An evolution based classifier for prediction of protein interfaces without using protein structures

Prediction of Protein-Protein Interaction Sites by Multifeature Fusion and RF with mRMR and IFS

Prediction of protein-protein interaction (PPI) sites is one of the most perplexing problems in drug discovery and computational biology. Although significant progress has been made by combining different machine learning techniques with a variety of distinct characteristics, the problem still remains unresolved. In this study, a technique for PPI sites is presented using a random forest (RF) algorithm followed by the minimum redundancy maximal relevance (mRMR) approach, and the method of incremental feature selection (IFS). Physicochemical properties of proteins and the features of the residual disorder, sequence conservation, secondary structure, and solvent accessibility are incorporated. Five 3D structural characteristics are also used to predict PPI sites. Analysis of features shows that 3D structural features such as relative solvent-accessible surface area (RASA) and surface curvature (SC) help in the prediction of PPI sites. Results show that the performance of the proposed predictor is superior to several other state-of-the-art predictors, whose average prediction accuracy is 81.44%, sensitivity is 82.17%, and specificity is 80.71%, respectively. The proposed predictor is expected to become a helpful tool for finding PPI sites, and the feature analysis presented in this study will give useful insights into protein interaction mechanisms.

Protein–Protein Interaction Methods and Protein Phase Separation

In the last decade, newly developed experimental methods have made it possible to highlight that macromolecules in the cell milieu physically interact to support physiology. This has shifted the problem of protein–protein interaction from a microscopic, electron-density scale to a mesoscopic one. Further, nowadays there is increasing evidence that proteins in the nucleus and in the cytoplasm can aggregate in membraneless organelles for different physiological reasons. In this scenario, it is urgent to face the problem of biomolecule functional annotation with efficient computational methods, suited to extract knowledge from reliable data and transfer information across different domains of investigation. Here, we revise the present state of the art of our knowledge of protein–protein interaction and the computational methods that differently implement it. Furthermore, we explore experimental and computational features of a set of proteins involved in phase separation.

ConvsPPIS: Identifying Protein-protein Interaction Sites by an Ensemble Convolutional Neural Network with Feature Graph

Background/Objective:

Protein-protein interactions are essentials for most cellular processes and thus, unveiling how proteins interact with is a crucial question that can be better understood by recognizing which residues participate in the interaction. Although many computational approaches have been proposed to predict interface residues, their feature perspective and model learning ability are not enough to achieve ideal results. So, our objective is to improve the predictive performance under considering feature perspective and new learning algorithm.

Method:

In this study, we proposed an ensemble deep convolutional neural network, which explores the context and positional context of consecutive residues within a protein sub-sequence. Specifically, unlike the feature view of previous methods, ConvsPPIS uses evolutionary, physicochemical, and structural protein characteristics to construct their own feature graph respectively. After that, three independent deep convolutional neural networks are trained on each type of feature graph for learning the underlying pattern in sub-sequence. Lastly, we integrated those three deep networks into an ensemble predictor with leveraging complementary information of those features to predict potential interface residues.

Results:

Some comparative experiments have conducted through 10-fold cross-validation. The results indicated that ConvsPPIS achieved superior performance on DBv5-Sel dataset with an accuracy of 88%. Additional experiments on CAPRI-Alone dataset demonstrated ConvsPPIS has also better prediction performance.

Conclusion:

The ConvsPPIS method provided a new perspective to capture protein feature expression for identifying protein-protein interaction sites. The results proved the superiority of this method.

An Evolutionary Trace method defines functionally important bases and sites common to RNA families

Functional non-coding (fnc)RNAs are nucleotide sequences of varied lengths, structures, and mechanisms that ubiquitously influence gene expression and translation, genome stability and dynamics, and human health and disease. Here, to shed light on their functional determinants, we seek to exploit the evolutionary record of variation and divergence read from sequence comparisons. The approach follows the phylogenetic Evolutionary Trace (ET) paradigm, first developed and extensively validated on proteins. We assigned a relative rank of importance to every base in a study of 1070 functional RNAs, including the ribosome, and observed evolutionary patterns strikingly similar to those seen in proteins, namely, (1) the top-ranked bases clustered in secondary and tertiary structures. (2) In turn, these clusters mapped functional regions for catalysis, binding proteins and drugs, post-transcriptional modification, and deleterious mutations. (3) Moreover, the quantitative quality of these clusters correlated with the identification of functional regions. (4) As a result of this correlation, smoother structural distributions of evolutionary important nucleotides improved functional site predictions. Thus, in practice, phylogenetic analysis can broadly identify functional determinants in RNA sequences and functional sites in RNA structures, and reveal details on the basis of RNA molecular functions. As example of application, we report several previously undocumented and potentially functional ET nucleotide clusters in the ribosome. This work is broadly relevant to studies of structure-function in ribonucleic acids. Additionally, this generalization of ET shows that evolutionary constraints among sequence, structure, and function are similar in structured RNA and proteins. RNA ET is currently available as part of the ET command-line package, and will be available as a web-server.

Traditionally, RNA has been delegated to the role of an intermediate between DNA and proteins. However, we now recognize that RNAs are broadly functional beyond their role in translation, and that a number of diverse classes exist. Because functional, non-coding RNAs are prevalent in biology and impact human health, it is important to better understand their functional determinants. However, the classical solution to this problem, targeted mutagenesis, is time-consuming and scales poorly. We propose an alternative computational approach to this problem, the Evolutionary Trace method. Previously developed and validated for proteins, Evolutionary Trace examines evolutionary history of a molecule and predicts evolutionarily important residues in the sequence. We apply Evolutionary Trace to a set of diverse RNAs, and find that the evolutionarily important nucleotides cluster on the three-dimensional structure, and that these clusters closely overlap functional sites. We also find that the clustering property can be used to refine and improve predictions. These findings are in close agreement with our observations of Evolutionary Trace in proteins, and suggest that structured functional RNAs and proteins evolve under similar constraints. In practice, the approach is to be used by RNA researches seeking insight into their molecule of interest, and the Evolutionary Trace program, along with a working example, is available at https://github.com/LichtargeLab/RNA_ET_ms.

