Critical assessment of sequence-based protein-protein interaction prediction methods that do not require homologous protein sequences

Robust and accurate prediction of protein-protein interactions by exploiting evolutionary information

Various biochemical functions of organisms are performed by protein-protein interactions (PPIs). Therefore, recognition of protein-protein interactions is very important for understanding most life activities, such as DNA replication and transcription, protein synthesis and secretion, signal transduction and metabolism. Although high-throughput technology makes it possible to generate large-scale PPIs data, it requires expensive cost of both time and labor, and leave a risk of high false positive rate. In order to formulate a more ingenious solution, biology community is looking for computational methods to quickly and efficiently discover massive protein interaction data. In this paper, we propose a computational method for predicting PPIs based on a fresh idea of combining orthogonal locality preserving projections (OLPP) and rotation forest (RoF) models, using protein sequence information. Specifically, the protein sequence is first converted into position-specific scoring matrices (PSSMs) containing protein evolutionary information by using the Position-Specific Iterated Basic Local Alignment Search Tool (PSI-BLAST). Then we characterize a protein as a fixed length feature vector by applying OLPP to PSSMs. Finally, we train an RoF classifier for the purpose of identifying non-interacting and interacting protein pairs. The proposed method yielded a significantly better results than existing methods, with 90.07% and 96.09% prediction accuracy on Yeast and Human datasets. Our experiment show the proposed method can serve as a useful tool to accelerate the process of solving key problems in proteomics.

Performance improvement for a 2D convolutional neural network by using SSC encoding on protein-protein interaction tasks

BACKGROUND

The interactions of proteins are determined by their sequences and affect the regulation of the cell cycle, signal transduction and metabolism, which is of extraordinary significance to modern proteomics research. Despite advances in experimental technology, it is still expensive, laborious, and time-consuming to determine protein-protein interactions (PPIs), and there is a strong demand for effective bioinformatics approaches to identify potential PPIs. Considering the large amount of PPI data, a high-performance processor can be utilized to enhance the capability of the deep learning method and directly predict protein sequences.

RESULTS

We propose the Sequence-Statistics-Content protein sequence encoding format (SSC) based on information extraction from the original sequence for further performance improvement of the convolutional neural network. The original protein sequences are encoded in the three-channel format by introducing statistical information (the second channel) and bigram encoding information (the third channel), which can increase the unique sequence features to enhance the performance of the deep learning model. On predicting protein-protein interaction tasks, the results using the 2D convolutional neural network (2D CNN) with the SSC encoding method are better than those of the 1D CNN with one hot encoding. The independent validation of new interactions from the HIPPIE database (version 2.1 published on July 18, 2017) and the validation of directly predicted results by applying a molecular docking tool indicate the effectiveness of the proposed protein encoding improvement in the CNN model.

CONCLUSION

The proposed protein sequence encoding method is efficient at improving the capability of the CNN model on protein sequence-related tasks and may also be effective at enhancing the capability of other machine learning or deep learning methods. Prediction accuracy and molecular docking validation showed considerable improvement compared to the existing hot encoding method, indicating that the SSC encoding method may be useful for analyzing protein sequence-related tasks. The source code of the proposed methods is freely available for academic research at https://github.com/wangy496/SSC-format/ .

Engineering protein fragments via evolutionary and protein-protein interaction algorithms: de novo design of peptide inhibitors for FO F1 -ATP synthase

Enzyme subunit interfaces have remarkable potential in drug design as both target and scaffold for their own inhibitors. We show an evolution-driven strategy for the de novo design of peptide inhibitors targeting interfaces of the Escherichia coli FoF1-ATP synthase as a case study. The evolutionary algorithm ROSE was applied to generate diversity-oriented peptide libraries by engineering peptide fragments from ATP synthase interfaces. The resulting peptides were scored with PPI-Detect, a sequence-based predictor of protein-protein interactions. Two selected peptides were confirmed by in vitro inhibition and binding tests. The proposed methodology can be widely applied to design peptides targeting relevant interfaces of enzymatic complexes.

