CaMELS: In silico prediction of calmodulin binding proteins and their binding sites

Due to Ca²⁺‐dependent binding and the sequence diversity of Calmodulin (CaM) binding proteins, identifying CaM interactions and binding sites in the wet‐lab is tedious and costly. Therefore, computational methods for this purpose are crucial to the design of such wet‐lab experiments. We present an algorithm suite called CaMELS (CalModulin intEraction Learning System) for predicting proteins that interact with CaM as well as their binding sites using sequence information alone. CaMELS offers state of the art accuracy for both CaM interaction and binding site prediction and can aid biologists in studying CaM binding proteins. For CaM interaction prediction, CaMELS uses protein sequence features coupled with a large‐margin classifier. CaMELS models the binding site prediction problem using multiple instance machine learning with a custom optimization algorithm which allows more effective learning over imprecisely annotated CaM‐binding sites during training. CaMELS has been extensively benchmarked using a variety of data sets, mutagenic studies, proteome‐wide Gene Ontology enrichment analyses and protein structures. Our experiments indicate that CaMELS outperforms simple motif‐based search and other existing methods for interaction and binding site prediction. We have also found that the whole sequence of a protein, rather than just its binding site, is important for predicting its interaction with CaM. Using the machine learning model in CaMELS, we have identified important features of protein sequences for CaM interaction prediction as well as characteristic amino acid sub‐sequences and their relative position for identifying CaM binding sites. Python code for training and evaluating CaMELS together with a webserver implementation is available at the URL: http://faculty.pieas.edu.pk/fayyaz/software.html#camels .     

Binding interface prediction by combining protein–protein docking results

We developed a method called residue contact frequency (RCF), which uses the complex structures generated by the protein–protein docking algorithm ZDOCK to predict interface residues. Unlike interface prediction algorithms that are based on monomers alone, RCF is binding partner specific. We evaluated the performance of RCF using the area under the precision‐recall (PR) curve (AUC) on a large protein docking Benchmark. RCF (AUC = 0.44) performed as well as meta‐PPISP (AUC = 0.43), which is one of the best monomer‐based interface prediction methods. In addition, we test a support vector machine (SVM) to combine RCF with meta‐PPISP and another monomer‐based interface prediction algorithm Evolutionary Trace to further improve the performance. We found that the SVM that combined RCF and meta‐PPISP achieved the best performance (AUC = 0.47). We used RCF to predict the binding interfaces of proteins that can bind to multiple partners and RCF was able to correctly predict interface residues that are unique for the respective binding partners. Furthermore, we found that residues that contributed greatly to binding affinity (hotspot residues) had significantly higher RCF than other residues. Proteins 2014; 82:57–66. © 2013 Wiley Periodicals, Inc.     

Prediction of protein–protein interaction sites from weakly homologous template structures using meta‐threading and machine learning

The identification of protein–protein interactions is vital for understanding protein function, elucidating interaction mechanisms, and for practical applications in drug discovery. With the exponentially growing protein sequence data, fully automated computational methods that predict interactions between proteins are becoming essential components of system‐level function inference. A thorough analysis of protein complex structures demonstrated that binding site locations as well as the interfacial geometry are highly conserved across evolutionarily related proteins. Because the conformational space of protein–protein interactions is highly covered by experimental structures, sensitive protein threading techniques can be used to identify suitable templates for the accurate prediction of interfacial residues. Toward this goal, we developed eFindSite^PPI, an algorithm that uses the three‐dimensional structure of a target protein, evolutionarily remotely related templates and machine learning techniques to predict binding residues. Using crystal structures, the average sensitivity (specificity) of eFindSite^PPI in interfacial residue prediction is 0.46 (0.92). For weakly homologous protein models, these values only slightly decrease to 0.40–0.43 (0.91–0.92) demonstrating that eFindSite^PPI performs well not only using experimental data but also tolerates structural imperfections in computer‐generated structures. In addition, eFindSite^PPI detects specific molecular interactions at the interface; for instance, it correctly predicts approximately one half of hydrogen bonds and aromatic interactions, as well as one third of salt bridges and hydrophobic contacts. Comparative benchmarks against several dimer datasets show that eFindSite^PPI outperforms other methods for protein‐binding residue prediction. It also features a carefully tuned confidence estimation system, which is particularly useful in large‐scale applications using raw genomic data. eFindSite^PPI is freely available to the academic community at http://www.brylinski.org/efindsiteppi . Copyright © 2014 John Wiley & Sons, Ltd.     