Protein-Protein Docking Using Evolutionary Information

The structural modeling of protein complexes by docking simulations has been attracting increasing interest with the rise of proteomics and of the number of experimentally identified binary interactions. Structures of unbound partners, either modeled or experimentally determined, can be used as input to sample as extensively as possible all putative binding modes and single out the most plausible ones. At the scoring step, evolutionary information contained in the joint multiple sequence alignments of both partners can provide key insights to recognize correct interfaces. Here, we describe a computational protocol based on the InterEvDock web server to exploit coevolution constraints in protein-protein docking methods. We provide methodology guidelines to prepare the input protein structures and generate improved alignments. We also explain how to extract and use the information returned by the server through the analysis of two representative examples.

Utilizing knowledge base of amino acids structural neighborhoods to predict protein-protein interaction sites

BACKGROUND

Protein-protein interactions (PPI) play a key role in an investigation of various biochemical processes, and their identification is thus of great importance. Although computational prediction of which amino acids take part in a PPI has been an active field of research for some time, the quality of in-silico methods is still far from perfect.

RESULTS

We have developed a novel prediction method called INSPiRE which benefits from a knowledge base built from data available in Protein Data Bank. All proteins involved in PPIs were converted into labeled graphs with nodes corresponding to amino acids and edges to pairs of neighboring amino acids. A structural neighborhood of each node was then encoded into a bit string and stored in the knowledge base. When predicting PPIs, INSPiRE labels amino acids of unknown proteins as interface or non-interface based on how often their structural neighborhood appears as interface or non-interface in the knowledge base. We evaluated INSPiRE's behavior with respect to different types and sizes of the structural neighborhood. Furthermore, we examined the suitability of several different features for labeling the nodes. Our evaluations showed that INSPiRE clearly outperforms existing methods with respect to Matthews correlation coefficient.

CONCLUSION

In this paper we introduce a new knowledge-based method for identification of protein-protein interaction sites called INSPiRE. Its knowledge base utilizes structural patterns of known interaction sites in the Protein Data Bank which are then used for PPI prediction. Extensive experiments on several well-established datasets show that INSPiRE significantly surpasses existing PPI approaches.

Predicting Protein-Protein Interaction Sites Using Sequence Descriptors and Site Propensity of Neighboring Amino Acids

Information about the interface sites of Protein–Protein Interactions (PPIs) is useful for many biological research works. However, despite the advancement of experimental techniques, the identification of PPI sites still remains as a challenging task. Using a statistical learning technique, we proposed a computational tool for predicting PPI interaction sites. As an alternative to similar approaches requiring structural information, the proposed method takes all of the input from protein sequences. In addition to typical sequence features, our method takes into consideration that interaction sites are not randomly distributed over the protein sequence. We characterized this positional preference using protein complexes with known structures, proposed a numerical index to estimate the propensity and then incorporated the index into a learning system. The resulting predictor, without using structural information, yields an area under the ROC curve (AUC) of 0.675, recall of 0.597, precision of 0.311 and accuracy of 0.583 on a ten-fold cross-validation experiment. This performance is comparable to the previous approach in which structural information was used. Upon introducing the B-factor data to our predictor, we demonstrated that the AUC can be further improved to 0.750. The tool is accessible at http://bsaltools.ym.edu.tw/predppis.

Progress and challenges in predicting protein interfaces

The majority of biological processes are mediated via protein-protein interactions. Determination of residues participating in such interactions improves our understanding of molecular mechanisms and facilitates the development of therapeutics. Experimental approaches to identifying interacting residues, such as mutagenesis, are costly and time-consuming and thus, computational methods for this purpose could streamline conventional pipelines. Here we review the field of computational protein interface prediction. We make a distinction between methods which address proteins in general and those targeted at antibodies, owing to the radically different binding mechanism of antibodies. We organize the multitude of currently available methods hierarchically based on required input and prediction principles to provide an overview of the field.

Sequence specificity between interacting and non-interacting homologs identifies interface residues--a homodimer and monomer use case

Background

Protein families participating in protein-protein interactions may contain sub-families that have different binding characteristics, ranging from right binding to showing no interaction at all. Composition differences at the sequence level in these sub-families are often decisive to their differential functional interaction. Methods to predict interface sites from protein sequences typically exploit conservation as a signal. Here, instead, we provide proof of concept that the sequence specificity between interacting versus non-interacting groups can be exploited to recognise interaction sites.

Results

We collected homodimeric and monomeric proteins and formed homologous groups, each having an interacting (homodimer) subgroup and a non-interacting (monomer) subgroup. We then compiled multiple sequence alignments of the proteins in the homologous groups and identified compositional differences between the homodimeric and monomeric subgroups for each of the alignment positions. Our results show that this specificity signal distinguishes interface and other surface residues with 40.9 % recall and up to 25.1 % precision.

Conclusions

To our best knowledge, this is the first large scale study that exploits sequence specificity between interacting and non-interacting homologs to predict interaction sites from sequence information only. The performance obtained indicates that this signal contains valuable information to identify protein-protein interaction sites.

Electronic supplementary material

The online version of this article (doi:10.1186/s12859-015-0758-y) contains supplementary material, which is available to authorized users.

MSCA: a spectral comparison algorithm between time series to identify protein-protein interactions

Background

The interactions between pathogen proteins and their hosts allow pathogens to manipulate host cellular mechanisms to their advantage. The identification of host proteins that are targeted by virulent pathogen proteins is crucial to increase our understanding of infection mechanisms and to propose new therapeutics that target pathogens. Understanding the virulence mechanisms of pathogens requires a detailed molecular description of the proteins involved, but acquiring this knowledge is time consuming and prohibitively expensive. Therefore, we develop a statistical method based on hypothesis testing to compare the time series obtained from conversion of the physicochemical characteristics of the amino acids that form the primary structure of proteins and thus to propose potential functional relation between proteins. We called this algorithm the multiple spectral comparison algorithm (MSCA); the MSCA was inspired by the BLASTP tool and was implemented in R code. The algorithm compares and relates multiple time series according to their spectral similarities, and the biological relation between them could be interpreted as either a similar function or protein-protein interaction (PPI).

