Assessment of protein side‐chain conformation prediction methods in different residue environments

Computational prediction of side‐chain conformation is an important component of protein structure prediction. Accurate side‐chain prediction is crucial for practical applications of protein structure models that need atomic‐detailed resolution such as protein and ligand design. We evaluated the accuracy of eight side‐chain prediction methods in reproducing the side‐chain conformations of experimentally solved structures deposited to the Protein Data Bank. Prediction accuracy was evaluated for a total of four different structural environments (buried, surface, interface, and membrane‐spanning) in three different protein types (monomeric, multimeric, and membrane). Overall, the highest accuracy was observed for buried residues in monomeric and multimeric proteins. Notably, side‐chains at protein interfaces and membrane‐spanning regions were better predicted than surface residues even though the methods did not all use multimeric and membrane proteins for training. Thus, we conclude that the current methods are as practically useful for modeling protein docking interfaces and membrane‐spanning regions as for modeling monomers. Proteins 2014; 82:1971–1984. © 2014 Wiley Periodicals, Inc.     

Deep-learning contact-map guided protein structure prediction in CASP13

We report the results of two fully automated structure prediction pipelines, “Zhang-Server” and “QUARK”, in CASP13. The pipelines were built upon the C-I-TASSER and C-QUARK programs, which in turn are based on I-TASSER and QUARK but with three new modules: (a) a novel multiple sequence alignment (MSA) generation protocol to construct deep sequence-profiles for contact prediction; (b) an improved meta-method, NeBcon, which combines multiple contact predictors, including ResPRE that predicts contact-maps by coupling precision-matrices with deep residual convolutional neural-networks; and (c) an optimized contact potential to guide structure assembly simulations. For 50 CASP13 FM domains that lacked homologous templates, average TM-scores of the first models produced by C-I-TASSER and C-QUARK were 28% and 56% higher than those constructed by I-TASSER and QUARK, respectively. For the first time, contact-map predictions demonstrated usefulness on TBM domains with close homologous templates, where TM-scores of C-I-TASSER models were significantly higher than those of I-TASSER models with a P-value <.05. Detailed data analyses showed that the success of C-I-TASSER and C-QUARK was mainly due to the increased accuracy of deep-learning-based contact-maps, as well as the careful balance between sequence-based contact restraints, threading templates, and generic knowledge-based potentials. Nevertheless, challenges still remain for predicting quaternary structure of multi-domain proteins, due to the difficulties in domain partitioning and domain reassembly. In addition, contact prediction in terminal regions was often unsatisfactory due to the sparsity of MSAs. Development of new contact-based domain partitioning and assembly methods and training contact models on sparse MSAs may help address these issues.     

Protein tertiary structure modeling driven by deep learning and contact distance prediction in CASP13

Predicting residue-residue distance relationships (eg, contacts) has become the key direction to advance protein structure prediction since 2014 CASP11 experiment, while deep learning has revolutionized the technology for contact and distance distribution prediction since its debut in 2012 CASP10 experiment. During 2018 CASP13 experiment, we enhanced our MULTICOM protein structure prediction system with three major components: contact distance prediction based on deep convolutional neural networks, distance-driven template-free (ab initio) modeling, and protein model ranking empowered by deep learning and contact prediction. Our experiment demonstrates that contact distance prediction and deep learning methods are the key reasons that MULTICOM was ranked 3rd out of all 98 predictors in both template-free and template-based structure modeling in CASP13. Deep convolutional neural network can utilize global information in pairwise residue-residue features such as coevolution scores to substantially improve contact distance prediction, which played a decisive role in correctly folding some free modeling and hard template-based modeling targets. Deep learning also successfully integrated one-dimensional structural features, two-dimensional contact information, and three-dimensional structural quality scores to improve protein model quality assessment, where the contact prediction was demonstrated to consistently enhance ranking of protein models for the first time. The success of MULTICOM system clearly shows that protein contact distance prediction and model selection driven by deep learning holds the key of solving protein structure prediction problem. However, there are still challenges in accurately predicting protein contact distance when there are few homologous sequences, folding proteins from noisy contact distances, and ranking models of hard targets.     

