Methods For Protein Interaction Prediction Research Articles

State-of-the-art computational methods to predict protein-protein interactions with high accuracy and coverage.

Prediction of protein-protein interactions (PPIs) commonly involves a significant computational component. Rapid recent advances in the power of computational methods for protein interaction prediction motivate a review of the state-of-the-art. We review the major approaches, organized according to the primary source of data utilized: protein sequence, protein structure, and protein co-abundance. The advent of deep learning (DL) has brought with it significant advances in interaction prediction, and we show how DL is used for each source data type. We review the literature taxonomically, present example case studies in each category, and conclude with observations about the strengths and weaknesses of machine learning methods in the context of the principal sources of data for protein interaction prediction.

On the choice of negative examples for prediction of host-pathogen protein interactions.

As practitioners of machine learning in the area of bioinformatics we know that the quality of the results crucially depends on the quality of our labeled data. While there is a tendency to focus on the quality of positive examples, the negative examples are equally as important. In this opinion paper we revisit the problem of choosing negative examples for the task of predicting protein-protein interactions, either among proteins of a given species or for host-pathogen interactions and describe important issues that are prevalent in the current literature. The challenge in creating datasets for this task is the noisy nature of the experimentally derived interactions and the lack of information on non-interacting proteins. A standard approach is to choose random pairs of non-interacting proteins as negative examples. Since the interactomes of all species are only partially known, this leads to a very small percentage of false negatives. This is especially true for host-pathogen interactions. To address this perceived issue, some researchers have chosen to select negative examples as pairs of proteins whose sequence similarity to the positive examples is sufficiently low. This clearly reduces the chance for false negatives, but also makes the problem much easier than it really is, leading to over-optimistic accuracy estimates. We demonstrate the effect of this form of bias using a selection of recent protein interaction prediction methods of varying complexity, and urge researchers to pay attention to the details of generating their datasets for potential biases like this.

Critical assessment and performance improvement of plant-pathogen protein-protein interaction prediction methods.

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.

Protease-Inhibitor Interaction Predictions: Lessons on the Complexity of Protein–Protein Interactions

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.

Predicting physiologically relevant SH3 domain mediated protein-protein interactions in yeast.

Motivation: Many intracellular signaling processes are mediated by interactions involving peptide recognition modules such as SH3 domains. These domains bind to small, linear protein sequence motifs which can be identified using high-throughput experimental screens such as phage display. Binding motif patterns can then be used to computationally predict protein interactions mediated by these domains. While many protein–protein interaction prediction methods exist, most do not work with peptide recognition module mediated interactions or do not consider many of the known constraints governing physiologically relevant interactions between two proteins.Results: A novel method for predicting physiologically relevant SH3 domain-peptide mediated protein–protein interactions in S. cerevisae using phage display data is presented. Like some previous similar methods, this method uses position weight matrix models of protein linear motif preference for individual SH3 domains to scan the proteome for potential hits and then filters these hits using a range of evidence sources related to sequence-based and cellular constraints on protein interactions. The novelty of this approach is the large number of evidence sources used and the method of combination of sequence based and protein pair based evidence sources. By combining different peptide and protein features using multiple Bayesian models we are able to predict high confidence interactions with an overall accuracy of 0.97.Availability and implementation: Domain-Motif Mediated Interaction Prediction (DoMo-Pred) command line tool and all relevant datasets are available under GNU LGPL license for download from http://www.baderlab.org/Software/DoMo-Pred. The DoMo-Pred command line tool is implemented using Python 2.7 and C ++.Contact: gary.bader@utoronto.caSupplementary information: Supplementary data are available at Bioinformatics online.

