InterPred: A pipeline to identify and model protein-protein interactions

Improving protein-protein interaction prediction using protein language model and protein network features

Interactions between proteins are ubiquitous in a wide variety of biological processes. Accurately identifying the protein-protein interaction (PPI) is of significant importance for understanding the mechanisms of protein functions and facilitating drug discovery. Although the wet-lab technological methods are the best way to identify PPI, their major constraints are their time-consuming nature, high cost, and labor-intensiveness. Hence, lots of efforts have been made towards developing computational methods to improve the performance of PPI prediction. In this study, we propose a novel hybrid computational method (called KSGPPI) that aims at improving the prediction performance of PPI via extracting the discriminative information from protein sequences and interaction networks. The KSGPPI model comprises two feature extraction modules. In the first feature extraction module, a large protein language model, ESM-2, is employed to exploit the global complex patterns concealed within protein sequences. Subsequently, feature representations are further extracted through CKSAAP, and a two-dimensional convolutional neural network (CNN) is utilized to capture local information. In the second feature extraction module, the query protein acquires its similar protein from the STRING database via the sequence alignment tool NW-align and then captures the graph embedding feature for the query protein in the protein interaction network of the similar protein using the algorithm of Node2vec. Finally, the features of these two feature extraction modules are efficiently fused; the fused features are then fed into the multilayer perceptron to predict PPI. The results of five-fold cross-validation on the used benchmarked datasets demonstrate that KSGPPI achieves an average prediction accuracy of 88.96 %. Additionally, the average Matthews correlation coefficient value (0.781) of KSGPPI is significantly higher than that of those state-of-the-art PPI prediction methods. The standalone package of KSGPPI is freely downloaded at https://github.com/rickleezhe/KSGPPI.

Improving peptide-protein docking with AlphaFold-Multimer using forced sampling

Protein interactions are key in vital biological processes. In many cases, particularly in regulation, this interaction is between a protein and a shorter peptide fragment. Such peptides are often part of larger disordered regions in other proteins. The flexible nature of peptides enables the rapid yet specific regulation of important functions in cells, such as their life cycle. Consequently, knowledge of the molecular details of peptide-protein interactions is crucial for understanding and altering their function, and many specialized computational methods have been developed to study them. The recent release of AlphaFold and AlphaFold-Multimer has led to a leap in accuracy for the computational modeling of proteins. In this study, the ability of AlphaFold to predict which peptides and proteins interact, as well as its accuracy in modeling the resulting interaction complexes, are benchmarked against established methods. We find that AlphaFold-Multimer predicts the structure of peptide-protein complexes with acceptable or better quality (DockQ ≥0.23) for 66 of the 112 complexes investigated-25 of which were high quality (DockQ ≥0.8). This is a massive improvement on previous methods with 23 or 47 acceptable models and only four or eight high quality models, when using energy-based docking or interaction templates, respectively. In addition, AlphaFold-Multimer can be used to predict whether a peptide and a protein will interact. At 1% false positives, AlphaFold-Multimer found 26% of the possible interactions with a precision of 85%, the best among the methods benchmarked. However, the most interesting result is the possibility of improving AlphaFold by randomly perturbing the neural network weights to force the network to sample more of the conformational space. This increases the number of acceptable models from 66 to 75 and improves the median DockQ from 0.47 to 0.55 (17%) for first ranked models. The best possible DockQ improves from 0.58 to 0.72 (24%), indicating that selecting the best possible model is still a challenge. This scheme of generating more structures with AlphaFold should be generally useful for many applications involving multiple states, flexible regions, and disorder.

Protein-protein interaction prediction with deep learning: A comprehensive review

Most proteins perform their biological function by interacting with themselves or other molecules. Thus, one may obtain biological insights into protein functions, disease prevalence, and therapy development by identifying protein-protein interactions (PPI). However, finding the interacting and non-interacting protein pairs through experimental approaches is labour-intensive and time-consuming, owing to the variety of proteins. Hence, protein-protein interaction and protein-ligand binding problems have drawn attention in the fields of bioinformatics and computer-aided drug discovery. Deep learning methods paved the way for scientists to predict the 3-D structure of proteins from genomes, predict the functions and attributes of a protein, and modify and design new proteins to provide desired functions. This review focuses on recent deep learning methods applied to problems including predicting protein functions, protein-protein interaction and their sites, protein-ligand binding, and protein design.

