BetaTPred: prediction of beta-TURNS in a protein using statistical algorithms

MOTIVATION: beta-turns play an important role from a structural and functional point of view. beta-turns are the most common type of non-repetitive structures in proteins and comprise on average, 25% of the residues. In the past numerous methods have been developed to predict beta-turns in a protein. Most of these prediction methods are based on statistical approaches. In order to utilize the full potential of these methods, there is a need to develop a web server. RESULTS: This paper describes a web server called BetaTPred, developed for predicting beta-TURNS in a protein from its amino acid sequence. BetaTPred allows the user to predict turns in a protein using existing statistical algorithms. It also allows to predict different types of beta-TURNS e.g. type I, I', II, II', VI, VIII and non-specific. This server assists the users in predicting the consensus beta-TURNS in a protein. AVAILABILITY: The server is accessible from http://imtech.res.in/raghava/betatpred/     

Water and side‐chain embedded π‐turns

Elucidating protein function from its structure is central to the understanding of cellular mechanisms. This involves deciphering the dependence of local structural motifs on sequence. These structural motifs may be stabilized by direct or water‐mediated hydrogen bonding among the constituent residues. π‐Turns, defined by interactions between (i) and (i + 5) positions, are large enough to contain a central space that can embed a water molecule (or a protein moiety) to form a stable structure. This work is an analysis of such embedded π‐turns using a nonredundant dataset of protein structures. A total of 2965 embedded π‐turns have been identified, as also 281 embedded Schellman motif, a type of π‐turn which occurs at the C‐termini of α‐helices. Embedded π‐turns and Schellman motifs have been classified on the basis of the protein atoms of the terminal turn residues that are linked by the embedded moiety, conformation, residue composition, and compared with the turns that have terminal residues connected by direct hydrogen bonds. Geometrically, the turns have been fitted to a circle and the position of the linker relative to its center analyzed. The hydroxyl group of Ser and Thr, located at (i + 3) position, is the most prominent linker for the side‐chain mediated π‐turns. Consideration of residue conservation among homologous sequences indicates the terminal and the linker positions to be the most conserved. The embedded π‐turn as a binding site (for the linker) is discussed in the context of “nest,” a concave depression that is formed in protein structures with adjacent residues having enantiomeric main‐chain conformations. © 2013 Wiley Periodicals, Inc. Biopolymers 101: 441–453, 2014.     

ω‐Turn: A novel β‐turn mimic in globular proteins stabilized by main‐chain to side‐chain CH···O interaction

Mimicry of structural motifs is a common feature in proteins. The 10‐membered hydrogen‐bonded ring involving the main‐chain C?O in a β‐turn can be formed using a side‐chain carbonyl group leading to Asx‐turn. We show that the N? H component of hydrogen bond can be replaced by a C^γ‐H group in the side chain, culminating in a nonconventional C? H···O interaction. Because of its shape this β‐turn mimic is designated as ω‐turn, which is found to occur ～three times per 100 residues. Three residues (i to i + 2) constitute the turn with the C? H···O interaction occurring between the terminal residues, constraining the torsion angles ?_{i + 1}, ψ_{i + 1}, ?_{i + 2} and χ′_{1(i + 2)} (using the interacting C^γ atom). Based on these angles there are two types of ω‐turns, each of which can be further divided into two groups. C^β‐branched side‐chains, and Met and Gln have high propensities to occur at i + 2; for the last two residues the carbonyl oxygen may participate in an additional interaction involving the S and amino group, respectively. With Cys occupying the i + 1 position, such turns are found in the metal‐binding sites. N‐linked glycosylation occurs at the consensus pattern Asn‐Xaa‐Ser/Thr; with Thr at i + 2, the sequence can adopt the secondary structure of a ω‐turn, which may be the recognition site for protein modification. Location between two β‐strands is the most common occurrence in protein tertiary structure, and being generally exposed ω‐turn may constitute the antigenic determinant site. It is a stable scaffold and may be used in protein engineering and peptide design. Proteins 2015; 83:203–214. © 2014 Wiley Periodicals, Inc.     