COMSAT: Residue contact prediction of transmembrane proteins based on support vector machines and mixed integer linear programming

In this article, we present COMSAT, a hybrid framework for residue contact prediction of transmembrane (TM) proteins, integrating a support vector machine (SVM) method and a mixed integer linear programming (MILP) method. COMSAT consists of two modules: COMSAT_SVM which is trained mainly on position–specific scoring matrix features, and COMSAT_MILP which is an ab initio method based on optimization models. Contacts predicted by the SVM model are ranked by SVM confidence scores, and a threshold is trained to improve the reliability of the predicted contacts. For TM proteins with no contacts above the threshold, COMSAT_MILP is used. The proposed hybrid contact prediction scheme was tested on two independent TM protein sets based on the contact definition of 14 Å between Cα‐Cα atoms. First, using a rigorous leave‐one‐protein‐out cross validation on the training set of 90 TM proteins, an accuracy of 66.8%, a coverage of 12.3%, a specificity of 99.3% and a Matthews' correlation coefficient (MCC) of 0.184 were obtained for residue pairs that are at least six amino acids apart. Second, when tested on a test set of 87 TM proteins, the proposed method showed a prediction accuracy of 64.5%, a coverage of 5.3%, a specificity of 99.4% and a MCC of 0.106. COMSAT shows satisfactory results when compared with 12 other state‐of‐the‐art predictors, and is more robust in terms of prediction accuracy as the length and complexity of TM protein increase. COMSAT is freely accessible at http://hpcc.siat.ac.cn/COMSAT/ . Proteins 2016; 84:332–348. © 2016 Wiley Periodicals, Inc.     

Great interactions: How binding incorrect partners can teach us about protein recognition and function

Protein–protein interactions play a key part in most biological processes and understanding their mechanism is a fundamental problem leading to numerous practical applications. The prediction of protein binding sites in particular is of paramount importance since proteins now represent a major class of therapeutic targets. Amongst others methods, docking simulations between two proteins known to interact can be a useful tool for the prediction of likely binding patches on a protein surface. From the analysis of the protein interfaces generated by a massive cross‐docking experiment using the 168 proteins of the Docking Benchmark 2.0, where all possible protein pairs, and not only experimental ones, have been docked together, we show that it is also possible to predict a protein's binding residues without having any prior knowledge regarding its potential interaction partners. Evaluating the performance of cross‐docking predictions using the area under the specificity‐sensitivity ROC curve (AUC) leads to an AUC value of 0.77 for the complete benchmark (compared to the 0.5 AUC value obtained for random predictions). Furthermore, a new clustering analysis performed on the binding patches that are scattered on the protein surface show that their distribution and growth will depend on the protein's functional group. Finally, in several cases, the binding‐site predictions resulting from the cross‐docking simulations will lead to the identification of an alternate interface, which corresponds to the interaction with a biomolecular partner that is not included in the original benchmark. Proteins 2016; 84:1408–1421. © 2016 The Authors Proteins: Structure, Function, and Bioinformatics Published by Wiley Periodicals, Inc.     

