Protein-protein interaction site prediction based on conditional random fields

RGCNPPIS: A Residual Graph Convolutional Network for Protein-Protein Interaction Site Prediction

Accurate identification of protein-protein interaction (PPI) sites is crucial for understanding the mechanisms of biological processes, developing PPI networks, and detecting protein functions. Currently, most computational methods primarily concentrate on sequence context features and rarely consider the spatial neighborhood features. To address this limitation, we propose a novel residual graph convolutional network for structure-based PPI site prediction (RGCNPPIS). Specifically, we use a GCN module to extract the global structural features from all spatial neighborhoods, and utilize the GraphSage module to extract local structural features from local spatial neighborhoods. To the best of our knowledge, this is the first work utilizing local structural features for PPI site prediction. We also propose an enhanced residual graph connection to combine the initial node representation, local structural features, and the previous GCN layer's node representation, which enables information transfer between layers and alleviates the over-smoothing problem. Evaluation results demonstrate that RGCNPPIS outperforms state-of-the-art methods on three independent test sets. In addition, the results of ablation experiments and case studies confirm that RGCNPPIS is an effective tool for PPI site prediction.

Protein-Protein Interaction Prediction Model Based on ProtBert-BiGRU-Attention

The physiological activities within cells are mainly regulated through protein-protein interactions (PPI). Therefore, studying protein interactions has become an essential part of researching protein function and mechanisms. Traditional biological experiments required for PPI prediction are expensive and time consuming. For this reason, many methods based on predicting PPI from protein sequences have been proposed in recent years. However, existing computational methods usually require the combination of evolutionary feature information of proteins to predict PPI docking situations. Because different relevant features of selected proteins are chosen, there may be differences in the predicted results for PPI. This article proposes a PPI prediction method based on the pretrained protein sequence model ProtBert, combined with the Bidirectional Gated Recurrent Unit (BiGRU) and attention mechanism. Only using protein sequence information and leveraging ProtBert's powerful ability to capture amino acid feature information, BiGRU is used for further feature extraction of the amino acid vectors output by ProtBert. The attention mechanism is then applied to enhance the focus on different amino acid features and improve the expression ability of protein sequence features, ultimately obtaining binary classification results for protein interactions. Experimental results show that our proposed ProtBert-BiGRU-Attention model has good predictive performance for PPI. Through relevant comparative experiments, it has been proven that our model performs well in protein binary prediction. Furthermore, through the ablation experiment of the model, different deep learning modules' contributions to the prediction have been demonstrated.

E(3) equivariant graph neural networks for robust and accurate protein-protein interaction site prediction

Artificial intelligence-powered protein structure prediction methods have led to a paradigm-shift in computational structural biology, yet contemporary approaches for predicting the interfacial residues (i.e., sites) of protein-protein interaction (PPI) still rely on experimental structures. Recent studies have demonstrated benefits of employing graph convolution for PPI site prediction, but ignore symmetries naturally occurring in 3-dimensional space and act only on experimental coordinates. Here we present EquiPPIS, an E(3) equivariant graph neural network approach for PPI site prediction. EquiPPIS employs symmetry-aware graph convolutions that transform equivariantly with translation, rotation, and reflection in 3D space, providing richer representations for molecular data compared to invariant convolutions. EquiPPIS substantially outperforms state-of-the-art approaches based on the same experimental input, and exhibits remarkable robustness by attaining better accuracy with predicted structural models from AlphaFold2 than what existing methods can achieve even with experimental structures. Freely available at https://github.com/Bhattacharya-Lab/EquiPPIS, EquiPPIS enables accurate PPI site prediction at scale.

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.

ProB-Site: Protein Binding Site Prediction Using Local Features

Protein–protein interactions (PPIs) are responsible for various essential biological processes. This information can help develop a new drug against diseases. Various experimental methods have been employed for this purpose; however, their application is limited by their cost and time consumption. Alternatively, computational methods are considered viable means to achieve this crucial task. Various techniques have been explored in the literature using the sequential information of amino acids in a protein sequence, including machine learning and deep learning techniques. The current efficiency of interaction-site prediction still has growth potential. Hence, a deep neural network-based model, ProB-site, is proposed. ProB-site utilizes sequential information of a protein to predict its binding sites. The proposed model uses evolutionary information and predicted structural information extracted from sequential information of proteins, generating three unique feature sets for every amino acid in a protein sequence. Then, these feature sets are fed to their respective sub-CNN architecture to acquire complex features. Finally, the acquired features are concatenated and classified using fully connected layers. This methodology performed better than state-of-the-art techniques because of the selection of the best features and contemplation of local information of each amino acid.