PIPE4: Fast PPI Predictor for Comprehensive Inter- and Cross-Species Interactomes

The need for larger-scale and increasingly complex protein-protein interaction (PPI) prediction tasks demands that state-of-the-art predictors be highly efficient and adapted to inter- and cross-species predictions. Furthermore, the ability to generate comprehensive interactomes has enabled the appraisal of each PPI in the context of all predictions leading to further improvements in classification performance in the face of extreme class imbalance using the Reciprocal Perspective (RP) framework. We here describe the PIPE4 algorithm. Adaptation of the PIPE3/MP-PIPE sequence preprocessing step led to upwards of 50x speedup and the new Similarity Weighted Score appropriately normalizes for window frequency when applied to any inter- and cross-species prediction schemas. Comprehensive interactomes for three prediction schemas are generated: (1) cross-species predictions, where Arabidopsis thaliana is used as a proxy to predict the comprehensive Glycine max interactome, (2) inter-species predictions between Homo sapiens-HIV1, and (3) a combined schema involving both cross- and inter-species predictions, where both Arabidopsis thaliana and Caenorhabditis elegans are used as proxy species to predict the interactome between Glycine max (the soybean legume) and Heterodera glycines (the soybean cyst nematode). Comparing PIPE4 with the state-of-the-art resulted in improved performance, indicative that it should be the method of choice for complex PPI prediction schemas.

Evolving knowledge graph similarity for supervised learning in complex biomedical domains

Background

In recent years, biomedical ontologies have become important for describing existing biological knowledge in the form of knowledge graphs. Data mining approaches that work with knowledge graphs have been proposed, but they are based on vector representations that do not capture the full underlying semantics. An alternative is to use machine learning approaches that explore semantic similarity. However, since ontologies can model multiple perspectives, semantic similarity computations for a given learning task need to be fine-tuned to account for this. Obtaining the best combination of semantic similarity aspects for each learning task is not trivial and typically depends on expert knowledge.

Results

We have developed a novel approach, evoKGsim, that applies Genetic Programming over a set of semantic similarity features, each based on a semantic aspect of the data, to obtain the best combination for a given supervised learning task. The approach was evaluated on several benchmark datasets for protein-protein interaction prediction using the Gene Ontology as the knowledge graph to support semantic similarity, and it outperformed competing strategies, including manually selected combinations of semantic aspects emulating expert knowledge. evoKGsim was also able to learn species-agnostic models with different combinations of species for training and testing, effectively addressing the limitations of predicting protein-protein interactions for species with fewer known interactions.

Conclusions

evoKGsim can overcome one of the limitations in knowledge graph-based semantic similarity applications: the need to expertly select which aspects should be taken into account for a given application. Applying this methodology to protein-protein interaction prediction proved successful, paving the way to broader applications.

Automated feature engineering improves prediction of protein-protein interactions

Over the last decade, various machine learning (ML) and statistical approaches for protein-protein interaction (PPI) predictions have been developed to help annotating functional interactions among proteins, essential for our system-level understanding of life. Efficient ML approaches require informative and non-redundant features. In this paper, we introduce novel types of expert-crafted sequence, evolutionary and graph features and apply automatic feature engineering to further expand feature space to improve predictive modeling. The two-step automatic feature-engineering process encompasses the hybrid method for feature generation and unsupervised feature selection, followed by supervised feature selection through a genetic algorithm (GA). The optimization of both steps allows the feature-engineering procedure to operate on a large transformed feature space with no considerable computational cost and to efficiently provide newly engineered features. Based on GA and correlation filtering, we developed a stacking algorithm GA-STACK for automatic ensembling of different ML algorithms to improve prediction performance. We introduced a unified method, HP-GAS, for the prediction of human PPIs, which incorporates GA-STACK and rests on both expert-crafted and 40% of newly engineered features. The extensive cross validation and comparison with the state-of-the-art methods showed that HP-GAS represents currently the most efficient method for proteome-wide forecasting of protein interactions, with prediction efficacy of 0.93 AUC and 0.85 accuracy. We implemented the HP-GAS method as a free standalone application which is a time-efficient and easy-to-use tool. HP-GAS software with supplementary data can be downloaded from: http://www.vinca.rs/180/tools/HP-GAS.php .

Protein-protein interaction prediction using a hybrid feature representation and a stacked generalization scheme

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.