Predicting Protein–Protein Interactions from Multimodal Biological Data Sources via Nonnegative Matrix Tri-Factorization

Protein interactions are central to all the biological processes and structural scaffolds in living organisms, because they orchestrate a number of cellular processes such as metabolic pathways and immunological recognition. Several high-throughput methods, for example, yeast two-hybrid system and mass spectrometry method, can help determine protein interactions, which, however, suffer from high false-positive rates. Moreover, many protein interactions predicted by one method are not supported by another. Therefore, computational methods are necessary and crucial to complete the interactome expeditiously. In this work, we formulate the problem of predicting protein interactions from a new mathematical perspective--sparse matrix completion, and propose a novel nonnegative matrix factorization (NMF)-based matrix completion approach to predict new protein interactions from existing protein interaction networks. Through using manifold regularization, we further develop our method to integrate different biological data sources, such as protein sequences, gene expressions, protein structure information, etc. Extensive experimental results on four species, Saccharomyces cerevisiae, Drosophila melanogaster, Homo sapiens, and Caenorhabditis elegans, have shown that our new methods outperform related state-of-the-art protein interaction prediction methods.

Inference of Functional Relations in Predicted Protein Networks with a Machine Learning Approach

BackgroundMolecular biology is currently facing the challenging task of functionally characterizing the proteome. The large number of possible protein-protein interactions and complexes, the variety of environmental conditions and cellular states in which these interactions can be reorganized, and the multiple ways in which a protein can influence the function of others, requires the development of experimental and computational approaches to analyze and predict functional associations between proteins as part of their activity in the interactome.Methodology/Principal FindingsWe have studied the possibility of constructing a classifier in order to combine the output of the several protein interaction prediction methods. The AODE (Averaged One-Dependence Estimators) machine learning algorithm is a suitable choice in this case and it provides better results than the individual prediction methods, and it has better performances than other tested alternative methods in this experimental set up. To illustrate the potential use of this new AODE-based Predictor of Protein InterActions (APPIA), when analyzing high-throughput experimental data, we show how it helps to filter the results of published High-Throughput proteomic studies, ranking in a significant way functionally related pairs. Availability: All the predictions of the individual methods and of the combined APPIA predictor, together with the used datasets of functional associations are available at http://ecid.bioinfo.cnio.es/.ConclusionsWe propose a strategy that integrates the main current computational techniques used to predict functional associations into a unified classifier system, specifically focusing on the evaluation of poorly characterized protein pairs. We selected the AODE classifier as the appropriate tool to perform this task. AODE is particularly useful to extract valuable information from large unbalanced and heterogeneous data sets. The combination of the information provided by five prediction interaction prediction methods with some simple sequence features in APPIA is useful in establishing reliability values and helpful to prioritize functional interactions that can be further experimentally characterized.

Predicting protein–protein interactions in the context of protein evolution

Here we review the methods for the prediction of protein interactions and the ideas in protein evolution that relate to them. The evolutionary assumptions implicit in many of the protein interaction prediction methods are elucidated. We draw attention to the caution needed in deploying certain evolutionary assumptions, in particular cross-organism transfer of interactions by sequence homology, and discuss the known issues in deriving interaction predictions from evidence of co-evolution. We also conject that there is evolutionary knowledge yet to be exploited in the prediction of interactions, in particular the heterogeneity of interactions, the increasing availability of interaction data from multiple species, and the models of protein interaction network growth.

EcID. A database for the inference of functional interactions in E. coli

The EcID database (Escherichia coli Interaction Database) provides a framework for the integration of information on functional interactions extracted from the following sources: EcoCyc (metabolic pathways, protein complexes and regulatory information), KEGG (metabolic pathways), MINT and IntAct (protein interactions). It also includes information on protein complexes from the two E. coli high-throughput pull-down experiments and potential interactions extracted from the literature using the web services associated to the iHOP text-mining system. Additionally, EcID incorporates results of various prediction methods, including two protein interaction prediction methods based on genomic information (Phylogenetic Profiles and Gene Neighbourhoods) and three methods based on the analysis of co-evolution (Mirror Tree, In Silico 2 Hybrid and Context Mirror). EcID associates to each prediction a specifically developed confidence score. The two main features that make EcID different from other systems are the combination of co-evolution-based predictions with the experimental data, and the introduction of E. coli-specific information, such as gene regulation information from EcoCyc. The possibilities offered by the combination of the EcID database information are illustrated with a prediction of potential functions for a group of poorly characterized genes related to yeaG. EcID is available online at http://ecid.bioinfo.cnio.es.