AAIndexLoc: predicting subcellular localization of proteins based on a new representation of sequences using amino acid indices

Identifying a protein's subcellular localization is an important step to understand its function. However, the involved experimental work is usually laborious, time consuming and costly. Computational prediction hence becomes valuable to reduce the inefficiency. Here we provide a method to predict protein subcellular localization by using amino acid composition and physicochemical properties. The method concatenates the information extracted from a protein's N-terminal, middle and full sequence. Each part is represented by amino acid composition, weighted amino acid composition, five-level grouping composition and five-level dipeptide composition. We divided our dataset into training and testing set. The training set is used to determine the best performing amino acid index by using five-fold cross validation, whereas the testing set acts as the independent dataset to evaluate the performance of our model. With the novel representation method, we achieve an accuracy of approximately 75% on independent dataset. We conclude that this new representation indeed performs well and is able to extract the protein sequence information. We have developed a web server for predicting protein subcellular localization. The web server is available at http://aaindexloc.bii.a-star.edu.sg .     

Increasing protein stability by improving beta‐turns

Our goal was to gain a better understanding of how protein stability can be increased by improving β‐turns. We studied 22 β‐turns in nine proteins with 66–370 residues by replacing other residues with proline and glycine and measuring the stability. These two residues are statistically preferred in some β‐turn positions. We studied: Cold shock protein B (CspB), Histidine‐containing phosphocarrier protein, Ubiquitin, Ribonucleases Sa2, Sa3, T1, and HI, Tryptophan synthetase α‐subunit, and Maltose binding protein. Of the 15 single proline mutations, 11 increased stability (Average = 0.8 ± 0.3; Range = 0.3–1.5 kcal/mol), and the stabilizing effect of double proline mutants was additive. On the basis of this and our previous work, we conclude that proteins can generally be stabilized by replacing nonproline residues with proline residues at the i + 1 position of Type I and II β‐turns and at the i position in Type II β‐turns. Other turn positions can sometimes be used if the φ angle is near ?60° for the residue replaced. It is important that the side chain of the residue replaced is less than 50% buried. Identical substitutions in β‐turns in related proteins give similar results. Proline substitutions increase stability mainly by decreasing the entropy of the denatured state. In contrast, the large, diverse group of proteins considered here had almost no residues in β‐turns that could be replaced by Gly to increase protein stability. Improving β‐turns by substituting Pro residues is a generally useful way of increasing protein stability. Proteins 2009. © 2009 Wiley‐Liss, Inc.     

A deep dense inception network for protein beta-turn prediction

Beta-turn prediction is useful in protein function studies and experimental design. Although recent approaches using machine-learning techniques such as support vector machine (SVM), neural networks, and K nearest neighbor have achieved good results for beta-turn prediction, there is still significant room for improvement. As previous predictors utilized features in a sliding window of 4-20 residues to capture interactions among sequentially neighboring residues, such feature engineering may result in incomplete or biased features and neglect interactions among long-range residues. Deep neural networks provide a new opportunity to address these issues. Here, we proposed a deep dense inception network (DeepDIN) for beta-turn prediction, which takes advantage of the state-of-the-art deep neural network design of dense networks and inception networks. A test on a recent BT6376 benchmark data set shows that DeepDIN outperformed the previous best tool BetaTPred3 significantly in both the overall prediction accuracy and the nine-type beta-turn classification accuracy. A tool, called MUFold-BetaTurn, was developed, which is the first beta-turn prediction tool utilizing deep neural networks. The tool can be downloaded at http://dslsrv8.cs.missouri.edu/~cf797/MUFoldBetaTurn/download.html .     

Identification of mannose interacting residues using local composition

Background

Mannose binding proteins (MBPs) play a vital role in several biological functions such as defense mechanisms. These proteins bind to mannose on the surface of a wide range of pathogens and help in eliminating these pathogens from our body. Thus, it is important to identify mannose interacting residues (MIRs) in order to understand mechanism of recognition of pathogens by MBPs.

