Improving Fold Recognition Without Folds

A secondary structure-based position-specific scoring matrix applied to the improvement in protein secondary structure prediction

Protein secondary structure prediction (SSP) has a variety of applications; however, there has been relatively limited improvement in accuracy for years. With a vision of moving forward all related fields, we aimed to make a fundamental advance in SSP. There have been many admirable efforts made to improve the machine learning algorithm for SSP. This work thus took a step back by manipulating the input features. A secondary structure element-based position-specific scoring matrix (SSE-PSSM) is proposed, based on which a new set of machine learning features can be established. The feasibility of this new PSSM was evaluated by rigid independent tests with training and testing datasets sharing <25% sequence identities. In all experiments, the proposed PSSM outperformed the traditional amino acid PSSM. This new PSSM can be easily combined with the amino acid PSSM, and the improvement in accuracy was remarkable. Preliminary tests made by combining the SSE-PSSM and well-known SSP methods showed 2.0% and 5.2% average improvements in three- and eight-state SSP accuracies, respectively. If this PSSM can be integrated into state-of-the-art SSP methods, the overall accuracy of SSP may break the current restriction and eventually bring benefit to all research and applications where secondary structure prediction plays a vital role during development. To facilitate the application and integration of the SSE-PSSM with modern SSP methods, we have established a web server and standalone programs for generating SSE-PSSM available at http://10.life.nctu.edu.tw/SSE-PSSM.

Accurate Prediction of One-Dimensional Protein Structure Features Using SPINE-X

Accurate prediction of protein secondary structure and other one-dimensional structure features is essential for accurate sequence alignment, three-dimensional structure modeling, and function prediction. SPINE-X is a software package to predict secondary structure as well as accessible surface area and dihedral angles ϕ and ψ. For secondary structure SPINE-X achieves an accuracy of between 81 and 84 % depending on the dataset and choice of tests. The Pearson correlation coefficient for accessible surface area prediction is 0.75 and the mean absolute error from the ϕ and ψ dihedral angles are 20^∘ and 33^∘, respectively. The source code and a Linux executables for SPINE-X are available from Research and Information Systems at http://mamiris.com .

A Deep Learning Network Approach to ab initio Protein Secondary Structure Prediction

Ab initio protein secondary structure (SS) predictions are utilized to generate tertiary structure predictions, which are increasingly demanded due to the rapid discovery of proteins. Although recent developments have slightly exceeded previous methods of SS prediction, accuracy has stagnated around 80 percent and many wonder if prediction cannot be advanced beyond this ceiling. Disciplines that have traditionally employed neural networks are experimenting with novel deep learning techniques in attempts to stimulate progress. Since neural networks have historically played an important role in SS prediction, we wanted to determine whether deep learning could contribute to the advancement of this field as well. We developed an SS predictor that makes use of the position-specific scoring matrix generated by PSI-BLAST and deep learning network architectures, which we call DNSS. Graphical processing units and CUDA software optimize the deep network architecture and efficiently train the deep networks. Optimal parameters for the training process were determined, and a workflow comprising three separately trained deep networks was constructed in order to make refined predictions. This deep learning network approach was used to predict SS for a fully independent test dataset of 198 proteins, achieving a Q3 accuracy of 80.7 percent and a Sov accuracy of 74.2 percent.

Context similarity scoring improves protein sequence alignments in the midnight zone

MOTIVATION

High-quality protein sequence alignments are essential for a number of downstream applications such as template-based protein structure prediction. In addition to the similarity score between sequence profile columns, many current profile-profile alignment tools use extra terms that compare 1D-structural properties such as secondary structure and solvent accessibility, which are predicted from short profile windows around each sequence position. Such scores add non-redundant information by evaluating the conservation of local patterns of hydrophobicity and other amino acid properties and thus exploiting correlations between profile columns.

RESULTS

Here, instead of predicting and comparing known 1D properties, we follow an agnostic approach. We learn in an unsupervised fashion a set of maximally conserved patterns represented by 13-residue sequence profiles, without the need to know the cause of the conservation of these patterns. We use a maximum likelihood approach to train a set of 32 such profiles that can best represent patterns conserved within pairs of remotely homologs, structurally aligned training profiles. We include the new context score into our Hmm-Hmm alignment tool hhsearch and improve especially the quality of difficult alignments significantly.

CONCLUSION

The context similarity score improves the quality of homology models and other methods that depend on accurate pairwise alignments.

From local structure to a global framework: recognition of protein folds

Protein folding has been a major area of research for many years. Nonetheless, the mechanisms leading to the formation of an active biological fold are still not fully apprehended. The huge amount of available sequence and structural information provides hints to identify the putative fold for a given sequence. Indeed, protein structures prefer a limited number of local backbone conformations, some being characterized by preferences for certain amino acids. These preferences largely depend on the local structural environment. The prediction of local backbone conformations has become an important factor to correctly identifying the global protein fold. Here, we review the developments in the field of local structure prediction and especially their implication in protein fold recognition.

