Prediction of the transmembrane regions of beta-barrel membrane proteins with a neural network-based predictor

A method based on neural networks is trained and tested on a nonredundant set of beta-barrel membrane proteins known at atomic resolution with a jackknife procedure. The method predicts the topography of transmembrane beta strands with residue accuracy as high as 78% when evolutionary information is used as input to the network. Of the transmembrane beta-strands included in the training set, 93% are correctly assigned. The predictor includes an algorithm of model optimization, based on dynamic programming, that correctly models eight out of the 11 proteins present in the training/testing set. In addition, protein topology is assigned on the basis of the location of the longest loops in the models. We propose this as a general method to fill the gap of the prediction of beta-barrel membrane proteins.     

Modeling ensembles of transmembrane beta-barrel proteins

Transmembrane beta-barrel (TMB) proteins are embedded in the outer membrane of gram-negative bacteria, mitochondria, and chloroplasts. Despite their importance, very few nonhomologous TMB structures have been determined by X-ray diffraction because of the experimental difficulty encountered in crystallizing transmembrane proteins. We introduce the program partiFold to investigate the folding landscape of TMBs. By computing the Boltzmann partition function, partiFold estimates inter-beta-strand residue interaction probabilities, predicts contacts and per-residue X-ray crystal structure B-values, and samples conformations from the Boltzmann low energy ensemble. This broad range of predictive capabilities is achieved using a single, parameterizable grammatical model to describe potential beta-barrel supersecondary structures, combined with a novel energy function of stacked amino acid pair statistical potentials. PartiFold outperforms existing programs for inter-beta-strand residue contact prediction on TMB proteins, offering both higher average predictive accuracy as well as more consistent results. Moreover, the integration of these contact probabilities inside a stochastic contact map can be used to infer a more meaningful picture of the TMB folding landscape, which cannot be achieved with other methods. Partifold's predictions of B-values are competitive with recent methods specifically designed for this problem. Finally, we show that sampling TMBs from the Boltzmann ensemble matches the X-ray crystal structure better than single structure prediction methods. A webserver running partiFold is available at http://partiFold.csail.mit.edu/.     

Better prediction of the location of alpha-turns in proteins with support vector machine

We have developed a novel method named AlphaTurn to predict alpha-turns in proteins based on the support vector machine (SVM). The prediction was done on a data set of 469 nonhomologous proteins containing 967 alpha-turns. A great improvement in prediction performance was achieved by using multiple sequence alignment generated by PSI-BLAST as input instead of the single amino acid sequence. The introduction of secondary structure information predicted by PSIPRED also improved the prediction performance. Moreover, we handled the very uneven data set by combining the cost factor j with the "state-shifting" rule. This further promoted the prediction quality of our method. The final SVM model yielded a Matthews correlation coefficient (MCC) of 0.25 by a 10-fold cross-validation. To our knowledge, this MCC value is the highest obtained so far for predicting alpha-turns. An online Web server based on this method has been developed and can be freely accessed at http://bmc.hust.edu.cn/bioinformatics/ or http://210.42.106.80/.     

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 the location and type of beta-turns in proteins using neural networks.

A neural network has been used to predict both the location and the type of beta-turns in a set of 300 nonhomologous protein domains. A substantial improvement in prediction accuracy compared with previous methods has been achieved by incorporating secondary structure information in the input data. The total percentage of residues correctly classified as beta-turn or not-beta-turn is around 75% with predicted secondary structure information. More significantly, the method gives a Matthews correlation coefficient (MCC) of around 0.35, compared with a typical MCC of around 0.20 using other beta-turn prediction methods. Our method also distinguishes the two most numerous and well-defined types of beta-turn, types I and II, with a significant level of accuracy (MCCs 0.22 and 0.26, respectively).     

Prediction of pi-turns in proteins using PSI-BLAST profiles and secondary structure information

Due to the structural and functional importance of tight turns, some methods have been proposed to predict gamma-turns, beta-turns, and alpha-turns in proteins. In the past, studies of pi-turns were made, but not a single prediction approach has been developed so far. It will be useful to develop a method for identifying pi-turns in a protein sequence. In this paper, the support vector machine (SVM) method has been introduced to predict pi-turns from the amino acid sequence. The training and testing of this approach is performed with a newly collected data set of 640 non-homologous protein chains containing 1931 pi-turns. Different sequence encoding schemes have been explored in order to investigate their effects on the prediction performance. With multiple sequence alignment and predicted secondary structure, the final SVM model yields a Matthews correlation coefficient (MCC) of 0.556 by a 7-fold cross-validation. A web server implementing the prediction method is available at the following URL: http://210.42.106.80/piturn/.     

