Search

Motivation Modern bioinformatics is facing increasingly complex problems to solve, and we are indeed rapidly approaching an era in which the ability to seamlessly integrate heterogeneous sources of information will be crucial for the scientific progress. Here, we present a novel non-linear data fusion framework that generalizes the conventional matrix factorization paradigm allowing inference over arbitrary entity-relation graphs, and we applied it to the prediction of protein–protein interactions (PPIs). Improving our knowledge of PPI networks at the proteome scale is indeed crucial to understand protein function, physiological and disease states and cell life in general. Results We devised three data fusion-based models for the proteome-level prediction of PPIs, and we show that our method outperforms state of the art approaches on common benchmarks. Moreover, we investigate its predictions on newly published PPIs, showing that this new data has a clear shift in its underlying distributions and we thus train and test our models on this extended dataset. Supplementary information Supplementary data are available at Bioinformatics online.

The scientific community is rapidly generating protein sequence information, but only a fraction of these proteins can be experimentally characterized. While promising deep learning approaches for protein prediction tasks have emerged, they have computational limitations or are designed to solve a specific task. We present a Transformer neural network that pre-trains task-agnostic sequence representations. This model is fine-tuned to solve two different protein prediction tasks: protein family classification and protein interaction prediction. Our method is comparable to existing state-of-the art approaches for protein family classification, while being much more general than other architectures. Further, our method outperforms all other approaches for protein interaction prediction. These results offer a promising framework for fine-tuning the pre-trained sequence representations for other protein prediction tasks.

Motivation Predicting residue–residue contacts between interacting proteins is an important problem in bioinformatics. The growing wealth of sequence data can be used to infer these contacts through correlated mutation analysis on multiple sequence alignments of interacting homologs of the proteins of interest. This requires correct identification of pairs of interacting proteins for many species, in order to avoid introducing noise (i.e. non-interacting sequences) in the analysis that will decrease predictive performance. Results We have designed Ouroboros, a novel algorithm to reduce such noise in intermolecular contact prediction. Our method iterates between weighting proteins according to how likely they are to interact based on the correlated mutations signal, and predicting correlated mutations based on the weighted sequence alignment. We show that this approach accurately discriminates between protein interaction versus non-interaction and simultaneously improves the prediction of intermolecular contact residues compared to a naive application of correlated mutation analysis. This requires no training labels concerning interactions or contacts. Furthermore, the method relaxes the assumption of one-to-one interaction of previous approaches, allowing for the study of many-to-many interactions. Availability and implementation Source code and test data are available at www.bif.wur.nl/. Supplementary information Supplementary data are available at Bioinformatics online.

The unicellular cyanobacterium Cyanothece ATCC 51142 is capable of oxygenic photosynthesis and biological N(2)-fixation (BNF), a process highly sensitive to oxygen. Previous work has focused on determining protein expression levels under different growth conditions. A major gap of our knowledge is an understanding how these expressed proteins are assembled into complexes and organized into metabolic pathways, an area that has not been thoroughly investigated. Here, we combined size-exclusion chromatography (SEC) with label-free quantitative mass spectrometry (MS) and bioinformatics to characterize many protein complexes in from Cyanothece 51142 cells grown under 12-h light-dark cycle. We identified 1386 proteins in duplicate biological replicates, and 64% of those proteins were identified as putative complexes. Pair-wise computational prediction of protein-protein interaction (PPI) identified 74,822 putative interactions, of which 2337 interactions were highly correlated with published protein co-expressions. Many sequential glycolytic and TCA cycle enzymes were identified as putative complexes. We also identified many membrane complexes that contain cytoplasmic domains. Subunits of NDH-1 complex eluted in a fraction with an approximate mass of ~669 kDa, and subunits composition revealed co-existence of distinct forms of NDH-1 complex subunits responsible for respiration, electron flow and CO(2) uptake. The complex form of the phycocyanin beta subunit was non-phosphorylated and the monomer form was phosphorylated at Ser20, suggesting phosphorylation-dependent de-oligomerization of the phycocyanin beta subunit. This study provides an analytical platform for future studies to reveal how these complexes assemble and disassemble as a function of diurnal and circadian rhythms.