Results

A simulation study showed that the MSCA works satisfactorily well when we compare unequal time series generated from ARMA processes because its power was close to 1. The MSCA presented a 70% average accuracy of detecting protein interactions using a threshold of 0.7 for our spectral measure, indicating that this algorithm could predict novel PPIs and pathogen-host interactions (PHIs) with acceptable confidence. The MSCA also was validated by its identification of well-known interactions of the human proteins MAGI1, SCRIB and JAK1, as well as interactions of the virulence proteins ROP16, ROP18, ROP17 and ROP5. We verified the spectral similarities for human intraspecific PPIs and PHIs that were previously demonstrated experimentally by other authors. We suggest that human GBP (GTPase group induced by interferon) and the CREB transcription factor family could be human substrates for the complex of ROP18, ROP17 and ROP5.

Conclusions

Using multiple-hypothesis testing between the spectral densities of a set of unequal time series, we developed an algorithm that is able to identify the similarities or interactions between a set of proteins.

Electronic supplementary material

The online version of this article (doi:10.1186/s12859-015-0599-8) contains supplementary material, which is available to authorized users.

CRF-based models of protein surfaces improve protein-protein interaction site predictions

Background

The identification of protein-protein interaction sites is a computationally challenging task and important for understanding the biology of protein complexes. There is a rich literature in this field. A broad class of approaches assign to each candidate residue a real-valued score that measures how likely it is that the residue belongs to the interface. The prediction is obtained by thresholding this score.

Some probabilistic models classify the residues on the basis of the posterior probabilities. In this paper, we introduce pairwise conditional random fields (pCRFs) in which edges are not restricted to the backbone as in the case of linear-chain CRFs utilized by Li et al. (2007). In fact, any 3D-neighborhood relation can be modeled. On grounds of a generalized Viterbi inference algorithm and a piecewise training process for pCRFs, we demonstrate how to utilize pCRFs to enhance a given residue-wise score-based protein-protein interface predictor on the surface of the protein under study. The features of the pCRF are solely based on the interface predictions scores of the predictor the performance of which shall be improved.

Results

We performed three sets of experiments with synthetic scores assigned to the surface residues of proteins taken from the data set PlaneDimers compiled by Zellner et al. (2011), from the list published by Keskin et al. (2004) and from the very recent data set due to Cukuroglu et al. (2014). That way we demonstrated that our pCRF-based enhancer is effective given the interface residue score distribution and the non-interface residue score are unimodal.

Moreover, the pCRF-based enhancer is also successfully applicable, if the distributions are only unimodal over a certain sub-domain. The improvement is then restricted to that domain. Thus we were able to improve the prediction of the PresCont server devised by Zellner et al. (2011) on PlaneDimers.

Conclusions

Our results strongly suggest that pCRFs form a methodological framework to improve residue-wise score-based protein-protein interface predictors given the scores are appropriately distributed. A prototypical implementation of our method is accessible at http://ppicrf.informatik.uni-goettingen.de/index.html.

Prediction and redesign of protein-protein interactions

Understanding the molecular basis of protein function remains a central goal of biology, with the hope to elucidate the role of human genes in health and in disease, and to rationally design therapies through targeted molecular perturbations. We review here some of the computational techniques and resources available for characterizing a critical aspect of protein function - those mediated by protein-protein interactions (PPI). We describe several applications and recent successes of the Evolutionary Trace (ET) in identifying molecular events and shapes that underlie protein function and specificity in both eukaryotes and prokaryotes. ET is a part of analytical approaches based on the successes and failures of evolution that enable the rational control of PPI.

Transient protein-protein interface prediction: datasets, features, algorithms, and the RAD-T predictor

Background

Transient protein-protein interactions (PPIs), which underly most biological processes, are a prime target for therapeutic development. Immense progress has been made towards computational prediction of PPIs using methods such as protein docking and sequence analysis. However, docking generally requires high resolution structures of both of the binding partners and sequence analysis requires that a significant number of recurrent patterns exist for the identification of a potential binding site. Researchers have turned to machine learning to overcome some of the other methods’ restrictions by generalising interface sites with sets of descriptive features. Best practices for dataset generation, features, and learning algorithms have not yet been identified or agreed upon, and an analysis of the overall efficacy of machine learning based PPI predictors is due, in order to highlight potential areas for improvement.

Results

The presence of unknown interaction sites as a result of limited knowledge about protein interactions in the testing set dramatically reduces prediction accuracy. Greater accuracy in labelling the data by enforcing higher interface site rates per domain resulted in an average 44% improvement across multiple machine learning algorithms. A set of 10 biologically unrelated proteins that were consistently predicted on with high accuracy emerged through our analysis. We identify seven features with the most predictive power over multiple datasets and machine learning algorithms. Through our analysis, we created a new predictor, RAD-T, that outperforms existing non-structurally specializing machine learning protein interface predictors, with an average 59% increase in MCC score on a dataset with a high number of interactions.

Conclusion

Current methods of evaluating machine-learning based PPI predictors tend to undervalue their performance, which may be artificially decreased by the presence of un-identified interaction sites. Changes to predictors’ training sets will be integral to the future progress of interface prediction by machine learning methods. We reveal the need for a larger test set of well studied proteins or domain-specific scoring algorithms to compensate for poor interaction site identification on proteins in general.

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.

SVM based model generation for binding site prediction on helix turn helix motif type of transcription factors in eukaryotes

Support vector machine is a class of machine learning algorithms which uses a set of related supervised learning methods for classification and regression. Nowadays this method is vividly applied to many detection problems related with secondary structure, tumor cell and binding residue prediction. In this work, support vector machines (SVMs) have been trained on 90 sequences of transcription factors with HTH motif. Four sequence features were used as attribute for the prediction of interaction site in HTH motif. A web page was also developed so that user can easily enter the protein sequence and receive the output as interaction site predicted or not predicted. The generated model shows a very high amount of accuracy, sensitivity and specificity which proves to be a good model for the selected case.