Prediction of protein secondary structure using feature selection and analysis approach

The prediction of the secondary structure of a protein from its amino acid sequence is an important step towards the prediction of its three-dimensional structure. However, the accuracy of ab initio secondary structure prediction from sequence is about 80% currently, which is still far from satisfactory. In this study, we proposed a novel method that uses binomial distribution to optimize tetrapeptide structural words and increment of diversity with quadratic discriminant to perform prediction for protein three-state secondary structure. A benchmark dataset including 2,640 proteins with sequence identity of less than 25% was used to train and test the proposed method. The results indicate that overall accuracy of 87.8% was achieved in secondary structure prediction by using ten-fold cross-validation. Moreover, the accuracy of predicted secondary structures ranges from 84 to 89% at the level of residue. These results suggest that the feature selection technique can detect the optimized tetrapeptide structural words which affect the accuracy of predicted secondary structures.

Exploiting intrastructure information for secondary structure prediction with multifaceted pipelines

Predicting the secondary structure of proteins is still a typical step in several bioinformatic tasks, in particular, for tertiary structure prediction. Notwithstanding the impressive results obtained so far, mostly due to the advent of sequence encoding schemes based on multiple alignment, in our view the problem should be studied from a novel perspective, in which understanding how available information sources are dealt with plays a central role. After revisiting a well-known secondary structure predictor viewed from this perspective (with the goal of identifying which sources of information have been considered and which have not), we propose a generic software architecture designed to account for all relevant information sources. To demonstrate the validity of the approach, a predictor compliant with the proposed generic architecture has been implemented and compared with several state-of-the-art secondary structure predictors. Experiments have been carried out on standard data sets, and the corresponding results confirm the validity of the approach. The predictor is available at http://iasc.diee.unica.it/ssp2/ through the corresponding web application or as downloadable stand-alone portable unpack-and-run bundle.

CONCORD: a consensus method for protein secondary structure prediction via mixed integer linear optimization

Most of the protein structure prediction methods use a multi-step process, which often includes secondary structure prediction, contact prediction, fragment generation, clustering, etc. For many years, secondary structure prediction has been the workhorse for numerous methods aimed at predicting protein structure and function. This paper presents a new mixed integer linear optimization (MILP)-based consensus method: a Consensus scheme based On a mixed integer liNear optimization method for seCOndary stRucture preDiction (CONCORD). Based on seven secondary structure prediction methods, SSpro, DSC, PROF, PROFphd, PSIPRED, Predator and GorIV, the MILP-based consensus method combines the strengths of different methods, maximizes the number of correctly predicted amino acids and achieves a better prediction accuracy. The method is shown to perform well compared with the seven individual methods when tested on the PDBselect25 training protein set using sixfold cross validation. It also performs well compared with another set of 10 online secondary structure prediction servers (including several recent ones) when tested on the CASP9 targets ( http://predictioncenter.org/casp9/ ). The average Q3 prediction accuracy is 83.04 per cent for the sixfold cross validation of the PDBselect25 set and 82.3 per cent for the CASP9 targets. We have developed a MILP-based consensus method for protein secondary structure prediction. A web server, CONCORD, is available to the scientific community at http://helios.princeton.edu/CONCORD .

Enhanced Inter-helical Residue Contact Prediction in Transmembrane Proteins

In this paper, based on a recent work by McAllister and Floudas who developed a mathematical optimization model to predict the contacts in transmembrane alpha-helical proteins from a limited protein data set [1], we have enhanced this method by 1) building a more comprehensive data set for transmembrane alpha-helical proteins and this enhanced data set is then used to construct the probability sets, MIN-1N and MIN-2N, for residue contact prediction, 2) enhancing the mathematical model via modifications of several important physical constraints and 3) applying a new blind contact prediction scheme on different protein sets proposed from analyzing the contact prediction on 65 proteins from Fuchs et al. [2]. The blind contact prediction scheme has been tested on two different membrane protein sets. Firstly it is applied to five carefully selected proteins from the training set. The contact prediction of these five proteins uses probability sets built by excluding the target protein from the training set, and an average accuracy of 56% was obtained. Secondly, it is applied to six independent membrane proteins with complicated topologies, and the prediction accuracies are 73% for 2ZY9A, 21% for 3KCUA, 46% for 2W1PA, 64% for 3CN5A, 77% for 3IXZA and 83% for 3K3FA. The average prediction accuracy for the six proteins is 60.7%. The proposed approach is also compared with a support vector machine method (TMhit [3]) and it is shown that it exhibits better prediction accuracy.