Building Biological Relevance Into Integrative Modelling of Macromolecular Assemblies

Recent advances in structural biophysics and integrative modelling methods now allow us to decipher the structures of large macromolecular assemblies. Understanding the dynamics and mechanisms involved in their biological function requires rigorous integration of all available data. We have developed a complete modelling pipeline that includes analyses to extract biologically significant information by consistently combining automated and interactive human-guided steps. We illustrate this idea with two examples. First, we describe the ryanodine receptor, an ion channel that controls ion flux across the cell membrane through transitions between open and closed states. The conformational changes associated with the transitions are small compared to the considerable system size of the receptor; it is challenging to consistently track these states with the available cryo-EM structures. The second example involves homologous recombination, in which long filaments of a recombinase protein and DNA catalyse the exchange of homologous DNA strands to reliably repair DNA double-strand breaks. The nucleoprotein filament reaction intermediates in this process are short-lived and heterogeneous, making their structures particularly elusive. The pipeline we describe, which incorporates experimental and theoretical knowledge combined with state-of-the-art interactive and immersive modelling tools, can help overcome these challenges. In both examples, we point to new insights into biological processes that arise from such interdisciplinary approaches.

Modeling the Dynamics of Protein-Protein Interfaces, How and Why?

Protein-protein assemblies act as a key component in numerous cellular processes. Their accurate modeling at the atomic level remains a challenge for structural biology. To address this challenge, several docking and a handful of deep learning methodologies focus on modeling protein-protein interfaces. Although the outcome of these methods has been assessed using static reference structures, more and more data point to the fact that the interaction stability and specificity is encoded in the dynamics of these interfaces. Therefore, this dynamics information must be taken into account when modeling and assessing protein interactions at the atomistic scale. Expanding on this, our review initially focuses on the recent computational strategies aiming at investigating protein-protein interfaces in a dynamic fashion using enhanced sampling, multi-scale modeling, and experimental data integration. Then, we discuss how interface dynamics report on the function of protein assemblies in globular complexes, in fuzzy complexes containing intrinsically disordered proteins, as well as in active complexes, where chemical reactions take place across the protein-protein interface.

Recent advances in predicting protein-protein interactions with the aid of artificial intelligence algorithms

Protein-protein interactions (PPIs) are essential in the regulation of biological functions and cell events, therefore understanding PPIs have become a key issue to understanding the molecular mechanism and investigating the design of drugs. Here we highlight the major developments in computational methods developed for predicting PPIs by using types of artificial intelligence algorithms. The first part introduces the source of experimental PPI data. The second part is devoted to the PPI prediction methods based on sequential information. The third part covers representative methods using structural information as the input feature. The last part is methods designed by combining different types of features. For each part, the state-of-the-art computational PPI prediction methods are reviewed in an inclusive view. Finally, we discuss the flaws existing in this area and future directions of next-generation algorithms.

Learning spatial structures of proteins improves protein-protein interaction prediction

Spatial structures of proteins are closely related to protein functions. Integrating protein structures improves the performance of protein-protein interaction (PPI) prediction. However, the limited quantity of known protein structures restricts the application of structure-based prediction methods. Utilizing the predicted protein structure information is a promising method to improve the performance of sequence-based prediction methods. We propose a novel end-to-end framework, TAGPPI, to predict PPIs using protein sequence alone. TAGPPI extracts multi-dimensional features by employing 1D convolution operation on protein sequences and graph learning method on contact maps constructed from AlphaFold. A contact map contains abundant spatial structure information, which is difficult to obtain from 1D sequence data directly. We further demonstrate that the spatial information learned from contact maps improves the ability of TAGPPI in PPI prediction tasks. We compare the performance of TAGPPI with those of nine state-of-the-art sequence-based methods, and TAGPPI outperforms such methods in all metrics. To the best of our knowledge, this is the first method to use the predicted protein topology structure graph for sequence-based PPI prediction. More importantly, our proposed architecture could be extended to other prediction tasks related to proteins.