Identification of DNA-binding and protein-binding proteins using enhanced graph wavelet features

Interactions between biomolecules play an essential role in various biological processes. For predicting DNA-binding or protein-binding proteins, many machine-learning-based techniques have used various types of features to represent the interface of the complexes, but they only deal with the properties of a single atom in the interface and do not take into account the information of neighborhood atoms directly. This paper proposes a new feature representation method for biomolecular interfaces based on the theory of graph wavelet. The enhanced graph wavelet features (EGWF) provides an effective way to characterize interface feature through adding physicochemical features and exploiting a graph wavelet formulation. Particularly, graph wavelet condenses the information around the center atom, and thus enhances the discrimination of features of biomolecule binding proteins in the feature space. Experiment results show that EGWF performs effectively for predicting DNA-binding and protein-binding proteins in terms of Matthew's correlation coefficient (MCC) score and the area value under the receiver operating characteristic curve (AUC).

The development of a universal in silico predictor of protein-protein interactions

Protein-protein interactions (PPIs) are essential for understanding the function of biological systems and have been characterized using a vast array of experimental techniques. These techniques detect only a small proportion of all PPIs and are labor intensive and time consuming. Therefore, the development of computational methods capable of predicting PPIs accelerates the pace of discovery of new interactions. This paper reports a machine learning-based prediction model, the Universal In Silico Predictor of Protein-Protein Interactions (UNISPPI), which is a decision tree model that can reliably predict PPIs for all species (including proteins from parasite-host associations) using only 20 combinations of amino acids frequencies from interacting and non-interacting proteins as learning features. UNISPPI was able to correctly classify 79.4% and 72.6% of experimentally supported interactions and non-interacting protein pairs, respectively, from an independent test set. Moreover, UNISPPI suggests that the frequencies of the amino acids asparagine, cysteine and isoleucine are important features for distinguishing between interacting and non-interacting protein pairs. We envisage that UNISPPI can be a useful tool for prioritizing interactions for experimental validation.

InterEvScore: a novel coarse-grained interface scoring function using a multi-body statistical potential coupled to evolution

MOTIVATION

Structural prediction of protein interactions currently remains a challenging but fundamental goal. In particular, progress in scoring functions is critical for the efficient discrimination of near-native interfaces among large sets of decoys. Many functions have been developed using knowledge-based potentials, but few make use of multi-body interactions or evolutionary information, although multi-residue interactions are crucial for protein-protein binding and protein interfaces undergo significant selection pressure to maintain their interactions.

RESULTS

This article presents InterEvScore, a novel scoring function using a coarse-grained statistical potential including two- and three-body interactions, which provides each residue with the opportunity to contribute in its most favorable local structural environment. Combination of this potential with evolutionary information considerably improves scoring results on the 54 test cases from the widely used protein docking benchmark for which evolutionary information can be collected. We analyze how our way to include evolutionary information gradually increases the discriminative power of InterEvScore. Comparison with several previously published scoring functions (ZDOCK, ZRANK and SPIDER) shows the significant progress brought by InterEvScore.

AVAILABILITY

http://biodev.cea.fr/interevol/interevscore

CONTACT

guerois@cea.fr

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Alternative protein-protein interfaces are frequent exceptions

The intricate molecular details of protein-protein interactions (PPIs) are crucial for function. Therefore, measuring the same interacting protein pair again, we expect the same result. This work measured the similarity in the molecular details of interaction for the same and for homologous protein pairs between different experiments. All scores analyzed suggested that different experiments often find exceptions in the interfaces of similar PPIs: up to 22% of all comparisons revealed some differences even for sequence-identical pairs of proteins. The corresponding number for pairs of close homologs reached 68%. Conversely, the interfaces differed entirely for 12-29% of all comparisons. All these estimates were calculated after redundancy reduction. The magnitude of interface differences ranged from subtle to the extreme, as illustrated by a few examples. An extreme case was a change of the interacting domains between two observations of the same biological interaction. One reason for different interfaces was the number of copies of an interaction in the same complex: the probability of observing alternative binding modes increases with the number of copies. Even after removing the special cases with alternative hetero-interfaces to the same homomer, a substantial variability remained. Our results strongly support the surprising notion that there are many alternative solutions to make the intricate molecular details of PPIs crucial for function.

ETAscape: analyzing protein networks to predict enzymatic function and substrates in Cytoscape

Most proteins lack experimentally validated functions. To address this problem, we implemented the Evolutionary Trace Annotation (ETA) method in the Cytoscape network visualization environment. The result is the ETAscape plugin, which builds a structural genomics network based on local structural and evolutionary similarities among proteins and then globally diffuses known annotations across the resulting network. The plugin displays these novel functional annotations, their confidence, the molecular basis for individual matches and the set of matches that lead to a prediction.

AVAILABILITY

The ETA Network Plugin is available publicly for download at http://mammoth.bcm.tmc.edu/networks/.

