Accuracy Of Secondary Structure Prediction Research Articles

Sequence Representation and Prediction of Protein Secondary Structure for Structural Motifs in Twilight Zone Proteins

Characterizing and classifying regularities in protein structure is an important element in uncovering the mechanisms that regulate protein structure, function and evolution. Recent research concentrates on analysis of structural motifs that can be used to describe larger, fold-sized structures based on homologous primary sequences. At the same time, accuracy of secondary protein structure prediction based on multiple sequence alignment drops significantly when low homology (twilight zone) sequences are considered. To this end, this paper addresses a problem of providing an alternative sequences representation that would improve ability to distinguish secondary structures for the twilight zone sequences without using alignment. We consider a novel classification problem, in which, structural motifs, referred to as structural fragments (SFs) are defined as uniform strand, helix and coil fragments. Classification of SFs allows to design novel sequence representations, and to investigate which other factors and prediction algorithms may result in the improved discrimination. Comprehensive experimental results show that statistically significant improvement in classification accuracy can be achieved by: (1) improving sequence representations, and (2) removing possible noise on the terminal residues in the SFs. Combining these two approaches reduces the error rate on average by 15% when compared to classification using standard representation and noisy information on the terminal residues, bringing the classification accuracy to over 70%. Finally, we show that certain prediction algorithms, such as neural networks and boosted decision trees, are superior to other algorithms.

A Consensus Data Mining secondary structure prediction by combining GOR V and Fragment Database Mining

The major aim of tertiary structure prediction is to obtain protein models with the highest possible accuracy. Fold recognition, homology modeling, and de novo prediction methods typically use predicted secondary structures as input, and all of these methods may significantly benefit from more accurate secondary structure predictions. Although there are many different secondary structure prediction methods available in the literature, their cross-validated prediction accuracy is generally <80%. In order to increase the prediction accuracy, we developed a novel hybrid algorithm called Consensus Data Mining (CDM) that combines our two previous successful methods: (1) Fragment Database Mining (FDM), which exploits the Protein Data Bank structures, and (2) GOR V, which is based on information theory, Bayesian statistics, and multiple sequence alignments (MSA). In CDM, the target sequence is dissected into smaller fragments that are compared with fragments obtained from related sequences in the PDB. For fragments with a sequence identity above a certain sequence identity threshold, the FDM method is applied for the prediction. The remainder of the fragments are predicted by GOR V. The results of the CDM are provided as a function of the upper sequence identities of aligned fragments and the sequence identity threshold. We observe that the value 50% is the optimum sequence identity threshold, and that the accuracy of the CDM method measured by Q(3) ranges from 67.5% to 93.2%, depending on the availability of known structural fragments with sufficiently high sequence identity. As the Protein Data Bank grows, it is anticipated that this consensus method will improve because it will rely more upon the structural fragments.

Improving the accuracy of protein secondary structure prediction using structural alignment.

BackgroundThe accuracy of protein secondary structure prediction has steadily improved over the past 30 years. Now many secondary structure prediction methods routinely achieve an accuracy (Q3) of about 75%. We believe this accuracy could be further improved by including structure (as opposed to sequence) database comparisons as part of the prediction process. Indeed, given the large size of the Protein Data Bank (>35,000 sequences), the probability of a newly identified sequence having a structural homologue is actually quite high.ResultsWe have developed a method that performs structure-based sequence alignments as part of the secondary structure prediction process. By mapping the structure of a known homologue (sequence ID >25%) onto the query protein's sequence, it is possible to predict at least a portion of that query protein's secondary structure. By integrating this structural alignment approach with conventional (sequence-based) secondary structure methods and then combining it with a "jury-of-experts" system to generate a consensus result, it is possible to attain very high prediction accuracy. Using a sequence-unique test set of 1644 proteins from EVA, this new method achieves an average Q3 score of 81.3%. Extensive testing indicates this is approximately 4–5% better than any other method currently available. Assessments using non sequence-unique test sets (typical of those used in proteome annotation or structural genomics) indicate that this new method can achieve a Q3 score approaching 88%.ConclusionBy using both sequence and structure databases and by exploiting the latest techniques in machine learning it is possible to routinely predict protein secondary structure with an accuracy well above 80%. A program and web server, called PROTEUS, that performs these secondary structure predictions is accessible at . For high throughput or batch sequence analyses, the PROTEUS programs, databases (and server) can be downloaded and run locally.