A Deep Learning and XGBoost-Based Method for Predicting Protein-Protein Interaction Sites

Knowledge about protein-protein interactions is beneficial in understanding cellular mechanisms. Protein-protein interactions are usually determined according to their protein-protein interaction sites. Due to the limitations of current techniques, it is still a challenging task to detect protein-protein interaction sites. In this article, we presented a method based on deep learning and XGBoost (called DeepPPISP-XGB) for predicting protein-protein interaction sites. The deep learning model served as a feature extractor to remove redundant information from protein sequences. The Extreme Gradient Boosting algorithm was used to construct a classifier for predicting protein-protein interaction sites. The DeepPPISP-XGB achieved the following results: area under the receiver operating characteristic curve of 0.681, a recall of 0.624, and area under the precision-recall curve of 0.339, being competitive with the state-of-the-art methods. We also validated the positive role of global features in predicting protein-protein interaction sites.

Prediction of protein-protein interaction sites through eXtreme gradient boosting with kernel principal component analysis

Predicting protein-protein interaction sites (PPI sites) can provide important clues for understanding biological activity. Using machine learning to predict PPI sites can mitigate the cost of running expensive and time-consuming biological experiments. Here we propose PPISP-XGBoost, a novel PPI sites prediction method based on eXtreme gradient boosting (XGBoost). First, the characteristic information of protein is extracted through the pseudo-position specific scoring matrix (PsePSSM), pseudo-amino acid composition (PseAAC), hydropathy index and solvent accessible surface area (ASA) under the sliding window. Next, these raw features are preprocessed to obtain more optimal representations in order to achieve better prediction. In particular, the synthetic minority oversampling technique (SMOTE) is used to circumvent class imbalance, and the kernel principal component analysis (KPCA) is applied to remove redundant characteristics. Finally, these optimal features are fed to the XGBoost classifier to identify PPI sites. Using PPISP-XGBoost, the prediction accuracy on the training dataset Dset186 reaches 85.4%, and the accuracy on the independent validation datasets Dtestset72, PDBtestset164, Dset_448 and Dset_355 reaches 85.3%, 83.9%, 85.8% and 85.4%, respectively, which all show an increase in accuracy against existing PPI sites prediction methods. These results demonstrate that the PPISP-XGBoost method can further enhance the prediction of PPI sites.

Protein-protein interaction site prediction through combining local and global features with deep neural networks

MOTIVATION

Protein-protein interactions (PPIs) play important roles in many biological processes. Conventional biological experiments for identifying PPI sites are costly and time-consuming. Thus, many computational approaches have been proposed to predict PPI sites. Existing computational methods usually use local contextual features to predict PPI sites. Actually, global features of protein sequences are critical for PPI site prediction.

RESULTS

A new end-to-end deep learning framework, named DeepPPISP, through combining local contextual and global sequence features, is proposed for PPI site prediction. For local contextual features, we use a sliding window to capture features of neighbors of a target amino acid as in previous studies. For global sequence features, a text convolutional neural network is applied to extract features from the whole protein sequence. Then the local contextual and global sequence features are combined to predict PPI sites. By integrating local contextual and global sequence features, DeepPPISP achieves the state-of-the-art performance, which is better than the other competing methods. In order to investigate if global sequence features are helpful in our deep learning model, we remove or change some components in DeepPPISP. Detailed analyses show that global sequence features play important roles in DeepPPISP.

AVAILABILITY AND IMPLEMENTATION

The DeepPPISP web server is available at http://bioinformatics.csu.edu.cn/PPISP/. The source code can be obtained from https://github.com/CSUBioGroup/DeepPPISP.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

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.