Protein-protein interaction site predictions with three-dimensional probability distributions of interacting atoms on protein surfaces

Protein-protein interactions are key to many biological processes. Computational methodologies devised to predict protein-protein interaction (PPI) sites on protein surfaces are important tools in providing insights into the biological functions of proteins and in developing therapeutics targeting the protein-protein interaction sites. One of the general features of PPI sites is that the core regions from the two interacting protein surfaces are complementary to each other, similar to the interior of proteins in packing density and in the physicochemical nature of the amino acid composition. In this work, we simulated the physicochemical complementarities by constructing three-dimensional probability density maps of non-covalent interacting atoms on the protein surfaces. The interacting probabilities were derived from the interior of known structures. Machine learning algorithms were applied to learn the characteristic patterns of the probability density maps specific to the PPI sites. The trained predictors for PPI sites were cross-validated with the training cases (consisting of 432 proteins) and were tested on an independent dataset (consisting of 142 proteins). The residue-based Matthews correlation coefficient for the independent test set was 0.423; the accuracy, precision, sensitivity, specificity were 0.753, 0.519, 0.677, and 0.779 respectively. The benchmark results indicate that the optimized machine learning models are among the best predictors in identifying PPI sites on protein surfaces. In particular, the PPI site prediction accuracy increases with increasing size of the PPI site and with increasing hydrophobicity in amino acid composition of the PPI interface; the core interface regions are more likely to be recognized with high prediction confidence. The results indicate that the physicochemical complementarity patterns on protein surfaces are important determinants in PPIs, and a substantial portion of the PPI sites can be predicted correctly with the physicochemical complementarity features based on the non-covalent interaction data derived from protein interiors.

SPPS: a sequence-based method for predicting probability of protein-protein interaction partners

Background

The molecular network sustained by different types of interactions among proteins is widely manifested as the fundamental driving force of cellular operations. Many biological functions are determined by the crosstalk between proteins rather than by the characteristics of their individual components. Thus, the searches for protein partners in global networks are imperative when attempting to address the principles of biology.

Results

We have developed a web-based tool “Sequence-based Protein Partners Search” (SPPS) to explore interacting partners of proteins, by searching over a large repertoire of proteins across many species. SPPS provides a database containing more than 60,000 protein sequences with annotations and a protein-partner search engine in two modes (Single Query and Multiple Query). Two interacting proteins of human FBXO6 protein have been found using the service in the study. In addition, users can refine potential protein partner hits by using annotations and possible interactive network in the SPPS web server.

Conclusions

SPPS provides a new type of tool to facilitate the identification of direct or indirect protein partners which may guide scientists on the investigation of new signaling pathways. The SPPS server is available to the public at http://mdl.shsmu.edu.cn/SPPS/.

Protein docking prediction using predicted protein-protein interface

Background

Many important cellular processes are carried out by protein complexes. To provide physical pictures of interacting proteins, many computational protein-protein prediction methods have been developed in the past. However, it is still difficult to identify the correct docking complex structure within top ranks among alternative conformations.

Results

We present a novel protein docking algorithm that utilizes imperfect protein-protein binding interface prediction for guiding protein docking. Since the accuracy of protein binding site prediction varies depending on cases, the challenge is to develop a method which does not deteriorate but improves docking results by using a binding site prediction which may not be 100% accurate. The algorithm, named PI-LZerD (using Predicted Interface with Local 3D Zernike descriptor-based Docking algorithm), is based on a pair wise protein docking prediction algorithm, LZerD, which we have developed earlier. PI-LZerD starts from performing docking prediction using the provided protein-protein binding interface prediction as constraints, which is followed by the second round of docking with updated docking interface information to further improve docking conformation. Benchmark results on bound and unbound cases show that PI-LZerD consistently improves the docking prediction accuracy as compared with docking without using binding site prediction or using the binding site prediction as post-filtering.

Conclusion

We have developed PI-LZerD, a pairwise docking algorithm, which uses imperfect protein-protein binding interface prediction to improve docking accuracy. PI-LZerD consistently showed better prediction accuracy over alternative methods in the series of benchmark experiments including docking using actual docking interface site predictions as well as unbound docking cases.

Prediction of protein-protein interaction sites using patch-based residue characterization

Identifying protein-protein interaction sites provides important clues to the function of a protein and is becoming increasingly relevant in topics such as systems biology and drug discovery. Using a patch-based model for residue characterization, we trained random forest classifiers for residue-based interface prediction, which was followed by a clustering procedure to produce patches for patch-based interface prediction. For residue-based interface prediction, our method achieves a specificity rate of 0.7 and a sensitivity rate of 0.78. For patch-based interface prediction, a success rate of 0.80 is achieved. Based on same datasets, we also compare it with several published methods. The results show that our method is a successful predictor for residue-based and patch-based interface prediction.

HomPPI: a class of sequence homology based protein-protein interface prediction methods

BACKGROUND

Although homology-based methods are among the most widely used methods for predicting the structure and function of proteins, the question as to whether interface sequence conservation can be effectively exploited in predicting protein-protein interfaces has been a subject of debate.

RESULTS

We studied more than 300,000 pair-wise alignments of protein sequences from structurally characterized protein complexes, including both obligate and transient complexes. We identified sequence similarity criteria required for accurate homology-based inference of interface residues in a query protein sequence.Based on these analyses, we developed HomPPI, a class of sequence homology-based methods for predicting protein-protein interface residues. We present two variants of HomPPI: (i) NPS-HomPPI (Non partner-specific HomPPI), which can be used to predict interface residues of a query protein in the absence of knowledge of the interaction partner; and (ii) PS-HomPPI (Partner-specific HomPPI), which can be used to predict the interface residues of a query protein with a specific target protein.Our experiments on a benchmark dataset of obligate homodimeric complexes show that NPS-HomPPI can reliably predict protein-protein interface residues in a given protein, with an average correlation coefficient (CC) of 0.76, sensitivity of 0.83, and specificity of 0.78, when sequence homologs of the query protein can be reliably identified. NPS-HomPPI also reliably predicts the interface residues of intrinsically disordered proteins. Our experiments suggest that NPS-HomPPI is competitive with several state-of-the-art interface prediction servers including those that exploit the structure of the query proteins. The partner-specific classifier, PS-HomPPI can, on a large dataset of transient complexes, predict the interface residues of a query protein with a specific target, with a CC of 0.65, sensitivity of 0.69, and specificity of 0.70, when homologs of both the query and the target can be reliably identified. The HomPPI web server is available at http://homppi.cs.iastate.edu/.

CONCLUSIONS

Sequence homology-based methods offer a class of computationally efficient and reliable approaches for predicting the protein-protein interface residues that participate in either obligate or transient interactions. For query proteins involved in transient interactions, the reliability of interface residue prediction can be improved by exploiting knowledge of putative interaction partners.