Protein sequence comparison and fold recognition: progress and good-practice benchmarking

Protein sequence comparison methods have grown increasingly sensitive during the last decade and can often identify distantly related proteins sharing a common ancestor some 3 billion years ago. Although cellular function is not conserved so long, molecular functions and structures of protein domains often are. In combination with a domain-centered approach to function and structure prediction, modern remote homology detection methods have a great and largely underexploited potential for elucidating protein functions and evolution. Advances during the last few years include nonlinear scoring functions combining various sequence features, the use of sequence context information, and powerful new software packages. Since progress depends on realistically assessing new and existing methods and published benchmarks are often hard to compare, we propose 10 rules of good-practice benchmarking.

Structural characterization of the predominant family of histidine kinase sensor domains

Histidine kinase (HK) receptors are used ubiquitously by bacteria to monitor environmental changes, and they are also prevalent in plants, fungi, and other protists. Typical HK receptors have an extracellular sensor portion that detects a signal, usually a chemical ligand, and an intracellular transmitter portion that includes both the kinase domain itself and the site for histidine phosphorylation. While kinase domains are highly conserved, sensor domains are diverse. HK receptors function as dimers, but the molecular mechanism for signal transduction across cell membranes remains obscure. In this study, eight crystal structures were determined from five sensor domains representative of the most populated family, family HK1, found in a bioinformatic analysis of predicted sensor domains from transmembrane HKs. Each structure contains an inserted repeat of PhoQ/DcuS/CitA (PDC) domains, and similarity between sequence and structure is correlated across these and other double-PDC sensor proteins. Three of the five sensors crystallize as dimers that appear to be physiologically relevant, and comparisons between ligated structures and apo-state structures provide insights into signal transmission. Some HK1 family proteins prove to be sensors for chemotaxis proteins or diguanylate cyclase receptors, implying a combinatorial molecular evolution.

Identification of specific DNA binding residues in the TCP family of transcription factors in Arabidopsis

The TCP transcription factors control multiple developmental traits in diverse plant species. Members of this family share an approximately 60-residue-long TCP domain that binds to DNA. The TCP domain is predicted to form a basic helix-loop-helix (bHLH) structure but shares little sequence similarity with canonical bHLH domain. This classifies the TCP domain as a novel class of DNA binding domain specific to the plant kingdom. Little is known about how the TCP domain interacts with its target DNA. We report biochemical characterization and DNA binding properties of a TCP member in Arabidopsis thaliana, TCP4. We have shown that the 58-residue domain of TCP4 is essential and sufficient for binding to DNA and possesses DNA binding parameters comparable to canonical bHLH proteins. Using a yeast-based random mutagenesis screen and site-directed mutants, we identified the residues important for DNA binding and dimer formation. Mutants defective in binding and dimerization failed to rescue the phenotype of an Arabidopsis line lacking the endogenous TCP4 activity. By combining structure prediction, functional characterization of the mutants, and molecular modeling, we suggest a possible DNA binding mechanism for this class of transcription factors.

Improving the prediction accuracy of residue solvent accessibility and real-value backbone torsion angles of proteins by guided-learning through a two-layer neural network

This article attempts to increase the prediction accuracy of residue solvent accessibility and real-value backbone torsion angles of proteins through improved learning. Most methods developed for improving the backpropagation algorithm of artificial neural networks are limited to small neural networks. Here, we introduce a guided-learning method suitable for networks of any size. The method employs a part of the weights for guiding and the other part for training and optimization. We demonstrate this technique by predicting residue solvent accessibility and real-value backbone torsion angles of proteins. In this application, the guiding factor is designed to satisfy the intuitive condition that for most residues, the contribution of a residue to the structural properties of another residue is smaller for greater separation in the protein-sequence distance between the two residues. We show that the guided-learning method makes a 2-4% reduction in 10-fold cross-validated mean absolute errors (MAE) for predicting residue solvent accessibility and backbone torsion angles, regardless of the size of database, the number of hidden layers and the size of input windows. This together with introduction of two-layer neural network with a bipolar activation function leads to a new method that has a MAE of 0.11 for residue solvent accessibility, 36 degrees for psi, and 22 degrees for phi. The method is available as a Real-SPINE 3.0 server in http://sparks.informatics.iupui.edu.

