Improving contact predictions by the combination of correlated mutations and other sources of sequence information

General strategies for using amino acid sequence data to guide biochemical investigation of protein function

The rapid increase of '-omics' data warrants the reconsideration of experimental strategies to investigate general protein function. Studying individual members of a protein family is likely insufficient to provide a complete mechanistic understanding of family functions, especially for diverse families with thousands of known members. Strategies that exploit large amounts of available amino acid sequence data can inspire and guide biochemical experiments, generating broadly applicable insights into a given family. Here we review several methods that utilize abundant sequence data to focus experimental efforts and identify features truly representative of a protein family or domain. First, coevolutionary relationships between residues within primary sequences can be successfully exploited to identify structurally and/or functionally important positions for experimental investigation. Second, functionally important variable residue positions typically occupy a limited sequence space, a property useful for guiding biochemical characterization of the effects of the most physiologically and evolutionarily relevant amino acids. Third, amino acid sequence variation within domains shared between different protein families can be used to sort a particular domain into multiple subtypes, inspiring further experimental designs. Although generally applicable to any kind of protein domain because they depend solely on amino acid sequences, the second and third approaches are reviewed in detail because they appear to have been used infrequently and offer immediate opportunities for new advances. Finally, we speculate that future technologies capable of analyzing and manipulating conserved and variable aspects of the three-dimensional structures of a protein family could lead to broad insights not attainable by current methods.

AlphaFold 2: Why It Works and Its Implications for Understanding the Relationships of Protein Sequence, Structure, and Function

AlphaFold 2 (AF2) was the star of CASP14, the last biannual structure prediction experiment. Using novel deep learning, AF2 predicted the structures of many difficult protein targets at or near experimental resolution. Here, we present our perspective of why AF2 works and show that it is a very sophisticated fold recognition algorithm that exploits the completeness of the library of single domain PDB structures. It has also learned local side chain packing rearrangements that enable it to refine proteins to high resolution. The benefits and limitations of its ability to predict the structures of many more proteins at or close to atomic detail are discussed.

Assessing the accuracy of contact and distance predictions in CASP14

We present the results of the assessment of the intramolecular residue-residue contact and distance predictions from groups participating in the 14th round of the CASP experiment. The performance of contact prediction methods was evaluated with the measures used in previous CASPs, while distance predictions were assessed based on a new protocol, which considers individual distance pairs as well as the whole predicted distance matrix, using a graph-based framework. The results of the evaluation indicate that predictions by the tFold framework, TripletRes and DeepPotential were the most accurate in both categories. With regards to progress in method performance, the results of the assessment in contact prediction did not reveal any discernible difference when compared to CASP13. Arguably, this could be due to CASP14 FM targets being more challenging than ever before.

Rheostat functional outcomes occur when substitutions are introduced at nonconserved positions that diverge with speciation

When amino acids vary during evolution, the outcome can be functionally neutral or biologically-important. We previously found that substituting a subset of nonconserved positions, "rheostat" positions, can have surprising effects on protein function. Since changes at rheostat positions can facilitate functional evolution or cause disease, more examples are needed to understand their unique biophysical characteristics. Here, we explored whether "phylogenetic" patterns of change in multiple sequence alignments (such as positions with subfamily specific conservation) predict the locations of functional rheostat positions. To that end, we experimentally tested eight phylogenetic positions in human liver pyruvate kinase (hLPYK), using 10-15 substitutions per position and biochemical assays that yielded five functional parameters. Five positions were strongly rheostatic and three were non-neutral. To test the corollary that positions with low phylogenetic scores were not rheostat positions, we combined these phylogenetic positions with previously-identified hLPYK rheostat, "toggle" (most substitution abolished function), and "neutral" (all substitutions were like wild-type) positions. Despite representing 428 variants, this set of 33 positions was poorly statistically powered. Thus, we turned to the in vivo phenotypic dataset for E. coli lactose repressor protein (LacI), which comprised 12-13 substitutions at 329 positions and could be used to identify rheostat, toggle, and neutral positions. Combined hLPYK and LacI results show that positions with strong phylogenetic patterns of change are more likely to exhibit rheostat substitution outcomes than neutral or toggle outcomes. Furthermore, phylogenetic patterns were more successful at identifying rheostat positions than were co-evolutionary or eigenvector centrality measures of evolutionary change.

Identification of biochemically neutral positions in liver pyruvate kinase

Understanding how each residue position contributes to protein function has been a long-standing goal in protein science. Substitution studies have historically focused on conserved protein positions. However, substitutions of nonconserved positions can also modify function. Indeed, we recently identified nonconserved positions that have large substitution effects in human liver pyruvate kinase (hLPYK), including altered allosteric coupling. To facilitate a comparison of which characteristics determine when a nonconserved position does vs does not contribute to function, the goal of the current work was to identify neutral positions in hLPYK. However, existing hLPYK data showed that three features commonly associated with neutral positions-high sequence entropy, high surface exposure, and alanine scanning-lacked the sensitivity needed to guide experimental studies. We used multiple evolutionary patterns identified in a sequence alignment of the PYK family to identify which positions were least patterned, reasoning that these were most likely to be neutral. Nine positions were tested with a total of 117 amino acid substitutions. Although exploring all potential functions is not feasible for any protein, five parameters associated with substrate/effector affinities and allosteric coupling were measured for hLPYK variants. For each position, the aggregate functional outcomes of all variants were used to quantify a "neutrality" score. Three positions showed perfect neutral scores for all five parameters. Furthermore, the nine positions showed larger neutral scores than 17 positions located near allosteric binding sites. Thus, our strategy successfully enriched the dataset for positions with neutral and modest substitutions.

Protein Inter-Residue Contacts Prediction: Methods, Performances and Applications

Background:

Protein inter-residue contacts prediction play an important role in the field of protein structure and function research. As a low-dimensional representation of protein tertiary structure, protein inter-residue contacts could greatly help de novo protein structure prediction methods to reduce the conformational search space. Over the past two decades, various methods have been developed for protein inter-residue contacts prediction.

Objective:

We provide a comprehensive and systematic review of protein inter-residue contacts prediction methods.

