Protein fold recognition using sequence-derived predictions.

In protein fold recognition, one assigns a probe amino acid sequence of unknown structure to one of a library of target 3D structures. Correct assignment depends on effective scoring of the probe sequence for its compatibility with each of the target structures. Here we show that, in addition to the amino acid sequence of the probe, sequence-derived properties of the probe sequence (such as the predicted secondary structure) are useful in fold assignment. The additional measure of compatibility between probe and target is the level of agreement between the predicted secondary structure of the probe and the known secondary structure of the target fold. That is, we recommend a sequence-structure compatibility function that combines previously developed compatibility functions (such as the 3D-1D scores of Bowie et al. [1991] or sequence-sequence replacement tables) with the predicted secondary structure of the probe sequence. The effect on fold assignment of adding predicted secondary structure is evaluated here by using a benchmark set of proteins (Fischer et al., 1996a). The 3D structures of the probe sequences of the benchmark are actually known, but are ignored by our method. The results show that the inclusion of the predicted secondary structure improves fold assignment by about 25%. The results also show that, if the true secondary structure of the probe were known, correct fold assignment would increase by an additional 8-32%. We conclude that incorporating sequence-derived predictions significantly improves assignment of sequences to known 3D folds. Finally, we apply the new method to assign folds to sequences in the SWISSPROT database; six fold assignments are given that are not detectable by standard sequence-sequence comparison methods; for two of these, the fold is known from X-ray crystallography and the fold assignment is correct.     

Molecular Modeling of Immunoglobulin Superfamily Proteins: Predicting the Three Dimensional Structure of the Extracellular Domain of CTLA-4 (CD152)

The interactions between CD28/CTLA-4 (CD152) on T cells and their ligands CD80/CD86 on antigen presenting cells provide costimulatory signals critical for T cell activation. CD28/CTLA-4 and CD80/CD86 are members of the immunoglobulin superfamily (IgSF). CD28 and CTLA-4 both contain a single extracellular immunoglobulin (Ig) domain which binds CD80/CD86. Here we report modeling studies on the three-dimensional (3D) structure of the CTLA-4 binding domain. Since CTLA-4 displays only very weak sequence homology to proteins with known 3D structure, conventional modeling techniques were difficult to apply. Structure-oriented sequence comparison, consensus residue analysis, conformational searching, and inverse folding calculations were employed to aid in the generation of a comparative CTLA-4 model. Regions of high and low prediction confidence were identified, and the sequence-structure compatibility of the model was determined. Characteristics of the modeled structure, which resembles an Ig V domain, were analyzed, and the model was used to map N-linked glycosylation sites and residues critical for CTLA-4 function. The modeling approach described here can be applied to predict 3D structures of other IgSF proteins.Supplementary material to this paper is available in electronic form at http://dx.doi.org/10.1007/s008940050025     

Molecular Modeling of Immunoglobulin Superfamily Proteins: Predicting the Three Dimensional Structure of the Extracellular Domain of CTLA-4 (CD152)

The interactions between CD28/CTLA-4 (CD152) on T cells and their ligands CD80/CD86 on antigen presenting cells provide costimulatory signals critical for T cell activation. CD28/CTLA-4 and CD80/CD86 are members of the immunoglobulin superfamily (IgSF). CD28 and CTLA-4 both contain a single extracellular immunoglobulin (Ig) domain which binds CD80/CD86. Here we report modeling studies on the three-dimensional (3D) structure of the CTLA-4 binding domain. Since CTLA-4 displays only very weak sequence homology to proteins with known 3D structure, conventional modeling techniques were difficult to apply. Structure-oriented sequence comparison, consensus residue analysis, conformational searching, and inverse folding calculations were employed to aid in the generation of a comparative CTLA-4 model. Regions of high and low prediction confidence were identified, and the sequence-structure compatibility of the model was determined. Characteristics of the modeled structure, which resembles an Ig V domain, were analyzed, and the model was used to map N-linked glycosylation sites and residues critical for CTLA-4 function. The modeling approach described here can be applied to predict 3D structures of other IgSF proteins.     