Cell cycle kinases predicted from conserved biophysical properties

Machine-learning techniques can classify functionally related proteins where homology-transfer as well as sequence and structure motifs fail. Here, we present a method that aimed at complementing homology-transfer in the identification of cell cycle control kinases from sequence alone. First, we identified functionally significant residues in cell cycle proteins through their high sequence conservation and biophysical properties. We then incorporated these residues and their features into support vector machines (SVM) to identify new kinases and more specifically to differentiate cell cycle kinases from other kinases and other proteins. As expected, the most informative residues tend to be highly conserved and tend to localize in the ATP binding regions of the kinases. Another observation confirmed that ATP binding regions are typically not found on the surface but in partially buried sites, and that this fact is correctly captured by accessibility predictions. Using these highly conserved, semi-buried residues and their biophysical properties, we could distinguish cell cycle S/T kinases from other kinase families at levels around 70-80% accuracy and 62-81% coverage. An application to the entire human proteome predicted at least 97 human proteins with limited previous annotations to be candidates for cell cycle kinases.

Exploring the extremes of sequence/structure space with ensemble fold recognition in the program Phyre

Structural and functional annotation of the large and growing database of genomic sequences is a major problem in modern biology. Protein structure prediction by detecting remote homology to known structures is a well-established and successful annotation technique. However, the broad spectrum of evolutionary change that accompanies the divergence of close homologues to become remote homologues cannot easily be captured with a single algorithm. Recent advances to tackle this problem have involved the use of multiple predictive algorithms available on the Internet. Here we demonstrate how such ensembles of predictors can be designed in-house under controlled conditions and permit significant improvements in recognition by using a concept taken from protein loop energetics and applying it to the general problem of 3D clustering. We have developed a stringent test that simulates the situation where a protein sequence of interest is submitted to multiple different algorithms and not one of these algorithms can make a confident (95%) correct assignment. A method of meta-server prediction (Phyre) that exploits the benefits of a controlled environment for the component methods was implemented. At 95% precision or higher, Phyre identified 64.0% of all correct homologous query-template relationships, and 84.0% of the individual test query proteins could be accurately annotated. In comparison to the improvement that the single best fold recognition algorithm (according to training) has over PSI-Blast, this represents a 29.6% increase in the number of correct homologous query-template relationships, and a 46.2% increase in the number of accurately annotated queries. It has been well recognised in fold prediction, other bioinformatics applications, and in many other areas, that ensemble predictions generally are superior in accuracy to any of the component individual methods. However there is a paucity of information as to why the ensemble methods are superior and indeed this has never been systematically addressed in fold recognition. Here we show that the source of ensemble power stems from noise reduction in filtering out false positive matches. The results indicate greater coverage of sequence space and improved model quality, which can consequently lead to a reduction in the experimental workload of structural genomics initiatives.

LTHREADER: prediction of extracellular ligand-receptor interactions in cytokines using localized threading

Identification of extracellular ligand-receptor interactions is important for drug design and the treatment of diseases. Difficulties in detecting these interactions using high-throughput experimental techniques motivate the development of computational prediction methods. We propose a novel threading algorithm, LTHREADER, which generates accurate local sequence-structure interface alignments and integrates various statistical scores and experimental binding data to predict interactions within ligand-receptor families. LTHREADER uses a profile of secondary structure and solvent accessibility predictions with residue contact maps to guide and constrain alignments. Using a decision tree classifier and low-throughput experimental data for training, it combines information inferred from statistical interaction potentials, energy functions, correlated mutations, and conserved residue pairs to predict interactions. We apply our method to cytokines, which play a central role in the development of many diseases including cancer and inflammatory and autoimmune disorders. We tested our approach on two representative families from different structural classes (all-alpha and all-beta proteins) of cytokines. In comparison with the state-of-the-art threader RAPTOR, LTHREADER generates on average 20% more accurate alignments of interacting residues. Furthermore, in cross-validation tests, LTHREADER correctly predicts experimentally confirmed interactions for a common binding mode within the 4-helical long-chain cytokine family with 75% sensitivity and 86% specificity with 40% gain in sensitivity compared to RAPTOR. For the TNF-like family our method achieves 70% sensitivity with 55% specificity with 70% gain in sensitivity. LTHREADER combines information from multiple complex templates when such data are available. When only one solved structure is available, a localized PSI-BLAST approach also outperforms standard threading methods with 25%-50% improvements in sensitivity.

Conformation of the c-Fos/c-Jun complex in vivo: a combined FRET, FCCS, and MD-modeling study