Genome‐wide computational determination of the human metalloproteome

Accurate prediction of protein function in humans is important for understanding biological processes at the molecular level in biomedicine and drug design. Over a third of proteins are commonly held to bind metal, and ～10% of human proteins, to bind zinc. Therefore, an initial step in protein function prediction frequently involves predicting metal ion binding. In recent years, methods have been developed to predict a set of residues in 3D space forming the metal‐ion binding site, often with a high degree of accuracy. Here, using extensions of these methods, we provide an extensive list of human proteins and their putative metal ion binding site residues, using translated gene sequences derived from the complete, resolved human genome. Under conditions of ～90% selectivity, over 900 new human putative metal ion binding proteins are identified. A statistical analysis of resolved metal ion binding sites in the human metalloproteome is furnished and the importance of remote homology analysis is demonstrated. As an example, a novel metal‐ion binding site involving a complex of a botulinum substrate with its inhibitor is presented. On the basis of the location of the predicted site and the interactions of the contacting residues at the complex interface, we postulate that metal ion binding in this region could influence complex formation and, consequently, the functioning of the protein. Thus, this work provides testable hypotheses about novel functions of known proteins. Proteins 2015; 83:931–939. © 2015 Wiley Periodicals, Inc.     

A novel method for protein-protein interaction site prediction using phylogenetic substitution models

Protein-protein binding events mediate many critical biological functions in the cell. Typically, functionally important sites in proteins can be well identified by considering sequence conservation. However, protein-protein interaction sites exhibit higher sequence variation than other functional regions, such as catalytic sites of enzymes. Consequently, the mutational behavior leading to weak sequence conservation poses significant challenges to the protein-protein interaction site prediction. Here, we present a phylogenetic framework to capture critical sequence variations that favor the selection of residues essential for protein-protein binding. Through the comprehensive analysis of diverse protein families, we show that protein binding interfaces exhibit distinct amino acid substitution as compared with other surface residues. On the basis of this analysis, we have developed a novel method, BindML, which utilizes the substitution models to predict protein-protein binding sites of protein with unknown interacting partners. BindML estimates the likelihood that a phylogenetic tree of a local surface region in a query protein structure follows the substitution patterns of protein binding interface and nonbinding surfaces. BindML is shown to perform well compared to alternative methods for protein binding interface prediction. The methodology developed in this study is very versatile in the sense that it can be generally applied for predicting other types of functional sites, such as DNA, RNA, and membrane binding sites in proteins.     

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.     

Combining features in a graphical model to predict protein binding sites

Large efforts have been made in classifying residues as binding sites in proteins using machine learning methods. The prediction task can be translated into the computational challenge of assigning each residue the label binding site or non‐binding site. Observational data comes from various possibly highly correlated sources. It includes the structure of the protein but not the structure of the complex. The model class of conditional random fields (CRFs) has previously successfully been used for protein binding site prediction. Here, a new CRF‐approach is presented that models the dependencies of residues using a general graphical structure defined as a neighborhood graph and thus our model makes fewer independence assumptions on the labels than sequential labeling approaches. A novel node feature “change in free energy” is introduced into the model, which is then denoted by ΔF‐CRF. Parameters are trained with an online large‐margin algorithm. Using the standard feature class relative accessible surface area alone, the general graph‐structure CRF already achieves higher prediction accuracy than the linear chain CRF of Li et al. ΔF‐CRF performs significantly better on a large range of false positive rates than the support‐vector‐machine‐based program PresCont of Zellner et al. on a homodimer set containing 128 chains. ΔF‐CRF has a broader scope than PresCont since it is not constrained to protein subgroups and requires no multiple sequence alignment. The improvement is attributed to the advantageous combination of the novel node feature with the standard feature and to the adopted parameter training method. Proteins 2015; 83:844–852. © 2015 Wiley Periodicals, Inc.     

Characterization of PDZ domain‐peptide interaction interface based on energetic patterns

PDZ domain is one of the abundant modular domains that recognize short peptide sequences to mediate protein–protein interactions. To decipher the binding specificity of PDZ domain, we analyzed the interactions between 11 mouse PDZ domains and 217 peptides using a method called MIECSVM, which energetically characterizes the domain‐peptide interaction using molecular interaction energy components (MIECs) and predicts binding specificity using support vector machine (SVM). Cross‐validation and leave‐one‐domain‐out test showed that the MIEC‐SVM using all 44 PDZ‐peptide residue pairs at the interaction interface outperformed the sequence‐based methods in the literature. A further feature (residue pair) selection procedure illustrated that 16 residue pairs were uninformative to the binding specificity, even though they contributed significantly (～50%) to the binding energy. If only using the 28 informative residue pairs, the performance of the MIEC‐SVM on predicting the PDZ binding specificity was significantly improved. This analysis suggests that the informative and uninformative residue interactions between the PDZ domain and the peptide may represent those contributing to binding specificity and affinity, respectively. We performed additional structural and energetic analyses to shed light on understanding how the PDZ‐peptide recognition is established. The success of the MIEC‐SVM method on PDZ domains in this study and SH3 domains in our previous studies illustrates its generality on characterizing protein‐ peptide interactions and understanding protein recognition from a structural and energetic viewpoint.     