PPI-Detect: A support vector machine model for sequence-based prediction of protein-protein interactions

The prediction of peptide-protein or protein-protein interactions (PPI) is a challenging task, especially if amino acid sequences are the only information available. Machine learning methods allow us to exploit the information content in PPI datasets. However, the numerical codification of these datasets often influences the performance of data mining approaches. Here, we introduce a procedure for the general-purpose numerical codification of polypeptides. This procedure transforms pairs of amino acid sequences into a machine learning-friendly vector, whose elements represent numerical descriptors of residues in proteins. We used this numerical encoding procedure for the development of a support vector machine model (PPI-Detect), which allows predicting whether two proteins will interact or not. PPI-Detect (https://ppi-detect.zmb.uni-due.de/) outperforms state of the art sequence-based predictors of PPI. We employed PPI-Detect for the analysis of derivatives of EPI-X4, an endogenous peptide inhibitor of CXCR4, a G-protein-coupled receptor. There, we identified with high accuracy those peptides which bind better than EPI-X4 to the receptor. Also using PPI-Detect, we designed a novel peptide and then experimentally established its anti-CXCR4 activity. © 2019 Wiley Periodicals, Inc.

Reciprocal Perspective for Improved Protein-Protein Interaction Prediction

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 < 0.001) in all cases over all organisms and this new rescoring approach can apply to any PPI prediction method.

ProfPPIdb: Pairs of physical protein-protein interactions predicted for entire proteomes

MOTIVATION

Protein-protein interactions (PPIs) play a key role in many cellular processes. Most annotations of PPIs mix experimental and computational data. The mix optimizes coverage, but obfuscates the annotation origin. Some resources excel at focusing on reliable experimental data. Here, we focused on new pairs of interacting proteins for several model organisms based solely on sequence-based prediction methods.

RESULTS

We extracted reliable experimental data about which proteins interact (binary) for eight diverse model organisms from public databases, namely from Escherichia coli, Schizosaccharomyces pombe, Plasmodium falciparum, Drosophila melanogaster, Caenorhabditis elegans, Mus musculus, Rattus norvegicus, Arabidopsis thaliana, and for the previously used Homo sapiens and Saccharomyces cerevisiae. Those data were the base to develop a PPI prediction method for each model organism. The method used evolutionary information through a profile-kernel Support Vector Machine (SVM). With the resulting eight models, we predicted all possible protein pairs in each organism and made the top predictions available through a web application. Almost all of the PPIs made available were predicted between proteins that have not been observed in any interaction, in particular for less well-studied organisms. Thus, our work complements existing resources and is particularly helpful for designing experiments because of its uniqueness. Experimental annotations and computational predictions are strongly influenced by the fact that some proteins have many partners and others few. To optimize machine learning, recent methods explicitly ignored such a network-structure and rely either on domain knowledge or sequence-only methods. Our approach is independent of domain-knowledge and leverages evolutionary information. The database interface representing our results is accessible from https://rostlab.org/services/ppipair/. The data can also be downloaded from https://figshare.com/collections/ProfPPI-DB/4141784.

SPRINT: ultrafast protein-protein interaction prediction of the entire human interactome

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.

A New Feature Vector Based on Gene Ontology Terms for Protein-Protein Interaction Prediction

Protein-protein interaction (PPI) plays a key role in understanding cellular mechanisms in different organisms. Many supervised classifiers like Random Forest (RF) and Support Vector Machine (SVM) have been used for intra or inter-species interaction prediction. For improving the prediction performance, in this paper we propose a novel set of features to represent a protein pair using their annotated Gene Ontology (GO) terms, including their ancestors. In our approach, a protein pair is treated as a document (bag of words), where the terms annotating the two proteins represent the words. Feature value of each word is calculated using information content of the corresponding term multiplied by a coefficient, which represents the weight of that term inside a document (i.e., a protein pair). We have tested the performance of the classifier using the proposed feature on different well known data sets of different species like S. cerevisiae, H. Sapiens, E. Coli, and D. melanogaster. We compare it with the other GO based feature representation technique, and demonstrate its competitive performance.

Evolution of protein-protein interaction networks in yeast

Interest in the evolution of protein-protein and genetic interaction networks has been rising in recent years, but the lack of large-scale high quality comparative datasets has acted as a barrier. Here, we carried out a comparative analysis of computationally predicted protein-protein interaction (PPI) networks from five closely related yeast species. We used the Protein-protein Interaction Prediction Engine (PIPE), which uses a database of known interactions to make sequence-based PPI predictions, to generate high quality predicted interactomes. Simulated proteomes and corresponding PPI networks were used to provide null expectations for the extent and nature of PPI network evolution. We found strong evidence for conservation of PPIs, with lower than expected levels of change in PPIs for about a quarter of the proteome. Furthermore, we found that changes in predicted PPI networks are poorly predicted by sequence divergence. Our analyses identified a number of functional classes experiencing fewer PPI changes than expected, suggestive of purifying selection on PPIs. Our results demonstrate the added benefit of considering predicted PPI networks when studying the evolution of closely related organisms.