The activator protein-1 transcription factor is a heterodimer containing one of each of the Fos and Jun subfamilies of basic-region leucine-zipper proteins. We have previously shown by fluorescence cross-correlation spectroscopy (FCCS) that the fluorescent fusion proteins Fos-EGFP and Jun-mRFP1, cotransfected in HeLa cells, formed stable complexes in situ. Here we studied the relative position of the C-terminal domains via fluorescence resonance energy transfer (FRET) measured by flow cytometry and confocal microscopy. To get a more detailed insight into the conformation of the C-terminal domains of the complex we constructed C-terminal labeled full-length and truncated forms of Fos. We developed a novel iterative evaluation method to determine accurate FRET efficiencies regardless of relative protein expression levels, using a spectral- or intensity-based approach. The full-length C-terminal-labeled Jun and Fos proteins displayed a FRET-measured average distance of 8 +/- 1 nm. Deletion of the last 164 amino acids at the C-terminus of Fos resulted in a distance of 6.1 +/- 1 nm between the labels. FCCS shows that Jun-mRFP1 and the truncated Fos-EGFP also interact stably in the nucleus, although they bind to nuclear components with lower affinity. Thus, the C-terminal end of Fos may play a role in the stabilization of the interaction between activator protein-1 and DNA. Molecular dynamics simulations predict a dye-to-dye distance of 6.7 +/- 0.1 nm for the dimer between Jun-mRFP1 and the truncated Fos-EGFP, in good agreement with our FRET data. A wide variety of models could be developed for the full-length dimer, with possible dye-to-dye distances varying largely between 6 and 20 nm. However, from our FRET results we can conclude that more than half of the occurring dye-to-dye distances are between 6 and 10 nm.

Computational methods in protein structure prediction

This review presents the advances in protein structure prediction from the computational methods perspective. The approaches are classified into four major categories: comparative modeling, fold recognition, first principles methods that employ database information, and first principles methods without database information. Important advances along with current limitations and challenges are presented.

Polyglutamine variation in a flowering time protein correlates with island age in a Hawaiian plant radiation

Background

A controversial topic in evolutionary developmental biology is whether morphological diversification in natural populations can be driven by expansions and contractions of amino acid repeats in proteins. To promote adaptation, selection on protein length variation must overcome deleterious effects of multiple correlated traits (pleiotropy). Thus far, systems that demonstrate this capacity include only ancient or artificial morphological diversifications. The Hawaiian Islands, with their linear geological sequence, present a unique environment to study recent, natural radiations. We have focused our research on the Hawaiian endemic mints (Lamiaceae), a large and diverse lineage with paradoxically low genetic variation, in order to test whether a direct relationship between coding-sequence repeat diversity and morphological change can be observed in an actively evolving system.

Results

Here we show that in the Hawaiian mints, extensive polyglutamine (CAG codon repeat) polymorphism within a homolog of the pleiotropic flowering time protein and abscisic acid receptor FCA tracks the natural environmental cline of the island chain, consequent with island age, across a period of 5 million years. CAG expansions, perhaps following their natural tendency to elongate, are more frequent in colonists of recently-formed, nutrient-rich islands than in their forebears on older, nutrient-poor islands. Values for several quantitative morphological variables related to reproductive investment, known from Arabidopsis fca mutant studies, weakly though positively correlate with increasing glutamine tract length. Together with protein modeling of FCA, which indicates that longer polyglutamine tracts could induce suboptimally mobile functional domains, we suggest that CAG expansions may form slightly deleterious alleles (with respect to protein function) that become fixed in founder populations.

Conclusion

In the Hawaiian mint FCA system, we infer that contraction of slightly deleterious CAG repeats occurred because of competition for resources along the natural environmental cline of the island chain. The observed geographical structure of FCA variation and its correlation with morphologies expected from Arabidopsis mutant studies may indicate that developmental pleiotropy played a role in the diversification of the mints. This discovery is important in that it concurs with other suggestions that repetitive amino acid motifs might provide a mechanism for driving morphological evolution, and that variation at such motifs might permit rapid tuning to environmental change.

Accurate prediction of protein secondary structure and solvent accessibility by consensus combiners of sequence and structure information

BACKGROUND

Structural properties of proteins such as secondary structure and solvent accessibility contribute to three-dimensional structure prediction, not only in the ab initio case but also when homology information to known structures is available. Structural properties are also routinely used in protein analysis even when homology is available, largely because homology modelling is lower throughput than, say, secondary structure prediction. Nonetheless, predictors of secondary structure and solvent accessibility are virtually always ab initio.

RESULTS

Here we develop high-throughput machine learning systems for the prediction of protein secondary structure and solvent accessibility that exploit homology to proteins of known structure, where available, in the form of simple structural frequency profiles extracted from sets of PDB templates. We compare these systems to their state-of-the-art ab initio counterparts, and with a number of baselines in which secondary structures and solvent accessibilities are extracted directly from the templates. We show that structural information from templates greatly improves secondary structure and solvent accessibility prediction quality, and that, on average, the systems significantly enrich the information contained in the templates. For sequence similarity exceeding 30%, secondary structure prediction quality is approximately 90%, close to its theoretical maximum, and 2-class solvent accessibility roughly 85%. Gains are robust with respect to template selection noise, and significant for marginal sequence similarity and for short alignments, supporting the claim that these improved predictions may prove beneficial beyond the case in which clear homology is available.

CONCLUSION

The predictive system are publicly available at the address http://distill.ucd.ie.