Results:

Protein inter-residue contacts prediction methods are roughly classified into five categories: correlated mutations methods, machine-learning methods, fusion methods, templatebased methods and 3D model-based methods. In this paper, firstly we describe the common definition of protein inter-residue contacts and show the typical application of protein inter-residue contacts. Then, we present a comprehensive review of the three main categories for protein interresidue contacts prediction: correlated mutations methods, machine-learning methods and fusion methods. Besides, we analyze the constraints for each category. Furthermore, we compare several representative methods on the CASP11 dataset and discuss performances of these methods in detail.

Conclusion:

Correlated mutations methods achieve better performances for long-range contacts, while the machine-learning method performs well for short-range contacts. Fusion methods could take advantage of the machine-learning and correlated mutations methods. Employing more effective fusion strategy could be helpful to further improve the performances of fusion methods.

A large-scale comparative assessment of methods for residue-residue contact prediction

Sequence-based prediction of residue-residue contact in proteins becomes increasingly more important for improving protein structure prediction in the big data era. In this study, we performed a large-scale comparative assessment of 15 locally installed contact predictors. To assess these methods, we collected a big data set consisting of 680 nonredundant proteins covering different structural classes and target difficulties. We investigated a wide range of factors that may influence the precision of contact prediction, including target difficulty, structural class, the alignment depth and distribution of contact pairs in a protein structure. We found that: (1) the machine learning-based methods outperform the direct-coupling-based methods for short-range contact prediction, while the latter are significantly better for long-range contact prediction. The consensus-based methods, which combine machine learning and direct-coupling methods, perform the best. (2) The target difficulty does not have clear influence on the machine learning-based methods, while it does affect the direct-coupling and consensus-based methods significantly. (3) The alignment depth has relatively weak effect on the machine learning-based methods. However, for the direct-coupling-based methods and consensus-based methods, the predicted contacts for targets with deeper alignment tend to be more accurate. (4) All methods perform relatively better on β and α + β proteins than on α proteins. (5) Residues buried in the core of protein structure are more prone to be in contact than residues on the surface (22 versus 6%). We believe these are useful results for guiding future development of new approach to contact prediction.

Recent advances in sequence-based protein structure prediction

The most accurate characterizations of the structure of proteins are provided by structural biology experiments. However, because of the high cost and labor-intensive nature of the structural experiments, the gap between the number of protein sequences and solved structures is widening rapidly. Development of computational methods to accurately model protein structures from sequences is becoming increasingly important to the biological community. In this article, we highlight some important progress in the field of protein structure prediction, especially those related to free modeling (FM) methods that generate structure models without using homologous templates. We also provide a short synopsis of some of the recent advances in FM approaches as demonstrated in the recent Computational Assessment of Structure Prediction competition as well as recent trends and outlook for FM approaches in protein structure prediction.

Deep Learning in Biomedical Data Science

Since the 1980s, deep learning and biomedical data have been coevolving and feeding each other. The breadth, complexity, and rapidly expanding size of biomedical data have stimulated the development of novel deep learning methods, and application of these methods to biomedical data have led to scientific discoveries and practical solutions. This overview provides technical and historical pointers to the field, and surveys current applications of deep learning to biomedical data organized around five subareas, roughly of increasing spatial scale: chemoinformatics, proteomics, genomics and transcriptomics, biomedical imaging, and health care. The black box problem of deep learning methods is also briefly discussed.

Contact prediction is hardest for the most informative contacts, but improves with the incorporation of contact potentials

Co-evolution between pairs of residues in a multiple sequence alignment (MSA) of homologous proteins has long been proposed as an indicator of structural contacts. Recently, several methods, such as direct-coupling analysis (DCA) and MetaPSICOV, have been shown to achieve impressive rates of contact prediction by taking advantage of considerable sequence data. In this paper, we show that prediction success rates are highly sensitive to the structural definition of a contact, with more permissive definitions (i.e., those classifying more pairs as true contacts) naturally leading to higher positive predictive rates, but at the expense of the amount of structural information contributed by each contact. Thus, the remaining limitations of contact prediction algorithms are most noticeable in conjunction with geometrically restrictive contacts—precisely those that contribute more information in structure prediction. We suggest that to improve prediction rates for such “informative” contacts one could combine co-evolution scores with additional indicators of contact likelihood. Specifically, we find that when a pair of co-varying positions in an MSA is occupied by residue pairs with favorable statistical contact energies, that pair is more likely to represent a true contact. We show that combining a contact potential metric with DCA or MetaPSICOV performs considerably better than DCA or MetaPSICOV alone, respectively. This is true regardless of contact definition, but especially true for stricter and more informative contact definitions. In summary, this work outlines some remaining challenges to be addressed in contact prediction and proposes and validates a promising direction towards improvement.

Finding the needle in the haystack: towards solving the protein-folding problem computationally

Prediction of protein tertiary structures from amino acid sequence and understanding the mechanisms of how proteins fold, collectively known as "the protein folding problem," has been a grand challenge in molecular biology for over half a century. Theories have been developed that provide us with an unprecedented understanding of protein folding mechanisms. However, computational simulation of protein folding is still difficult, and prediction of protein tertiary structure from amino acid sequence is an unsolved problem. Progress toward a satisfying solution has been slow due to challenges in sampling the vast conformational space and deriving sufficiently accurate energy functions. Nevertheless, several techniques and algorithms have been adopted to overcome these challenges, and the last two decades have seen exciting advances in enhanced sampling algorithms, computational power and tertiary structure prediction methodologies. This review aims at summarizing these computational techniques, specifically conformational sampling algorithms and energy approximations that have been frequently used to study protein-folding mechanisms or to de novo predict protein tertiary structures. We hope that this review can serve as an overview on how the protein-folding problem can be studied computationally and, in cases where experimental approaches are prohibitive, help the researcher choose the most relevant computational approach for the problem at hand. We conclude with a summary of current challenges faced and an outlook on potential future directions.

RRCRank: a fusion method using rank strategy for residue-residue contact prediction

Background

In structural biology area, protein residue-residue contacts play a crucial role in protein structure prediction. Some researchers have found that the predicted residue-residue contacts could effectively constrain the conformational search space, which is significant for de novo protein structure prediction. In the last few decades, related researchers have developed various methods to predict residue-residue contacts, especially, significant performance has been achieved by using fusion methods in recent years. In this work, a novel fusion method based on rank strategy has been proposed to predict contacts. Unlike the traditional regression or classification strategies, the contact prediction task is regarded as a ranking task. First, two kinds of features are extracted from correlated mutations methods and ensemble machine-learning classifiers, and then the proposed method uses the learning-to-rank algorithm to predict contact probability of each residue pair.