InterPepRank: Assessment of Docked Peptide Conformations by a Deep Graph Network

Peptide-protein interactions between a smaller or disordered peptide stretch and a folded receptor make up a large part of all protein-protein interactions. A common approach for modeling such interactions is to exhaustively sample the conformational space by fast-Fourier-transform docking, and then refine a top percentage of decoys. Commonly, methods capable of ranking the decoys for selection fast enough for larger scale studies rely on first-principle energy terms such as electrostatics, Van der Waals forces, or on pre-calculated statistical potentials. We present InterPepRank for peptide-protein complex scoring and ranking. InterPepRank is a machine learning-based method which encodes the structure of the complex as a graph; with physical pairwise interactions as edges and evolutionary and sequence features as nodes. The graph network is trained to predict the LRMSD of decoys by using edge-conditioned graph convolutions on a large set of peptide-protein complex decoys. InterPepRank is tested on a massive independent test set with no targets sharing CATH annotation nor 30% sequence identity with any target in training or validation data. On this set, InterPepRank has a median AUC of 0.86 for finding coarse peptide-protein complexes with LRMSD < 4Å. This is an improvement compared to other state-of-the-art ranking methods that have a median AUC between 0.65 and 0.79. When included as a selection-method for selecting decoys for refinement in a previously established peptide docking pipeline, InterPepRank improves the number of medium and high quality models produced by 80% and 40%, respectively. The InterPepRank program as well as all scripts for reproducing and retraining it are available from: http://wallnerlab.org/InterPepRank.

Divergent acyl carrier protein decouples mitochondrial Fe-S cluster biogenesis from fatty acid synthesis in malaria parasites

Most eukaryotic cells retain a mitochondrial fatty acid synthesis (FASII) pathway whose acyl carrier protein (mACP) and 4-phosphopantetheine (Ppant) prosthetic group provide a soluble scaffold for acyl chain synthesis and biochemically couple FASII activity to mitochondrial electron transport chain (ETC) assembly and Fe-S cluster biogenesis. In contrast, the mitochondrion of Plasmodium falciparum malaria parasites lacks FASII enzymes yet curiously retains a divergent mACP lacking a Ppant group. We report that ligand-dependent knockdown of mACP is lethal to parasites, indicating an essential FASII-independent function. Decyl-ubiquinone rescues parasites temporarily from death, suggesting a dominant dysfunction of the mitochondrial ETC. Biochemical studies reveal that Plasmodium mACP binds and stabilizes the Isd11-Nfs1 complex required for Fe-S cluster biosynthesis, despite lacking the Ppant group required for this association in other eukaryotes, and knockdown of parasite mACP causes loss of Nfs1 and the Rieske Fe-S protein in ETC complex III. This work reveals that Plasmodium parasites have evolved to decouple mitochondrial Fe-S cluster biogenesis from FASII activity, and this adaptation is a shared metabolic feature of other apicomplexan pathogens, including Toxoplasma and Babesia. This discovery unveils an evolutionary driving force to retain interaction of mitochondrial Fe-S cluster biogenesis with ACP independent of its eponymous function in FASII.

A Novel Network-Based Algorithm for Predicting Protein-Protein Interactions Using Gene Ontology

Proteins are one of most significant components in living organism, and their main role in cells is to undertake various physiological functions by interacting with each other. Thus, the prediction of protein-protein interactions (PPIs) is crucial for understanding the molecular basis of biological processes, such as chronic infections. Given the fact that laboratory-based experiments are normally time-consuming and labor-intensive, computational prediction algorithms have become popular at present. However, few of them could simultaneously consider both the structural information of PPI networks and the biological information of proteins for an improved accuracy. To do so, we assume that the prior information of functional modules is known in advance and then simulate the generative process of a PPI network associated with the biological information of proteins, i.e., Gene Ontology, by using an established Bayesian model. In order to indicate to what extent two proteins are likely to interact with each other, we propose a novel scoring function by combining the membership distributions of proteins with network paths. Experimental results show that our algorithm has a promising performance in terms of several independent metrics when compared with state-of-the-art prediction algorithms, and also reveal that the consideration of modularity in PPI networks provides us an alternative, yet much more flexible, way to accurately predict PPIs.