Exploring protein sequence space using knowledge-based potentials

Knowledge-based potentials can be used to decide whether an amino acid sequence is likely to fold into a prescribed native protein structure. We use this idea to survey the sequence-structure relations in protein space. In particular, we test the following two propositions which were found to be important for efficient evolution: the sequences folding into a particular native fold form extensive neutral networks that percolate through sequence space. The neutral networks of any two native folds approach each other to within a few point mutations. Computer simulations using two very different potential functions, M. Sippl's PROSA pair potential and a neural network based potential, are used to verify these claims.     

Prediction of helix-helix contacts and interacting helices in polytopic membrane proteins using neural networks

Despite rapidly increasing numbers of available 3D structures, membrane proteins still account for less than 1% of all structures in the Protein Data Bank. Recent high-resolution structures indicate a clearly broader structural diversity of membrane proteins than initially anticipated, motivating the development of reliable structure prediction methods specifically tailored for this class of molecules. One important prediction target capturing all major aspects of a protein's 3D structure is its contact map. Our analysis shows that computational methods trained to predict residue contacts in globular proteins perform poorly when applied to membrane proteins. We have recently published a method to identify interacting alpha-helices in membrane proteins based on the analysis of coevolving residues in predicted transmembrane regions. Here, we present a substantially improved algorithm for the same problem, which uses a newly developed neural network approach to predict helix-helix contacts. In addition to the input features commonly used for contact prediction of soluble proteins, such as windowed residue profiles and residue distance in the sequence, our network also incorporates features that apply to membrane proteins only, such as residue position within the transmembrane segment and its orientation toward the lipophilic environment. The obtained neural network can predict contacts between residues in transmembrane segments with nearly 26% accuracy. It is therefore the first published contact predictor developed specifically for membrane proteins performing with equal accuracy to state-of-the-art contact predictors available for soluble proteins. The predicted helix-helix contacts were employed in a second step to identify interacting helices. For our dataset consisting of 62 membrane proteins of solved structure, we gained an accuracy of 78.1%. Because the reliable prediction of helix interaction patterns is an important step in the classification and prediction of membrane protein folds, our method will be a helpful tool in compiling a structural census of membrane proteins.     

Improving sequence-based fold recognition by using 3D model quality assessment

MOTIVATION: The ability of a simple method (MODCHECK) to determine the sequence-structure compatibility of a set of structural models generated by fold recognition is tested in a thorough benchmark analysis. Four Model Quality Assessment Programs (MQAPs) were tested on 188 targets from the latest LiveBench-9 automated structure evaluation experiment. We systematically test and evaluate whether the MQAP methods can successfully detect native-like models. RESULTS: We show that compared with the other three methods tested MODCHECK is the most reliable method for consistently performing the best top model selection and for ranking the models. In addition, we show that the choice of model similarity score used to assess a model's similarity to the experimental structure can influence the overall performance of these tools. Although these MQAP methods fail to improve the model selection performance for methods that already incorporate protein three dimension (3D) structural information, an improvement is observed for methods that are purely sequence-based, including the best profile-profile methods. This suggests that even the best sequence-based fold recognition methods can still be improved by taking into account the 3D structural information. CONTACT: d.jones@cs.ucl.ac.uk     

A hybrid genetic-neural model for predicting protein structural classes

A genetic algorithm (GA) for feature selection in conjunction with neural network was applied to predict protein structural classes based on single amino acid and all dipeptide composition frequencies. These sequence parameters were encoded as input features for a GA in feature selection procedure and classified with a three-layered neural network to predict protein structural classes. The system was established through optimization of the classification performance of neural network which was used as evaluation function. In this study, self-consistency and jackknife tests on a database containing 498 proteins were used to verify the performance of this hybrid method, and were compared with some of prior works. The adoption of a hybrid model, which encompasses genetic and neural technologies, demonstrated to be a promising approach in the task of protein structural class prediction.     