Fold recognition by concurrent use of solvent accessibility and residue depth

Recognizing the structural similarity without significant sequence identity (called fold recognition) is the key for bridging the gap between the number of known protein sequences and the number of structures solved. Previously, we developed a fold-recognition method called SP(3) which combines sequence-derived sequence profiles, secondary-structure profiles and residue-depth dependent, structure-derived sequence profiles. The use of residue-depth-dependent profiles makes SP(3) one of the best automatic predictors in CASP 6. Because residue depth (RD) and solvent accessible surface area (solvent accessibility) are complementary in describing the exposure of a residue to solvent, we test whether or not incorporation of solvent-accessibility profiles into SP(3) could further increase the accuracy of fold recognition. The resulting method, called SP(4), was tested in SALIGN benchmark for alignment accuracy and Lindahl, LiveBench 8 and CASP7 blind prediction for fold recognition sensitivity and model-structure accuracy. For remote homologs, SP(4) is found to consistently improve over SP(3) in the accuracy of sequence alignment and predicted structural models as well as in the sensitivity of fold recognition. Our result suggests that RD and solvent accessibility can be used concurrently for improving the accuracy and sensitivity of fold recognition. The SP(4) server and its local usage package are available on http://sparks.informatics.iupui.edu/SP4.

Real-SPINE: An integrated system of neural networks for real-value prediction of protein structural properties

Proteins can move freely in three-dimensional space. As a result, their structural properties, such as solvent accessible surface area, backbone dihedral angles, and atomic distances, are continuous variables. However, these properties are often arbitrarily divided into a few classes to facilitate prediction by statistical learning techniques. In this work, we establish an integrated system of neural networks (called Real-SPINE) for real-value prediction and apply the method to predict residue-solvent accessibility and backbone psi dihedral angles of proteins based on information derived from sequences only. Real-SPINE is trained with a large data set of 2640 protein chains, sequence profiles generated from multiple sequence alignment, representative amino-acid properties, a slow learning rate, overfitting protection, and predicted secondary structures. The method optimizes more than 200,000 weights and yields a 10-fold cross-validated Pearson's correlation coefficient (PCC) of 0.74 between predicted and actual solvent accessible surface areas and 0.62 between predicted and actual psi angles. In particular, 90% of 2640 proteins have a PCC value greater than 0.6 between predicted and actual solvent-accessible surface areas. The results of Real-SPINE can be compared with the best reported correlation coefficients of 0.64-0.67 for solvent-accessible surface areas and 0.47 for psi angles. The real-SPINE server, executable programs, and datasets are freely available on http://sparks.informatics.iupui.edu.

Consensus sequences improve PSI-BLAST through mimicking profile-profile alignments

Sequence alignments may be the most fundamental computational resource for molecular biology. The best methods that identify sequence relatedness through profile–profile comparisons are much slower and more complex than sequence–sequence and sequence–profile comparisons such as, respectively, BLAST and PSI-BLAST. Families of related genes and gene products (proteins) can be represented by consensus sequences that list the nucleic/amino acid most frequent at each sequence position in that family. Here, we propose a novel approach for consensus-sequence-based comparisons. This approach improved searches and alignments as a standard add-on to PSI-BLAST without any changes of code. Improvements were particularly significant for more difficult tasks such as the identification of distant structural relations between proteins and their corresponding alignments. Despite the fact that the improvements were higher for more divergent relations, they were consistent even at high accuracy/low error rates for non-trivially related proteins. The improvements were very easy to achieve; no parameter used by PSI-BLAST was altered and no single line of code changed. Furthermore, the consensus sequence add-on required relatively little additional CPU time. We discuss how advanced users of PSI-BLAST can immediately benefit from using consensus sequences on their local computers. We have also made the method available through the Internet (http://www.rostlab.org/services/consensus/).

Automatic procedure for using models of proteins in molecular replacement

In a crystallography experiment, a crystal is irradiated with X-rays whose diffracted waves are collected and measured. The reconstruction of the structure of the molecule in the crystal requires knowledge of the phase of the diffracted waves, information that is lost in the passage from the three-dimensional structure of the molecule to its diffraction pattern. It can be recovered using experimental methods such as heavy-atom isomorphous replacement and anomalous scattering or by molecular replacement, which relies on the availability of an atomic model of the target structure. This can be the structure of the target protein itself, if a previous structure determination is available, or a computational model or, in some cases, the structure of a homologous protein. It is not straightforward to predict beforehand whether or not a computational model will work in a molecular replacement experiment, although some rules of thumb exist. The consensus is that even minor differences in the quality of the model, which are rather difficult to estimate a priori, can have a significant effect on the outcome of the procedure. We describe here a method for quickly assessing whether a protein structure can be solved by molecular replacement. The procedure consists in submitting the sequence of the target protein to a selected list of freely available structure prediction servers, cluster the resulting models, select the representative structures of each cluster and use them as search models in an automatic phasing procedure. We tested the procedure using the structure factors of newly released proteins of known structure downloaded from the Protein Data Bank as soon as they were made available. Using our automatic procedure we were able to obtain an interpretable electron density map in more than half the cases.