Binding site prediction for protein-protein interactions and novel motif discovery using re-occurring polypeptide sequences

Background

While there are many methods for predicting protein-protein interaction, very few can determine the specific site of interaction on each protein. Characterization of the specific sequence regions mediating interaction (binding sites) is crucial for an understanding of cellular pathways. Experimental methods often report false binding sites due to experimental limitations, while computational methods tend to require data which is not available at the proteome-scale. Here we present PIPE-Sites, a novel method of protein specific binding site prediction based on pairs of re-occurring polypeptide sequences, which have been previously shown to accurately predict protein-protein interactions. PIPE-Sites operates at high specificity and requires only the sequences of query proteins and a database of known binary interactions with no binding site data, making it applicable to binding site prediction at the proteome-scale.

Results

PIPE-Sites was evaluated using a dataset of 265 yeast and 423 human interacting proteins pairs with experimentally-determined binding sites. We found that PIPE-Sites predictions were closer to the confirmed binding site than those of two existing binding site prediction methods based on domain-domain interactions, when applied to the same dataset. Finally, we applied PIPE-Sites to two datasets of 2347 yeast and 14,438 human novel interacting protein pairs predicted to interact with high confidence. An analysis of the predicted interaction sites revealed a number of protein subsequences which are highly re-occurring in binding sites and which may represent novel binding motifs.

Conclusions

PIPE-Sites is an accurate method for predicting protein binding sites and is applicable to the proteome-scale. Thus, PIPE-Sites could be useful for exhaustive analysis of protein binding patterns in whole proteomes as well as discovery of novel binding motifs. PIPE-Sites is available online at http://pipe-sites.cgmlab.org/.

In silico modeling of pH-optimum of protein-protein binding

Protein-protein association is a pH-dependent process and thus the binding affinity depends on the local pH. In vivo the association occurs in a particular cellular compartment, where the individual monomers are supposed to meet and form a complex. Since the monomers and the complex exist in the same micro environment, it is plausible that they coevolved toward its properties, in particular, toward the characteristic subcellular pH. Here we show that the pH at which the monomers are most stable (pH-optimum) or the pH at which stability is almost pH-independent (pH-flat) of monomers are correlated with the pH-optimum of maximal affinity (pH-optimum of binding) or pH interval at which affinity is almost pH-independent (pH-flat of binding) of the complexes made of the corresponding monomers. The analysis of interfacial properties of protein complexes demonstrates that pH-dependent properties can be roughly estimated using the interface charge alone. In addition, we introduce a parameter beta, proportional to the square root of the absolute product of the net charges of monomers, and show that protein complexes characterized with small or very large beta tend to have neutral pH-optimum. Further more, protein complexes made of monomers carrying the same polarity net charge at neutral pH have either very low or very high pH-optimum of binding. These findings are used to propose empirical rule for predicting pH-optimum of binding provided that the amino acid compositions of the corresponding monomers are available.

Interaction site prediction by structural similarity to neighboring clusters in protein-protein interaction networks

BACKGROUND

Recently, revealing the function of proteins with protein-protein interaction (PPI) networks is regarded as one of important issues in bioinformatics. With the development of experimental methods such as the yeast two-hybrid method, the data of protein interaction have been increasing extremely. Many databases dealing with these data comprehensively have been constructed and applied to analyzing PPI networks. However, few research on prediction interaction sites using both PPI networks and the 3D protein structures complementarily has explored.

RESULTS

We propose a method of predicting interaction sites in proteins with unknown function by using both of PPI networks and protein structures. For a protein with unknown function as a target, several clusters are extracted from the neighboring proteins based on their structural similarity. Then, interaction sites are predicted by extracting similar sites from the group of a protein cluster and the target protein. Moreover, the proposed method can improve the prediction accuracy by introducing repetitive prediction process.

CONCLUSIONS

The proposed method has been applied to small scale dataset, then the effectiveness of the method has been confirmed. The challenge will now be to apply the method to large-scale datasets.

Protein-protein binding site prediction by local structural alignment

Generalization of an earlier algorithm has led to the development of new local structural alignment algorithms for prediction of protein-protein binding sites. The algorithms use maximum cliques on protein graphs to define structurally similar protein regions. The search for structural neighbors in the new algorithms has been extended to all the proteins in the PDB and the query protein is compared to more than 60,000 proteins or over 300,000 single-chain structures. The resulting structural similarities are combined and used to predict the protein binding sites. This study shows that the location of protein binding sites can be predicted by comparing only local structural similarities irrespective of general protein folds.

Sequence-based identification of interface residues by an integrative profile combining hydrophobic and evolutionary information

BACKGROUND

Protein-protein interactions play essential roles in protein function determination and drug design. Numerous methods have been proposed to recognize their interaction sites, however, only a small proportion of protein complexes have been successfully resolved due to the high cost. Therefore, it is important to improve the performance for predicting protein interaction sites based on primary sequence alone.

RESULTS

We propose a new idea to construct an integrative profile for each residue in a protein by combining its hydrophobic and evolutionary information. A support vector machine (SVM) ensemble is then developed, where SVMs train on different pairs of positive (interface sites) and negative (non-interface sites) subsets. The subsets having roughly the same sizes are grouped in the order of accessible surface area change before and after complexation. A self-organizing map (SOM) technique is applied to group similar input vectors to make more accurate the identification of interface residues. An ensemble of ten-SVMs achieves an MCC improvement by around 8% and F1 improvement by around 9% over that of three-SVMs. As expected, SVM ensembles constantly perform better than individual SVMs. In addition, the model by the integrative profiles outperforms that based on the sequence profile or the hydropathy scale alone. As our method uses a small number of features to encode the input vectors, our model is simpler, faster and more accurate than the existing methods.

CONCLUSIONS

The integrative profile by combining hydrophobic and evolutionary information contributes most to the protein-protein interaction prediction. Results show that evolutionary context of residue with respect to hydrophobicity makes better the identification of protein interface residues. In addition, the ensemble of SVM classifiers improves the prediction performance.