Results

First, we perform two benchmark tests for the proposed fusion method (RRCRank) on CASP11 dataset and CASP12 dataset respectively. The test results show that the RRCRank method outperforms other well-developed methods, especially for medium and short range contacts. Second, in order to verify the superiority of ranking strategy, we predict contacts by using the traditional regression and classification strategies based on the same features as ranking strategy. Compared with these two traditional strategies, the proposed ranking strategy shows better performance for three contact types, in particular for long range contacts. Third, the proposed RRCRank has been compared with several state-of-the-art methods in CASP11 and CASP12. The results show that the RRCRank could achieve comparable prediction precisions and is better than three methods in most assessment metrics.

Conclusions

The learning-to-rank algorithm is introduced to develop a novel rank-based method for the residue-residue contact prediction of proteins, which achieves state-of-the-art performance based on the extensive assessment.

Electronic supplementary material

The online version of this article (10.1186/s12859-017-1811-9) contains supplementary material, which is available to authorized users.

Co-evolution techniques are reshaping the way we do structural bioinformatics

Co-evolution techniques were originally conceived to assist in protein structure prediction by inferring pairs of residues that share spatial proximity. However, the functional relationships that can be extrapolated from co-evolution have also proven to be useful in a wide array of structural bioinformatics applications. These techniques are a powerful way to extract structural and functional information in a sequence-rich world.

Improving protein-protein interaction prediction using evolutionary information from low-quality MSAs

Evolutionary information stored in multiple sequence alignments (MSAs) has been used to identify the interaction interface of protein complexes, by measuring either co-conservation or co-mutation of amino acid residues across the interface. Recently, maximum entropy related correlated mutation measures (CMMs) such as direct information, decoupling direct from indirect interactions, have been developed to identify residue pairs interacting across the protein complex interface. These studies have focussed on carefully selected protein complexes with large, good-quality MSAs. In this work, we study protein complexes with a more typical MSA consisting of fewer than 400 sequences, using a set of 79 intramolecular protein complexes. Using a maximum entropy based CMM at the residue level, we develop an interface level CMM score to be used in re-ranking docking decoys. We demonstrate that our interface level CMM score compares favourably to the complementarity trace score, an evolutionary information-based score measuring co-conservation, when combined with the number of interface residues, a knowledge-based potential and the variability score of individual amino acid sites. We also demonstrate, that, since co-mutation and co-complementarity in the MSA contain orthogonal information, the best prediction performance using evolutionary information can be achieved by combining the co-mutation information of the CMM with co-conservation information of a complementarity trace score, predicting a near-native structure as the top prediction for 41% of the dataset. The method presented is not restricted to small MSAs, and will likely improve interface prediction also for complexes with large and good-quality MSAs.

Emerging Computational Methods for the Rational Discovery of Allosteric Drugs

Allosteric drug development holds promise for delivering medicines that are more selective and less toxic than those that target orthosteric sites. To date, the discovery of allosteric binding sites and lead compounds has been mostly serendipitous, achieved through high-throughput screening. Over the past decade, structural data has become more readily available for larger protein systems and more membrane protein classes (e.g., GPCRs and ion channels), which are common allosteric drug targets. In parallel, improved simulation methods now provide better atomistic understanding of the protein dynamics and cooperative motions that are critical to allosteric mechanisms. As a result of these advances, the field of predictive allosteric drug development is now on the cusp of a new era of rational structure-based computational methods. Here, we review algorithms that predict allosteric sites based on sequence data and molecular dynamics simulations, describe tools that assess the druggability of these pockets, and discuss how Markov state models and topology analyses provide insight into the relationship between protein dynamics and allosteric drug binding. In each section, we first provide an overview of the various method classes before describing relevant algorithms and software packages.

Protein Residue Contacts and Prediction Methods

In the field of computational structural proteomics, contact predictions have shown new prospects of solving the longstanding problem of ab initio protein structure prediction. In the last few years, application of deep learning algorithms and availability of large protein sequence databases, combined with improvement in methods that derive contacts from multiple sequence alignments, have shown a huge increase in the precision of contact prediction. In addition, these predicted contacts have also been used to build three-dimensional models from scratch.In this chapter, we briefly discuss many elements of protein residue-residue contacts and the methods available for prediction, focusing on a state-of-the-art contact prediction tool, DNcon. Illustrating with a case study, we describe how DNcon can be used to make ab initio contact predictions for a given protein sequence and discuss how the predicted contacts may be analyzed and evaluated.

Amino acid positions subject to multiple coevolutionary constraints can be robustly identified by their eigenvector network centrality scores

As proteins evolve, amino acid positions key to protein structure or function are subject to mutational constraints. These positions can be detected by analyzing sequence families for amino acid conservation or for coevolution between pairs of positions. Coevolutionary scores are usually rank-ordered and thresholded to reveal the top pairwise scores, but they also can be treated as weighted networks. Here, we used network analyses to bypass a major complication of coevolution studies: For a given sequence alignment, alternative algorithms usually identify different, top pairwise scores. We reconciled results from five commonly-used, mathematically divergent algorithms (ELSC, McBASC, OMES, SCA, and ZNMI), using the LacI/GalR and 1,6-bisphosphate aldolase protein families as models. Calculations used unthresholded coevolution scores from which column-specific properties such as sequence entropy and random noise were subtracted; "central" positions were identified by calculating various network centrality scores. When compared among algorithms, network centrality methods, particularly eigenvector centrality, showed markedly better agreement than comparisons of the top pairwise scores. Positions with large centrality scores occurred at key structural locations and/or were functionally sensitive to mutations. Further, the top central positions often differed from those with top pairwise coevolution scores: instead of a few strong scores, central positions often had multiple, moderate scores. We conclude that eigenvector centrality calculations reveal a robust evolutionary pattern of constraints-detectable by divergent algorithms--that occur at key protein locations. Finally, we discuss the fact that multiple patterns coexist in evolutionary data that, together, give rise to emergent protein functions.