Distill: a suite of web servers for the prediction of one-, two- and three-dimensional structural features of proteins

BACKGROUND

We describe Distill, a suite of servers for the prediction of protein structural features: secondary structure; relative solvent accessibility; contact density; backbone structural motifs; residue contact maps at 6, 8 and 12 Angstrom; coarse protein topology. The servers are based on large-scale ensembles of recursive neural networks and trained on large, up-to-date, non-redundant subsets of the Protein Data Bank. Together with structural feature predictions, Distill includes a server for prediction of Calpha traces for short proteins (up to 200 amino acids).

RESULTS

The servers are state-of-the-art, with secondary structure predicted correctly for nearly 80% of residues (currently the top performance on EVA), 2-class solvent accessibility nearly 80% correct, and contact maps exceeding 50% precision on the top non-diagonal contacts. A preliminary implementation of the predictor of protein Calpha traces featured among the top 20 Novel Fold predictors at the last CASP6 experiment as group Distill (ID 0348). The majority of the servers, including the Calpha trace predictor, now take into account homology information from the PDB, when available, resulting in greatly improved reliability.

CONCLUSION

All predictions are freely available through a simple joint web interface and the results are returned by email. In a single submission the user can send protein sequences for a total of up to 32k residues to all or a selection of the servers. Distill is accessible at the address: http://distill.ucd.ie/distill/.

Multiple mapping method: a novel approach to the sequence-to-structure alignment problem in comparative protein structure modeling

A major bottleneck in comparative protein structure modeling is the quality of input alignment between the target sequence and the template structure. A number of alignment methods are available, but none of these techniques produce consistently good solutions for all cases. Alignments produced by alternative methods may be superior in certain segments but inferior in others when compared to each other; therefore, an accurate solution often requires an optimal combination of them. To address this problem, we have developed a new approach, Multiple Mapping Method (MMM). The algorithm first identifies the alternatively aligned regions from a set of input alignments. These alternatively aligned segments are scored using a composite scoring function, which determines their fitness within the structural environment of the template. The best scoring regions from a set of alternative segments are combined with the core part of the alignments to produce the final MMM alignment. The algorithm was tested on a dataset of 1400 protein pairs using 11 combinations of two to four alignment methods. In all cases MMM showed statistically significant improvement by reducing alignment errors in the range of 3 to 17%. MMM also compared favorably over two alignment meta-servers. The algorithm is computationally efficient; therefore, it is a suitable tool for genome scale modeling studies.

Advances in homology protein structure modeling

Homology modeling plays a central role in determining protein structure in the structural genomics project. The importance of homology modeling has been steadily increasing because of the large gap that exists between the overwhelming number of available protein sequences and experimentally solved protein structures, and also, more importantly, because of the increasing reliability and accuracy of the method. In fact, a protein sequence with over 30% identity to a known structure can often be predicted with an accuracy equivalent to a low-resolution X-ray structure. The recent advances in homology modeling, especially in detecting distant homologues, aligning sequences with template structures, modeling of loops and side chains, as well as detecting errors in a model, have contributed to reliable prediction of protein structure, which was not possible even several years ago. The ongoing efforts in solving protein structures, which can be time-consuming and often difficult, will continue to spur the development of a host of new computational methods that can fill in the gap and further contribute to understanding the relationship between protein structure and function.

Progress over the first decade of CASP experiments

CASP has now completed a decade of monitoring the state of the art in protein structure prediction. The quality of structure models produced in the latest experiment, CASP6, has been compared with that in earlier CASPs. Significant although modest progress has again been made in the fold recognition regime, and cumulatively, progress in this area is impressive. Models of previously unknown folds again appear to have modestly improved, and several mixed alpha/beta structures have been modeled in a topologically correct manner. Progress remains hard to detect in high sequence identity comparative modeling, but server performance in this area has moved forward.

Rigorous performance evaluation in protein structure modelling and implications for computational biology

In principle, given the amino acid sequence of a protein, it is possible to compute the corresponding three-dimensional structure. Methods for modelling structure based on this premise have been under development for more than 40 years. For the past decade, a series of community wide experiments (termed Critical Assessment of Structure Prediction (CASP)) have assessed the state of the art, providing a detailed picture of what has been achieved in the field, where we are making progress, and what major problems remain. The rigorous evaluation procedures of CASP have been accompanied by substantial progress. Lessons from this area of computational biology suggest a set of principles for increasing rigor in the field as a whole.