Results

This paper describes modules developed for predicting MIRs in a protein. Support vector machine (SVM) based models have been developed on 120 mannose binding protein chains, where no two chains have more than 25% sequence similarity. SVM models were developed on two types of datasets: 1) main dataset consists of 1029 mannose interacting and 1029 non-interacting residues, 2) realistic dataset consists of 1029 mannose interacting and 10320 non-interacting residues. In this study, firstly, we developed standard modules using binary and PSSM profile of patterns and got maximum MCC around 0.32. Secondly, we developed SVM modules using composition profile of patterns and achieved maximum MCC around 0.74 with accuracy 86.64% on main dataset. Thirdly, we developed a model on a realistic dataset and achieved maximum MCC of 0.62 with accuracy 93.08%. Based on this study, a standalone program and web server have been developed for predicting mannose interacting residues in proteins (http://www.imtech.res.in/raghava/premier/).

Conclusions

Compositional analysis of mannose interacting and non-interacting residues shows that certain types of residues are preferred in mannose interaction. It was also observed that residues around mannose interacting residues have a preference for certain types of residues. Composition of patterns/peptide/segment has been used for predicting MIRs and achieved reasonable high accuracy. It is possible that this novel strategy may be effective to predict other types of interacting residues. This study will be useful in annotating the function of protein as well as in understanding the role of mannose in the immune system.     

Position-specific residue preference features around the ends of helices and strands and a novel strategy for the prediction of secondary structures

It has been many years since position-specific residue preference around the ends of a helix was revealed. However, all the existing secondary structure prediction methods did not exploit this preference feature, resulting in low accuracy in predicting the ends of secondary structures. In this study, we collected a relatively large data set consisting of 1860 high-resolution, non-homology proteins from the PDB, and further analyzed the residue distributions around the ends of regular secondary structures. It was found that there exist position-specific residue preferences (PSRP) around the ends of not only helices but also strands. Based on the unique features, we proposed a novel strategy and developed a tool named E-SSpred that treats the secondary structure as a whole and builds models to predict entire secondary structure segments directly by integrating relevant features. In E-SSpred, the support vector machine (SVM) method is adopted to model and predict the ends of helices and strands according to the unique residue distributions around them. A simple linear discriminate analysis method is applied to model and predict entire secondary structure segments by integrating end-prediction results, tri-peptide composition, and length distribution features of secondary structures, as well as the prediction results of the most famous program PSIPRED. The results of fivefold cross-validation on a widely used data set demonstrate that the accuracy of E-SSpred in predicting ends of secondary structures is about 10% higher than PSIPRED, and the overall prediction accuracy (Q(3) value) of E-SSpred (82.2%) is also better than PSIPRED (80.3%). The E-SSpred web server is available at http://bioinfo.hust.edu.cn/bio/tools/E-SSpred/index.html.     

Conformational dynamics of a short antigenic peptide in its free and antibody bound forms gives insight into the role of β‐turns in peptide immunogenicity

Earlier immunological experiments with a synthetic 36‐residue peptide (75‐110) from Influenza hemagglutinin have been shown to elicit anti‐peptide antibodies (Ab) which could cross‐react with the parent protein. In this article, we have studied the conformational features of a short antigenic (Ag) peptide (⁹⁸YPYDVPDYASLRS¹¹⁰) from Influenza hemagglutinin in its free and antibody (Ab) bound forms with molecular dynamics simulations using GROMACS package and OPLS‐AA/L all‐atom force field at two different temperatures (293 K and 310 K). Multiple simulations for the free Ag peptide show sampling of ordered conformations and suggest different conformational preferences of the peptide at the two temperatures. The free Ag samples a conformation crucial for Ab binding (β‐turn formed by “DYAS” sequence) with greater preference at 310 K while, it samples a native‐like conformation with relatively greater propensity at 293 K. The sequence “DYAS” samples β‐turn conformation with greater propensity at 310 K as part of the hemagglutinin protein also. The bound Ag too samples the β‐turn involving “DYAS” sequence and in addition it also samples a β‐turn formed by the sequence “YPYD” at its N‐terminus, which seems to be induced upon binding to the Ab. Further, the bound Ag displays conformational flexibility at both 293 K and 310 K, particularly at terminal residues. The implications of these results for peptide immunogenicity and Ag–Ab recognition are discussed. Proteins 2015; 83:1352–1367. © 2015 Wiley Periodicals, Inc.     