Computational modeling of membrane proteins

The determination of membrane protein (MP) structures has always trailed that of soluble proteins due to difficulties in their overexpression, reconstitution into membrane mimetics, and subsequent structure determination. The percentage of MP structures in the protein databank (PDB) has been at a constant 1–2% for the last decade. In contrast, over half of all drugs target MPs, only highlighting how little we understand about drug‐specific effects in the human body. To reduce this gap, researchers have attempted to predict structural features of MPs even before the first structure was experimentally elucidated. In this review, we present current computational methods to predict MP structure, starting with secondary structure prediction, prediction of trans‐membrane spans, and topology. Even though these methods generate reliable predictions, challenges such as predicting kinks or precise beginnings and ends of secondary structure elements are still waiting to be addressed. We describe recent developments in the prediction of 3D structures of both α‐helical MPs as well as β‐barrels using comparative modeling techniques, de novo methods, and molecular dynamics (MD) simulations. The increase of MP structures has (1) facilitated comparative modeling due to availability of more and better templates, and (2) improved the statistics for knowledge‐based scoring functions. Moreover, de novo methods have benefited from the use of correlated mutations as restraints. Finally, we outline current advances that will likely shape the field in the forthcoming decade. Proteins 2015; 83:1–24. © 2014 Wiley Periodicals, Inc.     

Princeton_TIGRESS: Protein geometry refinement using simulations and support vector machines

Protein structure refinement aims to perform a set of operations given a predicted structure to improve model quality and accuracy with respect to the native in a blind fashion. Despite the numerous computational approaches to the protein refinement problem reported in the previous three CASPs, an overwhelming majority of methods degrade models rather than improve them. We initially developed a method tested using blind predictions during CASP10 which was officially ranked in 5th place among all methods in the refinement category. Here, we present Princeton_TIGRESS, which when benchmarked on all CASP 7,8,9, and 10 refinement targets, simultaneously increased GDT_TS 76% of the time with an average improvement of 0.83 GDT_TS points per structure. The method was additionally benchmarked on models produced by top performing three‐dimensional structure prediction servers during CASP10. The robustness of the Princeton_TIGRESS protocol was also tested for different random seeds. We make the Princeton_TIGRESS refinement protocol freely available as a web server at http://atlas.princeton.edu/refinement . Using this protocol, one can consistently refine a prediction to help bridge the gap between a predicted structure and the actual native structure. Proteins 2014; 82:794–814. © 2013 Wiley Periodicals, Inc.     

A global machine learning based scoring function for protein structure prediction

We present a knowledge‐based function to score protein decoys based on their similarity to native structure. A set of features is constructed to describe the structure and sequence of the entire protein chain. Furthermore, a qualitative relationship is established between the calculated features and the underlying electromagnetic interaction that dominates this scale. The features we use are associated with residue–residue distances, residue–solvent distances, pairwise knowledge‐based potentials and a four‐body potential. In addition, we introduce a new target to be predicted, the fitness score, which measures the similarity of a model to the native structure. This new approach enables us to obtain information both from decoys and from native structures. It is also devoid of previous problems associated with knowledge‐based potentials. These features were obtained for a large set of native and decoy structures and a back‐propagating neural network was trained to predict the fitness score. Overall this new scoring potential proved to be superior to the knowledge‐based scoring functions used as its inputs. In particular, in the latest CASP (CASP10) experiment our method was ranked third for all targets, and second for freely modeled hard targets among about 200 groups for top model prediction. Ours was the only method ranked in the top three for all targets and for hard targets. This shows that initial results from the novel approach are able to capture details that were missed by a broad spectrum of protein structure prediction approaches. Source codes and executable from this work are freely available at http://mathmed.org /#Software and http://mamiris.com/ . Proteins 2014; 82:752–759. © 2013 Wiley Periodicals, Inc.     