DPANN: improved sequence to structure alignments following fold recognition

In fold recognition (FR) a protein sequence of unknown structure is assigned to the closest known three-dimensional (3D) fold. Although FR programs can often identify among all possible folds the one a sequence adopts, they frequently fail to align the sequence to the equivalent residue positions in that fold. Such failures frustrate the next step in structure prediction, protein model building. Hence it is desirable to improve the quality of the alignments between the sequence and the identified structure. We have used artificial neural networks (ANN) to derive a substitution matrix to create alignments between a protein sequence and a protein structure through dynamic programming (DPANN: Dynamic Programming meets Artificial Neural Networks). The matrix is based on the amino acid type and the secondary structure state of each residue. In a database of protein pairs that have the same fold but lack sequences-similarity, DPANN aligns over 30% of all sequences to the paired structure, resembling closely the structural superposition of the pair. In over half of these cases the DPANN alignment is close to the structural superposition, although the initial alignment from the step of fold recognition is not close. Conversely, the alignment created during fold recognition outperforms DPANN in only 10% of all cases. Thus application of DPANN after fold recognition leads to substantial improvements in alignment accuracy, which in turn provides more useful templates for the modeling of protein structures. In the artificial case of using actual instead of predicted secondary structures for the probe protein, over 50% of the alignments are successful.     

Assessing a novel approach for predicting local 3D protein structures from sequence

We developed a novel approach for predicting local protein structure from sequence. It relies on the Hybrid Protein Model (HPM), an unsupervised clustering method we previously developed. This model learns three-dimensional protein fragments encoded into a structural alphabet of 16 protein blocks (PBs). Here, we focused on 11-residue fragments encoded as a series of seven PBs and used HPM to cluster them according to their local similarities. We thus built a library of 120 overlapping prototypes (mean fragments from each cluster), with good three-dimensional local approximation, i.e., a mean accuracy of 1.61 A Calpha root-mean-square distance. Our prediction method is intended to optimize the exploitation of the sequence-structure relations deduced from this library of long protein fragments. This was achieved by setting up a system of 120 experts, each defined by logistic regression to optimize the discrimination from sequence of a given prototype relative to the others. For a target sequence window, the experts computed probabilities of sequence-structure compatibility for the prototypes and ranked them, proposing the top scorers as structural candidates. Predictions were defined as successful when a prototype <2.5 A from the true local structure was found among those proposed. Our strategy yielded a prediction rate of 51.2% for an average of 4.2 candidates per sequence window. We also proposed a confidence index to estimate prediction quality. Our approach predicts from sequence alone and will thus provide valuable information for proteins without structural homologs. Candidates will also contribute to global structure prediction by fragment assembly.     

Predicting Protein Function and Binding Profile via Matching of Local Evolutionary and Geometric Surface Patterns

Inferring protein functions from structures is a challenging task, as a large number of orphan protein structures from structural genomics project are now solved without their biochemical functions characterized. For proteins binding to similar substrates or ligands and carrying out similar functions, their binding surfaces are under similar physicochemical constraints, and hence the sets of allowed and forbidden residue substitutions are similar. However, it is difficult to isolate such selection pressure due to protein function from selection pressure due to protein folding, and evolutionary relationship reflected by global sequence and structure similarities between proteins is often unreliable for inferring protein function. We have developed a method, called pevoSOAR (pocket-based evolutionary search of amino acid residues), for predicting protein functions by solving the problem of uncovering amino acids residue substitution pattern due to protein function and separating it from amino acids substitution pattern due to protein folding. We incorporate evolutionary information specific to an individual binding region and match local surfaces on a large scale with millions of precomputed protein surfaces to identify those with similar functions. Our pevoSOAR method also generates a probablistic model called the computed binding a profile that characterizes protein-binding activities that may involve multiple substrates or ligands. We show that our method can be used to predict enzyme functions with accuracy. Our method can also assess enzyme binding specificity and promiscuity. In an objective large-scale test of 100 enzyme families with thousands of structures, our predictions are found to be sensitive and specific: At the stringent specificity level of 99.98%, we can correctly predict enzyme functions for 80.55% of the proteins. The overall area under the receiver operating characteristic curve measuring the performance of our prediction is 0.955, close to the perfect value of 1.00. The best Matthews coefficient is 86.6%. Our method also works well in predicting the biochemical functions of orphan proteins from structural genomics projects.     