AVAILABILITY

Datasets and software are available at http://mail.ustc.edu.cn/~bigeagle/BMCBioinfo2010/index.htm.

Applying the Naïve Bayes classifier with kernel density estimation to the prediction of protein-protein interaction sites

MOTIVATION

The limited availability of protein structures often restricts the functional annotation of proteins and the identification of their protein-protein interaction sites. Computational methods to identify interaction sites from protein sequences alone are, therefore, required for unraveling the functions of many proteins. This article describes a new method (PSIVER) to predict interaction sites, i.e. residues binding to other proteins, in protein sequences. Only sequence features (position-specific scoring matrix and predicted accessibility) are used for training a Naïve Bayes classifier (NBC), and conditional probabilities of each sequence feature are estimated using a kernel density estimation method (KDE).

RESULTS

The leave-one out cross-validation of PSIVER achieved a Matthews correlation coefficient (MCC) of 0.151, an F-measure of 35.3%, a precision of 30.6% and a recall of 41.6% on a non-redundant set of 186 protein sequences extracted from 105 heterodimers in the Protein Data Bank (consisting of 36 219 residues, of which 15.2% were known interface residues). Even though the dataset used for training was highly imbalanced, a randomization test demonstrated that the proposed method managed to avoid overfitting. PSIVER was also tested on 72 sequences not used in training (consisting of 18 140 residues, of which 10.6% were known interface residues), and achieved an MCC of 0.135, an F-measure of 31.5%, a precision of 25.0% and a recall of 46.5%, outperforming other publicly available servers tested on the same dataset. PSIVER enables experimental biologists to identify potential interface residues in unknown proteins from sequence information alone, and to mutate those residues selectively in order to unravel protein functions.

AVAILABILITY

Freely available on the web at http://tardis.nibio.go.jp/PSIVER/

Conserved residue clusters at protein-protein interfaces and their use in binding site identification

BACKGROUND

Biological evolution conserves protein residues that are important for structure and function. Both protein stability and function often require a certain degree of structural co-operativity between spatially neighboring residues and it has previously been shown that conserved residues occur clustered together in protein tertiary structures, enzyme active sites and protein-DNA interfaces. Residues comprising protein interfaces are often more conserved compared to those occurring elsewhere on the protein surface. We investigate the extent to which conserved residues within protein-protein interfaces are clustered together in three-dimensions.

RESULTS

Out of 121 and 392 interfaces in homodimers and heterocomplexes, 96.7 and 86.7%, respectively, have the conserved positions clustered within the overall interface region. The significance of this clustering was established in comparison to what is seen for the subsets of the same size of randomly selected residues from the interface. Conserved residues occurring in larger interfaces could often be sub-divided into two or more distinct sub-clusters. These structural cluster(s) comprising conserved residues indicate functionally important regions within the protein-protein interface that can be targeted for further structural and energetic analysis by experimental scanning mutagenesis. Almost 60% of experimental hot spot residues (with DeltaDeltaG > 2 kcal/mol) were localized to these conserved residue clusters. An analysis of the residue types that are enriched within these conserved subsets compared to the overall interface showed that hydrophobic and aromatic residues are favored, but charged residues (both positive and negative) are less common. The potential use of this method for discriminating binding sites (interfaces) versus random surface patches was explored by comparing the clustering of conserved residues within each of these regions--in about 50% cases the true interface is ranked among the top 10% of all surface patches.

CONCLUSIONS

Protein-protein interaction sites are much larger than small molecule biding sites, but still conserved residues are not randomly distributed over the whole interface and are distinctly clustered. The clustered nature of evolutionarily conserved residues within interfaces as compared to those within other surface patches not involved in binding has important implications for the identification of protein-protein binding sites and would have applications in docking studies.

DNABINDPROT: fluctuation-based predictor of DNA-binding residues within a network of interacting residues

DNABINDPROT is designed to predict DNA-binding residues, based on the fluctuations of residues in high-frequency modes by the Gaussian network model. The residue pairs that display high mean-square distance fluctuations are analyzed with respect to DNA binding, which are then filtered with their evolutionary conservation profiles and ranked according to their DNA-binding propensities. If the analyses are based on the exact outcome of fluctuations in the highest mode, using a conservation threshold of 5, the results have a sensitivity, specificity, precision and accuracy of 9.3%, 90.5%, 18.1% and 78.6%, respectively, on a dataset of 36 unbound–bound protein structure pairs. These values increase up to 24.3%, 93.4%, 45.3% and 83.3% for the respective cases, when the neighboring two residues are considered. The relatively low sensitivity appears with the identified residues being selective and susceptible more for the binding core residues rather than all DNA-binding residues. The predicted residues that are not tagged as DNA-binding residues are those whose fluctuations are coupled with DNA-binding sites. They are in close proximity as well as plausible for other functional residues, such as ligand and protein–protein interaction sites. DNABINDPROT is free and open to all users without login requirement available at: http://www.prc.boun.edu.tr/appserv/prc/dnabindprot/.

Energy based approach for understanding the recognition mechanism in protein-protein complexes

Protein-protein interactions play an essential role in the regulation of various cellular processes. Understanding the recognition mechanism of protein-protein complexes is a challenging task in molecular and computational biology. In this work, we have developed an energy based approach for identifying the binding sites and important residues for binding in protein-protein complexes. The new approach is different from the traditional distance based contacts in which the repulsive interactions are treated as binding sites as well as the contacts within a specific cutoff have been treated in the same way. We found that the residues and residue-pairs with charged and aromatic side chains are important for binding. These residues influence to form cation-, electrostatic and aromatic interactions. Our observation has been verified with the experimental binding specificity of protein-protein complexes and found good agreement with experiments. Based on these results we have proposed a novel mechanism for the recognition of protein-protein complexes: the charged and aromatic residues in receptor and ligand initiate recognition by making suitable interactions between them; the neighboring hydrophobic residues assist the stability of complex along with other hydrogen bonding partners by the polar residues. Further, the propensity of residues in the binding sites of receptors and ligands, atomic contributions and the influence on secondary structure will be discussed.