Machine learning in protein structure prediction

Prediction of protein structure from sequence has been intensely studied for many decades, owing to the problem's importance and its uniquely well-defined physical and computational bases. While progress has historically ebbed and flowed, the past two years saw dramatic advances driven by the increasing “neuralization” of structure prediction pipelines, whereby computations previously based on energy models and sampling procedures are replaced by neural networks. The extraction of physical contacts from the evolutionary record; the distillation of sequence–structure patterns from known structures; the incorporation of templates from homologs in the Protein Databank; and the refinement of coarsely predicted structures into finely resolved ones have all been reformulated using neural networks. Cumulatively, this transformation has resulted in algorithms that can now predict single protein domains with a median accuracy of 2.1 Å, setting the stage for a foundational reconfiguration of the role of biomolecular modeling within the life sciences.     

A seqlet-based maximum entropy Markov approach for protein secondary structure prediction

A novel method for predicting the secondary structures of proteins from amino acid sequence has been presented. The protein secondary structure seqlets that are analogous to the words in natural language have been extracted. These seqlets will capture the relationship between amino acid sequence and the secondary structures of proteins and further form the protein secondary structure dictionary. To be elaborate, the dictionary is organism-specific. Protein secondary structure prediction is formulated as an integrated word segmentation and part of speech tagging problem. The word-lattice is used to represent the results of the word segmentation and the maximum entropy model is used to calculate the probability of a seqlet tagged as a certain secondary structure type. The method is markovian in the seqlets, permitting efficient exact calculation of the posterior probability distribution over all possible word segmentations and their tags by viterbi algorithm. The optimal segmentations and their tags are computed as the results of protein secondary structure prediction. The method is applied to predict the secondary structures of proteins of four organisms respectively and compared with the PHD method. The results show that the performance of this method is higher than that of PHD by about 3.9% Q3 accuracy and 4.6% SOV accuracy. Combining with the local similarity protein sequences that are obtained by BLAST can give better prediction. The method is also tested on the 50 CASP5 target proteins with Q₃ accuracy 78.9% and SOV accuracy 77.1%. A web server for protein secondary structure prediction has been constructed which is available at http://www.insun.hit.edu.cn:81/demos/biology/index.html.     

BCL::Fold—Protein topology determination from limited NMR restraints

When experimental protein NMR data are too sparse to apply traditional structure determination techniques, de novo protein structure prediction methods can be leveraged. Here, we describe the incorporation of NMR restraints into the protein structure prediction algorithm BCL::Fold. The method assembles discreet secondary structure elements using a Monte Carlo sampling algorithm with a consensus knowledge‐based energy function. New components were introduced into the energy function to accommodate chemical shift, nuclear Overhauser effect, and residual dipolar coupling data. In particular, since side chains are not explicitly modeled during the minimization process, a knowledge based potential was created to relate experimental side chain proton–proton distances to C_β–C_β distances. In a benchmark test of 67 proteins of known structure with the incorporation of sparse NMR restraints, the correct topology was sampled in 65 cases, with an average best model RMSD100 of 3.4 ± 1.3 Å versus 6.0 ± 2.0 Å produced with the de novo method. Additionally, the correct topology is present in the best scoring 1% of models in 61 cases. The benchmark set includes both soluble and membrane proteins with up to 565 residues, indicating the method is robust and applicable to large and membrane proteins that are less likely to produce rich NMR datasets. Proteins 2014; 82:587–595. © 2013 Wiley Periodicals, Inc.     