Improving accuracy of protein contact prediction using balanced network deconvolution

Residue contact map is essential for protein three-dimensional structure determination. But most of the current contact prediction methods based on residue co-evolution suffer from high false-positives as introduced by indirect and transitive contacts (i.e., residues A-B and B-C are in contact, but A-C are not). Built on the work by Feizi et al. (Nat Biotechnol 2013; 31:726-733), which demonstrated a general network model to distinguish direct dependencies by network deconvolution, this study presents a new balanced network deconvolution (BND) algorithm to identify optimized dependency matrix without limit on the eigenvalue range in the applied network systems. The algorithm was used to filter contact predictions of five widely used co-evolution methods. On the test of proteins from three benchmark datasets of the 9th critical assessment of protein structure prediction (CASP9), CASP10, and PSICOV (precise structural contact prediction using sparse inverse covariance estimation) database experiments, the BND can improve the medium- and long-range contact predictions at the L/5 cutoff by 55.59% and 47.68%, respectively, without additional central processing unit cost. The improvement is statistically significant, with a P-value < 5.93 × 10(-3) in the Student's t-test. A further comparison with the ab initio structure predictions in CASPs showed that the usefulness of the current co-evolution-based contact prediction to the three-dimensional structure modeling relies on the number of homologous sequences existing in the sequence databases. BND can be used as a general contact refinement method, which is freely available at: http://www.csbio.sjtu.edu.cn/bioinf/BND/.

Quality assessment of modeled protein structure using physicochemical properties

Physicochemical properties of proteins always guide to determine the quality of the protein structure, therefore it has been rigorously used to distinguish native or native-like structure from other predicted structures. In this work, we explore nine machine learning methods with six physicochemical properties to predict the Root Mean Square Deviation (RMSD), Template Modeling (TM-score), and Global Distance Test (GDT_TS-score) of modeled protein structure in the absence of its true native state. Physicochemical properties namely total surface area, euclidean distance (ED), total empirical energy, secondary structure penalty (SS), sequence length (SL), and pair number (PN) are used. There are a total of 95,091 modeled structures of 4896 native targets. A real coded Self-adaptive Differential Evolution algorithm (SaDE) is used to determine the feature importance. The K-fold cross validation is used to measure the robustness of the best predictive method. Through the intensive experiments, it is found that Random Forest method outperforms over other machine learning methods. This work makes the prediction faster and inexpensive. The performance result shows the prediction of RMSD, TM-score, and GDT_TS-score on Root Mean Square Error (RMSE) as 1.20, 0.06, and 0.06 respectively; correlation scores are 0.96, 0.92, and 0.91 respectively; R(2) are 0.92, 0.85, and 0.84 respectively; and accuracy are 78.82% (with ± 0.1 err), 86.56% (with ± 0.1 err), and 87.37% (with ± 0.1 err) respectively on the testing data set. The data set used in the study is available as supplement at http://bit.ly/RF-PCP-DataSets.

De novo structure prediction of globular proteins aided by sequence variation-derived contacts

The advent of high accuracy residue-residue intra-protein contact prediction methods enabled a significant boost in the quality of de novo structure predictions. Here, we investigate the potential benefits of combining a well-established fragment-based folding algorithm--FRAGFOLD, with PSICOV, a contact prediction method which uses sparse inverse covariance estimation to identify co-varying sites in multiple sequence alignments. Using a comprehensive set of 150 diverse globular target proteins, up to 266 amino acids in length, we are able to address the effectiveness and some limitations of such approaches to globular proteins in practice. Overall we find that using fragment assembly with both statistical potentials and predicted contacts is significantly better than either statistical potentials or contacts alone. Results show up to nearly 80% of correct predictions (TM-score ≥0.5) within analysed dataset and a mean TM-score of 0.54. Unsuccessful modelling cases emerged either from conformational sampling problems, or insufficient contact prediction accuracy. Nevertheless, a strong dependency of the quality of final models on the fraction of satisfied predicted long-range contacts was observed. This not only highlights the importance of these contacts on determining the protein fold, but also (combined with other ensemble-derived qualities) provides a powerful guide as to the choice of correct models and the global quality of the selected model. A proposed quality assessment scoring function achieves 0.93 precision and 0.77 recall for the discrimination of correct folds on our dataset of decoys. These findings suggest the approach is well-suited for blind predictions on a variety of globular proteins of unknown 3D structure, provided that enough homologous sequences are available to construct a large and accurate multiple sequence alignment for the initial contact prediction step.

Multiple co-evolutionary networks are supported by the common tertiary scaffold of the LacI/GalR proteins

Protein families might evolve paralogous functions on their common tertiary scaffold in two ways. First, the locations of functionally-important sites might be "hard-wired" into the structure, with novel functions evolved by altering the amino acid (e.g. Ala vs Ser) at these positions. Alternatively, the tertiary scaffold might be adaptable, accommodating a unique set of functionally important sites for each paralogous function. To discriminate between these possibilities, we compared the set of functionally important sites in the six largest paralogous subfamilies of the LacI/GalR transcription repressor family. LacI/GalR paralogs share a common tertiary structure, but have low sequence identity (≤ 30%), and regulate a variety of metabolic processes. Functionally important positions were identified by conservation and co-evolutionary sequence analyses. Results showed that conserved positions use a mixture of the "hard-wired" and "accommodating" scaffold frameworks, but that the co-evolution networks were highly dissimilar between any pair of subfamilies. Therefore, the tertiary structure can accommodate multiple networks of functionally important positions. This possibility should be included when designing and interpreting sequence analyses of other protein families. Software implementing conservation and co-evolution analyses is available at https://sourceforge.net/projects/coevolutils/.

Predicting protein contact map using evolutionary and physical constraints by integer programming

Motivation: Protein contact map describes the pairwise spatial and functional relationship of residues in a protein and contains key information for protein 3D structure prediction. Although studied extensively, it remains challenging to predict contact map using only sequence information. Most existing methods predict the contact map matrix element-by-element, ignoring correlation among contacts and physical feasibility of the whole-contact map. A couple of recent methods predict contact map by using mutual information, taking into consideration contact correlation and enforcing a sparsity restraint, but these methods demand for a very large number of sequence homologs for the protein under consideration and the resultant contact map may be still physically infeasible.