All protein-protein interaction (PPI) predictors require the determination of an operational decision threshold when differentiating positive PPIs from negatives. Historically, a single global threshold, typically optimized via cross-validation testing, is applied to all protein pairs. However, we here use data visualization techniques to show that no single decision threshold is suitable for all protein pairs, given the inherent diversity of protein interaction profiles. The recent development of high throughput PPI predictors has enabled the comprehensive scoring of all possible protein-protein pairs. This, in turn, has given rise to context, enabling us now to evaluate a PPI within the context of all possible predictions. Leveraging this context, we introduce a novel modeling framework called Reciprocal Perspective (RP), which estimates a localized threshold on a per-protein basis using several rank order metrics. By considering a putative PPI from the perspective of each of the proteins within the pair, RP rescores the predicted PPI and applies a cascaded Random Forest classifier leading to improvements in recall and precision. We here validate RP using two state-of-the-art PPI predictors, the Protein-protein Interaction Prediction Engine and the Scoring PRotein INTeractions methods, over five organisms: Homo sapiens, Saccharomyces cerevisiae, Arabidopsis thaliana, Caenorhabditis elegans, and Mus musculus. Results demonstrate the application of a post hoc RP rescoring layer significantly improves classification (p

We highlight new evolutionary insights enabled by recent genome-wide studies on protein-protein interaction (PPI) networks ('interactomes'). While most PPIs are mediated by a single sequence region promoting or inhibiting interactions, many PPIs are mediated by multiple sequence regions acting cooperatively. Most PPIs perform important functions maintained by negative selection: we estimate that less than ∼10% of the human interactome is effectively neutral upon perturbation (i.e. 'junk' PPIs), and the rest are deleterious upon perturbation; interfacial sites evolve more slowly than other sites; many conserved PPIs show signatures of co-evolution at the interface; PPIs evolve more slowly than protein sequence. At the same time, many PPIs undergo rewiring during evolution for lineage-specific adaptation. Finally, chaperone-protein and host-pathogen interactomes are governed by distinct evolutionary principles.

Pathogens infect host organisms by exploiting host cellular mechanisms and evading host defence mechanisms through molecular pathogen–host interactions (PHIs). Discovering new interactions between pathogen and human proteins is very crucial in understanding the infection mechanisms. By analysing interaction networks, the interactions responsible for infectious diseases can be detected and new drugs disabling these interactions can be delivered. In this paper, we propose a method based on Bayesian matrix factorization for predicting PHIs along with a projection-based technique and combine the results by employing an ensemble method. Furthermore, two features, target similarity and attacker similarity, are utilized for the first time in the literature for PHI prediction. The advantages of the proposed methods are two folds. Firstly, they relieve the need for negative samples which is significant since there is no available dataset providing negative samples for most of the pathogenic systems. Secondly, the experiments demonstrate that the proposed approach outperforms state-of-the-art methods; roughly 20% of top 50 predictions are among recently validated interactions. So, the search space for wet-lab experiments to obtain validated interactions can be considerably narrowed down from a huge number of possible interactions.

DifferentialNet is a novel database that provides users with differential interactome analysis of human tissues (http://netbio.bgu.ac.il/diffnet/). Users query DifferentialNet by protein, and retrieve its differential protein–protein interactions (PPIs) per tissue via an interactive graphical interface. To compute differential PPIs, we integrated available data of experimentally detected PPIs with RNA-sequencing profiles of tens of human tissues gathered by the Genotype-Tissue Expression consortium (GTEx) and by the Human Protein Atlas (HPA). We associated each PPI with a score that reflects whether its corresponding genes were expressed similarly across tissues, or were up- or down-regulated in the selected tissue. By this, users can identify tissue-specific interactions, filter out PPIs that are relatively stable across tissues, and highlight PPIs that show relative changes across tissues. The differential PPIs can be used to identify tissue-specific processes and to decipher tissue-specific phenotypes. Moreover, they unravel processes that are tissue-wide yet tailored to the specific demands of each tissue.

The identification of plant-pathogen protein-protein interactions (PPIs) is an attractive and challenging research topic for deciphering the complex molecular mechanism of plant immunity and pathogen infection. Considering that the experimental identification of plant-pathogen PPIs is time-consuming and labor-intensive, computational methods are emerging as an important strategy to complement the experimental methods. In this work, we first evaluated the performance of traditional computational methods such as interolog, domain-domain interaction and domain-motif interaction in predicting known plant-pathogen PPIs. Owing to the low sensitivity of the traditional methods, we utilized Random Forest to build an inter-species PPI prediction model based on multiple sequence encodings and novel network attributes in the established plant PPI network. Critical assessment of the features demonstrated that the integration of sequence information and network attributes resulted in significant and robust performance improvement. Additionally, we also discussed the influence of Gene Ontology and gene expression information on the prediction performance. The Web server implementing the integrated prediction method, named InterSPPI, has been made freely available at http://systbio.cau.edu.cn/intersppi/index.php. InterSPPI could achieve a reasonably high accuracy with a precision of 73.8% and a recall of 76.6% in the independent test. To examine the applicability of InterSPPI, we also conducted cross-species and proteome-wide plant-pathogen PPI prediction tests. Taken together, we hope this work can provide a comprehensive understanding of the current status of plant-pathogen PPI predictions, and the proposed InterSPPI can become a useful tool to accelerate the exploration of plant-pathogen interactions.