Prediction of the exposure status of transmembrane beta barrel residues from protein sequence

We present BTMX (Beta barrel TransMembrane eXposure), a computational method to predict the exposure status (i.e. exposed to the bilayer or hidden in the protein structure) of transmembrane residues in transmembrane beta barrel proteins (TMBs). BTMX predicts the exposure status of known TM residues with an accuracy of 84.2% over 2,225 residues and provides a confidence score for all predictions. Predictions made are in concert with the fact that hydrophobic residues tend to be more exposed to the bilayer. The biological relevance of the input parameters is also discussed. The highest prediction accuracy is obtained when a sliding window comprising three residues with similar C(α)-C(β) vector orientations is employed. The prediction accuracy of the BTMX method on a separate unseen non-redundant test dataset is 78.1%. By employing out-pointing residues that are exposed to the bilayer, we have identified various physico-chemical properties that show statistically significant differences between the beta strands located at the oligomeric interfaces compared to the non-oligomeric strands. The BTMX web server generates colored, annotated snake-plots as part of the prediction results and is available under the BTMX tab at http://service.bioinformatik.uni-saarland.de/tmx-site/. Exposure status prediction of TMB residues may be useful in 3D structure prediction of TMBs.     

CONFOLD: Residue‐residue contact‐guided ab initio protein folding

Predicted protein residue–residue contacts can be used to build three‐dimensional models and consequently to predict protein folds from scratch. A considerable amount of effort is currently being spent to improve contact prediction accuracy, whereas few methods are available to construct protein tertiary structures from predicted contacts. Here, we present an ab initio protein folding method to build three‐dimensional models using predicted contacts and secondary structures. Our method first translates contacts and secondary structures into distance, dihedral angle, and hydrogen bond restraints according to a set of new conversion rules, and then provides these restraints as input for a distance geometry algorithm to build tertiary structure models. The initially reconstructed models are used to regenerate a set of physically realistic contact restraints and detect secondary structure patterns, which are then used to reconstruct final structural models. This unique two‐stage modeling approach of integrating contacts and secondary structures improves the quality and accuracy of structural models and in particular generates better β‐sheets than other algorithms. We validate our method on two standard benchmark datasets using true contacts and secondary structures. Our method improves TM‐score of reconstructed protein models by 45% and 42% over the existing method on the two datasets, respectively. On the dataset for benchmarking reconstructions methods with predicted contacts and secondary structures, the average TM‐score of best models reconstructed by our method is 0.59, 5.5% higher than the existing method. The CONFOLD web server is available at http://protein.rnet.missouri.edu/confold/ . Proteins 2015; 83:1436–1449. © 2015 Wiley Periodicals, Inc.     

A neural network method for prediction of beta-turn types in proteins using evolutionary information