Mapping and identification of a potential candidate gene for a novel maturity locus, E10, in soybean

KEY MESSAGE

E10 is a new maturity locus in soybean and FT4 is the predicted/potential functional gene underlying the locus. Flowering and maturity time traits play crucial roles in economic soybean production. Early maturity is critical for north and west expansion of soybean in Canada. To date, 11 genes/loci have been identified which control time to flowering and maturity; however, the molecular bases of almost half of them are not yet clear. We have identified a new maturity locus called "E10" located at the end of chromosome Gm08. The gene symbol E10e10 has been approved by the Soybean Genetics Committee. The e10e10 genotype results in 5-10 days earlier maturity than E10E10. A set of presumed E10E10 and e10e10 genotypes was used to identify contrasting SSR and SNP haplotypes. These haplotypes, and their association with maturity, were maintained through five backcross generations. A functional genomics approach using a predicted protein-protein interaction (PPI) approach (Protein-protein Interaction Prediction Engine, PIPE) was used to investigate approximately 75 genes located in the genomic region that SSR and SNP analyses identified as the location of the E10 locus. The PPI analysis identified FT4 as the most likely candidate gene underlying the E10 locus. Sequence analysis of the two FT4 alleles identified three SNPs, in the 5'UTR, 3'UTR and fourth exon in the coding region, which result in differential mRNA structures. Allele-specific markers were developed for this locus and are available for soybean breeders to efficiently develop earlier maturing cultivars using molecular marker assisted breeding.

Extracting Coevolutionary Features from Protein Sequences for Predicting Protein-Protein Interactions

Knowing the ways proteins interact with each other are crucial to our understanding of the functional mechanisms of proteins. It is for this reason that different approaches have been developed in attempts to predict protein-protein interactions (PPIs) computationally. Among them, the sequence-based approaches are preferred to the others as they do not require any information about protein properties to perform their tasks. Instead, most sequence-based approaches make use of feature extraction methods to extract features directly from protein sequences so that for each protein sequence, we can construct a feature vector. The feature vectors of every pair of proteins are then concatenated to form two classes of interacting and non-interacting proteins. The prediction of whether or not two proteins interact with each other is then formulated as a classification problem. How accurate PPI predictions can be made therefore depends on how good the features are that can be extracted from the protein sequences to allow interacting or non-interacting to be best distinguished. To do so, instead of extracting such features from individual protein sequences independently of the other protein in the same pair, we propose to jointly consider features from both sequences in a protein pair during the feature extraction process through using a novel coevolutionary feature extraction approach called CoFex. Coevolutionary features extracted by CoFex refer to the covariations found at coevolving positions. Based on the presence and absence of these coevolutionary features in the sequences of two proteins, feature vectors can be composed for pairs of proteins rather than individual proteins. The experiment results show that CoFex is a promising feature extraction approach and can improve the performance of PPI prediction.

Issues in performance evaluation for host-pathogen protein interaction prediction

The study of interactions between host and pathogen proteins is important for understanding the underlying mechanisms of infectious diseases and for developing novel therapeutic solutions. Wet-lab techniques for detecting protein-protein interactions (PPIs) can benefit from computational predictions. Machine learning is one of the computational approaches that can assist biologists by predicting promising PPIs. A number of machine learning based methods for predicting host-pathogen interactions (HPI) have been proposed in the literature. The techniques used for assessing the accuracy of such predictors are of critical importance in this domain. In this paper, we question the effectiveness of K-fold cross-validation for estimating the generalization ability of HPI prediction for proteins with no known interactions. K-fold cross-validation does not model this scenario, and we demonstrate a sizable difference between its performance and the performance of an alternative evaluation scheme called leave one pathogen protein out (LOPO) cross-validation. LOPO is more effective in modeling the real world use of HPI predictors, specifically for cases in which no information about the interacting partners of a pathogen protein is available during training. We also point out that currently used metrics such as areas under the precision-recall or receiver operating characteristic curves are not intuitive to biologists and propose simpler and more directly interpretable metrics for this purpose.

