9 of 14 proteins. For 6 of 14 predictions, the RMSD is <5.0 A, with a GDT_TS score greater than 60.0. AVAILABILITY: http://www.igb.uci.edu/servers/psss.html.     

Conformational analysis corresponding to intra-chain disulfide bridged peptides in proteins of known three-dimensional structure

We have carried out a systematic analysis in order to evaluate whether Intra-Chain Disulfide Bridged Peptides (ICDBPs) observed in proteins of known three-dimensional structure adopt structurally similar conformations as they may correspond to structural/functional motifs. 406 representative ICDBPs comprising between 3 to 17 amino acid residues could be classified according to peptide sequence length and main-chain secondary structure conformation into 146 classes. ICDBPs comprising 6 amino acid residues are maximally represented in the Protein Data Bank. They also represent the maximum number of main-chain secondary structure conformational classes. Individual ICDBPs in each class represent different protein superfamilies and correspond to different amino acid sequences. We identified 145 ICDBP pairs that had not less-than 0.5 A root mean square deviation value corresponding to their equivalent peptide backbone atoms. We believe these ICDBPs represent structural motifs and possible candidates in order to further explore their structure/function role in the corresponding proteins. The common conformational classes observed for ICDBPs defined according to the main-chain secondary structure conformations; H (helix), B (residue in a isolated beta bridge), C (coil), E (extended beta strand), G (3(10) helix), I (pi helix), S (bend), T (hydrogen-bonded turn) were; "CHHH", "CTTC", "CSSS" and "CSSC" (for ICDBP length 4), "CSSCC" (length 5), "EETTEE", "CCSSCC", "CCSSSC" (length 6), "EETTTEE" (length 7), "EETTTTEE" (length 8), "EEEETTEEEE" (length 10), "EEEETTTEEEE" (length 11) and "EEEETTTTEEEE" (length 12).     

Distributions of beta sheets in proteins with application to structure prediction

We recently developed the Rosetta algorithm for ab initio protein structure prediction, which generates protein structures from fragment libraries using simulated annealing. The scoring function in this algorithm favors the assembly of strands into sheets. However, it does not discriminate between different sheet motifs. After generating many structures using Rosetta, we found that the folding algorithm predominantly generates very local structures. We surveyed the distribution of beta-sheet motifs with two edge strands (open sheets) in a large set of non-homologous proteins. We investigated how much of that distribution can be accounted for by rules previously published in the literature, and developed a filter and a scoring method that enables us to improve protein structure prediction for beta-sheet proteins. Proteins 2002;48:85-97.     

A step-by-step classification algorithm of protein secondary structures based on double-layer SVM model

In this paper, a step-by-step classification algorithm based on double-layer SVM model is constructed to predict the secondary structure of proteins. The most important feature of this algorithm is to improve the prediction accuracy of α+β and α/β classes through transforming the prediction of two classes of proteins, α+β and α/β classes, with low accuracy in the past, into the prediction of all-α and all-β classes with high accuracy. A widely-used dataset, 25PDB dataset with sequence similarity lower than 40%, is used to evaluate this method. The results show that this method has good performance, and on the basis of ensuring the accuracy of other three structural classes of proteins, the accuracy of α+β class proteins is improved significantly.     

Genes@Work: an efficient algorithm for pattern discovery and multivariate feature selection in gene expression data

MOTIVATION: Despite the growing literature devoted to finding differentially expressed genes in assays probing different tissues types, little attention has been paid to the combinatorial nature of feature selection inherent to large, high-dimensional gene expression datasets. New flexible data analysis approaches capable of searching relevant subgroups of genes and experiments are needed to understand multivariate associations of gene expression patterns with observed phenotypes. RESULTS: We present in detail a deterministic algorithm to discover patterns of multivariate gene associations in gene expression data. The patterns discovered are differential with respect to a control dataset. The algorithm is exhaustive and efficient, reporting all existent patterns that fit a given input parameter set while avoiding enumeration of the entire pattern space. The value of the pattern discovery approach is demonstrated by finding a set of genes that differentiate between two types of lymphoma. Moreover, these genes are found to behave consistently in an independent dataset produced in a different laboratory using different arrays, thus validating the genes selected using our algorithm. We show that the genes deemed significant in terms of their multivariate statistics will be missed using other methods. AVAILABILITY: Our set of pattern discovery algorithms including a user interface is distributed as a package called Genes@Work. This package is freely available to non-commercial users and can be downloaded from our website (http://www.research.ibm.com/FunGen).     