YASSPP: Better kernels and coding schemes lead to improvements in protein secondary structure prediction

The accurate prediction of a protein's secondary structure plays an increasingly critical role in predicting its function and tertiary structure, as it is utilized by many of the current state-of-the-art methods for remote homology, fold recognition, and ab initio structure prediction. We developed a new secondary structure prediction algorithm called YASSPP, which uses a pair of cascaded models constructed from two sets of binary SVM-based models. YASSPP uses an input coding scheme that combines both position-specific and nonposition-specific information, utilizes a kernel function designed to capture the sequence conservation signals around the local window of each residue, and constructs a second-level model by incorporating both the three-state predictions produced by the first-level model and information about the original sequence. Experiments on three standard datasets (RS126, CB513, and EVA common subset 4) show that YASSPP is capable of producing the highest Q3 and SOV scores than that achieved by existing widely used schemes such as PSIPRED, SSPro 4.0, SAM-T99sec, as well as previously developed SVM-based schemes. On the EVA dataset it achieves a Q3 and SOV score of 79.34 and 78.65%, which are considerably higher than the best reported scores of 77.64 and 76.05%, respectively.

Protein secondary structure prediction for a single-sequence using hidden semi-Markov models.

BackgroundThe accuracy of protein secondary structure prediction has been improving steadily towards the 88% estimated theoretical limit. There are two types of prediction algorithms: Single-sequence prediction algorithms imply that information about other (homologous) proteins is not available, while algorithms of the second type imply that information about homologous proteins is available, and use it intensively. The single-sequence algorithms could make an important contribution to studies of proteins with no detected homologs, however the accuracy of protein secondary structure prediction from a single-sequence is not as high as when the additional evolutionary information is present.ResultsIn this paper, we further refine and extend the hidden semi-Markov model (HSMM) initially considered in the BSPSS algorithm. We introduce an improved residue dependency model by considering the patterns of statistically significant amino acid correlation at structural segment borders. We also derive models that specialize on different sections of the dependency structure and incorporate them into HSMM. In addition, we implement an iterative training method to refine estimates of HSMM parameters. The three-state-per-residue accuracy and other accuracy measures of the new method, IPSSP, are shown to be comparable or better than ones for BSPSS as well as for PSIPRED, tested under the single-sequence condition.ConclusionsWe have shown that new dependency models and training methods bring further improvements to single-sequence protein secondary structure prediction. The results are obtained under cross-validation conditions using a dataset with no pair of sequences having significant sequence similarity. As new sequences are added to the database it is possible to augment the dependency structure and obtain even higher accuracy. Current and future advances should contribute to the improvement of function prediction for orphan proteins inscrutable to current similarity search methods.

Natural selection is not required to explain universal compositional patterns in rRNA secondary structure categories

We have encountered an unexpected property of rRNA secondary structures that may generalize to all RNAs. Analysis of 8892 ribosomal RNA sequences and structures from a wide range of species revealed unexpected universal compositional trends. First, different categories of rRNA secondary structure (stems, loops, bulges, and junctions) have distinct, characteristic base compositions. Second, the observed patterns of variation are similar among sequences from large and small rRNA subunits and all domains of life, despite extensive evolutionary divergence. Surprisingly, these differences do not seem to be related to selection for different compositions in different structural categories, but rather relate to the overall composition of the molecule: Randomized RNAs with no evolutionary history show the same structure-dependent compositional biases as rRNAs. These compositional trends may improve the accuracy of RNA secondary structure prediction, because they allow us to compare predicted structures against known compositional preferences. They also suggest caution in interpreting differences in the rate of change of the GC content in different parts of the molecule as evidence of differential selection.