Rigid-Docking Approaches to Explore Protein-Protein Interaction Space

Protein-protein interactions play core roles in living cells, especially in the regulatory systems. As information on proteins has rapidly accumulated on publicly available databases, much effort has been made to obtain a better picture of protein-protein interaction networks using protein tertiary structure data. Predicting relevant interacting partners from their tertiary structure is a challenging task and computer science methods have the potential to assist with this. Protein-protein rigid docking has been utilized by several projects, docking-based approaches having the advantages that they can suggest binding poses of predicted binding partners which would help in understanding the interaction mechanisms and that comparing docking results of both non-binders and binders can lead to understanding the specificity of protein-protein interactions from structural viewpoints. In this review we focus on explaining current computational prediction methods to predict pairwise direct protein-protein interactions that form protein complexes.

Efficient prediction of human protein-protein interactions at a global scale

BACKGROUND

Our knowledge of global protein-protein interaction (PPI) networks in complex organisms such as humans is hindered by technical limitations of current methods.

RESULTS

On the basis of short co-occurring polypeptide regions, we developed a tool called MP-PIPE capable of predicting a global human PPI network within 3 months. With a recall of 23% at a precision of 82.1%, we predicted 172,132 putative PPIs. We demonstrate the usefulness of these predictions through a range of experiments.

CONCLUSIONS

The speed and accuracy associated with MP-PIPE can make this a potential tool to study individual human PPI networks (from genomic sequences alone) for personalized medicine.

Homology-based prediction of interactions between proteins using Averaged One-Dependence Estimators

Background

Identification of protein-protein interactions (PPIs) is essential for a better understanding of biological processes, pathways and functions. However, experimental identification of the complete set of PPIs in a cell/organism (“an interactome”) is still a difficult task. To circumvent limitations of current high-throughput experimental techniques, it is necessary to develop high-performance computational methods for predicting PPIs.

Results

In this article, we propose a new computational method to predict interaction between a given pair of protein sequences using features derived from known homologous PPIs. The proposed method is capable of predicting interaction between two proteins (of unknown structure) using Averaged One-Dependence Estimators (AODE) and three features calculated for the protein pair: (a) sequence similarities to a known interacting protein pair (F_Seq), (b) statistical propensities of domain pairs observed in interacting proteins (F_Dom) and (c) a sum of edge weights along the shortest path between homologous proteins in a PPI network (F_Net). Feature vectors were defined to lie in a half-space of the symmetrical high-dimensional feature space to make them independent of the protein order. The predictability of the method was assessed by a 10-fold cross validation on a recently created human PPI dataset with randomly sampled negative data, and the best model achieved an Area Under the Curve of 0.79 (pAUC_0.5% = 0.16). In addition, the AODE trained on all three features (named PSOPIA) showed better prediction performance on a separate independent data set than a recently reported homology-based method.

Conclusions

Our results suggest that F_Net, a feature representing proximity in a known PPI network between two proteins that are homologous to a target protein pair, contributes to the prediction of whether the target proteins interact or not. PSOPIA will help identify novel PPIs and estimate complete PPI networks. The method proposed in this article is freely available on the web at http://mizuguchilab.org/PSOPIA.

Interrogating noise in protein sequences from the perspective of protein-protein interactions prediction

The past decades witnessed extensive efforts to study the relationship among proteins. Particularly, sequence-based protein-protein interactions (PPIs) prediction is fundamentally important in speeding up the process of mapping interactomes of organisms. High-throughput experimental methodologies make many model organism's PPIs known, which allows us to apply machine learning methods to learn understandable rules from the available PPIs. Under the machine learning framework, the composition vectors are usually applied to encode proteins as real-value vectors. However, the composition vector value might be highly correlated to the distribution of amino acids, i.e., amino acids which are frequently observed in nature tend to have a large value of composition vectors. Thus formulation to estimate the noise induced by the background distribution of amino acids may be needed during representations. Here, we introduce two kinds of denoising composition vectors, which were successfully used in construction of phylogenetic trees, to eliminate the noise. When validating these two denoising composition vectors on Escherichia coli (E. coli), Saccharomyces cerevisiae (S. cerevisiae) and human PPIs datasets, surprisingly, the predictive performance is not improved, and even worse than non-denoised prediction. These results suggest that the noise in phylogenetic tree construction may be valuable information in PPIs prediction.