Results: This article presents a novel method PhyCMAP for contact map prediction, integrating both evolutionary and physical restraints by machine learning and integer linear programming. The evolutionary restraints are much more informative than mutual information, and the physical restraints specify more concrete relationship among contacts than the sparsity restraint. As such, our method greatly reduces the solution space of the contact map matrix and, thus, significantly improves prediction accuracy. Experimental results confirm that PhyCMAP outperforms currently popular methods no matter how many sequence homologs are available for the protein under consideration.

Availability:http://raptorx.uchicago.edu.

Contact:jinboxu@gmail.com

A new formulation of protein evolutionary models that account for structural constraints

Despite the importance of a thermodynamically stable structure with a conserved fold for protein function, almost all evolutionary models neglect site-site correlations that arise from physical interactions between neighboring amino acid sites. This is mainly due to the difficulty in formulating a computationally tractable model since rate matrices can no longer be used. Here, we introduce a general framework, based on factor graphs, for constructing probabilistic models of protein evolution with site interdependence. Conveniently, efficient approximate inference algorithms, such as Belief Propagation, can be used to calculate likelihoods for these models. We fit an amino acid substitution model of this type that accounts for both solvent accessibility and site-site correlations. Comparisons of the new model with rate matrix models and alternative structure-dependent models demonstrate that it better fits the sequence data. We also examine evolution within a family of homohexameric enzymes and find that site-site correlations between most contacting subunits contribute to a higher likelihood. In addition, we show that the new substitution model has a similar mathematical form to the one introduced in Rodrigue et al. (Rodrigue N, Lartillot N, Bryant D, Philippe H. 2005. Site interdependence attributed to tertiary structure in amino acid sequence evolution. Gene 347:207-217), although with different parameter interpretations and values. We also perform a statistical analysis of the effects of amino acids at neighboring sites on substitution probabilities and find a significant perturbation of most probabilities, further supporting the significant role of site-site interactions in protein evolution and motivating the development of new evolutionary models similar to the one described here. Finally, we discuss possible extensions and applications of the new substitution model.

A study and benchmark of DNcon: a method for protein residue-residue contact prediction using deep networks

BACKGROUND

In recent years, the use and importance of predicted protein residue-residue contacts has grown considerably with demonstrated applications such as drug design, protein tertiary structure prediction and model quality assessment. Nevertheless, reported accuracies in the range of 25-35% stubbornly remain the norm for sequence based, long range contact predictions on hard targets. This is in spite of a prolonged effort on behalf of the community to improve the performance of residue-residue contact prediction. A thorough study of the quality of current residue-residue contact predictions and the evaluation metrics used as well as an analysis of current methods is needed to stimulate further advancement in contact prediction and its application. Such a study will better explain the quality and nature of residue-residue contact predictions generated by current methods and as a result lead to better use of this contact information.

RESULTS

We evaluated several sequence based residue-residue contact predictors that participated in the tenth Critical Assessment of protein Structure Prediction (CASP) experiment. The evaluation was performed using standard assessment techniques such as those used by the official CASP assessors as well as two novel evaluation metrics (i.e., cluster accuracy and cluster count). An in-depth analysis revealed that while most residue-residue contact predictions generated are not accurate at the residue level, there is quite a strong contact signal present when allowing for less than residue level precision. Our residue-residue contact predictor, DNcon, performed particularly well achieving an accuracy of 66% for the top L/10 long range contacts when evaluated in a neighbourhood of size 2. The coverage of residue-residue contact areas was also greater with DNcon when compared to other methods. We also provide an analysis of DNcon with respect to its underlying architecture and features used for classification.

CONCLUSIONS

Our novel evaluation metrics demonstrate that current residue-residue contact predictions do contain a strong contact signal and are of better quality than standard evaluation metrics indicate. Our method, DNcon, is a robust, state-of-the-art residue-residue sequence based contact predictor and excelled under a number of evaluation schemes. It is available as a web service at http://iris.rnet.missouri.edu/dncon/.

BCov: a method for predicting β-sheet topology using sparse inverse covariance estimation and integer programming

MOTIVATION

Prediction of protein residue contacts, even at the coarse-grain level, can help in finding solutions to the protein structure prediction problem. Unlike α-helices that are locally stabilized, β-sheets result from pairwise hydrogen bonding of two or more disjoint regions of the protein backbone. The problem of predicting contacts among β-strands in proteins has been addressed by several supervised computational approaches. Recently, prediction of residue contacts based on correlated mutations has been greatly improved and finally allows the prediction of 3D structures of the proteins.

RESULTS

In this article, we describe BCov, which is the first unsupervised method to predict the β-sheet topology starting from the protein sequence and its secondary structure. BCov takes advantage of the sparse inverse covariance estimation to define β-strand partner scores. Then an optimization based on integer programming is carried out to predict the β-sheet connectivity. When tested on the prediction of β-strand pairing, BCov scores with average values of Matthews Correlation Coefficient (MCC) and F1 equal to 0.56 and 0.61, respectively, on a non-redundant dataset of 916 protein chains known with atomic resolution. Our approach well compares with the state-of-the-art methods trained so far for this specific task.

AVAILABILITY AND IMPLEMENTATION

The method is freely available under General Public License at http://biocomp.unibo.it/savojard/bcov/bcov-1.0.tar.gz. The new dataset BetaSheet1452 can be downloaded at http://biocomp.unibo.it/savojard/bcov/BetaSheet1452.dat.

Evaluation of residue-residue contact prediction in CASP10

We present the results of the assessment of the intramolecular residue-residue contact predictions from 26 prediction groups participating in the 10th round of the CASP experiment. The most recently developed direct coupling analysis methods did not take part in the experiment likely because they require a very deep sequence alignment not available for any of the 114 CASP10 targets. The performance of contact prediction methods was evaluated with the measures used in previous CASPs (i.e., prediction accuracy and the difference between the distribution of the predicted contacts and that of all pairs of residues in the target protein), as well as new measures, such as the Matthews correlation coefficient, the area under the precision-recall curve and the ranks of the first correctly and incorrectly predicted contact. We also evaluated the ability to detect interdomain contacts and tested whether the difficulty of predicting contacts depends upon the protein length and the depth of the family sequence alignment. The analyses were carried out on the target domains for which structural homologs did not exist or were difficult to identify. The evaluation was performed for all types of contacts (short, medium, and long-range), with emphasis placed on long-range contacts, i.e. those involving residues separated by at least 24 residues along the sequence. The assessment suggests that the best CASP10 contact prediction methods perform at approximately the same level, and comparably to those participating in CASP9.