A survey on computational models for predicting protein-protein interactions

Proteins interact with each other to play critical roles in many biological processes in cells. Although promising, laboratory experiments usually suffer from the disadvantages of being time-consuming and labor-intensive. The results obtained are often not robust and considerably uncertain. Due recently to advances in high-throughput technologies, a large amount of proteomics data has been collected and this presents a significant opportunity and also a challenge to develop computational models to predict protein-protein interactions (PPIs) based on these data. In this paper, we present a comprehensive survey of the recent efforts that have been made towards the development of effective computational models for PPI prediction. The survey introduces the algorithms that can be used to learn computational models for predicting PPIs, and it classifies these models into different categories. To understand their relative merits, the paper discusses different validation schemes and metrics to evaluate the prediction performance. Biological databases that are commonly used in different experiments for performance comparison are also described and their use in a series of extensive experiments to compare different prediction models are discussed. Finally, we present some open issues in PPI prediction for future work. We explain how the performance of PPI prediction can be improved if these issues are effectively tackled.

Docking-based identification of small-molecule binding sites at protein-protein interfaces

Protein-protein interactions play an essential role in many biological processes, and their perturbation is a major cause of disease. The use of small molecules to modulate them is attracting increased attention, but protein interfaces generally do not have clear cavities for binding small compounds. A proposed strategy is to target interface hot-spot residues, but their identification through computational approaches usually require the complex structure, which is not often available. In this context, pyDock energy-based docking and scoring can predict hot-spots on the unbound proteins, thus not requiring the complex structure. Here, we have devised a new strategy to detect protein–protein inhibitor binding sites, based on the integration of molecular dynamics for the generation of transient cavities, and docking-based interface hot-spot prediction for the selection of the suitable cavities. This integrative approach has been validated on a test set formed by protein–protein complexes with known inhibitors for which complete structural data of unbound molecules and complexes is available. The results show that local conformational sampling with short molecular dynamics can generate transient cavities similar to the known inhibitor binding sites, and that docking simulations can identify the best cavities with similar predictive accuracy as when knowing the real interface. In a few cases, these predicted pockets are shown to be suitable for protein–ligand docking. The proposed strategy will be useful for many protein–protein complexes for which there is no available structure, as long as the the unbound proteins do not deviate dramatically from the bound conformations.

Amalgamation of 3D structure and sequence information for protein-protein interaction prediction

Protein is the primary building block of living organisms. It interacts with other proteins and is then involved in various biological processes. Protein-protein interactions (PPIs) help in predicting and hence help in understanding the functionality of the proteins, causes and growth of diseases, and designing new drugs. However, there is a vast gap between the available protein sequences and the identification of protein-protein interactions. To bridge this gap, researchers proposed several computational methods to reveal the interactions between proteins. These methods merely depend on sequence-based information of proteins. With the advancement of technology, different types of information related to proteins are available such as 3D structure information. Nowadays, deep learning techniques are adopted successfully in various domains, including bioinformatics. So, current work focuses on the utilization of different modalities, such as 3D structures and sequence-based information of proteins, and deep learning algorithms to predict PPIs. The proposed approach is divided into several phases. We first get several illustrations of proteins using their 3D coordinates information, and three attributes, such as hydropathy index, isoelectric point, and charge of amino acids. Amino acids are the building blocks of proteins. A pre-trained ResNet50 model, a subclass of a convolutional neural network, is utilized to extract features from these representations of proteins. Autocovariance and conjoint triad are two widely used sequence-based methods to encode proteins, which are used here as another modality of protein sequences. A stacked autoencoder is utilized to get the compact form of sequence-based information. Finally, the features obtained from different modalities are concatenated in pairs and fed into the classifier to predict labels for protein pairs. We have experimented on the human PPIs dataset and Saccharomyces cerevisiae PPIs dataset and compared our results with the state-of-the-art deep-learning-based classifiers. The results achieved by the proposed method are superior to those obtained by the existing methods. Extensive experimentations on different datasets indicate that our approach to learning and combining features from two different modalities is useful in PPI prediction.

InterPep2: global peptide-protein docking using interaction surface templates

Motivation

Interactions between proteins and peptides or peptide-like intrinsically disordered regions are involved in many important biological processes, such as gene expression and cell life-cycle regulation. Experimentally determining the structure of such interactions is time-consuming and difficult because of the inherent flexibility of the peptide ligand. Although several prediction-methods exist, most are limited in performance or availability.