Highly accurate and consistent method for prediction of helix and strand content from primary protein sequences

One of interesting computational topics in bioinformatics is prediction of secondary structure of proteins. Over 30 years of research has been devoted to the topic but we are still far away from having reliable prediction methods. A critical piece of information for accurate prediction of secondary structure is the helix and strand content of a given protein sequence. Ability to accurately predict content of those two secondary structures has a good potential to improve accuracy of prediction of the secondary structure. Most of the existing methods use composition vector to predict the content. Their underlying assumption is that the vector can be used to provide functional mapping between primary sequence and helix/strand content. While this is true for small sets of proteins we show that for larger protein sets such mapping are inconsistent, i.e. the same composition vectors correspond to different contents. To this end, we propose a method for prediction of helix/strand content from primary protein sequences that is fundamentally different from currently available methods. Our method is accurate and uses a novel approach to obtain information from primary sequence based on a composition moment vector, which is a measure that includes information about both composition of a given primary sequence and the position of amino acids in the sequence. In contrast to the composition vector, we show that it provides functional mapping between primary sequence and the helix/strand content. A set of benchmarks involving a large protein dataset consisting of over 11,000 protein sequences from Protein Data Bank was performed to validate the method. Prediction done by a neural network had average accuracy of 91.5% for the helix and 94.5% for the strand contents. We also show that using the new measure results in about 40% reduction of error rates when compared with the composition vector results. The developed method has much better accuracy when compared with other existing methods, as shown on a large body of proteins, in contrast to other reported results that often target small sets of specific protein types, such as globular proteins.

The effect of long‐range interactions on the secondary structure formation of proteins

The influence of long-range residue interactions on defining secondary structure in a protein has long been discussed and is often cited as the current limitation to accurate secondary structure prediction. There are several experimental examples where a local sequence alone is not sufficient to determine its secondary structure, but a comprehensive survey on a large data set has not yet been done. Interestingly, some earlier studies denied the negative effect of long-range interactions on secondary structure prediction accuracy. Here, we have introduced the residue contact order (RCO), which directly indicates the separation of contacting residues in terms of the position in the sequence, and examined the relationship between the RCO and the prediction accuracy. A large data set of 2777 nonhomologous proteins was used in our analysis. Unlike previous studies, we do find that prediction accuracy drops as residues have contacts with more distant residues. Moreover, this negative correlation between the RCO and the prediction accuracy was found not only for beta-strands, but also for alpha-helices. The prediction accuracy of beta-strands is lower if residues have a high RCO or a low RCO, which corresponds to the situation that a beta-sheet is formed by beta-strands from different chains in a protein complex. The reason why the current study draws the opposite conclusion from the previous studies is examined. The implication for protein folding is also discussed.

Improving protein secondary structure prediction by using the residue conformational classes

In this paper, based on the 340 protein sequences and their corresponding secondary structures retrieved from the protein data bank (PDB), we group the 20 different amino acid residues into 3 conformational categories: f (Former), b (Breaker) and n (Neutral), which reflect the intrinsic preference of the residue for a given type of secondary structure (α-helix, β-sheets and Coil). Then, based on radial basis function neural network (RBFNN) technique, we use this information to reconstruct the input vectors and try to improve globulin protein secondary structure prediction (SSP) accuracy. The experimental results indicate that our approach outperforms the previous conventional methods.

Cofolga: a genetic algorithm for finding the common folding of two RNAs

In order to predict non-coding RNA genes and functions on the basis of genome sequences, accurate secondary structure prediction is useful. Although single-sequence folding programs such as mfold have been successful, it is of great importance to develop a novel approach for further improvement of the prediction performance. In the present paper, a secondary structure prediction method based on genetic algorithm, Cofolga, is proposed. The program developed performs folding and alignment of two homologous RNAs simultaneously. Cofolga was tested with a dataset composed of 13 tRNAs, seven 5S rRNAs, five RNase P RNAs, and five SRP RNAs; as a result, it turned out that the average prediction accuracies for the tRNAs, 5S rRNAs, RNase P RNAs, and SRP RNAs obtained by Cofolga with an optimal weight factor and default parameters were 83.6, 81.8, 73.5, and 67.7%, respectively. These results were superior to those obtained by a single-sequence folding based on free-energy minimization in which corresponding average prediction accuracies were 52.4, 47.4, 57.7, and 52.3%, respectively. Cofolga has a post-processing in which a single-sequence folding is performed after fixation of a predicted common structure; this post-processing enables Cofolga to predict a structure that is present in one of two RNAs alone. The executable files of Cofolga (for Windows/Unix/Mac) can be obtained by an e-mail request.