Emerging methods in protein co-evolution

Co-evolution is a fundamental component of the theory of evolution and is essential for understanding the relationships between species in complex ecological networks. A wide range of co-evolution-inspired computational methods has been designed to predict molecular interactions, but it is only recently that important advances have been made. Breakthroughs in the handling of phylogenetic information and in disentangling indirect relationships have resulted in an improved capacity to predict interactions between proteins and contacts between different protein residues. Here, we review the main co-evolution-based computational approaches, their theoretical basis, potential applications and foreseeable developments.

Prediction of disulfide connectivity in proteins with machine-learning methods and correlated mutations

Background

Recently, information derived by correlated mutations in proteins has regained relevance for predicting protein contacts. This is due to new forms of mutual information analysis that have been proven to be more suitable to highlight direct coupling between pairs of residues in protein structures and to the large number of protein chains that are currently available for statistical validation. It was previously discussed that disulfide bond topology in proteins is also constrained by correlated mutations.

Results

In this paper we exploit information derived from a corrected mutual information analysis and from the inverse of the covariance matrix to address the problem of the prediction of the topology of disulfide bonds in Eukaryotes. Recently, we have shown that Support Vector Regression (SVR) can improve the prediction for the disulfide connectivity patterns. Here we show that the inclusion of the correlated mutation information increases of 5 percentage points the SVR performance (from 54% to 59%). When this approach is used in combination with a method previously developed by us and scoring at the state of art in predicting both location and topology of disulfide bonds in Eukaryotes (DisLocate), the per-protein accuracy is 38%, 2 percentage points higher than that previously obtained.

Conclusions

In this paper we show that the inclusion of information derived from correlated mutations can improve the performance of the state of the art methods for predicting disulfide connectivity patterns in Eukaryotic proteins. Our analysis also provides support to the notion that improving methods to extract evolutionary information from multiple sequence alignments greatly contributes to the scoring performance of predictors suited to detect relevant features from protein chains.

Predicting protein β-sheet contacts using a maximum entropy-based correlated mutation measure

MOTIVATION

The problem of ab initio protein folding is one of the most difficult in modern computational biology. The prediction of residue contacts within a protein provides a more tractable immediate step. Recently introduced maximum entropy-based correlated mutation measures (CMMs), such as direct information, have been successful in predicting residue contacts. However, most correlated mutation studies focus on proteins that have large good-quality multiple sequence alignments (MSA) because the power of correlated mutation analysis falls as the size of the MSA decreases. However, even with small autogenerated MSAs, maximum entropy-based CMMs contain information. To make use of this information, in this article, we focus not on general residue contacts but contacts between residues in β-sheets. The strong constraints and prior knowledge associated with β-contacts are ideally suited for prediction using a method that incorporates an often noisy CMM.

RESULTS

Using contrastive divergence, a statistical machine learning technique, we have calculated a maximum entropy-based CMM. We have integrated this measure with a new probabilistic model for β-contact prediction, which is used to predict both residue- and strand-level contacts. Using our model on a standard non-redundant dataset, we significantly outperform a 2D recurrent neural network architecture, achieving a 5% improvement in true positives at the 5% false-positive rate at the residue level. At the strand level, our approach is competitive with the state-of-the-art single methods achieving precision of 61.0% and recall of 55.4%, while not requiring residue solvent accessibility as an input.

AVAILABILITY

http://www2.warwick.ac.uk/fac/sci/systemsbiology/research/software/

Predicting protein residue-residue contacts using deep networks and boosting

MOTIVATION

Protein residue-residue contacts continue to play a larger and larger role in protein tertiary structure modeling and evaluation. Yet, while the importance of contact information increases, the performance of sequence-based contact predictors has improved slowly. New approaches and methods are needed to spur further development and progress in the field.

RESULTS

Here we present DNCON, a new sequence-based residue-residue contact predictor using deep networks and boosting techniques. Making use of graphical processing units and CUDA parallel computing technology, we are able to train large boosted ensembles of residue-residue contact predictors achieving state-of-the-art performance.

AVAILABILITY

The web server of the prediction method (DNCON) is available at http://iris.rnet.missouri.edu/dncon/.

CONTACT

chengji@missouri.edu

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Mining residue contacts in proteins using local structure predictions

In this paper we develop data mining techniques to predict 3D contact potentials among protein residues (or amino acids) based on the hierarchical nucleation-propagation model of protein folding. We apply a hybrid approach, using a hidden Markov model to extract folding initiation sites, and then apply association mining to discover contact potentials. The new hybrid approach achieves accuracy results better than those reported previously.

Computational identification of novel amino-acid interactions in HIV Gag via correlated evolution

Pairs of amino acid positions that evolve in a correlated manner are proposed to play important roles in protein structure or function. Methods to detect them might fare better with families for which sequences of thousands of closely related homologs are available than families with only a few distant relatives. We applied co-evolution analysis to thousands of sequences of HIV Gag, finding that the most significantly co-evolving positions are proximal in the quaternary structures of the viral capsid. A reduction in infectivity caused by mutating one member of a significant pair could be rescued by a compensatory mutation of the other.

Deep architectures for protein contact map prediction

MOTIVATION

Residue-residue contact prediction is important for protein structure prediction and other applications. However, the accuracy of current contact predictors often barely exceeds 20% on long-range contacts, falling short of the level required for ab initio structure prediction.

RESULTS

Here, we develop a novel machine learning approach for contact map prediction using three steps of increasing resolution. First, we use 2D recursive neural networks to predict coarse contacts and orientations between secondary structure elements. Second, we use an energy-based method to align secondary structure elements and predict contact probabilities between residues in contacting alpha-helices or strands. Third, we use a deep neural network architecture to organize and progressively refine the prediction of contacts, integrating information over both space and time. We train the architecture on a large set of non-redundant proteins and test it on a large set of non-homologous domains, as well as on the set of protein domains used for contact prediction in the two most recent CASP8 and CASP9 experiments. For long-range contacts, the accuracy of the new CMAPpro predictor is close to 30%, a significant increase over existing approaches.

AVAILABILITY

CMAPpro is available as part of the SCRATCH suite at http://scratch.proteomics.ics.uci.edu/.