RBRDetector: Improved prediction of binding residues on RNA‐binding protein structures using complementary feature‐ and template‐based strategies

Computational prediction of RNA‐binding residues is helpful in uncovering the mechanisms underlying protein‐RNA interactions. Traditional algorithms individually applied feature‐ or template‐based prediction strategy to recognize these crucial residues, which could restrict their predictive power. To improve RNA‐binding residue prediction, herein we propose the first integrative algorithm termed RBRDetector (RNA‐Binding Residue Detector) by combining these two strategies. We developed a feature‐based approach that is an ensemble learning predictor comprising multiple structure‐based classifiers, in which well‐defined evolutionary and structural features in conjunction with sequential or structural microenvironment were used as the inputs of support vector machines. Meanwhile, we constructed a template‐based predictor to recognize the putative RNA‐binding regions by structurally aligning the query protein to the RNA‐binding proteins with known structures. The final RBRDetector algorithm is an ingenious fusion of our feature‐ and template‐based approaches based on a piecewise function. By validating our predictors with diverse types of structural data, including bound and unbound structures, native and simulated structures, and protein structures binding to different RNA functional groups, we consistently demonstrated that RBRDetector not only had clear advantages over its component methods, but also significantly outperformed the current state‐of‐the‐art algorithms. Nevertheless, the major limitation of our algorithm is that it performed relatively well on DNA‐binding proteins and thus incorrectly predicted the DNA‐binding regions as RNA‐binding interfaces. Finally, we implemented the RBRDetector algorithm as a user‐friendly web server, which is freely accessible at http://ibi.hzau.edu.cn/rbrdetector . Proteins 2014; 82:2455–2471. © 2014 Wiley Periodicals, Inc.     

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/ . Proteins 2015; 83:485–496. © 2014 Wiley Periodicals, Inc.     

Simultaneous prediction of protein secondary structure and transmembrane spans

Prediction of transmembrane spans and secondary structure from the protein sequence is generally the first step in the structural characterization of (membrane) proteins. Preference of a stretch of amino acids in a protein to form secondary structure and being placed in the membrane are correlated. Nevertheless, current methods predict either secondary structure or individual transmembrane states. We introduce a method that simultaneously predicts the secondary structure and transmembrane spans from the protein sequence. This approach not only eliminates the necessity to create a consensus prediction from possibly contradicting outputs of several predictors but bears the potential to predict conformational switches, i.e., sequence regions that have a high probability to change for example from a coil conformation in solution to an α‐helical transmembrane state. An artificial neural network was trained on databases of 177 membrane proteins and 6048 soluble proteins. The output is a 3 × 3 dimensional probability matrix for each residue in the sequence that combines three secondary structure types (helix, strand, coil) and three environment types (membrane core, interface, solution). The prediction accuracies are 70.3% for nine possible states, 73.2% for three‐state secondary structure prediction, and 94.8% for three‐state transmembrane span prediction. These accuracies are comparable to state‐of‐the‐art predictors of secondary structure (e.g., Psipred) or transmembrane placement (e.g., OCTOPUS). The method is available as web server and for download at www.meilerlab.org . Proteins 2013; 81:1127–1140. © 2013 Wiley Periodicals, Inc.     

Improving fragment quality for de novo structure prediction

De novo structure prediction can be defined as a search in conformational space under the guidance of an energy function. The most successful de novo structure prediction methods, such as Rosetta, assemble the fragments from known structures to reduce the search space. Therefore, the fragment quality is an important factor in structure prediction. In our study, a method is proposed to generate a new set of fragments from the lowest energy de novo models. These fragments were subsequently used to predict the next‐round of models. In a benchmark of 30 proteins, the new set of fragments showed better performance when used to predict de novo structures. The lowest energy model predicted using our method was closer to native structure than Rosetta for 22 proteins. Following a similar trend, the best model among top five lowest energy models predicted using our method was closer to native structure than Rosetta for 20 proteins. In addition, our experiment showed that the C‐alpha root mean square deviation was improved from 5.99 to 5.03 Å on average compared to Rosetta when the lowest energy models were picked as the best predicted models. Proteins 2014; 82:2240–2252. © 2014 Wiley Periodicals, Inc.     