Combining prediction of secondary structure and solvent accessibility in proteins

Owing to the use of evolutionary information and advanced machine learning protocols, secondary structures of amino acid residues in proteins can be predicted from the primary sequence with more than 75% per-residue accuracy for the 3-state (i.e., helix, beta-strand, and coil) classification problem. In this work we investigate whether further progress may be achieved by incorporating the relative solvent accessibility (RSA) of an amino acid residue as a fingerprint of the overall topology of the protein. Toward that goal, we developed a novel method for secondary structure prediction that uses predicted RSA in addition to attributes derived from evolutionary profiles. Our general approach follows the 2-stage protocol of Rost and Sander, with a number of Elman-type recurrent neural networks (NNs) combined into a consensus predictor. The RSA is predicted using our recently developed regression-based method that provides real-valued RSA, with the overall correlation coefficients between the actual and predicted RSA of about 0.66 in rigorous tests on independent control sets. Using the predicted RSA, we were able to improve the performance of our secondary structure prediction by up to 1.4% and achieved the overall per-residue accuracy between 77.0% and 78.4% for the 3-state classification problem on different control sets comprising, together, 603 proteins without homology to proteins included in the training. The effects of including solvent accessibility depend on the quality of RSA prediction. In the limit of perfect prediction (i.e., when using the actual RSA values derived from known protein structures), the accuracy of secondary structure prediction increases by up to 4%. We also observed that projecting real-valued RSA into 2 discrete classes with the commonly used threshold of 25% RSA decreases the classification accuracy for secondary structure prediction. While the level of improvement of secondary structure prediction may be different for prediction protocols that implicitly account for RSA in other ways, we conclude that an increase in the 3-state classification accuracy may be achieved when combining RSA with a state-of-the-art protocol utilizing evolutionary profiles. The new method is available through a Web server at http://sable.cchmc.org.

Predicting the Secondary Structure Common to Two RNA Sequences with Dynalign

Dynalign is a dynamic programming algorithm for the simultaneous prediction of the lowest-free-energy secondary structure common to two RNA sequences and the alignment of the two sequences. It has been shown that the average accuracy of secondary structure prediction is improved using Dynalign, as compared to free-energy minimization of a single sequence. This unit provides protocols for using Dynalign on a Microsoft Windows platform as part of the RNAstructure package, and for compiling and using Dynalign on Unix/Linux computers.

The influence of gapped positions in multiple sequence alignments on secondary structure prediction methods

All currently leading protein secondary structure prediction methods use a multiple protein sequence alignment to predict the secondary structure of the top sequence. In most of these methods, prior to prediction, alignment positions showing a gap in the top sequence are deleted, consequently leading to shrinking of the alignment and loss of position-specific information. In this paper we investigate the effect of this removal of information on secondary structure prediction accuracy. To this end, we have designed SymSSP, an algorithm that post-processes the predicted secondary structure of all sequences in a multiple sequence alignment by (i) making use of the alignment's evolutionary information and (ii) re-introducing most of the information that would otherwise be lost. The post-processed information is then given to a new dynamic programming routine that produces an optimally segmented consensus secondary structure for each of the multiple alignment sequences. We have tested our method on the state-of-the-art secondary structure prediction methods PHD, PROFsec, SSPro2 and JNET using the HOMSTRAD database of reference alignments. Our consensus-deriving dynamic programming strategy is consistently better at improving the segmentation quality of the predictions compared to the commonly used majority voting technique. In addition, we have applied several weighting schemes from the literature to our novel consensus-deriving dynamic programming routine. Finally, we have investigated the level of noise introduced by prediction errors into the consensus and show that predictions of edges of helices and strands are half the time wrong for all the four tested prediction methods.