A consensus algorithm to screen genomes for novel families of transmembrane beta barrel proteins

The ability to search sequence datasets for membrane spanning proteins is an important requirement for genome annotation. However, the development of algorithms to identify novel types of transmembrane beta-barrel (TMB) protein has proven substantially harder than for transmembrane helical proteins, owing to a shorter TM domain in which only alternate residues are hydrophobic. Although recent reports have described important improvements in the development of such algorithms, there is still concern over their ability to confidently screen genomes. Here we describe a new algorithm combining composition and hidden Markov model topology based classifiers (called TMB-Hunt2), which achieves a crossvalidation accuracy of >95%, with 96.7% precision and 94.2% recall. An overview is given of the algorithm design, with a thorough assessment of performance and application to a number of genomes. Of particular note is that TMB/extracellular protein discrimination is significantly more difficult than TMB/cytoplasmic protein discrimination, with the predictor correctly rejecting just 74% of extracellular proteins, in comparison to 98% of cytoplasmic proteins. Focus is given to directions for further improvements in TMB/non-TMB protein discrimination, with a call for the development of standardized tests and assessments of such algorithms. Tools and datasets are made available through a website called TMB-Web (http://www.bioinformatics.leeds.ac.uk/TMB-Web/TMB-Hunt2).     

Predicting transmembrane beta-barrels and interstrand residue interactions from sequence

Transmembrane beta-barrel (TMB) proteins are embedded in the outer membrane of Gram-negative bacteria, mitochondria, and chloroplasts. The cellular location and functional diversity of beta-barrel outer membrane proteins (omps) makes them an important protein class. At the present time, very few nonhomologous TMB structures have been determined by X-ray diffraction because of the experimental difficulty encountered in crystallizing transmembrane proteins. A novel method using pairwise interstrand residue statistical potentials derived from globular (nonouter membrane) proteins is introduced to predict the supersecondary structure of transmembrane beta-barrel proteins. The algorithm transFold employs a generalized hidden Markov model (i.e., multitape S-attribute grammar) to describe potential beta-barrel supersecondary structures and then computes by dynamic programming the minimum free energy beta-barrel structure. Hence, the approach can be viewed as a "wrapping" component that may capture folding processes with an initiation stage followed by progressive interaction of the sequence with the already-formed motifs. This approach differs significantly from others, which use traditional machine learning to solve this problem, because it does not require a training phase on known TMB structures and is the first to explicitly capture and predict long-range interactions. TransFold outperforms previous programs for predicting TMBs on smaller (相似文献   

Discrimination of outer membrane proteins using machine learning algorithms

Discriminating outer membrane proteins (OMPs) from other folding types of globular and membrane proteins is an important task both for identifying OMPs from genomic sequences and for the successful prediction of their secondary and tertiary structures. In this work, we have analyzed the performance of different methods, based on Bayes rules, logistic functions, neural networks, support vector machines, decision trees, etc. for discriminating OMPs. We found that most of the machine learning techniques discriminate OMPs with similar accuracy. The neural network-based method could discriminate the OMPs from other proteins [globular/transmembrane helical (TMH)] at the fivefold cross-validation accuracy of 91.0% in a dataset of 1,088 proteins. The accuracy of discriminating globular proteins is 88.8% and that of TMH proteins is 93.7%. Further, the neural network method is tested with globular proteins belonging to 30 different folding types and it could successfully exclude 95% of the considered proteins. The proteins with SAM domain such as knottins, rubredoxin, and thioredoxin folds are eliminated with 100% accuracy. These accuracy levels are comparable to or better than other methods in the literature. We suggest that this method could be effectively used to discriminate OMPs and for detecting OMPs in genomic sequences.     