BioSeq-Analysis2.0: an updated platform for analyzing DNA, RNA and protein sequences at sequence level and residue level based on machine learning approaches

As the first web server to analyze various biological sequences at sequence level based on machine learning approaches, many powerful predictors in the field of computational biology have been developed with the assistance of the BioSeq-Analysis. However, the BioSeq-Analysis can be only applied to the sequence-level analysis tasks, preventing its applications to the residue-level analysis tasks, and an intelligent tool that is able to automatically generate various predictors for biological sequence analysis at both residue level and sequence level is highly desired. In this regard, we decided to publish an important updated server covering a total of 26 features at the residue level and 90 features at the sequence level called BioSeq-Analysis2.0 (http://bliulab.net/BioSeq-Analysis2.0/), by which the users only need to upload the benchmark dataset, and the BioSeq-Analysis2.0 can generate the predictors for both residue-level analysis and sequence-level analysis tasks. Furthermore, the corresponding stand-alone tool was also provided, which can be downloaded from http://bliulab.net/BioSeq-Analysis2.0/download/. To the best of our knowledge, the BioSeq-Analysis2.0 is the first tool for generating predictors for biological sequence analysis tasks at residue level. Specifically, the experimental results indicated that the predictors developed by BioSeq-Analysis2.0 can achieve comparable or even better performance than the existing state-of-the-art predictors.

BioSeq-Analysis: a platform for DNA, RNA and protein sequence analysis based on machine learning approaches

With the avalanche of biological sequences generated in the post-genomic age, one of the most challenging problems is how to computationally analyze their structures and functions. Machine learning techniques are playing key roles in this field. Typically, predictors based on machine learning techniques contain three main steps: feature extraction, predictor construction and performance evaluation. Although several Web servers and stand-alone tools have been developed to facilitate the biological sequence analysis, they only focus on individual step. In this regard, in this study a powerful Web server called BioSeq-Analysis (http://bioinformatics.hitsz.edu.cn/BioSeq-Analysis/) has been proposed to automatically complete the three main steps for constructing a predictor. The user only needs to upload the benchmark data set. BioSeq-Analysis can generate the optimized predictor based on the benchmark data set, and the performance measures can be reported as well. Furthermore, to maximize user's convenience, its stand-alone program was also released, which can be downloaded from http://bioinformatics.hitsz.edu.cn/BioSeq-Analysis/download/, and can be directly run on Windows, Linux and UNIX. Applied to three sequence analysis tasks, experimental results showed that the predictors generated by BioSeq-Analysis even outperformed some state-of-the-art methods. It is anticipated that BioSeq-Analysis will become a useful tool for biological sequence analysis.

Prediction of Protein-Protein Interaction Sites Using Convolutional Neural Network and Improved Data Sets

Protein-protein interaction (PPI) sites play a key role in the formation of protein complexes, which is the basis of a variety of biological processes. Experimental methods to solve PPI sites are expensive and time-consuming, which has led to the development of different kinds of prediction algorithms. We propose a convolutional neural network for PPI site prediction and use residue binding propensity to improve the positive samples. Our method obtains a remarkable result of the area under the curve (AUC) = 0.912 on the improved data set. In addition, it yields much better results on samples with high binding propensity than on randomly selected samples. This suggests that there are considerable false-positive PPI sites in the positive samples defined by the distance between residue atoms.

Protein-protein interaction sites prediction by ensemble random forests with synthetic minority oversampling technique

MOTIVATION

The prediction of protein-protein interaction (PPI) sites is a key to mutation design, catalytic reaction and the reconstruction of PPI networks. It is a challenging task considering the significant abundant sequences and the imbalance issue in samples.

RESULTS

A new ensemble learning-based method, Ensemble Learning of synthetic minority oversampling technique (SMOTE) for Unbalancing samples and RF algorithm (EL-SMURF), was proposed for PPI sites prediction in this study. The sequence profile feature and the residue evolution rates were combined for feature extraction of neighboring residues using a sliding window, and the SMOTE was applied to oversample interface residues in the feature space for the imbalance problem. The Multi-dimensional Scaling feature selection method was implemented to reduce feature redundancy and subset selection. Finally, the Random Forest classifiers were applied to build the ensemble learning model, and the optimal feature vectors were inserted into EL-SMURF to predict PPI sites. The performance validation of EL-SMURF on two independent validation datasets showed 77.1% and 77.7% accuracy, which were 6.2-15.7% and 6.1-18.9% higher than the other existing tools, respectively.