A simple recipe for the non-expert bioinformaticist for building experimentally-testable hypotheses for proteins with no known homologs

The study of the protein-protein interactions (PPIs) of unique ORFs is a strategy for deciphering the biological roles of unique ORFs of interest. For uniform reference, we define unique ORFs as those for which no matching protein is found after PDB-BLAST search with default parameters. The uniqueness of the ORFs generally precludes the straightforward use of structure-based approaches in the design of experiments to explore PPIs. Many open-source bioinformatics tools, from the commonly-used to the relatively esoteric, have been built and validated to perform analyses and/or predictions of sorts on proteins. How can these available tools be combined into a protocol that helps the non-expert bioinformaticist researcher to design experiments to explore the PPIs of their unique ORF? Here we define a pragmatic protocol based on accessibility of software to achieve this and we make it concrete by applying it on two proteins-the ImuB and ImuA' proteins from Mycobacterium tuberculosis. The protocol is pragmatic in that decisions are made largely based on the availability of easy-to-use freeware. We define the following basic and user-friendly software pathway to build testable PPI hypotheses for a query protein sequence: PSI-PRED → MUSTER → metaPPISP → ASAView and ConSurf. Where possible, other analytical and/or predictive tools may be included. Our protocol combines the software predictions and analyses with general bioinformatics principles to arrive at consensus, prioritised and testable PPI hypotheses.

Can simple codon pair usage predict protein-protein interaction?

Deciphering functional interactions between proteins is one of the great challenges in biology. Sequence-based homology-free encoding schemes have been increasingly applied to develop promising protein-protein interaction (PPI) predictors by means of statistical or machine learning methods. Here we analyze the relationship between codon pair usage and PPIs in yeast. We show that codon pair usage of interacting protein pairs differs significantly from randomly expected. This motivates the development of a novel approach for predicting PPIs, with codon pair frequency difference as input to a Support Vector Machine predictor, termed as CCPPI. 10-fold cross-validation tests based on yeast PPI datasets with balanced positive-to-negative ratios indicate that CCPPI performs better than other sequence-based encoding schemes. Moreover, it ranks the best when tested on an unbalanced large-scale dataset. Although CCPPI is subjected to high false positive rates like many PPI predictors, statistical analyses of the predicted true positives confirm that the success of CCPPI is partly ascribed to its capability to capture proteomic co-expression and functional similarities between interacting protein pairs. Our findings suggest that codon pairs of interacting protein pairs evolve in a coordinated manner and consequently they provide additional information beyond amino acids-based encoding schemes. CCPPI has been made freely available at: http://protein.cau.edu.cn/ccppi.

Short Co-occurring Polypeptide Regions Can Predict Global Protein Interaction Maps

A goal of the post-genomics era has been to elucidate a detailed global map of protein-protein interactions (PPIs) within a cell. Here, we show that the presence of co-occurring short polypeptide sequences between interacting protein partners appears to be conserved across different organisms. We present an algorithm to automatically generate PPI prediction method parameters for various organisms and illustrate that global PPIs can be predicted from previously reported PPIs within the same or a different organism using protein primary sequences. The PPI prediction code is further accelerated through the use of parallel multi-core programming, which improves its usability for large scale or proteome-wide PPI prediction. We predict and analyze hundreds of novel human PPIs, experimentally confirm protein functions and importantly predict the first genome-wide PPI maps for S. pombe (∼9,000 PPIs) and C. elegans (∼37,500 PPIs).

Revisiting the negative example sampling problem for predicting protein-protein interactions

MOTIVATION

A number of computational methods have been proposed that predict protein-protein interactions (PPIs) based on protein sequence features. Since the number of potential non-interacting protein pairs (negative PPIs) is very high both in absolute terms and in comparison to that of interacting protein pairs (positive PPIs), computational prediction methods rely upon subsets of negative PPIs for training and validation. Hence, the need arises for subset sampling for negative PPIs.

RESULTS

We clarify that there are two fundamentally different types of subset sampling for negative PPIs. One is subset sampling for cross-validated testing, where one desires unbiased subsets so that predictive performance estimated with them can be safely assumed to generalize to the population level. The other is subset sampling for training, where one desires the subsets that best train predictive algorithms, even if these subsets are biased. We show that confusion between these two fundamentally different types of subset sampling led one study recently published in Bioinformatics to the erroneous conclusion that predictive algorithms based on protein sequence features are hardly better than random in predicting PPIs. Rather, both protein sequence features and the 'hubbiness' of interacting proteins contribute to effective prediction of PPIs. We provide guidance for appropriate use of random versus balanced sampling.