Predicting the helix‐helix interactions from correlated residue mutations

Helix‐helix interactions are crucial in the structure assembly, stability and function of helix‐rich proteins including many membrane proteins. In spite of remarkable progresses over the past decades, the accuracy of predicting protein structures from their amino acid sequences is still far from satisfaction. In this work, we focused on a simpler problem, the prediction of helix‐helix interactions, the results of which could facilitate practical protein structure prediction by constraining the sampling space. Specifically, we started from the noisy 2D residue contact maps derived from correlated residue mutations, and utilized ridge detection to identify the characteristic residue contact patterns for helix‐helix interactions. The ridge information as well as a few additional features were then fed into a machine learning model HHConPred to predict interactions between helix pairs. In an independent test, our method achieved an F‐measure of ～60% for predicting helix‐helix interactions. Moreover, although the model was trained mainly using soluble proteins, it could be extended to membrane proteins with at least comparable performance relatively to previous approaches that were generated purely using membrane proteins. All data and source codes are available at http://166.111.152.91/Downloads.html or https://github.com/dpxiong/HHConPred .     

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.     

Analysis of anisotropic side-chain packing in proteins and application to high-resolution structure prediction

pi-pi, Cation-pi, and hydrophobic packing interactions contribute specificity to protein folding and stability to the native state. As a step towards developing improved models of these interactions in proteins, we compare the side-chain packing arrangements in native proteins to those found in compact decoys produced by the Rosetta de novo structure prediction method. We find enrichments in the native distributions for T-shaped and parallel offset arrangements of aromatic residue pairs, in parallel stacked arrangements of cation-aromatic pairs, in parallel stacked pairs involving proline residues, and in parallel offset arrangements for aliphatic residue pairs. We then investigate the extent to which the distinctive features of native packing can be explained using Lennard-Jones and electrostatics models. Finally, we derive orientation-dependent pi-pi, cation-pi and hydrophobic interaction potentials based on the differences between the native and compact decoy distributions and investigate their efficacy for high-resolution protein structure prediction. Surprisingly, the orientation-dependent potential derived from the packing arrangements of aliphatic side-chain pairs distinguishes the native structure from compact decoys better than the orientation-dependent potentials describing pi-pi and cation-pi interactions.     

Protein contact prediction using patterns of correlation

We describe a new method for using neural networks to predict residue contact pairs in a protein. The main inputs to the neural network are a set of 25 measures of correlated mutation between all pairs of residues in two "windows" of size 5 centered on the residues of interest. While the individual pair-wise correlations are a relatively weak predictor of contact, by training the network on windows of correlation the accuracy of prediction is significantly improved. The neural network is trained on a set of 100 proteins and then tested on a disjoint set of 1033 proteins of known structure. An average predictive accuracy of 21.7% is obtained taking the best L/2 predictions for each protein, where L is the sequence length. Taking the best L/10 predictions gives an average accuracy of 30.7%. The predictor is also tested on a set of 59 proteins from the CASP5 experiment. The accuracy is found to be relatively consistent across different sequence lengths, but to vary widely according to the secondary structure. Predictive accuracy is also found to improve by using multiple sequence alignments containing many sequences to calculate the correlations.     