AVAILABILITY AND IMPLEMENTATION

The source codes and data used in this study are publicly available at http://github.com/QUST-AIBBDRC/EL-SMURF/.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Identification of Intrinsically Disordered Proteins and Regions by Length-Dependent Predictors Based on Conditional Random Fields

Accurate identification of intrinsically disordered proteins/regions (IDPs/IDRs) is critical for predicting protein structure and function. Previous studies have shown that IDRs of different lengths have different characteristics, and several classification-based predictors have been proposed for predicting different types of IDRs. Compared with these classification-based predictors, the previously proposed predictor IDP-CRF exhibits state-of-the-art performance for predicting IDPs/IDRs, which is a sequence labeling model based on conditional random fields (CRFs). Motivated by these methods, we propose a predictor called IDP-FSP, which is an ensemble of three CRF-based predictors called IDP-FSP-L, IDP-FSP-S, and IDP-FSP-G. These three predictors are specially designed to predict long, short, and generic disordered regions, respectively, and they are constructed based on different features. To the best of our knowledge, IDP-FSP is the first predictor that combines a sequence labeling algorithm with IDRs of different lengths. Experimental results using two independent test datasets show that IDP-FSP achieves better or at least comparable predictive performance with 26 existing state-of-the-art methods in this field, proving the effectiveness of IDP-FSP.

Protein-protein binding supersites

The lack of a deep understanding of how proteins interact remains an important roadblock in advancing efforts to identify binding partners and uncover the corresponding regulatory mechanisms of the functions they mediate. Understanding protein-protein interactions is also essential for designing specific chemical modifications to develop new reagents and therapeutics. We explored the hypothesis of whether protein interaction sites serve as generic biding sites for non-cognate protein ligands, just as it has been observed for small-molecule-binding sites in the past. Using extensive computational docking experiments on a test set of 241 protein complexes, we found that indeed there is a strong preference for non-cognate ligands to bind to the cognate binding site of a receptor. This observation appears to be robust to variations in docking programs, types of non-cognate protein probes, sizes of binding patches, relative sizes of binding patches and full-length proteins, and the exploration of obligate and non-obligate complexes. The accuracy of the docking scoring function appears to play a role in defining the correct site. The frequency of interaction of unrelated probes recognizing the binding interface was utilized in a simple prediction algorithm that showed accuracy competitive with other state of the art methods.

IDP⁻CRF: Intrinsically Disordered Protein/Region Identification Based on Conditional Random Fields

Accurate prediction of intrinsically disordered proteins/regions is one of the most important tasks in bioinformatics, and some computational predictors have been proposed to solve this problem. How to efficiently incorporate the sequence-order effect is critical for constructing an accurate predictor because disordered region distributions show global sequence patterns. In order to capture these sequence patterns, several sequence labelling models have been applied to this field, such as conditional random fields (CRFs). However, these methods suffer from certain disadvantages. In this study, we proposed a new computational predictor called IDP⁻CRF, which is trained on an updated benchmark dataset based on the MobiDB database and the DisProt database, and incorporates more comprehensive sequence-based features, including PSSMs (position-specific scoring matrices), kmer, predicted secondary structures, and relative solvent accessibilities. Experimental results on the benchmark dataset and two independent datasets show that IDP⁻CRF outperforms 25 existing state-of-the-art methods in this field, demonstrating that IDP⁻CRF is a very useful tool for identifying IDPs/IDRs (intrinsically disordered proteins/regions). We anticipate that IDP⁻CRF will facilitate the development of protein sequence analysis.

Deep Conditional Random Field Approach to Transmembrane Topology Prediction and Application to GPCR Three-Dimensional Structure Modeling

Transmembrane proteins play important roles in cellular energy production, signal transmission, and metabolism. Many shallow machine learning methods have been applied to transmembrane topology prediction, but the performance was limited by the large size of membrane proteins and the complex biological evolution information behind the sequence. In this paper, we proposed a novel deep approach based on conditional random fields named as dCRF-TM for predicting the topology of transmembrane proteins. Conditional random fields take into account more complicated interrelation between residue labels in full-length sequence than HMM and SVM-based methods. Three widely-used datasets were employed in the benchmark. DCRF-TM had the accuracy 95 percent over helix location prediction and the accuracy 78 percent over helix number prediction. DCRF-TM demonstrated a more robust performance on large size proteins (>350 residues) against 11 state-of-the-art predictors. Further dCRF-TM was applied to ab initio modeling three-dimensional structures of seven-transmembrane receptors, also known as G protein-coupled receptors. The predictions on 24 solved G protein-coupled receptors and unsolved vasopressin V2 receptor illustrated that dCRF-TM helped abGPCR-I-TASSER to improve TM-score 34.3 percent rather than using the random transmembrane definition. Two out of five predicted models caught the experimental verified disulfide bonds in vasopressin V2 receptor.