Results

InterPep2 is a freely available method for predicting the structure of peptide–protein interactions. Improved performance is obtained by using templates from both peptide–protein and regular protein–protein interactions, and by a random forest trained to predict the DockQ-score for a given template using sequence and structural features. When tested on 252 bound peptide–protein complexes from structures deposited after the complexes used in the construction of the training and templates sets of InterPep2, InterPep2-Refined correctly positioned 67 peptides within 4.0 Å LRMSD among top10, similar to another state-of-the-art template-based method which positioned 54 peptides correctly. However, InterPep2 displays a superior ability to evaluate the quality of its own predictions. On a previously established set of 27 non-redundant unbound-to-bound peptide–protein complexes, InterPep2 performs on-par with leading methods. The extended InterPep2-Refined protocol managed to correctly model 15 of these complexes within 4.0 Å LRMSD among top10, without using templates from homologs. In addition, combining the template-based predictions from InterPep2 with ab initio predictions from PIPER-FlexPepDock resulted in 22% more near-native predictions compared to the best single method (22 versus 18).

Availability and implementation

The program is available from: http://wallnerlab.org/InterPep2.

Supplementary information

Supplementary data are available at Bioinformatics online.

ProteinFishing: a protein complex generator within the ModelX toolsuite

Summary

Accurate 3D modelling of protein–protein interactions (PPI) is essential to compensate for the absence of experimentally determined complex structures. Here, we present a new set of commands within the ModelX toolsuite capable of generating atomic-level protein complexes suitable for interface design. Among these commands, the new tool ProteinFishing proposes known and/or putative alternative 3D PPI for a given protein complex. The algorithm exploits backbone compatibility of protein fragments to generate mutually exclusive protein interfaces that are quickly evaluated with a knowledge-based statistical force field. Using interleukin-10-R2 co-crystalized with interferon-lambda-3, and a database of X-ray structures containing interleukin-10, this algorithm was able to generate interleukin-10-R2/interleukin-10 structural models in agreement with experimental data.

Availability and implementation

ProteinFishing is a portable command-line tool included in the ModelX toolsuite, written in C++, that makes use of an SQL (tested for MySQL and MariaDB) relational database delivered with a template SQL dump called FishXDB. FishXDB contains the empty tables of ModelX fragments and the data used by the embedded statistical force field. ProteinFishing is compiled for Linux-64bit, MacOS-64bit and Windows-32bit operating systems. This software is a proprietary license and is distributed as an executable with its correspondent database dumps. It can be downloaded publicly at http://modelx.crg.es/. Licenses are freely available for academic users after registration on the website and are available under commercial license for for-profit organizations or companies.

Contact

javier.delgado@crg.eu or luis.serrano@crg.eu

Supplementary information

Supplementary data are available at Bioinformatics online.

Application of docking methodologies to modeled proteins

Protein docking is essential for structural characterization of protein interactions. Besides providing the structure of protein complexes, modeling of proteins and their complexes is important for understanding the fundamental principles and specific aspects of protein interactions. The accuracy of protein modeling, in general, is still less than that of the experimental approaches. Thus, it is important to investigate the applicability of docking techniques to modeled proteins. We present new comprehensive benchmark sets of protein models for the development and validation of protein docking, as well as a systematic assessment of free and template-based docking techniques on these sets. As opposed to previous studies, the benchmark sets reflect the real case modeling/docking scenario where the accuracy of the models is assessed by the modeling procedure, without reference to the native structure (which would be unknown in practical applications). We also expanded the analysis to include docking of protein pairs where proteins have different structural accuracy. The results show that, in general, the template-based docking is less sensitive to the structural inaccuracies of the models than the free docking. The near-native docking poses generated by the template-based approach, typically, also have higher ranks than those produces by the free docking (although the free docking is indispensable in modeling the multiplicity of protein interactions in a crowded cellular environment). The results show that docking techniques are applicable to protein models in a broad range of modeling accuracy. The study provides clear guidelines for practical applications of docking to protein models.