AVAILABILITY

The datasets used for this study are available at http://www.marcottelab.org/PPINegativeDataSampling.

CONTACT

yungki@mail.utexas.edu; marcotte@icmb.utexas.edu.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Recent advances in protein-protein interaction prediction: experimental and computational methods

INTRODUCTION

Proteins within the cell act as part of complex networks, which allow pathways and processes to function. Therefore, understanding how proteins interact is a significant area of current research.

AREAS COVERED

This review aims to present an overview of key experimental techniques (yeast two-hybrid, tandem affinity purification and protein microarrays) used to discover protein-protein interactions (PPIs), as well as to briefly discuss certain computational methods for predicting protein interactions based on gene localization, phylogenetic information, 3D structural modeling or primary protein sequence data. Due to the large-scale applicability of primary sequence-based methods, the authors have chosen to focus on this strategy for our review. There is an emphasis on a recent algorithm called Protein Interaction Prediction Engine (PIPE) that can predict global PPIs. The readers will discover recent advances both in the practical determination of protein interaction and the strategies that are available to attempt to anticipate interactions without the time and costs of experimental work.

EXPERT OPINION

Global PPI maps can help understand the biology of complex diseases and facilitate the identification of novel drug target sites. This study describes different techniques used for PPI prediction that we believe will significantly impact the development of the field in a new future. We expect to see a growing number of similar techniques capable of large-scale PPI predictions.

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

Background

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

Results

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

Conclusions

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

Adaptive compressive learning for prediction of protein-protein interactions from primary sequence

Protein-protein interactions (PPIs) play an important role in biological processes. Although much effort has been devoted to the identification of novel PPIs by integrating experimental biological knowledge, there are still many difficulties because of lacking enough protein structural and functional information. It is highly desired to develop methods based only on amino acid sequences for predicting PPIs. However, sequence-based predictors are often struggling with the high-dimensionality causing over-fitting and high computational complexity problems, as well as the redundancy of sequential feature vectors. In this paper, a novel computational approach based on compressed sensing theory is proposed to predict yeast Saccharomyces cerevisiae PPIs from primary sequence and has achieved promising results. The key advantage of the proposed compressed sensing algorithm is that it can compress the original high-dimensional protein sequential feature vector into a much lower but more condensed space taking the sparsity property of the original signal into account. What makes compressed sensing much more attractive in protein sequence analysis is its compressed signal can be reconstructed from far fewer measurements than what is usually considered necessary in traditional Nyquist sampling theory. Experimental results demonstrate that proposed compressed sensing method is powerful for analyzing noisy biological data and reducing redundancy in feature vectors. The proposed method represents a new strategy of dealing with high-dimensional protein discrete model and has great potentiality to be extended to deal with many other complicated biological systems.

Large-scale prediction of human protein-protein interactions from amino acid sequence based on latent topic features

Protein-protein interaction (PPI) is at the core of the entire interactomic system of any living organism. Although there are many human protein-protein interaction links being experimentally determined, the number is still relatively very few compared to the estimation that there are ∼300,000 protein-protein interactions in human beings. Hence, it is still urgent and challenging to develop automated computational methods to accurately and efficiently predict protein-protein interactions. In this paper, we propose a novel hierarchical LDA-RF (latent dirichlet allocation-random forest) model to predict human protein-protein interactions from protein primary sequences directly, which is featured by a high success rate and strong ability for handling large-scale data sets by digging the hidden internal structures buried into the noisy amino acid sequences in low dimensional latent semantic space. First, the local sequential features represented by conjoint triads are constructed from sequences. Then the generative LDA model is used to project the original feature space into the latent semantic space to obtain low dimensional latent topic features, which reflect the hidden structures between proteins. Finally, the powerful random forest model is used to predict the probability for interaction of two proteins. Our results show that the proposed latent topic feature is very promising for PPI prediction and could also become a powerful strategy to deal with many other bioinformatics problems. As a web server, LDA-RF is freely available at http://www.csbio.sjtu.edu.cn/bioinf/LR_PPI for academic use.