Fishing new proteins in the twilight zone of genomes: the test case of outer membrane proteins in Escherichia coli K12, Escherichia coli O157:H7, and other Gram-negative bacteria

We address the problem of clustering the whole protein content of genomes into three different categories-globular, all-alpha, and all-beta membrane proteins-with the aim of fishing new membrane proteins in the pool of nonannotated proteins (twilight zone). The focus is then mainly on outer membrane proteins. This is performed by using an integrated suite of programs (Hunter) specifically developed for predicting the occurrence of signal peptides in proteins of Gram-negative bacteria and the topography of all-alpha and all-beta membrane proteins. Hunter is tested on the well and partially annotated proteins (2160 and 760, respectively) of Escherichia coli K 12 scoring as high as 95.6% in the correct assignment of each chain to the category. Of the remaining 1253 nonannotated sequences, 1099 are predicted globular, 136 are all-alpha, and 18 are all-beta membrane proteins. In Escherichia coli 0157:H7 we filtered 1901 nonannotated proteins. Our analysis classifies 1564 globular chains, 327 inner membrane proteins, and 10 outer membrane proteins. With Hunter, new membrane proteins are added to the list of putative membrane proteins of Gram-negative bacteria. The content of outer membrane proteins per genome (nine are analyzed) ranges from 1.5% to 2.4%, and it is one order of magnitude lower than that of inner membrane proteins. The finding is particularly relevant when it is considered that this is the first large-scale analysis based on validated tools that can predict the content of outer membrane proteins in a genome and can allow cross-comparison of the same protein type between different species.     

Prediction of alpha-turns in proteins using PSI-BLAST profiles and secondary structure information

In this paper a systematic attempt has been made to develop a better method for predicting alpha-turns in proteins. Most of the commonly used approaches in the field of protein structure prediction have been tried in this study, which includes statistical approach "Sequence Coupled Model" and machine learning approaches; i) artificial neural network (ANN); ii) Weka (Waikato Environment for Knowledge Analysis) Classifiers and iii) Parallel Exemplar Based Learning (PEBLS). We have also used multiple sequence alignment obtained from PSIBLAST and secondary structure information predicted by PSIPRED. The training and testing of all methods has been performed on a data set of 193 non-homologous protein X-ray structures using five-fold cross-validation. It has been observed that ANN with multiple sequence alignment and predicted secondary structure information outperforms other methods. Based on our observations we have developed an ANN-based method for predicting alpha-turns in proteins. The main components of the method are two feed-forward back-propagation networks with a single hidden layer. 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 obtained 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. The final network yields an overall prediction accuracy of 78.0% and MCC of 0.16. A web server AlphaPred (http://www.imtech.res.in/raghava/alphapred/) has been developed based on this approach.     

Prediction of strand pairing in antiparallel and parallel beta-sheets using information theory

An information theory approach was developed to predict the alignment of interacting antiparallel and parallel beta-strands. Information scores were derived for the preference of a residue on a beta-strand to be opposite a sequence of residues on an adjacent beta-strand. These scores were used to predict the interstrand register of interacting beta-strands from 10 alternative offset positions either side of the experimentally observed beta-sheet register. The amino acid sequence of an internal beta-strand can be correctly aligned with two beta-strands in a fixed position either side of the strand in 45% of antiparallel and 48% of parallel arrangements. For comparison, when another beta-strand from a nonhomologous protein substitutes the internal beta-strand, the same register is predicted for only 24 and 36% of antiparallel and parallel arrangements. As expected, alignment of a single fixed strand with just a second beta-strand sequence was more difficult, and gave a correct register in 31 and 37% of antiparallel and parallel beta-pairs, respectively. These scores are 10% higher than for two randomly selected beta-strand sequences. In general, prediction accuracy was not improved by information tables that distinguished hydrogen-bonding patterns or beta-strand order. These results will contribute to predicting the arrangement of beta-strands in beta-pleated sheets and protein topology.     

Prediction of secondary structure by evolutionary comparison: application to the alpha subunit of tryptophan synthase

The amino acid sequences of the a subunits of tryptophan synthase from ten different microorganisms were aligned by standard procedures. The alpha helices, beta strands and turns of each sequence were predicted separately by two standard prediction algorithms and averaged at homologous sequence positions. Additional evidence for conserved secondary structure was derived from profiles of average hydropathy and chain flexibility values, leading to a joint prediction. There is good agreement between (1) predicted beta strands, maximal hydropathy and minimal flexibility, and (2) predicted loops, great chain flexibility, and protein segments that accept insertions of various lengths in individual sequences. The a subunit is predicted to have eight repeated beta-loop-alpha-loop motifs with an extra N-terminal alpha helix and an intercalated segment of highly conserved residues. This pattern suggests that the territory structure of the a subunit is an eightfold alpha/beta barrel. The distribution of conserved amino acid residues and published data on limited proteolysis, chemical modification, and mutagenesis are consistent with the alpha/beta barrel structure. Both the active site of the a subunit and the combining site for the beta 2 subunit are at the end of the barrel formed by the carboxyl-termini of the beta strands.     