CONTACT

pfbaldi@uci.edu

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Accurate de novo structure prediction of large transmembrane protein domains using fragment-assembly and correlated mutation analysis

A new de novo protein structure prediction method for transmembrane proteins (FILM3) is described that is able to accurately predict the structures of large membrane proteins domains using an ensemble of two secondary structure prediction methods to guide fragment selection in combination with a scoring function based solely on correlated mutations detected in multiple sequence alignments. This approach has been validated by generating models for 28 membrane proteins with a diverse range of complex topologies and an average length of over 300 residues with results showing that TM-scores > 0.5 can be achieved in almost every case following refinement using MODELLER. In one of the most impressive results, a model of mitochondrial cytochrome c oxidase polypeptide I was obtained with a TM-score > 0.75 and an rmsd of only 5.7 Å over all 514 residues. These results suggest that FILM3 could be applicable to a wide range of transmembrane proteins of as-yet-unknown 3D structure given sufficient homologous sequences.

A cationic lumen in the Wzx flippase mediates anionic O-antigen subunit translocation in Pseudomonas aeruginosa PAO1

Heteropolymeric B-band O-antigen (O-Ag) biosynthesis in Pseudomonas aeruginosa PAO1 follows the Wzy-dependent pathway, beginning with translocation of undecaprenyl pyrophosphate-linked anionic O-Ag subunits (O units) from the inner to the outer leaflets of the inner membrane (IM). This translocation is mediated by the integral IM flippase Wzx. Through experimentally based and unbiased topological mapping, our group previously observed that Wzx possesses many charged and aromatic amino acid residues within its 12 transmembrane segments (TMS). Herein, site-directed mutagenesis targeting 102 residues was carried out on the TMS and loops of Wzx, followed by assessment of each construct's ability to restore B-band O-Ag production, identifying eight residues important for flippase function. The importance of various charged and aromatic residues was highlighted, predominantly within the TMS of the protein, revealing functional ‘hotspots’ within the flippase, particularly within TMS2 and TMS8. Construction of a tertiary structure homology model for Wzx indicated that TMS2 and TMS8 line a central cationic lumen. This is the first report to describe a charged flippase lumen for mediating anionic O-unit translocation across the hydrophobic IM.

Requirements for efficient correction of ΔF508 CFTR revealed by analyses of evolved sequences

Misfolding of ΔF508 cystic fibrosis (CF) transmembrane conductance regulator (CFTR) underlies pathology in most CF patients. F508 resides in the first nucleotide-binding domain (NBD1) of CFTR near a predicted interface with the fourth intracellular loop (ICL4). Efforts to identify small molecules that restore function by correcting the folding defect have revealed an apparent efficacy ceiling. To understand the mechanistic basis of this obstacle, positions statistically coupled to 508, in evolved sequences, were identified and assessed for their impact on both NBD1 and CFTR folding. The results indicate that both NBD1 folding and interaction with ICL4 are altered by the ΔF508 mutation and that correction of either individual process is only partially effective. By contrast, combination of mutations that counteract both defects restores ΔF508 maturation and function to wild-type levels. These results provide a mechanistic rationale for the limited efficacy of extant corrector compounds and suggest approaches for identifying compounds that correct both defective steps.

Improving protein structure prediction using multiple sequence-based contact predictions

Although residue-residue contact maps dictate the topology of proteins, sequence-based ab initio contact predictions have been found little use in actual structure prediction due to the low accuracy. We developed a composite set of nine SVM-based contact predictors that are used in I-TASSER simulation in combination with sparse template contact restraints. When testing the strategy on 273 nonhomologous targets, remarkable improvements of I-TASSER models were observed for both easy and hard targets, with p value by Student's t test<0.00001 and 0.001, respectively. In several cases, template modeling score increases by >30%, which essentially converts "nonfoldable" targets into "foldable" ones. In CASP9, I-TASSER employed ab initio contact predictions, and generated models for 26 FM targets with a GDT-score 16% and 44% higher than the second and third best servers from other groups, respectively. These findings demonstrate a new avenue to improve the accuracy of protein structure prediction especially for free-modeling targets.

PSICOV: precise structural contact prediction using sparse inverse covariance estimation on large multiple sequence alignments

MOTIVATION

The accurate prediction of residue-residue contacts, critical for maintaining the native fold of a protein, remains an open problem in the field of structural bioinformatics. Interest in this long-standing problem has increased recently with algorithmic improvements and the rapid growth in the sizes of sequence families. Progress could have major impacts in both structure and function prediction to name but two benefits. Sequence-based contact predictions are usually made by identifying correlated mutations within multiple sequence alignments (MSAs), most commonly through the information-theoretic approach of calculating mutual information between pairs of sites in proteins. These predictions are often inaccurate because the true covariation signal in the MSA is often masked by biases from many ancillary indirect-coupling or phylogenetic effects. Here we present a novel method, PSICOV, which introduces the use of sparse inverse covariance estimation to the problem of protein contact prediction. Our method builds on work which had previously demonstrated corrections for phylogenetic and entropic correlation noise and allows accurate discrimination of direct from indirectly coupled mutation correlations in the MSA.

RESULTS

PSICOV displays a mean precision substantially better than the best performing normalized mutual information approach and Bayesian networks. For 118 out of 150 targets, the L/5 (i.e. top-L/5 predictions for a protein of length L) precision for long-range contacts (sequence separation >23) was ≥ 0.5, which represents an improvement sufficient to be of significant benefit in protein structure prediction or model quality assessment.

AVAILABILITY

The PSICOV source code can be downloaded from http://bioinf.cs.ucl.ac.uk/downloads/PSICOV.

Predicting residue-residue contacts and helix-helix interactions in transmembrane proteins using an integrative feature-based random forest approach

Integral membrane proteins constitute 25-30% of genomes and play crucial roles in many biological processes. However, less than 1% of membrane protein structures are in the Protein Data Bank. In this context, it is important to develop reliable computational methods for predicting the structures of membrane proteins. Here, we present the first application of random forest (RF) for residue-residue contact prediction in transmembrane proteins, which we term as TMhhcp. Rigorous cross-validation tests indicate that the built RF models provide a more favorable prediction performance compared with two state-of-the-art methods, i.e., TMHcon and MEMPACK. Using a strict leave-one-protein-out jackknifing procedure, they were capable of reaching the top L/5 prediction accuracies of 49.5% and 48.8% for two different residue contact definitions, respectively. The predicted residue contacts were further employed to predict interacting helical pairs and achieved the Matthew's correlation coefficients of 0.430 and 0.424, according to two different residue contact definitions, respectively. To facilitate the academic community, the TMhhcp server has been made freely accessible at http://protein.cau.edu.cn/tmhhcp.