MOTIVATION: The prediction of beta-turns is an important element of protein secondary structure prediction. Recently, a highly accurate neural network based method Betatpred2 has been developed for predicting beta-turns in proteins using position-specific scoring matrices (PSSM) generated by PSI-BLAST and secondary structure information predicted by PSIPRED. However, the major limitation of Betatpred2 is that it predicts only beta-turn and non-beta-turn residues and does not provide any information of different beta-turn types. Thus, there is a need to predict beta-turn types using an approach based on multiple sequence alignment, which will be useful in overall tertiary structure prediction. RESULTS: In the present work, a method has been developed for the prediction of beta-turn types I, II, IV and VIII. For each turn type, two consecutive feed-forward back-propagation networks with a single hidden layer have been used where the first sequence-to-structure network has been trained on single sequences as well as on PSI-BLAST PSSM. The output from the first network along with PSIPRED predicted secondary structure has been used as input for the second-level structure-to-structure network. The networks have been trained and tested on a non-homologous dataset of 426 proteins chains by 7-fold cross-validation. It has been observed that the prediction performance for each turn type is improved significantly by using multiple sequence alignment. The performance has been further improved by using a second level structure-to-structure network and PSIPRED predicted secondary structure information. It has been observed that Type I and II beta-turns have better prediction performance than Type IV and VIII beta-turns. The final network yields an overall accuracy of 74.5, 93.5, 67.9 and 96.5% with MCC values of 0.29, 0.29, 0.23 and 0.02 for Type I, II, IV and VIII beta-turns, respectively, and is better than random prediction. AVAILABILITY: A web server for prediction of beta-turn types I, II, IV and VIII based on above approach is available at http://www.imtech.res.in/raghava/betaturns/ and http://bioinformatics.uams.edu/mirror/betaturns/ (mirror site).     

Prediction of beta-turns in proteins from multiple alignment using neural network

A neural network-based method has been developed for the prediction of beta-turns in proteins by using multiple sequence alignment. Two feed-forward back-propagation networks with a single hidden layer are used where the first-sequence structure network is trained with the multiple sequence alignment in the form of PSI-BLAST-generated position-specific scoring matrices. The initial predictions from the first network and PSIPRED-predicted secondary structure are used as input to the second structure-structure network to refine the predictions obtained from the first net. A significant improvement in prediction accuracy has been achieved by using evolutionary information contained in the multiple sequence alignment. The final network yields an overall prediction accuracy of 75.5% when tested by sevenfold cross-validation on a set of 426 nonhomologous protein chains. The corresponding Q(pred), Q(obs), and Matthews correlation coefficient values are 49.8%, 72.3%, and 0.43, respectively, and are the best among all the previously published beta-turn prediction methods. The Web server BetaTPred2 (http://www.imtech.res.in/raghava/betatpred2/) has been developed based on this approach.     

Prediction of C alpha-H...O and C alpha-H...pi interactions in proteins using recurrent neural network

In this study, an attempt has been made to develop a method for predicting weak hydrogen bonding interactions, namely, C alpha-H...O and C alpha-H...pi interactions in proteins using artificial neural network. Both standard feed-forward neural network (FNN) and recurrent neural networks (RNN) have been trained and tested using five-fold cross-validation on a non-homologous dataset of 2298 protein chains where no pair of sequences has more than 25% sequence identity. It has been found that the prediction accuracy varies with the separation distance between donor and acceptor residues. The maximum sensitivity achieved with RNN for C alpha-H...O is 51.2% when donor and acceptor residues are four residues apart (i.e. at delta D-A = 4) and for C alpha-H...pi is 82.1% at delta D-A = 3. The performance of RNN is increased by 1-3% for both types of interactions when PSIPRED predicted protein secondary structure is used. Overall, RNN performs better than feed-forward networks at all separation distances between donor-acceptor pair for both types of interactions. Based on the observations, a web server CHpredict (available at http://www.imtech.res.in/raghava/chpredict/) has been developed for predicting donor and acceptor residues in C alpha-H...O and C alpha-H...pi interactions in proteins.     

Prediction of interface residues in protein-protein complexes by a consensus neural network method: test against NMR data

The number of structures of protein-protein complexes deposited to the Protein Data Bank is growing rapidly. These structures embed important information for predicting structures of new protein complexes. This motivated us to develop the PPISP method for predicting interface residues in protein-protein complexes. In PPISP, sequence profiles and solvent accessibility of spatially neighboring surface residues were used as input to a neural network. The network was trained on native interface residues collected from the Protein Data Bank. The prediction accuracy at the time was 70% with 47% coverage of native interface residues. Now we have extensively improved PPISP. The training set now consisted of 1156 nonhomologous protein chains. Test on a set of 100 nonhomologous protein chains showed that the prediction accuracy is now increased to 80% with 51% coverage. To solve the problem of over-prediction and under-prediction associated with individual neural network models, we developed a consensus method that combines predictions from multiple models with different levels of accuracy and coverage. Applied on a benchmark set of 68 proteins for protein-protein docking, the consensus approach outperformed the best individual models by 3-8 percentage points in accuracy. To demonstrate the predictive power of cons-PPISP, eight complex-forming proteins with interfaces characterized by NMR were tested. These proteins are nonhomologous to the training set and have a total of 144 interface residues identified by chemical shift perturbation. cons-PPISP predicted 174 interface residues with 69% accuracy and 47% coverage and promises to complement experimental techniques in characterizing protein-protein interfaces. .     