[Motivation] Computational prediction of protein–protein complex structure by docking can provide structural and mechanistic insights for protein interactions of biomedical interest. However, current methods struggle with difficult cases, such as those involving flexible proteins, low-affinity complexes or transient interactions. A major challenge is how to efficiently sample the structural and energetic landscape of the association at different resolution levels, given that each scoring function is often highly coupled to a specific type of search method. Thus, new methodologies capable of accommodating multi-scale conformational flexibility and scoring are strongly needed., [Results] We describe here a new multi-scale protein–protein docking methodology, LightDock, capable of accommodating conformational flexibility and a variety of scoring functions at different resolution levels. Implicit use of normal modes during the search and atomic/coarse-grained combined scoring functions yielded improved predictive results with respect to state-of-the-art rigidbody docking, especially in flexible cases., B.J-G was supported by a FPI fellowship from the Spanish Ministry of Economy and Competitiveness. This work was supported by grants BIO2013-48213-R, SEV-2015-0493, TIN2015-65316-P, and BIO2016- 79930-R from the Spanish Ministry of Economy and Competitiveness, GA 687698 from the EU H2020 program, and 2014-SGR-1051 from Universitats i Empresa program of Generalitat de Catalunya.

The binding affinity of a protein–protein interaction is concentrated at amino acids known as hot spots. It has been suggested that small molecules disrupt protein–protein interactions by either (i) engaging receptor protein hot spots or (ii) mimicking hot spots of the protein ligand. Yet, no systematic studies have been done to explore how effectively existing small-molecule protein–protein interaction inhibitors mimic or engage hot spots at protein interfaces. Here, we employ explicit-solvent molecular dynamics simulations and end-point MM-GBSA free energy calculations to explore this question. We select 36 compounds for which high-quality binding affinity and cocrystal structures are available. Five complexes that belong to three classes of protein–protein interactions (primary, secondary, and tertiary) were considered, namely, BRD4•H4, XIAP•Smac, MDM2•p53, Bcl-xL•Bak, and IL-2•IL-2Rα. Computational alanine scanning using MM-GBSA identified hot-spot residues at the interface of these protein interactio...

Protein interactions shape proteome function and thus biology. Identification of protein interactions is a major goal in molecular biology, but biochemical methods, although improving, remain limited in coverage and accuracy. Whereas computational predictions can guide biochemical experiments, low validation rates of predictions remain a major limitation. Here, we investigated computational methods in the prediction of a specific type of interaction, the inhibitory interactions between proteases and their inhibitors. Proteases generate thousands of proteoforms that dynamically shape the functional state of proteomes. Despite the important regulatory role of proteases, knowledge of their inhibitors remains largely incomplete with the vast majority of proteases lacking an annotated inhibitor. To link inhibitors to their target proteases on a large scale, we applied computational methods to predict inhibitory interactions between proteases and their inhibitors based on complementary data, including coexpression, phylogenetic similarity, structural information, co-annotation, and colocalization, and also surveyed general protein interaction networks for potential inhibitory interactions. In testing nine predicted interactions biochemically, we validated the inhibition of kallikrein 5 by serpin B12. Despite the use of a wide array of complementary data, we found a high false positive rate of computational predictions in biochemical follow-up. Based on a protease-specific definition of true negatives derived from the biochemical classification of proteases and inhibitors, we analyzed prediction accuracy of individual features, thereby we identified feature-specific limitations, which also affected general protein interaction prediction methods. Interestingly, proteases were often not coexpressed with most of their functional inhibitors, contrary to what is commonly assumed and extrapolated predominantly from cell culture experiments. Predictions of inhibitory interactions were indeed more challenging than predictions of nonproteolytic and noninhibitory interactions. In summary, we describe a novel and well-defined but difficult protein interaction prediction task and thereby highlight limitations of computational interaction prediction methods.

The amazing variety of protein functions are often covered by protein complexes, so understanding protein–protein interactions means coming deeply into the functional role of proteins in life. In the last years, the investigation of protein–protein interactions has become central in many fields, spanning from molecular biology to pharmacology. In this article, we present a state of the art of methods for such investigation, along with perspectives of applications. We stressed the multiscale nature of approaches, longing from genome-wide analysis to the detailed study of protein–protein interface on single residues. The most innovative approaches, based on complex network theory, shed a very bright light on future trends for protein–protein applications on drug design and on molecular therapy for diseases where protein association plays a pivotal role (misfolding). Key Concepts Protein–protein interactions underlie several physiological mechanisms. The analysis of protein–protein interfaces is crucial to quantify protein complex stability. Hotspot residues provide the largest contribution to protein–protein binding energy. Experimental methods point to identify hotspots and quantify binding energy. Molecular docking allows a fine analysis of protein–protein interface. Network-based approaches clarify the multiscale nature of protein–protein interactions. Keywords: protein–protein interactions; hotspots; protein–protein interface; computational methods; network pharmacology; drug design