Prediction of protein-protein interaction sites by means of ensemble learning and weighted feature descriptor

Background

Reliable prediction of protein–protein interaction sites is an important goal in the field of bioinformatics. Many computational methods have been explored for the large-scale prediction of protein–protein interaction sites based on various data types, including protein sequence, structural and genomic data. Although much progress has been achieved in recent years, the problem has not yet been satisfactorily solved.

Results

In this work, we presented an efficient approach that uses ensemble learning algorithm with weighted feature descriptor (EL-WFD) to predict protein–protein interaction sites. Moreover, weighted feature descriptor was designed to describe the distance influence of neighboring residues on interaction sites. The results on two dataset (Hetero and Homo), show that the proposed method yields a satisfactory accuracy with 83.8 % recall and 96.3 % precision on the Hetero dataset and 84.2 % recall and 96.3 % precision on the Homo dataset, respectively. In both datasets, our method tend to obtain high Mathews correlation coefficient compared with state-of-the-art technique random forest method.

Conclusions

The experimental results show that the EL-WFD method is quite effective in predicting protein–protein interaction sites. The novel weighted feature descriptor was proved to be promising in discovering interaction sites. Overall, the proposed method can be considered as a new powerful tool for predicting protein–protein interaction sites with excellence performance.

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.

Prediction of Protein-Protein Interaction Sites Based on Naive Bayes Classifier

Protein functions through interactions with other proteins and biomolecules and these interactions occur on the so-called interface residues of the protein sequences. Identifying interface residues makes us better understand the biological mechanism of protein interaction. Meanwhile, information about the interface residues contributes to the understanding of metabolic, signal transduction networks and indicates directions in drug designing. In recent years, researchers have focused on developing new computational methods for predicting protein interface residues. Here we creatively used a 181-dimension protein sequence feature vector as input to the Naive Bayes Classifier- (NBC-) based method to predict interaction sites in protein-protein complexes interaction. The prediction of interaction sites in protein interactions is regarded as an amino acid residue binary classification problem by applying NBC with protein sequence features. Independent test results suggested that Naive Bayes Classifier-based method with the protein sequence features as input vectors performed well.

Survey of Natural Language Processing Techniques in Bioinformatics

Informatics methods, such as text mining and natural language processing, are always involved in bioinformatics research. In this study, we discuss text mining and natural language processing methods in bioinformatics from two perspectives. First, we aim to search for knowledge on biology, retrieve references using text mining methods, and reconstruct databases. For example, protein-protein interactions and gene-disease relationship can be mined from PubMed. Then, we analyze the applications of text mining and natural language processing techniques in bioinformatics, including predicting protein structure and function, detecting noncoding RNA. Finally, numerous methods and applications, as well as their contributions to bioinformatics, are discussed for future use by text mining and natural language processing researchers.

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.

Algorithmic approaches to protein-protein interaction site prediction

Interaction sites on protein surfaces mediate virtually all biological activities, and their identification holds promise for disease treatment and drug design. Novel algorithmic approaches for the prediction of these sites have been produced at a rapid rate, and the field has seen significant advancement over the past decade. However, the most current methods have not yet been reviewed in a systematic and comprehensive fashion. Herein, we describe the intricacies of the biological theory, datasets, and features required for modern protein-protein interaction site (PPIS) prediction, and present an integrative analysis of the state-of-the-art algorithms and their performance. First, the major sources of data used by predictors are reviewed, including training sets, evaluation sets, and methods for their procurement. Then, the features employed and their importance in the biological characterization of PPISs are explored. This is followed by a discussion of the methodologies adopted in contemporary prediction programs, as well as their relative performance on the datasets most recently used for evaluation. In addition, the potential utility that PPIS identification holds for rational drug design, hotspot prediction, and computational molecular docking is described. Finally, an analysis of the most promising areas for future development of the field is presented.