CASP10–BCL::Fold efficiently samples topologies of large proteins

During CASP10 in summer 2012, we tested BCL::Fold for prediction of free modeling (FM) and template‐based modeling (TBM) targets. BCL::Fold assembles the tertiary structure of a protein from predicted secondary structure elements (SSEs) omitting more flexible loop regions early on. This approach enables the sampling of conformational space for larger proteins with more complex topologies. In preparation of CASP11, we analyzed the quality of CASP10 models throughout the prediction pipeline to understand BCL::Fold's ability to sample the native topology, identify native‐like models by scoring and/or clustering approaches, and our ability to add loop regions and side chains to initial SSE‐only models. The standout observation is that BCL::Fold sampled topologies with a GDT_TS score > 33% for 12 of 18 and with a topology score > 0.8 for 11 of 18 test cases de novo. Despite the sampling success of BCL::Fold, significant challenges still exist in clustering and loop generation stages of the pipeline. The clustering approach employed for model selection often failed to identify the most native‐like assembly of SSEs for further refinement and submission. It was also observed that for some β‐strand proteins model refinement failed as β‐strands were not properly aligned to form hydrogen bonds removing otherwise accurate models from the pool. Further, BCL::Fold samples frequently non‐natural topologies that require loop regions to pass through the center of the protein. Proteins 2015; 83:547–563. © 2015 Wiley Periodicals, Inc.     

Structural and sequence features of two residue turns in beta‐hairpins

Beta‐turns in beta‐hairpins have been implicated as important sites in protein folding. In particular, two residue β‐turns, the most abundant connecting elements in beta‐hairpins, have been a major target for engineering protein stability and folding. In this study, we attempted to investigate and update the structural and sequence properties of two residue turns in beta‐hairpins with a large data set. For this, 3977 beta‐turns were extracted from 2394 nonhomologous protein chains and analyzed. First, the distribution, dihedral angles and twists of two residue turn types were determined, and compared with previous data. The trend of turn type occurrence and most structural features of the turn types were similar to previous results, but for the first time Type II turns in beta‐hairpins were identified. Second, sequence motifs for the turn types were devised based on amino acid positional potentials of two‐residue turns, and their distributions were examined. From this study, we could identify code‐like sequence motifs for the two residue beta‐turn types. Finally, structural and sequence properties of beta‐strands in the beta‐hairpins were analyzed, which revealed that the beta‐strands showed no specific sequence and structural patterns for turn types. The analytical results in this study are expected to be a reference in the engineering or design of beta‐hairpin turn structures and sequences. Proteins 2014; 82:1721–1733. © 2014 Wiley Periodicals, Inc.     

InterProSurf: a web server for predicting interacting sites on protein surfaces

A new web server, InterProSurf, predicts interacting amino acid residues in proteins that are most likely to interact with other proteins, given the 3D structures of subunits of a protein complex. The prediction method is based on solvent accessible surface area of residues in the isolated subunits, a propensity scale for interface residues and a clustering algorithm to identify surface regions with residues of high interface propensities. Here we illustrate the application of InterProSurf to determine which areas of Bacillus anthracis toxins and measles virus hemagglutinin protein interact with their respective cell surface receptors. The computationally predicted regions overlap with those regions previously identified as interface regions by sequence analysis and mutagenesis experiments. AVAILABILITY: The InterProSurf web server is available at http://curie.utmb.edu/