There are many computational approaches to predict the protein-protein interactions using support vector machines (SVMs) with high performance. In fact, performance of currently reported methods are significantly over-estimated and affected by the object repetitiveness in the datasets used.To study the effect of object repetitiveness of datasets on predicting results.We present novel methods to construct different positive datasets with or without repeating proteins using graph maximum matching in the protein-protein interaction datasets and corresponding series of negative datasets with different proteins repetitiveness are constructed using graph adjacency matrix. The relationship between the SVM prediction results and the repeated proteins (repeat numbers and repeat rates) and the distributions of repeated proteins in the datasets are analyzed.Protein repetitiveness of positive and negative datasets can affect the prediction result: high protein repetitiveness of positive or negative datasets yield high performance prediction result.This indicate that dealing with object repetitiveness of datasets is a key issue in protein-protein interactions prediction using SVMs since real world data contain certain degrees of repeat proteins.

“Large Dimension” of features derived from protein sequences is a major problem in protein–protein interaction (PPI) prediction. Thus, reduction of the feature dimension may increase the classification accuracy. In this paper, particle swarm optimization (PSO) and principal component analysis (PCA) have been used for dimensionality reduction of PPI sequence features. The performance of the algorithm has been assessed using the intraspecies E coli protein–protein interaction database, containing an equal number of positive and negative interacting pairs. Standard sequence-based features such as amino acid composition (AAC), dipeptide composition (Dipep), and conjoint triad composition (CTD) are extracted. From the results, it is seen that the PSO-based dimensionality reduction method provides steady and better performance in terms of accuracy when applied to the features.

Identification of protein-protein interactions (PPIs) is an important problem in biology, since PPIs are related to many essential cellular processes. The development of large-scale high-throughput experiments has produced a large number of PPIs data, however, these data are often noisy and their coverage is still limited. To overcome the shortcomings of experimental methods, many computational methods have been proposed for the prediction of PPIs. Among these methods, most of them solely take the amino acid sequence of protein as input information to make predictions. As PPIs data form the PPIs networks graph, the position information of proteins in the graph can reflect the properties of proteins to some extent, which is an important complement to protein sequence information. But previous works did not consider the graph structure information to improve the prediction performance. In this work, we first time apply graph convolutional networks (GCNs) to capture the protein's position information in the graph and combine amino acid sequence information and position information to make representations in the prediction task. Our experimental results show that our work outperforms the state-of-the-art sequence-based methods on several benchmark datasets and our work computationally is more efficient compared with previous works.

Background Although various machine learning-based predictors have been developed for estimating protein–protein interactions, their performances vary with dataset and species, and are affected by two primary aspects: choice of learning algorithm, and the representation of protein pairs. To improve the performance of predicting protein–protein interactions, we exploit the synergy of multiple learning algorithms, and utilize the expressiveness of different protein-pair features. Results We developed a stacked generalization scheme that integrates five learning algorithms. We also designed three types of protein-pair features based on the physicochemical properties of amino acids, gene ontology annotations, and interaction network topologies. When tested on 19 published datasets collected from eight species, the proposed approach achieved a significantly higher or comparable overall performance, compared with seven competitive predictors. Conclusion We introduced an ensemble learning approach for PPI prediction that integrated multiple learning algorithms and different protein-pair representations. The extensive comparisons with other state-of-the-art prediction tools demonstrated the feasibility and superiority of the proposed method.

Proteins are essential molecules, that must correctly perform their roles for the good health of living organisms. The majority of proteins operate in complexes and the way they interact has pivotal influence on the proper functioning of such organisms. In this study we address the problem of protein–protein interaction and we propose and investigate a method based on the use of an ensemble of autoencoders. Our approach, entitled AutoPPI, adopts a strategy based on two autoencoders, one for each type of interactions (positive and negative) and we advance three types of neural network architectures for the autoencoders. Experiments were performed on several data sets comprising proteins from four different species. The results indicate good performances of our proposed model, with accuracy and AUC values of over 0.97 in all cases. The best performing model relies on a Siamese architecture in both the encoder and the decoder, which advantageously captures common features in protein pairs. Comparisons with other machine learning techniques applied for the same problem prove that AutoPPI outperforms most of its contenders, for the considered data sets.