In silico analysis of nonsynonymous single-nucleotide polymorphisms (nsSNPs) of the SMPX gene

Mutations in the SMPX gene can disrupt the regular activity of the SMPX protein, which is involved in the hearing process. Recent reports showing a link between nonsynonymous single-nucleotide polymorphisms (nsSNPs) in SMPX and hearing loss, thus classifying deleterious SNPs in SMPX will be an uphill task before designing a more extensive population study. In this study, damaging nsSNPs of SMPX from the dbSNP database were identified by using 13 bioinformatics tools. Initially, the impact of nsSNPs in the SMPX gene were evaluated through different in silico predictors; and the deleterious convergent changes were analyzed by energy-minimization-guided residual network analysis. In addition, the pathogenic effects of mutations in SMPX-mediated protein-protein interactions were also characterized by structural modeling and binding energy calculations. A total of four mutations (N19D, A29T, K54N, and S71L) were found to be highly deleterious by all the tools, which are located at highly conserved regions. Furthermore, all four mutants showed structural alterations, and the communities of amino acids for mutant proteins were readily changed, compared to the wild-type. Among them, A29T (rs772775896) was revealed as the most damaging nsSNP, which caused significant structural deviation of the SMPX protein, as a result reducing the binding affinity to other functional partners. These findings reflect the computational insights into the deleterious role of nsSNPs in SMPX, which might be helpful for subjecting wet-lab confirmatory analysis.

Topology independent structural matching discovers novel templates for protein interfaces

Motivation

Protein-protein interactions (PPI) are essential for the function of the cellular machinery. The rapid growth of protein-protein complexes with known 3D structures offers a unique opportunity to study PPI to gain crucial insights into protein function and the causes of many diseases. In particular, it would be extremely useful to compare interaction surfaces of monomers, as this would enable the pinpointing of potential interaction surfaces based solely on the monomer structure, without the need to predict the complete complex structure. While there are many structural alignment algorithms for individual proteins, very few have been developed for protein interfaces, and none that can align only the interface residues to other interfaces or surfaces of interacting monomer subunits in a topology independent (non-sequential) manner.

Results

We present InterComp, a method for topology and sequence-order independent structural comparisons. The method is general and can be applied to various structural comparison applications. By representing residues as independent points in space rather than as a sequence of residues, InterComp can be applied to a wide range of problems including interface-surface comparisons and interface-interface comparisons. We demonstrate a use-case by applying InterComp to find similar protein interfaces on the surface of proteins. We show that InterComp pinpoints the correct interface for almost half of the targets (283 of 586) when considering the top 10 hits, and for 24% of the top 1, even when no templates can be found with regular sequence-order dependent structural alignment methods.

Availability and implementation

The source code and the datasets are available at: http://wallnerlab.org/InterComp.

Supplementary information

Supplementary data are available at Bioinformatics online.

Structural modeling of protein complexes: Current capabilities and challenges

Proteins frequently interact with each other, and the knowledge of structures of the corresponding protein complexes is necessary to understand how they function. Computational methods are increasingly used to provide structural models of protein complexes. Not surprisingly, community-wide Critical Assessment of protein Structure Prediction (CASP) experiments have recently started monitoring the progress in this research area. We participated in CASP13 with the aim to evaluate our current capabilities in modeling of protein complexes and to gain a better understanding of factors that exert the largest impact on these capabilities. To model protein complexes in CASP13, we applied template-based modeling, free docking and hybrid techniques that enabled us to generate models of the topmost quality for 27 of 42 multimers. If templates for protein complexes could be identified, we modeled the structures with reasonable accuracy by straightforward homology modeling. If only partial templates were available, it was nevertheless possible to predict the interaction interfaces correctly or to generate acceptable models for protein complexes by combining template-based modeling with docking. If no templates were available, we used rigid-body docking with limited success. However, in some free docking models, despite the incorrect subunit orientation and missed interface contacts, the approximate location of protein binding sites was identified correctly. Apparently, our overall performance in docking was limited by the quality of monomer models and by the imperfection of scoring methods. The impact of human intervention on our results in modeling of protein complexes was significant indicating the need for improvements of automatic methods.

The Applications of Clustering Methods in Predicting Protein Functions

Background:

The understanding of protein function is essential to the study of biological processes. However, the prediction of protein function has been a difficult task for bioinformatics to overcome. This has resulted in many scholars focusing on the development of computational methods to address this problem.

Objective:

In this review, we introduce the recently developed computational methods of protein function prediction and assess the validity of these methods. We then introduce the applications of clustering methods in predicting protein functions.