Identification and application of the concepts important for accurate and reliable protein secondary structure prediction.

A protein secondary structure prediction method from multiply aligned homologous sequences is presented with an overall per residue three-state accuracy of 70.1%. There are two aims: to obtain high accuracy by identification of a set of concepts important for prediction followed by use of linear statistics; and to provide insight into the folding process. The important concepts in secondary structure prediction are identified as: residue conformational propensities, sequence edge effects, moments of hydrophobicity, position of insertions and deletions in aligned homologous sequence, moments of conservation, auto-correlation, residue ratios, secondary structure feedback effects, and filtering. Explicit use of edge effects, moments of conservation, and auto-correlation are new to this paper. The relative importance of the concepts used in prediction was analyzed by stepwise addition of information and examination of weights in the discrimination function. The simple and explicit structure of the prediction allows the method to be reimplemented easily. The accuracy of a prediction is predictable a priori. This permits evaluation of the utility of the prediction: 10% of the chains predicted were identified correctly as having a mean accuracy of > 80%. Existing high-accuracy prediction methods are "black-box" predictors based on complex nonlinear statistics (e.g., neural networks in PHD: Rost & Sander, 1993a). For medium- to short-length chains (> or = 90 residues and < 170 residues), the prediction method is significantly more accurate (P < 0.01) than the PHD algorithm (probably the most commonly used algorithm). In combination with the PHD, an algorithm is formed that is significantly more accurate than either method, with an estimated overall three-state accuracy of 72.4%, the highest accuracy reported for any prediction method.     

Delaunay‐based nonlocal interactions are sufficient and accurate in protein fold recognition

This study is aimed at showing that considering only nonlocal interactions (interactions of two atoms with a sequence separation larger than five amino acids) extracted using Delaunay tessellation is sufficient and accurate for protein fold recognition. An atomic knowledge‐based potential was extracted based on a Delaunay tessellation with 167 atom types from a sample of the native structures and the normalized energy was calculated for only nonlocal interactions in each structure. The performance of this method was tested on several decoy sets and compared to a method considering all interactions extracted by Delaunay tessellation and three other popular scoring functions. Features such as the contents of different types of interactions and atoms with the highest number of interactions were also studied. The results suggest that considering only nonlocal interactions in a Delaunay tessellation of protein structure is a discrete structure catching deep properties of the three‐dimensional protein data. Proteins 2014; 82:415–423. © 2013 Wiley Periodicals, Inc.     

A seqlet-based maximum entropy Markov approach for protein secondary structure prediction

1 Introduction The prediction of protein structure and function from amino acid sequences is one of the most impor-tant problems in molecular biology. This problem is becoming more pressing as the number of known pro-tein sequences is explored as a result of genome and other sequencing projects, and the protein sequence- structure gap is widening rapidly[1]. Therefore, com-putational tools to predict protein structures are needed to narrow the widening gap. Although the prediction of three dim…     

Analysis and prediction of protein local structure based on structure alphabets

In recent years, protein structure prediction using local structure information has made great progress. Many fragment libraries or structure alphabets have been developed. In this study, the entropies and correlations of local structures are first calculated. The results show that neighboring local structures are strongly correlated. Then, a dual-layer model has been designed for protein local structure prediction. The position-specific score matrix, generated by PSI-BLAST, is inputted to the first-layer classifier, whose output is further enhanced by a second-layer classifier. The neural network is selected as the classifier. Two structure alphabets are explored, which are represented in Cartesian coordinate space and in torsion angles space respectively. Testing on the nonredundant dataset shows that the dual-layer model is an efficient method for protein local structure prediction. The Q-scores are 0.456 and 0.585 for the two structure alphabets, which is a significant improvement in comparison with related works.     