A probabilistic model for secondary structure prediction from protein chemical shifts

Protein chemical shifts encode detailed structural information that is difficult and computationally costly to describe at a fundamental level. Statistical and machine learning approaches have been used to infer correlations between chemical shifts and secondary structure from experimental chemical shifts. These methods range from simple statistics such as the chemical shift index to complex methods using neural networks. Notwithstanding their higher accuracy, more complex approaches tend to obscure the relationship between secondary structure and chemical shift and often involve many parameters that need to be trained. We present hidden Markov models (HMMs) with Gaussian emission probabilities to model the dependence between protein chemical shifts and secondary structure. The continuous emission probabilities are modeled as conditional probabilities for a given amino acid and secondary structure type. Using these distributions as outputs of first‐ and second‐order HMMs, we achieve a prediction accuracy of 82.3%, which is competitive with existing methods for predicting secondary structure from protein chemical shifts. Incorporation of sequence‐based secondary structure prediction into our HMM improves the prediction accuracy to 84.0%. Our findings suggest that an HMM with correlated Gaussian distributions conditioned on the secondary structure provides an adequate generative model of chemical shifts. Proteins 2013; © 2012 Wiley Periodicals, Inc.     

Amino acid substitutions at protein–protein interfaces that modulate the oligomeric state

Despite similarities in their sequence and structure, there are a number of homologous proteins that adopt various oligomeric states. Comparisons of these homologous protein pairs, in terms of residue substitutions at the protein–protein interfaces, have provided fundamental characteristics that describe how proteins interact with each other. We have prepared a dataset composed of pairs of related proteins with different homo‐oligomeric states. Using the protein complexes, the interface residues were identified, and using structural alignments, the shadow‐interface residues have been defined as the surface residues that align with the interface residues. Subsequently, we investigated residue substitutions between the interfaces and the shadow interfaces. Based on the degree of the contributions to the interactions, the aligned sites of the interfaces and shadow interfaces were divided into primary and secondary sites; the primary sites are the focus of this work. The primary sites were further classified into two groups (i.e. exposed and buried) based on the degree to which the residue is buried within the shadow interfaces. Using these classifications, two simple mechanisms that mediate the oligomeric states were identified. In the primary‐exposed sites, the residues on the shadow interfaces are replaced by more hydrophobic or aromatic residues, which are physicochemically favored at protein–protein interfaces. In the primary‐buried sites, the residues on the shadow interfaces are replaced by larger residues that protrude into other proteins. These simple rules are satisfied in 23 out of 25 Structural Classification of Proteins (SCOP) families with a different‐oligomeric‐state pair, and thus represent a basic strategy for modulating protein associations and dissociations. Proteins 2010. © 2009 Wiley‐Liss, Inc.     

Tetramer protein complex interface residue pairs prediction with LSTM combined with graph representations

MotivationProtein-protein interactions are important for many biological processes. Theoretical understanding of the structurally determining factors of interaction sites will help to understand the underlying mechanism of protein-protein interactions. Taking advantage of advanced mathematical methods to correctly predict interaction sites will be useful. Although some previous studies have been devoted to the interaction interface of protein monomer and the interface residues between chains of protein dimers, very few studies about the interface residues prediction of protein multimers, including trimers, tetramer and even more monomers in a large protein complex. As we all know, a large number of proteins function with the form of multibody protein complexes. And the complexity of the protein multimers structure causes the difficulty of interface residues prediction on them. So, we hope to build a method for the prediction of protein tetramer interface residue pairs.ResultsHere, we developed a new deep network based on LSTM network combining with graph to predict protein tetramers interaction interface residue pairs. On account of the protein structure data is not the same as the image or video data which is well-arranged matrices, namely the Euclidean Structure mentioned in many researches. Because the Non-Euclidean Structure data can't keep the translation invariance, and we hope to extract some spatial features from this kind of data applying on deep learning, an algorithm combining with graph was developed to predict the interface residue pairs of protein interactions based on a topological graph building a relationship between vertexes and edges in graph theory combining multilayer Long Short-Term Memory network. First, selecting the training and test samples from the Protein Data Bank, and then extracting the physicochemical property features and the geometric features of surface residue associated with interfacial properties. Subsequently, we transform the protein multimers data to topological graphs and predict protein interaction interface residue pairs using the model. In addition, different types of evaluation indicators verified its validity.