A conformation ensemble approach to protein residue-residue contact

Background

Protein residue-residue contact prediction is important for protein model generation and model evaluation. Here we develop a conformation ensemble approach to improve residue-residue contact prediction. We collect a number of structural models stemming from a variety of methods and implementations. The various models capture slightly different conformations and contain complementary information which can be pooled together to capture recurrent, and therefore more likely, residue-residue contacts.

Results

We applied our conformation ensemble approach to free modeling targets from both CASP8 and CASP9. Given a diverse ensemble of models, the method is able to achieve accuracies of. 48 for the top L/5 medium range contacts and. 36 for the top L/5 long range contacts for CASP8 targets (L being the target domain length). When applied to targets from CASP9, the accuracies of the top L/5 medium and long range contact predictions were. 34 and. 30 respectively.

Conclusions

When operating on a moderately diverse ensemble of models, the conformation ensemble approach is an effective means to identify medium and long range residue-residue contacts. An immediate benefit of the method is that when tied with a scoring scheme, it can be used to successfully rank models.

Is there an optimal substitution matrix for contact prediction with correlated mutations?

Correlated mutations in proteins are believed to occur in order to preserve the protein functional folding through evolution. Their values can be deduced from sequence and/or structural alignments and are indicative of residue contacts in the protein three-dimensional structure. A correlation among pairs of residues is routinely evaluated with the Pearson correlation coefficient and the MCLACHLAN similarity matrix. In literature, there is no justification for the adoption of the MCLACHLAN instead of other substitution matrices. In this paper, we approach the problem of computing the optimal similarity matrix for contact prediction with correlated mutations, i.e., the similarity matrix that maximizes the accuracy of contact prediction with correlated mutations. We describe an optimization procedure, based on the gradient descent method, for computing the optimal similarity matrix and perform an extensive number of experimental tests. Our tests show that there is a large number of optimal matrices that perform similarly to MCLACHLAN. We also obtain that the upper limit to the accuracy achievable in protein contact prediction is independent of the optimized similarity matrix. This suggests that the poor scoring of the correlated mutations approach may be due to the choice of the linear correlation function in evaluating correlated mutations.

A bioinformatics approach to the structure, function, and evolution of the nucleoprotein of the order mononegavirales

The goal of this Bioinformatic study is to investigate sequence conservation in relation to evolutionary function/structure of the nucleoprotein of the order Mononegavirales. In the combined analysis of 63 representative nucleoprotein (N) sequences from four viral families (Bornaviridae, Filoviridae, Rhabdoviridae, and Paramyxoviridae) we predict the regions of protein disorder, intra-residue contact and co-evolving residues. Correlations between location and conservation of predicted regions illustrate a strong division between families while high- lighting conservation within individual families. These results suggest the conserved regions among the nucleoproteins, specifically within Rhabdoviridae and Paramyxoviradae, but also generally among all members of the order, reflect an evolutionary advantage in maintaining these sites for the viral nucleoprotein as part of the transcription/replication machinery. Results indicate conservation for disorder in the C-terminus region of the representative proteins that is important for interacting with the phosphoprotein and the large subunit polymerase during transcription and replication. Additionally, the C-terminus region of the protein preceding the disordered region, is predicted to be important for interacting with the encapsidated genome. Portions of the N-terminus are responsible for N∶N stability and interactions identified by the presence or lack of co-evolving intra-protein contact predictions. The validation of these prediction results by current structural information illustrates the benefits of the Disorder, Intra-residue contact and Compensatory mutation Correlator (DisICC) pipeline as a method for quickly characterizing proteins and providing the most likely residues and regions necessary to target for disruption in viruses that have little structural information available.

Computational approaches to therapeutic peptide discovery

The development of peptides with therapeutic activities can be based on naturally occurring peptides or alternatively on de novo design. The discovery of natural peptides is often a matter of serendipity. In part, this is because natural peptides are typically proteolytically cleaved out from precursor proteins, a feature that averts the direct benefits of the genomic revolution. The first part of this review describes attempts to create a more systematic identification of natural peptides relying on a two step process. In the initial step, an in silico peptidome is predicted through the use of machine learning. Then, various computational biology tools are tailored to focus on peptides predicted to have the desired biological activity; for example, activating a GPCR or modulating the cellular arm of the immune system. The second part of the review is devoted to de novo peptide design and focuses on arguably the simplest scenario in which the designed peptide corresponds to a contiguous protein subsequence. Amongst these peptides, those corresponding to helical segments are prominent, mainly due to their relative ability to fold independently. Inspired by the clinical success of viral entry inhibitors, which are peptides corresponding to helical segments in viral envelope proteins, a computational tool for the identification of intramolecular helix-helix interactions was developed. Using this approach, peptides having anti-cancer, anti-angiogenic, and anti-inflammatory activities have been recently rationally designed and biologically characterized.

Electrophysiological, biochemical, and bioinformatic methods for studying CFTR channel gating and its regulation

CFTR is the only member of the ABC (ATP-binding cassette) protein superfamily known to function as an ion channel. Most other ABC proteins are ATP-driven transporters, in which a cycle of ATP binding and hydrolysis, at intracellular nucleotide binding domains (NBDs), powers uphill substrate translocation across the membrane. In CFTR, this same ATP-driven cycle opens and closes a transmembrane pore through which chloride ions flow rapidly down their electrochemical gradient. Detailed analysis of the pattern of gating of CFTR channels thus offers the opportunity to learn about mechanisms of function not only of CFTR channels but also of their ABC transporter ancestors. In addition, CFTR channel gating is subject to complex regulation by kinase-mediated phosphorylation at multiple consensus sites in a cytoplasmic regulatory domain that is unique to CFTR. Here we offer a practical guide to extract useful information about the mechanisms that control opening and closing of CFTR channels: on how to plan (including information obtained from analysis of multiple sequence alignments), carry out, and analyze electrophysiological and biochemical experiments, as well as on how to circumvent potential pitfalls.