Barrel structures in proteins: automatic identification and classification including a sequence analysis of TIM barrels.

Automated methods for identifying and characterizing regular beta-barrels from coordinate data have been developed to analyze and classify various kinds of barrel structures based on geometric parameters such as the barrel strand number (n) and shear number (S). In total, we find 1,316 barrels in the January 1998 release of Protein Data Bank. Of 1,316 barrels, 1,277 barrels had an even shear number, corresponding to 50 nonhomologous families. The (beta alpha)8 triose phosphate isomerase (TIM) barrel (n = 8, S = 8) fold has the largest number of apparently nonhomologous entries, 16, although the trypsin like antiparallel (n = 6, S = 8) barrels (representing only three families) are the most common with 527 barrels. Of all the protein families that exhibit barrel structures, 68% are found to be various kinds of enzymes, the remainder being binding proteins and transport membrane proteins. In addition, the layers of side chains, which form the cores of barrels with S = n and S = 2n, are also analyzed. More sophisticated methods were developed for detecting TIM barrels specifically, including consideration of the amino acid propensities for the side chains that form the layers. We found that the residues on the outside of the eight stranded parallel beta-barrel, buried by the alpha-helices, are much more hydrophobic than the residues inside the barrel.     

G-protein-coupled receptor domain overexpression in Halobacterium salinarum: long-range transmembrane interactions in heptahelical membrane proteins

The aminergic alpha(2b)-adrenergic receptor (alpha(2b)-AR) third intracellular loop (alpha(2b)-AR 3i) mediates receptor subcellular compartmentalization and signal transduction processes via ligand-dependent interaction with G(i)- and G(o)- proteins. To understand the structural origins of these processes we engineered several lengths of alpha(2b)-AR 3i into the third intracellular loop of the proton pump bacteriorhodopsin (bR) and produced the fusion proteins in quantities suitable for physical studies. The fusion proteins were expressed in the Archaeon Halobacterium salinarum and purified. A highly expressed fusion protein was crystallized from bicelles and diffracted to low resolution on an in-house diffractometer. The bR-alpha(2b)-AR 3i(203-292) protein possessed a photocycle slightly perturbed from that of the wild-type bR. The first half of the fusion protein photocycle, correlated with proton release, is accelerated by a factor of 3, whereas the second half, correlated with proton uptake, is slightly slower than wild-type bR. In addition, there is a large decrease in the pK(a), (from 9.6 to 8.3) of the terminal proton release group in the unphotolyzed state of bR-alpha(2b)-AR 3i as deduced from the pH-dependence of the M-formation. Perturbation of a cytoplasmic loop has thus resulted in the perturbation of proton release at the extracellular surface. The current work indicates that long-range and highly coupled intramolecular interactions exist that are capable of "transducing" structural perturbations (e.g., signals) across the cellular membrane. This gene fusion approach may have general applicability for physical studies of G-protein-coupled receptor domains in the context of the bR structural scaffold.     

Toward minimalist models of larger proteins: a ubiquitin-like protein

Our recently developed off-lattice bead model capable of simulating protein structures with mixed alpha/beta content has been extended to model the folding of a ubiquitin-like protein and provides a means for examining the more complex kinetics involved in the folding of larger proteins. Using trajectories generated from constant-temperature Langevin dynamics simulations and sampling with the multiple multi-histogram method over five-order parameters, we are able to characterize the free energy landscape for folding and find evidence for folding through compact intermediates. Our model reproduces the observation that the C-terminus loop structure in ubiquitin is the last to fold in the folding process and most likely plays a spectator role in the folding kinetics. The possibility of a productive metastable intermediate along the folding pathway consisting of collapsed states with no secondary structure, and of intermediates or transition structures involving secondary structural elements occurring early in the sequence, is also supported by our model. The kinetics of folding remain multi-exponential below the folding temperature, with glass-like kinetics appearing at T/T(f) approximately 0.86. This new physicochemical model, designed to be predictive, helps validate the value of modeling protein folding at this level of detail for genomic-scale studies, and motivates further studies of other protein topologies and the impact of more complex energy functions, such as the addition of solvation forces.     