Comparative modeling for protein structure prediction

With the progression of structural genomics projects, comparative modeling remains an increasingly important method of choice. It helps to bridge the gap between the available sequence and structure information by providing reliable and accurate protein models. Comparative modeling based on more than 30% sequence identity is now approaching its natural template-based limits and further improvements require the development of effective refinement techniques capable of driving models toward native structure. For difficult targets, for which the most significant progress in recent years has been observed, optimal template selection and alignment accuracy are still the major problems.

Simple fold composition and modular architecture of the nuclear pore complex

The nuclear pore complex (NPC) consists of multiple copies of approximately 30 different proteins [nucleoporins (nups)], forming a channel in the nuclear envelope that mediates macromolecular transport between the cytosol and the nucleus. With <5% of the nup residues currently available in experimentally determined structures, little is known about the detailed structure of the NPC. Here, we use a combined computational and biochemical approach to assign folds for approximately 95% of the residues in the yeast and vertebrate nups. These fold assignments suggest an underlying simplicity in the composition and modularity in the architecture of all eukaryotic NPCs. The simplicity in NPC composition is reflected in the presence of only eight fold types, with the three most frequent folds accounting for approximately 85% of the residues. The modularity in NPC architecture is reflected in its hierarchical and symmetrical organization that partitions the predicted nup folds into three groups: the transmembrane group containing transmembrane helices and a cadherin fold, the central scaffold group containing beta-propeller and alpha-solenoid folds, and the peripheral FG group containing predominantly the FG repeats and the coiled-coil fold. Moreover, similarities between structures in coated vesicles and those in the NPC support our prior hypothesis for their common evolutionary origin in a progenitor protocoatomer. The small number of predicted fold types in the NPC and their internal symmetries suggest that the bulk of the NPC structure has evolved through extensive motif and gene duplication from a simple precursor set of only a few proteins.

A decade of CASP: progress, bottlenecks and prognosis in protein structure prediction

For the past ten years, CASP (Critical Assessment of Structure Prediction) has monitored the state of the art in modeling protein structure from sequence. During this period, there has been substantial progress in both comparative modeling of structure (using information from an evolutionarily related structural template) and template-free modeling. The quality of comparative models depends on the closeness of the evolutionary relationship on which they are based. Template-free modeling, although still very approximate, now produces topologically near correct models for some small proteins. Current major challenges are refining comparative models so that they match experimental accuracy, obtaining accurate sequence alignments for models based on remote evolutionary relationships, and extending template-free modeling methods so that they produce more accurate models, handle parts of comparative models not available from a template and deal with larger structures.

PROFcon: novel prediction of long-range contacts

MOTIVATION

Despite the continuing advance in the experimental determination of protein structures, the gap between the number of known protein sequences and structures continues to increase. Prediction methods can bridge this sequence-structure gap only partially. Better predictions of non-local contacts between residues could improve comparative modeling, fold recognition and could assist in the experimental structure determination.

RESULTS

Here, we introduced PROFcon, a novel contact prediction method that combines information from alignments, from predictions of secondary structure and solvent accessibility, from the region between two residues and from the average properties of the entire protein. In contrast to some other methods, PROFcon predicted short and long proteins at similar levels of accuracy. As expected, PROFcon was clearly less accurate when tested on sparse evolutionary profiles, that is, on families with few homologs. Prediction accuracy was highest for proteins belonging to the SCOP alpha/beta class. PROFcon compared favorably with state-of-the-art prediction methods at the CASP6 meeting. While the performance may still be perceived as low, our method clearly pushed the mark higher. Furthermore, predictions are already accurate enough to seed predictions of global features of protein structure.

Fold recognition by combining profile-profile alignment and support vector machine

MOTIVATION

Currently, the most accurate fold-recognition method is to perform profile-profile alignments and estimate the statistical significances of those alignments by calculating Z-score or E-value. Although this scheme is reliable in recognizing relatively close homologs related at the family level, it has difficulty in finding the remote homologs that are related at the superfamily or fold level.

RESULTS

In this paper, we present an alternative method to estimate the significance of the alignments. The alignment between a query protein and a template of length n in the fold library is transformed into a feature vector of length n + 1, which is then evaluated by support vector machine (SVM). The output from SVM is converted to a posterior probability that a query sequence is related to a template, given SVM output. Results show that a new method shows significantly better performance than PSI-BLAST and profile-profile alignment with Z-score scheme. While PSI-BLAST and Z-score scheme detect 16 and 20% of superfamily-related proteins, respectively, at 90% specificity, a new method detects 46% of these proteins, resulting in more than 2-fold increase in sensitivity. More significantly, at the fold level, a new method can detect 14% of remotely related proteins at 90% specificity, a remarkable result considering the fact that the other methods can detect almost none at the same level of specificity.