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.

A novel feature extraction scheme with ensemble coding for protein-protein interaction prediction

Protein–protein interactions (PPIs) play key roles in most cellular processes, such as cell metabolism, immune response, endocrine function, DNA replication, and transcription regulation. PPI prediction is one of the most challenging problems in functional genomics. Although PPI data have been increasing because of the development of high-throughput technologies and computational methods, many problems are still far from being solved. In this study, a novel predictor was designed by using the Random Forest (RF) algorithm with the ensemble coding (EC) method. To reduce computational time, a feature selection method (DX) was adopted to rank the features and search the optimal feature combination. The DXEC method integrates many features and physicochemical/biochemical properties to predict PPIs. On the Gold Yeast dataset, the DXEC method achieves 67.2% overall precision, 80.74% recall, and 70.67% accuracy. On the Silver Yeast dataset, the DXEC method achieves 76.93% precision, 77.98% recall, and 77.27% accuracy. On the human dataset, the prediction accuracy reaches 80% for the DXEC-RF method. We extended the experiment to a bigger and more realistic dataset that maintains 50% recall on the Yeast All dataset and 80% recall on the Human All dataset. These results show that the DXEC method is suitable for performing PPI prediction. The prediction service of the DXEC-RF classifier is available at http://ailab.ahu.edu.cn:8087/DXECPPI/index.jsp.

Protein binding site prediction by combining hidden Markov support vector machine and profile-based propensities

Identification of protein binding sites is critical for studying the function of the proteins. In this paper, we proposed a method for protein binding site prediction, which combined the order profile propensities and hidden Markov support vector machine (HM-SVM). This method employed the sequential labeling technique to the field of protein binding site prediction. The input features of HM-SVM include the profile-based propensities, the Position-Specific Score Matrix (PSSM), and Accessible Surface Area (ASA). When tested on different data sets, the proposed method showed promising results, and outperformed some closely relative methods by more than 10% in terms of AUC.

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.

Prediction of protein-protein interaction sites by random forest algorithm with mRMR and IFS

Prediction of protein-protein interaction (PPI) sites is one of the most challenging problems in computational biology. Although great progress has been made by employing various machine learning approaches with numerous characteristic features, the problem is still far from being solved. In this study, we developed a novel predictor based on Random Forest (RF) algorithm with the Minimum Redundancy Maximal Relevance (mRMR) method followed by incremental feature selection (IFS). We incorporated features of physicochemical/biochemical properties, sequence conservation, residual disorder, secondary structure and solvent accessibility. We also included five 3D structural features to predict protein-protein interaction sites and achieved an overall accuracy of 0.672997 and MCC of 0.347977. Feature analysis showed that 3D structural features such as Depth Index (DPX) and surface curvature (SC) contributed most to the prediction of protein-protein interaction sites. It was also shown via site-specific feature analysis that the features of individual residues from PPI sites contribute most to the determination of protein-protein interaction sites. It is anticipated that our prediction method will become a useful tool for identifying PPI sites, and that the feature analysis described in this paper will provide useful insights into the mechanisms of interaction.

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.

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.

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/.

Prediction of protein-protein interaction sites using an ensemble method

Background

Prediction of protein-protein interaction sites is one of the most challenging and intriguing problems in the field of computational biology. Although much progress has been achieved by using various machine learning methods and a variety of available features, the problem is still far from being solved.

Results

In this paper, an ensemble method is proposed, which combines bootstrap resampling technique, SVM-based fusion classifiers and weighted voting strategy, to overcome the imbalanced problem and effectively utilize a wide variety of features. We evaluate the ensemble classifier using a dataset extracted from 99 polypeptide chains with 10-fold cross validation, and get a AUC score of 0.86, with a sensitivity of 0.76 and a specificity of 0.78, which are better than that of the existing methods. To improve the usefulness of the proposed method, two special ensemble classifiers are designed to handle the cases of missing homologues and structural information respectively, and the performance is still encouraging. The robustness of the ensemble method is also evaluated by effectively classifying interaction sites from surface residues as well as from all residues in proteins. Moreover, we demonstrate the applicability of the proposed method to identify interaction sites from the non-structural proteins (NS) of the influenza A virus, which may be utilized as potential drug target sites.