Protein-protein interactions play a very important role in the process of cellular functionality. Intricate details about the interactions between the proteins in a macromolecular assembly are important to understand the function and significance of protein complexes. We are reporting about a database of protein-protein interactions in huge macromolecular assemblies (PIMADb) that records the intrinsic details of 189,532 interchain interactions in 40,049 complexes from the Protein Data Bank. These details include the results of the quantification and analysis of all the interactions in the complex. The availability of interprotomer interaction networks can enable the design of point mutation experiments. PIMADb can be accessed from the URL: http://caps.ncbs.res.in/pimadb.

Motivations: Characterizing protein–protein interfaces and the hydrogen bonds is a first step to better understand proteins’ structures and functions toward high-resolution protein design. However, there are few large-scale surveys of hydrogen bonds of interfaces. In addition, previous work of shape complementarity of protein complexes suggested that lower shape complementarity in antibody–antigen interfaces is related to their evolutionary origin. Results: Using 6637 non-redundant protein–protein interfaces, we revealed peculiar features of various protein complex types. In contrast to previous findings, the shape complementarity of antibody–antigen interfaces resembles that of the other interface types. These results highlight the importance of hydrogen bonds during evolution of protein interfaces and rectify the prevailing belief that antibodies have lower shape complementarity. Contact: jgray@jhu.edu Supplementary Information: Supplementary data are available at Bioinformatics online.

Identification of protein-protein interactions (PPIs) is at the center of molecular biology considering the unquestionable role of proteins in cells. Combinatorial interactions result in a repertoire of multiple functions; hence, knowledge of PPI and binding regions naturally serve to functional proteomics and drug discovery. Given experimental limitations to find all interactions in a proteome, computational prediction/modeling of protein interactions is a prerequisite to proceed on the way to complete interactions at the proteome level. This review aims to provide a background on PPIs and their types. Computational methods for PPI predictions can use a variety of biological data including sequence-, evolution-, expression-, and structure-based data. Physical and statistical modeling are commonly used to integrate these data and infer PPI predictions. We review and list the state-of-the-art methods, servers, databases, and tools for protein-protein interaction prediction.

Protein–protein interactions (PPIs) help to elucidate the molecular mechanisms of life activities and have a certain role in promoting disease treatment and new drug development. With the advent of the proteomics era, some PPIs prediction methods have emerged. However, the performances of these PPIs prediction methods still need to be optimized and improved. In order to optimize the performance of the PPIs prediction methods, we used the dropout method to reduce over-fitting by deep neural networks (DNNs), and combined with three types of feature extraction methods, conjoint triad (CT), auto covariance (AC) and local descriptor (LD), to build DNN models based on amino acid sequences. The results showed that the accuracy of the CT, AC and LD increased from 97.11% to 98.12%, 96.84% to 98.17%, and 95.30% to 95.60%, respectively. The loss values of the CT, AC and LD decreased from 27.47% to 14.96%, 65.91% to 17.82% and 36.23% to 15.34%, respectively. Experimental results show that dropout can optimize the performances of the DNN models. The results can provide a resource for scholars in future studies involving the prediction of PPIs. The experimental code is available at https://github.com/smalltalkman/hppi-tensorflow .

Sequence-based protein-protein interaction (PPI) prediction represents a fundamental computational biology problem. To address this problem, extensive research efforts have been made to extract predefined features from the sequences. Based on these features, statistical algorithms are learned to classify the PPIs. However, such explicit features are usually costly to extract, and typically have limited coverage on the PPI information. Hence, we present an end-to-end framework, Lasagna, for PPI predictions using only the primary sequences of a protein pair. Lasagna incorporates a deep residual recurrent convolutional neural network in the Siamese learning architecture, which leverages both robust local features and contextualized information that are significant for capturing the mutual influence of protein sequences. Our framework relieves the data pre-processing efforts that are required by other systems, and generalizes well to different application scenarios. Experimental evaluations show that Lasagna outperforms various state-of-the-art systems on the binary PPI prediction problem. Moreover, it shows a promising performance on more challenging problems of interaction type prediction and binding affinity estimation, where existing approaches fall short.

Protein function prediction is an important and challenging problem in bioinformatics and computational biology. Functionally relevant biological information such as protein sequences, gene expression, and protein-protein interactions has been used mostly separately for protein function prediction. One of the major challenges is how to effectively integrate multiple sources of both traditional and new information such as spatial gene-gene interaction networks generated from chromosomal conformation data together to improve protein function prediction.In this work, we developed three different probabilistic scores (MIS, SEQ, and NET score) to combine protein sequence, function associations, and protein-protein interaction and spatial gene-gene interaction networks for protein function prediction. The MIS score is mainly generated from homologous proteins found by PSI-BLAST search, and also association rules between Gene Ontology terms, which are learned by mining the Swiss-Prot database. The SEQ score is generated from protein sequences. The NET score is generated from protein-protein interaction and spatial gene-gene interaction networks. These three scores were combined in a new Statistical Multiple Integrative Scoring System (SMISS) to predict protein function. We tested SMISS on the data set of 2011 Critical Assessment of Function Annotation (CAFA). The method performed substantially better than three base-line methods and an advanced method based on protein profile-sequence comparison, profile-profile comparison, and domain co-occurrence networks according to the maximum F-measure.