The thermodynamics of DNA structural motifs.

DNA secondary structure plays an important role in biology, genotyping diagnostics, a variety of molecular biology techniques, in vitro-selected DNA catalysts, nanotechnology, and DNA-based computing. Accurate prediction of DNA secondary structure and hybridization using dynamic programming algorithms requires a database of thermodynamic parameters for several motifs including Watson-Crick base pairs, internal mismatches, terminal mismatches, terminal dangling ends, hairpins, bulges, internal loops, and multibranched loops. To make the database useful for predictions under a variety of salt conditions, empirical equations for monovalent and magnesium dependence of thermodynamics have been developed. Bimolecular hybridization is often inhibited by competing unimolecular folding of a target or probe DNA. Powerful numerical methods have been developed to solve multistate-coupled equilibria in bimolecular and higher-order complexes. This review presents the current parameter set available for making accurate DNA structure predictions and also points to future directions for improvement.

Modify possibilities of the secondary structures prediction method

It was analyzed dependence of the average accuracy of secondary protein structure prediction on various GOR algorithm modifications. In essence new modification has expanded informational parameter set by taking into account secondary structure of neighboring amino acid. The accuracy of the method with this modification increases almost for 1 percent. This increase in accuracy is quite significant, as the amount of informational parameters increases not much.

Identification of β-barrel membrane proteins based on amino acid composition properties and predicted secondary structure

Unlike all-helices membrane proteins, β-barrel membrane proteins can not be successfully discriminated from other proteins, especially from all-β soluble proteins. This paper performs an analysis on the amino acid composition in membrane parts of 12 β-barrel membrane proteins versus β-strands of 79 all-β soluble proteins. The average and variance of the amino acid composition in these two classes are calculated. Amino acids such as Gly, Asn, Val that are most likely associated with classification are selected based on Fishers discriminant ratio. A linear classifier built with these selected amino acids composition in observed β-strands achieves 100% classification accuracy for 12 membrane proteins and 79 soluble proteins in a four-fold cross-validation experiment. Since at present the accuracy of secondary structure prediction is quite high, a promising method to identify β-barrel membrane proteins is presented based on the linear classifier coupled with predicted secondary structure. Applied to 241 β-barrel membrane proteins and 3855 soluble proteins with various structures, the method achieves 85.48% (206/241) sensitivity and 92.53% specificity (3567/3855).

Secondary structure prediction and folding of globular protein: refolding of ferredoxin.

The physicochemical mechanism of protein folding has been elucidated by the island model, describing a growth type of folding. The folding pathway is closely related with nucleation on the polypeptide chain and thus the formation of small local structures or secondary structures at the earliest stage of folding is essential to all following steps. The island model is applicable to any protein, but a high precision of secondary structure prediction is indispensable to folding simulation. The secondary structures formed at the earliest stage of folding are supposed to be of standard form, but they are usually deformed during the folding process, especially at the last stage, although the degree of deformation is different for each protein. Ferredoxin is an example of a protein having this property. According to X-ray investigation (1FDX), ferredoxin is not supposed to have secondary structures. However, if we assumed that in ferredoxin all the residues are in a coil state, we could not attain the correct structure similar to the native one. Further, we found that some parts of the chain are not flexible, suggesting the presence of secondary structures, in agreement with the recent PDB data (1DUR). Assuming standard secondary structures (alpha-helices and beta-strands) at the nonflexible parts at the early stage of folding, and deforming these at the final stage, a structure similar to the native one was obtained. Another peculiarity of ferredoxin is the absence of disulfide bonds, in spite of its having eight cysteines. The reason cysteines do not form disulfide bonds became clear by applying the lampshade criterion, but more importantly, the two groups of cysteines are ready to make iron complexes, respectively, at a rather later stage of folding. The reason for poor prediction accuracy of secondary structure with conventional methods is discussed.

Sequence-based detection of distantly related proteins with the same fold.