Hot‐spot analysis to dissect the functional protein–protein interface of a tRNA‐modifying enzyme

Interference with protein–protein interactions of interfaces larger than 1500 Ų by small drug‐like molecules is notoriously difficult, particularly if targeting homodimers. The tRNA modifying enzyme Tgt is only functionally active as a homodimer. Thus, blocking Tgt dimerization is a promising strategy for drug therapy as this protein is key to the development of Shigellosis. Our goal was to identify hot‐spot residues which, upon mutation, result in a predominantly monomeric state of Tgt. The detailed understanding of the spatial location and stability contribution of the individual interaction hot‐spot residues and the plasticity of motifs involved in the interface formation is a crucial prerequisite for the rational identification of drug‐like inhibitors addressing the respective dimerization interface. Using computational analyses, we identified hot‐spot residues that contribute particularly to dimer stability: a cluster of hydrophobic and aromatic residues as well as several salt bridges. This in silico prediction led to the identification of a promising double mutant, which was validated experimentally. Native nano‐ESI mass spectrometry showed that the dimerization of the suggested mutant is largely prevented resulting in a predominantly monomeric state. Crystal structure analysis and enzyme kinetics of the mutant variant further support the evidence for enhanced monomerization and provide first insights into the structural consequences of the dimer destabilization. Proteins 2014; 82:2713–2732. © 2014 Wiley Periodicals, Inc.     

Comparing four different approaches for the determination of inter‐residue interactions provides insight for the structure prediction of helical membrane proteins

Studying inter‐residue interactions provides insight into the folding and stability of both soluble and membrane proteins and is essential for developing computational tools for protein structure prediction. As the first step, various approaches for elucidating such interactions within protein structures have been proposed and proven useful. Since different approaches may grasp different aspects of protein structural folds, it is of interest to systematically compare them. In this work, we applied four approaches for determining inter‐residue interactions to the analysis of three distinct structure datasets of helical membrane proteins and compared their correlation to the three individual quality measures of structures in these datasets. These datasets included one of 35 structures of rhodopsin receptors and bacterial rhodopsins determined at various resolutions, one derived from the HOMEP benchmark dataset previously reported, and one comprising of 139 homology models. It was found that the correlation between the average number of inter‐residue interactions obtained by applying the four approaches and the available structure quality measures varied quite significantly among them. The best correlation was achieved by the approach focusing exclusively on favorable inter‐residue interactions. These results provide interesting insight for the development of objective quality measure for the structure prediction of helical membrane proteins. © 2009 Wiley Periodicals, Inc. Biopolymers 91: 547–556, 2009. This article was originally published online as an accepted preprint. The “Published Online” date corresponds to the preprint version. You can request a copy of the preprint by emailing the Biopolymers editorial office at biopolymers@wiley.com     

Improved prediction for N-termini of alpha-helices using empirical information

The prediction of the secondary structure of proteins from their amino acid sequences remains a key component of many approaches to the protein folding problem. The most abundant form of regular secondary structure in proteins is the alpha-helix, in which specific residue preferences exist at the N-terminal locations. Propensities derived from these observed amino acid frequencies in the Protein Data Bank (PDB) database correlate well with experimental free energies measured for residues at different N-terminal positions in alanine-based peptides. We report a novel method to exploit this data to improve protein secondary structure prediction through identification of the correct N-terminal sequences in alpha-helices, based on existing popular methods for secondary structure prediction. With this algorithm, the number of correctly predicted alpha-helix start positions was improved from 30% to 38%, while the overall prediction accuracy (Q3) remained the same, using cross-validated testing. Although the algorithm was developed and tested on multiple sequence alignment-based secondary structure predictions, it was also able to improve the predictions of start locations by methods that use single sequences to make their predictions. Furthermore, the residue frequencies at N-terminal positions of the improved predictions better reflect those seen at the N-terminal positions of alpha-helices in proteins. This has implications for areas such as comparative modeling, where a more accurate prediction of the N-terminal regions of alpha-helices should benefit attempts to model adjacent loop regions. The algorithm is available as a Web tool, located at http://rocky.bms.umist.ac.uk/elephant.