Yeast hybrid systems have been widely used due to their convenience and low cost. Based on these systems, many methods have been developed to analyze protein-protein, protein-DNA and protein-RNA interactions. In this paper, we are reviewing these different yeast hybrid systems. According to the number of hybrid proteins, yeast hybrid systems can be divided into three categories, yeast one-hybrid, yeast two-hybrid and yeast three-hybrid systems. Alternatively, yeast hybrid systems can be categorized according to the subcellular localization of the protein interaction process in the cell into nuclear protein-protein interactions, cytosol protein-protein interactions and membrane protein-protein interactions. Throughout the review, we focus on the progress and limitations of each yeast hybrid system over the recent years.

A computational protein-protein docking method that predicts atomic details of protein-protein interactions from protein monomer structures is an invaluable tool for understanding the molecular mechanisms of protein interactions and for designing molecules that control such interactions. Compared to low-resolution docking, high-resolution docking explores the conformational space in atomic resolution to provide predictions with atomic details. This allows for applications to more challenging docking problems that involve conformational changes induced by binding. Recently, high-resolution methods have become more promising as additional information such as global shapes or residue contacts are now available from experiments or sequence/structure data. In this review article, we highlight developments in high-resolution docking made during the last decade, specifically regarding global optimization methods employed by the docking methods. We also discuss two major challenges in high-resolution docking: prediction of backbone flexibility and water-mediated interactions.

Interactions among proteins mediate regulatory, mechanical, structural and transport functions and are fundamental in the modulation of all cellular activities. About 15 years ago, it was first noted that physical interactions link most if not all proteins to each other in complex networks. The analysis of maps representing current knowledge about these molecular networks can provide insights that range from specific hypotheses on the function of a given protein to system-level properties on the organisation or evolution of biological systems. Here, we provide an updated introduction to the numerous ways and available tools by which protein–protein interaction maps can be analysed, and caveats that need to be kept in mind. Key Concepts Protein–protein interaction maps are important tools to develop functional hypothesis, contextualise ‘omic’ gene lists, analyse system properties and systems evolution and provide an important basis for analysing system dynamics. Networks can be assembled from small-scale literature data, bioinformatic prediction and experimental high-throughput technologies of which affinity-purification followed by mass spectrometry or binary yeast-based assays are most common. Global and local properties of protein–protein interaction maps can be influenced by sociological, technological and experimental biases that need to be taken into account. High-throughput technologies can provide data that are in quality at least comparable to the high-quality fraction from small-scale studies in public databases. Carefully benchmarked and appropriate quality controls must be implemented for all approaches. Binary and co-complex methodologies give rise to differential and complementary sets of protein interactions. Bioinformatic tools are available that enable nonspecialists to analyse and use protein–protein interaction networks. Keywords: protein–protein interactions; protein networks; molecular networks; interactome; yeast-two-hybrid; mass spectrometry; systems analysis; bioinformatics

It is beyond any doubt that proteins and their interactions play an essential role in most complex biological processes. The understanding of their function individually, but also in the form of protein complexes is of a great importance. Nowadays, despite the plethora of various high-throughput experimental approaches for detecting protein-protein interactions, many computational methods aiming to predict new interactions have appeared and gained interest. In this review, we focus on text-mining based computational methodologies, aiming to extract information for proteins and their interactions from public repositories such as literature and various biological databases. We discuss their strengths, their weaknesses and how they complement existing experimental techniques by simultaneously commenting on the biological databases which hold such information and the benchmark datasets that can be used for evaluating new tools.

Motivation: Many methods predict the physical interaction between two proteins (protein-protein interactions; PPIs) from sequence alone. Their performance drops substantially for proteins not used for training. Results: Here, we introduce a new approach to predict PPIs from sequence alone which is based on evolutionary profiles and profile-kernel support vector machines. It improved over the state-of-the-art, in particular for proteins that are sequence-dissimilar to proteins with known interaction partners. Filtering by gene expression data increased accuracy further for the few, most reliably predicted interactions (low recall). The overall improvement was so substantial that we compiled a list of the most reliably predicted PPIs in human. Our method makes a significant difference for biology because it improves most for the majority of proteins without experimental annotations. Availability and implementation: Implementation and most reliably predicted human PPIs available at https://rostlab.org/owiki/index.php/Profppikernel. Contact: rost@in.tum.de Supplementary information: Supplementary data are available at Bioinformatics online.