Conclusion

Our experimental results show that the ensemble classifiers are quite effective in predicting protein interaction sites. The Sub-EnClassifiers with resampling technique can alleviate the imbalanced problem and the combination of Sub-EnClassifiers with a wide variety of feature groups can significantly improve prediction performance.

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.

Grammatical-Restrained Hidden Conditional Random Fields for Bioinformatics applications

Background

Discriminative models are designed to naturally address classification tasks. However, some applications require the inclusion of grammar rules, and in these cases generative models, such as Hidden Markov Models (HMMs) and Stochastic Grammars, are routinely applied.

Results

We introduce Grammatical-Restrained Hidden Conditional Random Fields (GRHCRFs) as an extension of Hidden Conditional Random Fields (HCRFs). GRHCRFs while preserving the discriminative character of HCRFs, can assign labels in agreement with the production rules of a defined grammar. The main GRHCRF novelty is the possibility of including in HCRFs prior knowledge of the problem by means of a defined grammar. Our current implementation allows regular grammar rules. We test our GRHCRF on a typical biosequence labeling problem: the prediction of the topology of Prokaryotic outer-membrane proteins.

Conclusion

We show that in a typical biosequence labeling problem the GRHCRF performs better than CRF models of the same complexity, indicating that GRHCRFs can be useful tools for biosequence analysis applications.

Availability

GRHCRF software is available under GPLv3 licence at the website

Identifying protein-protein interaction sites using covering algorithm

Identification of protein-protein interface residues is crucial for structural biology. This paper proposes a covering algorithm for predicting protein-protein interface residues with features including protein sequence profile and residue accessible area. This method adequately utilizes the characters of a covering algorithm which have simple, lower complexity and high accuracy for high dimension data. The covering algorithm can achieve a comparable performance (69.62%, Complete dataset; 60.86%, Trim dataset with overall accuracy) to a support vector machine and maximum entropy on our dataset, a correlation coefficient (CC) of 0.2893, 58.83% specificity, 56.12% sensitivity on the Complete dataset and 0.2144 (CC), 53.34% (specificity), 65.59% (sensitivity) on the Trim dataset in identifying interface residues by 5-fold cross-validation on 61 protein chains. This result indicates that the covering algorithm is a powerful and robust protein-protein interaction site prediction method that can guide biologists to make specific experiments on proteins. Examination of the predictions in the context of the 3-dimensional structures of proteins demonstrates the effectiveness of this method.

Progress and challenges in predicting protein-protein interaction sites

The identification of protein-protein interaction sites is an essential intermediate step for mutant design and the prediction of protein networks. In recent years a significant number of methods have been developed to predict these interface residues and here we review the current status of the field. Progress in this area requires a clear view of the methodology applied, the data sets used for training and testing the systems, and the evaluation procedures. We have analysed the impact of a representative set of features and algorithms and highlighted the problems inherent in generating reliable protein data sets and in the posterior analysis of the results. Although it is clear that there have been some improvements in methods for predicting interacting sites, several major bottlenecks remain. Proteins in complexes are still under-represented in the structural databases and in particular many proteins involved in transient complexes are still to be crystallized. We provide suggestions for effective feature selection, and make it clear that community standards for testing, training and performance measures are necessary for progress in the field.

Structural deformation upon protein-protein interaction: a structural alphabet approach

Background

In a number of protein-protein complexes, the 3D structures of bound and unbound partners significantly differ, supporting the induced fit hypothesis for protein-protein binding.

Results

In this study, we explore the induced fit modifications on a set of 124 proteins available in both bound and unbound forms, in terms of local structure. The local structure is described thanks to a structural alphabet of 27 structural letters that allows a detailed description of the backbone. Using a control set to distinguish induced fit from experimental error and natural protein flexibility, we show that the fraction of structural letters modified upon binding is significantly greater than in the control set (36% versus 28%). This proportion is even greater in the interface regions (41%). Interface regions preferentially involve coils. Our analysis further reveals that some structural letters in coil are not favored in the interface. We show that certain structural letters in coil are particularly subject to modifications at the interface, and that the severity of structural change also varies. These information are used to derive a structural letter substitution matrix that summarizes the local structural changes observed in our data set. We also illustrate the usefulness of our approach to identify common binding motifs in unrelated proteins.

Conclusion

Our study provides qualitative information about induced fit. These results could be of help for flexible docking.