Learning the local landscape of protein structures with convolutional neural networks

One fundamental problem of protein biochemistry is to predict protein structure from amino acid sequence. The inverse problem, predicting either entire sequences or individual mutations that are consistent with a given protein structure, has received much less attention even though it has important applications in both protein engineering and evolutionary biology. Here, we ask whether 3D convolutional neural networks (3D CNNs) can learn the local fitness landscape of protein structure to reliably predict either the wild-type amino acid or the consensus in a multiple sequence alignment from the local structural context surrounding site of interest. We find that the network can predict wild type with good accuracy, and that network confidence is a reliable measure of whether a given prediction is likely going to be correct or not. Predictions of consensus are less accurate and are primarily driven by whether or not the consensus matches the wild type. Our work suggests that high-confidence mis-predictions of the wild type may identify sites that are primed for mutation and likely targets for protein engineering.

     

Role of context in the relationship between form and function: structural plasticity of some PROSITE patterns

True positive hits of PROSITE sequence pattern are expected to have a characteristic three-dimensional structure. The combined sequence-structure attributes of PROSITE patterns can be used for function prediction of an uncharacterized protein with known primary and 3D structure, a situation that might arise in structural genomics projects. We have found specific examples of true hits of PROSITE patterns displaying structural plasticity by assuming significantly different local conformation, depending upon the context. Our work highlights the importance of taking into account all the known distinct conformations of PROSITE patterns, while creating a sensitive 3D template for the pattern, for use in functional annotation.     

Sequence-structure specificity of a knowledge based energy function at the secondary structure level

MOTIVATION: This paper investigates the sequence-structure specificity of a representative knowledge based energy function by applying it to threading at the level of secondary structures of proteins. Assessing the strengths and weaknesses of an energy function at this fundamental level provides more detailed and insightful information than at the tertiary structure level and the results obtained can be useful in tertiary level threading. RESULTS: We threaded each of the 293 non-redundant proteins onto the secondary structures contained in its respective native protein (host template). We also used 68 pairs of proteins with similar folds and low sequence identity. For each pair, we threaded the sequence of one protein onto the secondary structures of the other protein. The discerning power of the total energy function and its one-body, pairwise, and mutation components is studied. We then applied our energy function to a recent study which demonstrated how a designed 11-amino acid sequence can replace distinct segments (one segment is an alpha-helix, the other is a beta-sheet) of a protein without changing its fold. We conducted random mutations of the designed sequence to determine the patterns for favorable mutations. We also studied the sequence-structure specificity at the boundaries of a secondary structure. Finally, we demonstrated how to speed up tertiary level threading by filtering out alignments found to be energetically unfavorable during the secondary structure threading. AVAILABILITY: The program is available on request from the authors. CONTACT: xud@ornl.gov     

Con-Struct Map: a comparative contact map analysis tool

Con-Struct Map is a graphical tool for the comparative study of protein structures. The tool detects potential conserved residue contacts shared by multiple protein structures by superimposing their contact maps according to a multiple structure alignment. In general, Con-Struct Map allows the study of structural changes resulting from, e.g. sequence substitutions, or alternatively, the study of conserved components of a structure framework across structurally aligned proteins. Specific applications include the study of sequence-structure relationship in distantly related proteins and the comparisons of wild type and mutant proteins. AVAILABILITY: http://pdbrs3.sdsc.edu/ConStructMap/viewer_argument_generator/singleArguments. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.     

Comprehensive mutagenesis of HIV-1 protease: a computational geometry approach

A computational geometry technique based on Delaunay tessellation of protein structure, represented by C(alpha) atoms, is used to study effects of single residue mutations on sequence-structure compatibility in HIV-1 protease. Profiles of residue scores derived from the four-body statistical potential are constructed for all 1881 mutants of the HIV-1 protease monomer and compared with the profile of the wild-type protein. The profiles for an isolated monomer of HIV-1 protease and the identical monomer in a dimeric state with an inhibitor are analyzed to elucidate changes to structural stability. Protease residues shown to undergo the greatest impact are those forming the dimer interface and flap region, as well as those known to be involved in inhibitor binding.     