Because proteins that have diverged beyond significant sequence similarity still retain the three-dimensional (3D) fold of their ancestor (Chothia and Lesk, 1986; Rost, 1997), the recognition of structural similarity between proteins provides powerful clues to ancestry. In fact, a large number of distant homology relationships were identified only after the structures of the proteins had been solved (Murzin, 1998). However, structures are being determined only for a small fraction of the proteins. There is a pressing need for improvement in the performance of sequence-based methods for the detection of proteins with the same fold but scant sequence similarity. Here, we examine how to achieve this goal by combining three kinds of information from a protein sequence. First, it has long been recognized that the use of multiplyaligned sequences from a protein family improves the sensitivity of homology detection. This idea is used by many recent computational procedures that exploit evolutionary information to uncover subtle sequence similarity. Examples of such procedures include sequence profiles (Gribskov et al., 1987), consensus templates or motifs (Taylor, 1986; Bairoch, 1991; Tatusov et al., 1994; Yi and Lander, 1994), positionspecific scoring matrices (PSSMs) (Henikoff and Henikoff, 1997), profile hidden Markov models (Eddy, 1998), and intermediate sequence methods (Holm and Sander, 1997; Neuwald et al., 1997; Park et al., 1997). PSI-BLAST (Altschul et al., 1997), one of the most widely used of these procedures, employs an iterative profile search strategy that combines the advantages of both PSSM and intermediate sequence methods. This program has been used effectively by several groups to assign 3D folds to predicted genome products (Teichmann et al., 1999). Second, proteins having the same fold also by definition have very similar secondary structures. In the light of the improved accuracy of secondary structure prediction (Rost and Sander, 1993), several groups have attempted to use sequencederived predictions to improve the sensitivity of fold recognition (Fischer and Eisenberg, 1996; Russel et al., 1996; Di Francesco et al., 1997; Rice and Eisenberg, 1997; Rost et al., 1997). These methods usually represent each protein in a template library by a one-dimensional (1D) string of symbols (profiles) each representing a distinctive 3D structural state, and then use dynamic programming (Needleman and Wunsch, 1970) to align the predicted structural profiles of the query

Enhanced Prediction Accuracy of Protein Secondary Structure Using Hydrogen Exchange Fourier Transform Infrared Spectroscopy

A novel equilibrium hydrogen exchange Fourier transform IR (HX-FTIR) spectroscopy method for predicting secondary structure content was employed using spectra obtained for a training set of 23 globular proteins. The IR bandshape and frequency changes resulting from controlled levels of H–D exchange were observed to be protein-dependent. Their analysis revealed these variations to be partly correlated to secondary structure. For each protein, a set of 6 spectra was measured with a systematic variation of the solvent H–D ratio and was subjected to factor analysis. The most significant component spectra for each protein, representing independent aspects of the spectral response to deuteration, were each subjected to a second factor analysis over the entire training set. Restricted multiple regression (RMR) analysis using the loadings of the principal components from 19 of these H–D analyses revealed an improvement in prediction accuracy compared with conventional bandshape-based analyses of FTIR data. Nearly a factor of 2 reduction in error for prediction of helix fractions was found using s1, the average spectral response for the H–D set. In some cases, significant error reduction for prediction of minor components was found using higher factors. Using the same analytical methods, prediction errors with this new deuteration–response–FTIR method were shown to be even better than those obtained by use of electronic circular dichroism (ECD) data for helix predictions and to be significantly lower for ECD-based sheet prediction, making these the best secondary structure predictions obtained with the RMR method. Tests of a limited variable selection scheme showed further improvements, consistent with previous results of this approach using ECD data.

The PSIPRED protein structure prediction server.

The PSIPRED protein structure prediction server allows users to submit a protein sequence, perform a prediction of their choice and receive the results of the prediction both textually via e-mail and graphically via the web. The user may select one of three prediction methods to apply to their sequence: PSIPRED, a highly accurate secondary structure prediction method; MEMSAT 2, a new version of a widely used transmembrane topology prediction method; or GenTHREADER, a sequence profile based fold recognition method. Freely available to non-commercial users at http://globin.bio.warwick.ac.uk/psipred/