Amino acid propensities for secondary structures are influenced by the protein structural class

Amino acid propensities for secondary structures were used since the 1970s, when Chou and Fasman evaluated them within datasets of few tens of proteins and developed a method to predict secondary structure of proteins, still in use despite prediction methods having evolved to very different approaches and higher reliability. Propensity for secondary structures represents an intrinsic property of amino acid, and it is used for generating new algorithms and prediction methods, therefore our work has been aimed to investigate what is the best protein dataset to evaluate the amino acid propensities, either larger but not homogeneous or smaller but homogeneous sets, i.e., all-alpha, all-beta, alpha-beta proteins. As a first analysis, we evaluated amino acid propensities for helix, beta-strand, and coil in more than 2000 proteins from the PDBselect dataset. With these propensities, secondary structure predictions performed with a method very similar to that of Chou and Fasman gave us results better than the original one, based on propensities derived from the few tens of X-ray protein structures available in the 1970s. In a refined analysis, we subdivided the PDBselect dataset of proteins in three secondary structural classes, i.e., all-alpha, all-beta, and alpha-beta proteins. For each class, the amino acid propensities for helix, beta-strand, and coil have been calculated and used to predict secondary structure elements for proteins belonging to the same class by using resubstitution and jackknife tests. This second round of predictions further improved the results of the first round. Therefore, amino acid propensities for secondary structures became more reliable depending on the degree of homogeneity of the protein dataset used to evaluate them. Indeed, our results indicate also that all algorithms using propensities for secondary structure can be still improved to obtain better predictive results.     

Widely predicting specific protein functions based on protein-protein interaction data and gene expression profile

GESTs (gene expression similarity and taxonomy similarity), a gene functional prediction approach previously proposed by us, is based on gene expression similarity and concept similarity of functional classes defined in Gene Ontology (GO). In this paper, we extend this method to protein-protein interaction data by introducing several methods to filter the neighbors in protein interaction networks for a protein of unknown function(s). Unlike other conventional methods, the proposed approach automatically selects the most appropriate functional classes as specific as possible during the learning process, and calls on genes annotated to nearby classes to support the predictions to some small-sized specific classes in GO. Based on the yeast protein-protein interaction information from MIPS and a dataset of gene expression profiles, we assess the performances of our approach for predicting protein functions to “biology process” by three measures particularly designed for functional classes organized in GO. Results show that our method is powerful for widely predicting gene functions with very specific functional terms. Based on the GO database published in December 2004, we predict some proteins whose functions were unknown at that time, and some of the predictions have been confirmed by the new SGD annotation data published in April, 2006.     

Murlet: a practical multiple alignment tool for structural RNA sequences

MOTIVATION: Structural RNA genes exhibit unique evolutionary patterns that are designed to conserve their secondary structures; these patterns should be taken into account while constructing accurate multiple alignments of RNA genes. The Sankoff algorithm is a natural alignment algorithm that includes the effect of base-pair covariation in the alignment model. However, the extremely high computational cost of the Sankoff algorithm precludes its application to most RNA sequences. RESULTS: We propose an efficient algorithm for the multiple alignment of structural RNA sequences. Our algorithm is a variant of the Sankoff algorithm, and it uses an efficient scoring system that reduces the time and space requirements considerably without compromising on the alignment quality. First, our algorithm computes the match probability matrix that measures the alignability of each position pair between sequences as well as the base pairing probability matrix for each sequence. These probabilities are then combined to score the alignment using the Sankoff algorithm. By itself, our algorithm does not predict the consensus secondary structure of the alignment but uses external programs for the prediction. We demonstrate that both the alignment quality and the accuracy of the consensus secondary structure prediction from our alignment are the highest among the other programs examined. We also demonstrate that our algorithm can align relatively long RNA sequences such as the eukaryotic-type signal recognition particle RNA that is approximately 300 nt in length; multiple alignment of such sequences has not been possible by using other Sankoff-based algorithms. The algorithm is implemented in the software named 'Murlet'. AVAILABILITY: The C++ source code of the Murlet software and the test dataset used in this study are available at http://www.ncrna.org/papers/Murlet/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.     

Identifying property based sequence motifs in protein families and superfamilies: application to DNase-1 related endonucleases

MOTIVATION: Identification of short conserved sequence motifs common to a protein family or superfamily can be more useful than overall sequence similarity in suggesting the function of novel gene products. Locating motifs still requires expert knowledge, as automated methods using stringent criteria may not differentiate subtle similarities from statistical noise. RESULTS: We have developed a novel automatic method, based on patterns of conservation of 237 physical-chemical properties of amino acids in aligned protein sequences, to find related motifs in proteins with little or no overall sequence similarity. As an application, our web-server MASIA identified 12 property-based motifs in the apurinic/apyrimidinic endonuclease (APE) family of DNA-repair enzymes of the DNase-I superfamily. Searching with these motifs located distantly related representatives of the DNase-I superfamily, such as Inositol 5'-polyphosphate phosphatases in the ASTRAL40 database, using a Bayesian scoring function. Other proteins containing APE motifs had no overall sequence or structural similarity. However, all were phosphatases and/or had a metal ion binding active site. Thus our automated method can identify discrete elements in distantly related proteins that define local structure and aspects of function. We anticipate that our method will complement existing ones to functionally annotate novel protein sequences from genomic projects. AVAILABILITY: MASIA WEB site: http://www.scsb.utmb.edu/masia/masia.html SUPPLEMENTARY INFORMATION: The dendrogram of 42 APE sequences used to derive motifs is available on http://www.scsb.utmb.edu/comp_biol.html/DNA_repair/publication.html     