Predicting residue-residue contacts between interacting proteins is an important problem in bioinformatics. The growing wealth of sequence data can be used to infer these contacts through correlated mutation analysis on multiple sequence alignments of interacting homologs of the proteins of interest. This requires correct identification of pairs of interacting proteins for many species, in order to avoid introducing noise (i.e. non-interacting sequences) in the analysis that will decrease predictive performance. We have designed Ouroboros, a novel algorithm to reduce such noise in intermolecular contact prediction. Our method iterates between weighting proteins according to how likely they are to interact based on the correlated mutations signal, and predicting correlated mutations based on the weighted sequence alignment. We show that this approach accurately discriminates between protein interaction versus noninteraction and simultaneously improves the prediction of intermolecular contact residues compared to a naive application of correlated mutation analysis. Furthermore, the method relaxes the assumption of one-to-one interaction of previous approaches, allowing for the study of many-to-many interactions. Source code and test data are available at www.bif.wur.nl/

A huge amount of genetic information is available thanks to the recent advances in sequencing technologies and the larger computational capabilities, but the interpretation of such genetic data at phenotypic level remains elusive. One of the reasons is that proteins are not acting alone, but are specifically interacting with other proteins and biomolecules, forming intricate interaction networks that are essential for the majority of cell processes and pathological conditions. Thus, characterizing such interaction networks is an important step in understanding how information flows from gene to phenotype. Indeed, structural characterization of protein–protein interactions at atomic resolution has many applications in biomedicine, from diagnosis and vaccine design, to drug discovery. However, despite the advances of experimental structural determination, the number of interactions for which there is available structural data is still very small. In this context, a complementary approach is computational modeling of protein interactions by docking, which is usually composed of two major phases: (i) sampling of the possible binding modes between the interacting molecules and (ii) scoring for the identification of the correct orientations. In addition, prediction of interface and hot-spot residues is very useful in order to guide and interpret mutagenesis experiments, as well as to understand functional and mechanistic aspects of the interaction. Computational docking is already being applied to specific biomedical problems within the context of personalized medicine, for instance, helping to interpret pathological mutations involved in protein–protein interactions, or providing modeled structural data for drug discovery targeting protein–protein interactions. Spanish Ministry of Economy grant number BIO2016-79960-R; D.B.B. is supported by a predoctoral fellowship from CONACyT; M.R. is supported by an FPI fellowship from the Severo Ochoa program. We are grateful to the Joint BSC-CRG-IRB Programme in Computational Biology.

Proteins are the essential building blocks and functional components of a cell. They account for the vital functions of an organism. Proteins interact with each other and form protein interaction networks. These protein interactions play a major role in all the biological processes and pathways. The previous methods of predicting protein interactions were experimental which focused on a small set of proteins or a particular protein. However, these experimental approaches are low-throughput as they are time-consuming and require a significant amount of human effort. This led to the development of computational techniques that uses high-throughput experimental data for analyzing protein-protein interactions. The main purpose of this review is to provide an overview on the computational advancements and tools for the prediction of protein interactions. The major databases for the deposition of these interactions are also described. The advantages, as well as the specific limitations of these tools, are highlighted which will shed light on the computational aspects that can help the biologist and researchers in their research.

Protein-Protein Interactions (PPIs) play a key role in many biological systems. Thus, identifying PPIs is critical for understanding cellular processes. Many experimental techniques were applied to predict PPIs. The data extracted using these techniques are incomplete and noisy. In this regard, a number of computational methods include machine learning classification techniques have been developed to reduce the noise data and predict new PPIs. Since, using regression methods to solve classification problems has good results in other applications. Therefore, in this paper, a regression view is applied to the PPI prediction classification problem, so a new approach is proposed using Principal Component Analysis (PCA) and Support Vector Regression (SVR) which has been improved by a new Parallel Hierarchical Cube Search (PHCS) method. Firstly, PCA algorithm is implemented to select an optimal subset of features which leads to reduce processing time and to lessen the effect of noise. Then, the PPIs would be predicted, by using SVR. To get a better performance of SVR, a new PHCS method has been applied to select the appropriate values of SVR parameters. The obtained classification accuracy of the proposed method is 74.505% on KUPS (The University of Kansas Proteomics Service) dataset which outperforms the other methods.