Utilizing shared interacting domain patterns and Gene Ontology information to improve protein-protein interaction prediction

Protein-protein interactions (PPIs) play a significant role in many crucial cellular operations such as metabolism, signaling and regulations. The computational methods for predicting PPIs have shown tremendous growth in recent years, but problem such as huge false positive rates has contributed to the lack of solid PPI information. We aimed at enhancing the overlap between computational predictions and experimental results in an effort to partially remove PPIs falsely predicted. The use of protein function predictor named PFP() that are based on shared interacting domain patterns is introduced in this study with the purpose of aiding the Gene Ontology Annotations (GOA). We used GOA and PFP() as agents in a filtering process to reduce false positive pairs in the computationally predicted PPI datasets. The functions predicted by PFP() were extracted from cross-species PPI data in order to assign novel functional annotations for the uncharacterized proteins and also as additional functions for those that are already characterized by the GO (Gene Ontology). The implementation of PFP() managed to increase the chances of finding matching function annotation for the first rule in the filtration process as much as 20%. To assess the capability of the proposed framework in filtering false PPIs, we applied it on the available S. cerevisiae PPIs and measured the performance in two aspects, the improvement made indicated as Signal-to-Noise Ratio (SNR) and the strength of improvement, respectively. The proposed filtering framework significantly achieved better performance than without it in both metrics.

Sequence and structural analysis of binding site residues in protein-protein complexes

The binding sites in protein-protein complexes have been identified with different methods including atomic contacts, reduction in solvent accessibility and interaction energy between the interacting partners. In our earlier work, we have developed an energy-based criteria for identifying the binding sites in protein-protein complexes, which showed that the interacting residues are different from that obtained with distance-based methods. In this work, we analyzed the binding site residues based on sequence and structural properties, such as, neighboring residues, secondary structure, solvent accessibility, conservation of residues, medium and long-range contacts and surrounding hydrophobicity. Our results showed that the neighboring residues of binding sites in proteins and ligands are different from each other although the interacting pairs of residues have a common behavior. The analysis on surrounding hydrophobicity reveals that the binding residues are less hydrophobic than non-binding sites, which suggests that the hydrophobic core are important for folding and stability whereas the surface seeking residues play a critical role in binding. This tendency has been verified with the number of contacts in binding sites. In addition, the binding site residues are highly conserved compared with non-binding residues. We suggest that the incorporation of sequence and structure-based features may improve the prediction accuracy of binding sites in protein-protein complexes.

Prediction of protein binding sites in protein structures using hidden Markov support vector machine

Background

Predicting the binding sites between two interacting proteins provides important clues to the function of a protein. Recent research on protein binding site prediction has been mainly based on widely known machine learning techniques, such as artificial neural networks, support vector machines, conditional random field, etc. However, the prediction performance is still too low to be used in practice. It is necessary to explore new algorithms, theories and features to further improve the performance.

Results

In this study, we introduce a novel machine learning model hidden Markov support vector machine for protein binding site prediction. The model treats the protein binding site prediction as a sequential labelling task based on the maximum margin criterion. Common features derived from protein sequences and structures, including protein sequence profile and residue accessible surface area, are used to train hidden Markov support vector machine. When tested on six data sets, the method based on hidden Markov support vector machine shows better performance than some state-of-the-art methods, including artificial neural networks, support vector machines and conditional random field. Furthermore, its running time is several orders of magnitude shorter than that of the compared methods.

Conclusion

The improved prediction performance and computational efficiency of the method based on hidden Markov support vector machine can be attributed to the following three factors. Firstly, the relation between labels of neighbouring residues is useful for protein binding site prediction. Secondly, the kernel trick is very advantageous to this field. Thirdly, the complexity of the training step for hidden Markov support vector machine is linear with the number of training samples by using the cutting-plane algorithm.

Predicting protein-protein binding sites in membrane proteins

Background

Many integral membrane proteins, like their non-membrane counterparts, form either transient or permanent multi-subunit complexes in order to carry out their biochemical function. Computational methods that provide structural details of these interactions are needed since, despite their importance, relatively few structures of membrane protein complexes are available.

Results

We present a method for predicting which residues are in protein-protein binding sites within the transmembrane regions of membrane proteins. The method uses a Random Forest classifier trained on residue type distributions and evolutionary conservation for individual surface residues, followed by spatial averaging of the residue scores. The prediction accuracy achieved for membrane proteins is comparable to that for non-membrane proteins. Also, like previous results for non-membrane proteins, the accuracy is significantly higher for residues distant from the binding site boundary. Furthermore, a predictor trained on non-membrane proteins was found to yield poor accuracy on membrane proteins, as expected from the different distribution of surface residue types between the two classes of proteins. Thus, although the same procedure can be used to predict binding sites in membrane and non-membrane proteins, separate predictors trained on each class of proteins are required. Finally, the contribution of each residue property to the overall prediction accuracy is analyzed and prediction examples are discussed.

Conclusion

Given a membrane protein structure and a multiple alignment of related sequences, the presented method gives a prioritized list of which surface residues participate in intramembrane protein-protein interactions. The method has potential applications in guiding the experimental verification of membrane protein interactions, structure-based drug discovery, and also in constraining the search space for computational methods, such as protein docking or threading, that predict membrane protein complex structures.

Prediction of binding hot spot residues by using structural and evolutionary parameters

In this work, we present a method for predicting hot spot residues by using a set of structural and evolutionary parameters. Unlike previous studies, we use a set of parameters which do not depend on the structure of the protein in complex, so that the predictor can also be used when the interface region is unknown. Despite the fact that no information concerning proteins in complex is used for prediction, the application of the method to a compiled dataset described in the literature achieved a performance of 60.4%, as measured by F-Measure, corresponding to a recall of 78.1% and a precision of 49.5%. This result is higher than those reported by previous studies using the same data set.