支持向量机方法预测蛋白质结构中的二硫键

在蛋白质结构预测的研究中,一个重要的问题就是正确预测二硫键的连接,二硫键的准确预测可以减少蛋白质构像的搜索空间,有利于蛋白质3D结构的预测,本文将预测二硫键的连接问题转化成对连接模式的分类问题,并成功地将支持向量机方法引入到预测工作中。通过对半胱氨酸局域序列连接模式的分类预测,可以由蛋白质的一级结构序列预测该蛋白质的二硫键的连接。结果表明蛋白质的二硫键的连接与半胱氨酸局域序列连接模式有重要联系,应用支持向量机方法对蛋白质结构的二硫键预测取得了良好的结果。     

基于CNN与LSTM模型的蛋白质二级结构预测

蛋白质结构的预测在理解蛋白质结构组成和蛋白质的生物学功能有重要意义,而蛋白质二级结构预测是蛋白质结构预测的重要环节。当PSSM位置特异性进化矩阵被广泛应用于将蛋白质初级结构序列编码作为输入样本后,每个残基可以被表示成二维空间的数据平面,由此文中尝试利用卷积神经网络对其进行训练。文中还设计了另一种卷积神经网络,利用长短记忆网络感知了CNN最后卷积特征面的横向特征和纵向特征后连同卷积神经网络的全连接共同完成分类,最后用ensemble方法对两类卷积神经网络模型进行了整合,最终ensemble方法中包含两类卷积神经网络的六个模型,在CB513蛋白质数据集测得的Q3结果为77.2。     

The impact of extremophiles on structural genomics (and vice versa)

The advent of the complete genome sequences of various organisms in the mid-1990s raised the issue of how one could determine the function of hypothetical proteins. While insight might be obtained from a 3D structure, the chances of being able to predict such a structure is limited for the deduced amino acid sequence of any uncharacterized gene. A template for modeling is required, but there was only a low probability of finding a protein closely-related in sequence with an available structure. Thus, in the late 1990s, an international effort known as structural genomics (SG) was initiated, its primary goal to “fill sequence-structure space” by determining the 3D structures of representatives of all known protein families. This was to be achieved mainly by X-ray crystallography and it was estimated that at least 5,000 new structures would be required. While the proteins (genes) for SG have subsequently been derived from hundreds of different organisms, extremophiles and particularly thermophiles have been specifically targeted due to the increased stability and ease of handling of their proteins, relative to those from mesophiles. This review summarizes the significant impact that extremophiles and proteins derived from them have had on SG projects worldwide. To what extent SG has influenced the field of extremophile research is also discussed.     

RCNPRED: prediction of the residue co-ordination numbers in proteins

The RCNPRED server implements a neural network-based method to predict the co-ordination numbers of residues starting from the protein sequence. Using evolutionary information as input, RCNPRED predicts the residue states of the proteins in the database with 69% accuracy and scores 12 percentage points higher than a simple statistical method. Moreover the server implements a neural network to predict the relative solvent accessibility of each residue. A protein sequence can be directly submitted to RCNPRED: residue co-ordination numbers and solvent accessibility for each chain are returned via e-mail. AVAILABILITY: Freely available to non-commercial users at http://prion.biocomp.unibo.it/rcnpred.html.     

A combinatorial toolbox for protein sequence design and landscape analysis in the grand canonical model.

In modern biology, one of the most important research problems is to understand how protein sequences fold into their native 3D structures. To investigate this problem at a high level, one wishes to analyze the protein landscapes, i.e., the structures of the space of all protein sequences and their native 3D structures. Perhaps the most basic computational problem at this level is to take a target 3D structure as input and design a fittest protein sequence with respect to one or more fitness functions of the target 3D structure. We develop a toolbox of combinatorial techniques for protein landscape analysis in the Grand Canonical model of Sun, Brem, Chan, and Dill. The toolbox is based on linear programming, network flow, and a linear-size representation of all minimum cuts of a network. It not only substantially expands the network flow technique for protein sequence design in Kleinberg's seminal work but also is applicable to a considerably broader collection of computational problems than those considered by Kleinberg. We have used this toolbox to obtain a number of efficient algorithms and hardness results. We have further used the algorithms to analyze 3D structures drawn from the Protein Data Bank and have discovered some novel relationships between such native 3D structures and the Grand Canonical model.