Widely predicting specific protein functions based on protein-protein interaction data and gene expression profile

GESTs (gene expression similarity and taxonomy similarity), a gene functional prediction approach previously proposed by us, is based on gene expression similarity and concept similarity of functional classes defined in Gene Ontology (GO). In this paper, we extend this method to protein-protein interac-tion data by introducing several methods to filter the neighbors in protein interaction networks for a protein of unknown function(s). Unlike other conventional methods, the proposed approach automati-cally selects the most appropriate functional classes as specific as possible during the learning proc-ess, and calls on genes annotated to nearby classes to support the predictions to some small-sized specific classes in GO. Based on the yeast protein-protein interaction information from MIPS and a dataset of gene expression profiles, we assess the performances of our approach for predicting protein functions to “biology process” by three measures particularly designed for functional classes organ-ized in GO. Results show that our method is powerful for widely predicting gene functions with very specific functional terms. Based on the GO database published in December 2004, we predict some proteins whose functions were unknown at that time, and some of the predictions have been confirmed by the new SGD annotation data published in April, 2006.     

Searching for protein signatures using a multilevel alphabet

Short motifs are known to play diverse roles in proteins, such as in mediating the interactions with other molecules, binding to membranes, or conducting a specific biological function. Standard approaches currently employed to detect short motifs in proteins search for enrichment of amino acid motifs considering mostly the sequence information. Here, we presented a new approach to search for common motifs (protein signatures) which share both physicochemical and structural properties, looking simultaneously at different features. Our method takes as an input an amino acid sequence and translates it to a new alphabet that reflects its intrinsic structural and chemical properties. Using the MEME search algorithm, we identified the proteins signatures within subsets of protein which encompass common sequence and structural information. We demonstrated that we can detect enriched structural motifs, such as the amphipathic helix, from large datasets of linear sequences, as well as predicting common structural properties (such as disorder, surface accessibility, or secondary structures) of known functional‐motifs. Finally, we applied the method to the yeast protein interactome and identified novel putative interacting motifs. We propose that our approach can be applied for de novo protein function prediction given either sequence or structural information. Proteins 2013; © 2012 Wiley Periodicals, Inc.     

Prediction of β-turns and β-turn types by a novel bidirectional Elman-type recurrent neural network with multiple output layers (MOLEBRNN)

Prediction of β-turns from amino acid sequences has long been recognized as an important problem in structural bioinformatics due to their frequent occurrence as well as their structural and functional significance. Because various structural features of proteins are intercorrelated, secondary structure information has been often employed as an additional input for machine learning algorithms while predicting β-turns. Here we present a novel bidirectional Elman-type recurrent neural network with multiple output layers (MOLEBRNN) capable of predicting multiple mutually dependent structural motifs and demonstrate its efficiency in recognizing three aspects of protein structure: β-turns, β-turn types, and secondary structure. The advantage of our method compared to other predictors is that it does not require any external input except for sequence profiles because interdependencies between different structural features are taken into account implicitly during the learning process. In a sevenfold cross-validation experiment on a standard test dataset our method exhibits the total prediction accuracy of 77.9% and the Mathew's Correlation Coefficient of 0.45, the highest performance reported so far. It also outperforms other known methods in delineating individual turn types. We demonstrate how simultaneous prediction of multiple targets influences prediction performance on single targets. The MOLEBRNN presented here is a generic method applicable in a variety of research fields where multiple mutually depending target classes need to be predicted. Availability: http://webclu.bio.wzw.tum.de/predator-web/.     

Profile-based short linear protein motif discovery

ABSTRACT: BACKGROUND: Short linear protein motifs are attracting increasing attention as functionally independent sites, typically 3-10 amino acids in length that are enriched in disordered regions of proteins. Multiple methods have recently been proposed to discover over-represented motifs within a set of proteins based on simple regular expressions. Here, we extend these approaches to profile-based methods, which provide a richer motif representation. RESULTS: The profile motif discovery method MEME performed relatively poorly for motifs in disordered regions of proteins. However, when we applied evolutionary weighting to account for redundancy amongst homologous proteins, and masked out poorly conserved regions of disordered proteins, the performance of MEME is equivalent to that of regular expression methods. However, the two approaches returned different subsets within both a benchmark dataset, and a more realistic discovery dataset. CONCLUSIONS: Profile-based motif discovery methods complement regular expression based methods. Whilst profile-based methods are computationally more intensive, they are likely to discover motifs currently overlooked by regular expression methods.