Determining protein-protein interaction (PPI) in biological systems is of considerable importance, and prediction of PPI has become a popular research area. Although different classifiers have been developed for PPI prediction, no single classifier seems to be able to predict PPI with high confidence. We postulated that by combining individual classifiers the accuracy of PPI prediction could be improved. We developed a method called protein-protein interaction prediction classifiers merger (PPCM), and this method combines output from two PPI prediction tools, GO2PPI and Phyloprof, using Random Forests algorithm. The performance of PPCM was tested by area under the curve (AUC) using an assembled Gold Standard database that contains both positive and negative PPI pairs. Our AUC test showed that PPCM significantly improved the PPI prediction accuracy over the corresponding individual classifiers. We found that additional classifiers incorporated into PPCM could lead to further improvement in the PPI prediction accuracy. Furthermore, cross species PPCM could achieve competitive and even better prediction accuracy compared to the single species PPCM. This study established a robust pipeline for PPI prediction by integrating multiple classifiers using Random Forests algorithm. This pipeline will be useful for predicting PPI in nonmodel species.

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

Background Proteins perform their functions usually by interacting with other proteins. Predicting which proteins interact is a fundamental problem. Experimental methods are slow, expensive, and have a high rate of error. Many computational methods have been proposed among which sequence-based ones are very promising. However, so far no such method is able to predict effectively the entire human interactome: they require too much time or memory. Results We present SPRINT (Scoring PRotein INTeractions), a new sequence-based algorithm and tool for predicting protein-protein interactions. We comprehensively compare SPRINT with state-of-the-art programs on seven most reliable human PPI datasets and show that it is more accurate while running orders of magnitude faster and using very little memory. Conclusion SPRINT is the only sequence-based program that can effectively predict the entire human interactome: it requires between 15 and 100 min, depending on the dataset. Our goal is to transform the very challenging problem of predicting the entire human interactome into a routine task. Availability The source code of SPRINT is freely available from https://github.com/lucian-ilie/SPRINT/ and the datasets and predicted PPIs from www.csd.uwo.ca/faculty/ilie/SPRINT/. Electronic supplementary material The online version of this article (doi:10.1186/s12859-017-1871-x) contains supplementary material, which is available to authorized users.

In this paper, we computationally predicted the interactions between HIV-1 and human proteins, based on the hypothesis that proteins with similar interface architecture share similar interaction partners. Evolution – aware protein structural alignment method UniAlign was used to calculate the similarity between two protein interface architectures. Using experimentally verified HIV-1, human protein-protein interactions data, we first selected 12 features, including geometric similarity, conversion similarity etc.; then trained a support vector machine (SVM) with Gaussian kernel for the binary classification problem: whether a given protein pairs ‘interact’ or ‘no interact’. We used the trained and tuned SVM classifier to discover potential novel HIV-1 interacting partners for human proteins. Many predicted interactions had significant literature support, and we modeled the novel 3D interacting complex for HIV-1 envelope gp120 and gp41 proteins. We provided the first structural evidence for those interactions.

A better understanding of biological processes, pathways and functions requires reliable information about protein-protein interactions (PPIs). However, it is still a difficult task to identify complete PPI-networks experimentally in a cell or organism. To supplement the limitations of current experimental techniques, we have proposed PSOPIA, a computational method to predict whether two proteins interact or not (http://mizuguchilab.org/PSOPIA/) [1]. The selection of datasets is a big issue for the PPI prediction [2, 3]. It is generally believed that increasing the size and diversity of examples makes the dataset more representative and reduces the noise effects; however, for many algorithms, it is impractical to use a large-scale dataset at the proteome level because of the memory and CPU time requirements. In this study, PSOPIA was retrained on a highly imbalanced large-scale dataset having a diverse set of examples at the proteome level. The dataset consisted of 43,060 high confidence direct physical PPIs obtained from TargetMine [4] (as positives being only 0.13% of the total) and 33,098,951 negative PPIs. As a result, the new prediction model achieved the higher AUC of 0.89 (pAUCfpr

Protein–protein interactions (PPIs) are at the heart of signal transduction and are central to the function of protein machine in biology. The highly specific protein–protein binding is quantitatively characterized by the binding free energy whose accurate calculation from first principle is a grand challenge in computational biology. Accurate prediction of critical residues along with their specific and quantitative contributions to protein–protein binding free energy is extremely helpful to reveal binding mechanisms and identify drug-like molecules that alter PPIs. In this overview, we describe an interaction entropy (IE) approach combined with the MM/GBSA method for solvation to compute residue-specific protein–protein binding free energy. In this approach, the entropic contribution to binding free energy of individual residue is explicitly computed by using the IE method from a single MD trajectory. Studies for an extensive set of realistic protein–protein interaction systems demonstrated that by including the entropic contribution, the agreement between the computed residue-specific binding free energies and the corresponding experimental data is systematically improved. We also show application of the current approach to the important major histocompatibility complex (MHC)-antigen binding to provide important information on hot spots with potential application for use in cancer vaccine.