PRIMSIPLR: Prediction of inner‐membrane situated pore‐lining residues for alpha‐helical transmembrane proteins

Transmembrane proteins such as transporters and channels mediate the passage of inorganic and organic substances across biological membranes through their central pore. Pore‐lining residues (PLRs) that make direct contacts to the substrates have a crucial impact on the function of the protein and, hence, their identification is a key step in mechanistic studies. Here, we established a nonredundant data set containing the three‐dimensional (3D) structures of 90 α‐helical transmembrane proteins and annotated the PLRs of these proteins by a pore identification software. A support vector machine was then trained to distinguish PLRs from other residues based on the protein sequence alone. Using sixfold cross‐validation, our best performing predictor gave a Matthews's correlation coefficient of 0.41 with an accuracy of 0.86, sensitivity of 0.61, and specificity of 0.89, respectively. We provide a novel software tool that will aid biomedical scientists working on transmembrane proteins with unknown 3D structures. Both standalone version and web service are freely available from the URL http://service.bioinformatik.uni-saarland.de/PRIMSIPLR/ . Proteins 2014; 82:1503–1511. © 2014 Wiley Periodicals, Inc.     

Actin polymerization in the equatorial and postacrosomal regions of guinea pig spermatozoa during the acrosome reaction is regulated by G proteins

The acrosome reaction (AR) is an exocytotic process of spermatozoa, and an absolute requirement for fertilization. During AR, actin polymerization is necessary in the equatorial and postacrosomal regions of guinea pig sperm for spermatozoa incorporation deep into the egg cytoplasm, but not for plasma membrane (PM) fusion nor the early steps of egg activation. To identify the mechanisms involved in this sperm actin polymerization, we searched for the protein members, known to be involved in a highly conserved model, that may apply to any cellular process in which de novo actin polymerization occurs from G protein activation. WASP, Arp 2/3, profilins I and II, and Cdc42, RhoA and RhoB GTPases were localized by indirect immunofluorescence (IIF) in guinea pig spermatozoa and their presence corroborated by Western blotting. WASP and profilin II were translocated to the postacrosomal region (Arp2/3 already were there) in long-term capacitated and acrosome-reacted spermatozoa, at the same time as actin polymerization occurred. These events were inhibited by GDP-beta-S and promoted by lysophosphatidic acid (LPA) and GTP-gamma-S, a small GTPase inhibitor and two activators, respectively. By immunoprecipitation, Cdc42-WASp association was identified in capacitated but not in noncapacitated gametes. Polymerized actin in the postacrosomal region is apparently anchored both to the postacrosomal perinuclear theca region and the overlying PM. Results suggest that GTPases are involved in sperm actin polymerization, in the postacrosomal region and the mechanism for polymerization might fit a previously proposed model (Mullins, 2000: Curr Opin Cell Biol 12:91-96).     

Guanidine hydrochloride unfolding of a transmembrane beta-strand in FepA using site-directed spin labeling.

We have used the electron spin resonance (ESR) site-directed spin-labeling (SDSL) technique to examine the guanidine hydrochloride (Gdn-HCl) induced denaturation of several sites along a transmembrane beta-strand located in the ferric enterobactin receptor, FepA. In addition, we have continued the characterization of the beta-strand previously identified by our group (Klug CS et al., 1997, Biochemistry 36:13027-13033) to extend from the periplasm to the extracellular surface loop in FepA, an integral membrane protein containing a beta-barrel motif comprised of a series of antiparallel beta-strands that is responsible for transport of the iron chelate, ferric enterobactin (FeEnt), across the outer membrane of Escherichia coli and many related enteric bacteria. We have previously shown that a large surface loop in FepA containing the FeEnt binding site denatures independently of the beta-barrel domain (Klug CS et al., 1995, Biochemistry 34:14230-14236). The SDSL approach allows examination of the unfolding at individual residues independent of the global unfolding of the protein. This work shows that sites along the beta-strand that are exposed to the aqueous lumen of the channel denature more rapidly and with higher cooperativity than the surface loop, while sites on the hydrophobic side of the beta-strand undergo a limited degree of noncooperative unfolding and do not fully denature even at high (e.g., 4 M) Gdn-HCl concentrations. We conclude that, in a transmembrane beta-strand, the local environment of a given residue plays a significant role in the loss of structure at each site.