Computational identification of protein-protein interactions in model plant proteomes

Protein-protein interactions (PPIs) play essential roles in many biological processes. A PPI network provides crucial information on how biological pathways are structured and coordinated from individual protein functions. In the past two decades, large-scale PPI networks of a handful of organisms were determined by experimental techniques. However, these experimental methods are time-consuming, expensive, and are not easy to perform on new target organisms. Large-scale PPI data is particularly sparse in plant organisms. Here, we developed a computational approach for detecting PPIs trained and tested on known PPIs of Arabidopsis thaliana and applied to three plants, Arabidopsis thaliana, Glycine max (soybean), and Zea mays (maize) to discover new PPIs on a genome-scale. Our method considers a variety of features including protein sequences, gene co-expression, functional association, and phylogenetic profiles. This is the first work where a PPI prediction method was developed for is the first PPI prediction method applied on benchmark datasets of Arabidopsis. The method showed a high prediction accuracy of over 90% and very high precision of close to 1.0. We predicted 50,220 PPIs in Arabidopsis thaliana, 13,175,414 PPIs in corn, and 13,527,834 PPIs in soybean. Newly predicted PPIs were classified into three confidence levels according to the availability of existing supporting evidence and discussed. Predicted PPIs in the three plant genomes are made available for future reference.

Predicting protein-peptide interaction sites using distant protein complexes as structural templates

Protein-peptide interactions play an important role in major cellular processes, and are associated with several human diseases. To understand and potentially regulate these cellular function and diseases it is important to know the molecular details of the interactions. However, because of peptide flexibility and the transient nature of protein-peptide interactions, peptides are difficult to study experimentally. Thus, computational methods for predicting structural information about protein-peptide interactions are needed. Here we present InterPep, a pipeline for predicting protein-peptide interaction sites. It is a novel pipeline that, given a protein structure and a peptide sequence, utilizes structural template matches, sequence information, random forest machine learning, and hierarchical clustering to predict what region of the protein structure the peptide is most likely to bind. When tested on its ability to predict binding sites, InterPep successfully pinpointed 255 of 502 (50.7%) binding sites in experimentally determined structures at rank 1 and 348 of 502 (69.3%) among the top five predictions using only structures with no significant sequence similarity as templates. InterPep is a powerful tool for identifying peptide-binding sites; with a precision of 80% at a recall of 20% it should be an excellent starting point for docking protocols or experiments investigating peptide interactions. The source code for InterPred is available at http://wallnerlab.org/InterPep/ .

ProBAPred: Inferring protein–protein binding affinity by incorporating protein sequence and structural features

Protein-protein binding interaction is the most prevalent biological activity that mediates a great variety of biological processes. The increasing availability of experimental data of protein–protein interaction allows a systematic construction of protein–protein interaction networks, significantly contributing to a better understanding of protein functions and their roles in cellular pathways and human diseases. Compared to well-established classification for protein–protein interactions (PPIs), limited work has been conducted for estimating protein–protein binding free energy, which can provide informative real-value regression models for characterizing the protein–protein binding affinity. In this study, we propose a novel ensemble computational framework, termed ProBAPred (Protein–protein Binding Affinity Predictor), for quantitative estimation of protein–protein binding affinity. A large number of sequence and structural features, including physical–chemical properties, binding energy and conformation annotations, were collected and calculated from currently available protein binding complex datasets and the literature. Feature selection based on the WEKA package was performed to identify and characterize the most informative and contributing feature subsets. Experiments on the independent test showed that our ensemble method achieved the lowest Mean Absolute Error (MAE; 1.657[Formula: see text]kcal/mol) and the second highest correlation coefficient ([Formula: see text]), compared with the existing methods. The datasets and source codes of ProBAPred, and the supplementary materials in this study can be downloaded at http://lightning.med.monash.edu/probapred/ for academic use. We anticipate that the developed ProBAPred regression models can facilitate computational characterization and experimental studies of protein–protein binding affinity.

Computational Methods for Predicting Protein-Protein Interactions Using Various Protein Features

Understanding protein-protein interactions (PPIs) in a cell is essential for learning protein functions, pathways, and mechanism of diseases. PPIs are also important targets for developing drugs. Experimental methods, both small-scale and large-scale, have identified PPIs in several model organisms. However, results cover only a part of PPIs of organisms; moreover, there are many organisms whose PPIs have not yet been investigated. To complement experimental methods, many computational methods have been developed that predict PPIs from various characteristics of proteins. Here we provide an overview of literature reports to classify computational PPI prediction methods that consider different features of proteins, including protein sequence, genomes, protein structure, function, PPI network topology, and those which integrate multiple methods. © 2018 by John Wiley & Sons, Inc.