Assessment of community efforts to advance computational prediction of protein-protein interactions

Comprehensive insights from the human protein-protein interaction (PPI) network, known as the human interactome, can provide important insights into the molecular mechanisms of complex biological processes and diseases. Despite the remarkable experimental efforts undertaken to date to determine the structure of the human interactome, many PPIs remain unmapped. Computational approaches, especially network-based methods, can facilitate the identification of new PPIs. Many such approaches have been proposed. However, a systematic evaluation of existing network-based methods in predicting PPIs is still lacking. Here, we report community efforts initiated by the International Network Medicine Consortium to benchmark the ability of 24 representative network-based methods to predict PPIs across five different interactomes, including a synthetic interactome generated by the duplication-mutation-complementation model, and the interactomes of four different organisms: A. thaliana, C. elegans, S. cerevisiae, and H. sapiens. We selected the top-seven methods through a computational validation on the human interactome. We next experimentally validated their top-500 predicted PPIs (in total 3,276 predicted PPIs) using the yeast two-hybrid assay, finding 1,177 new human PPIs (involving 633 proteins). Our results indicate that task-tailored similarity-based methods, which leverage the underlying network characteristics of PPIs, show superior performance over other general link prediction methods. Through experimental validation, we confirmed that the top-ranking methods show promising performance externally. For example, from the top 500 PPIs predicted by an advanced similarity-base method [MPS(B&T)], 430 were successfully tested by Y2H with 376 testing positive, yielding a precision of 87.4%. These results establish advanced similarity-based methods as powerful tools for the prediction of human PPIs.

Predicting Interactions Between Pathogen and Human Proteins Based on the Relation Between Sequence Length and Amino Acid Composition

Aim: Both bacterial infection and viral infection involve a large number of protein-protein interactions (PPIs) between a pathogen and its target host. Background: So far, many computational methods have focused on predicting PPIs within the same species rather than PPIs across different species. Methods: From the extensive analysis of PPIs between Yersinia pestis bacteria and humans, we recently discovered an interesting relation; a linear relation between amino acid composition and sequence length was observed in many proteins involved in PPIs. We have built a support vector machine (SVM) model, which predicts PPIs between human and bacteria using two feature types derived from the relation. The two feature types used in the SVM are the amino acid composition group (AACG) and the difference in amino acid composition between host and pathogen proteins. Result: The SVM model achieved high performance in predicting bacteria-human PPIs. The model showed an accuracy of 96%, sensitivity of 94%, and specificity of 98% in predicting PPIs between humans and Yersinia pestis, in which there is a strong relation between amino acid composition and sequence length. The SVM model was also tested in predicting PPIs between human and viruses, which include Ebola, HCV, and SARSCoV-2, and showed a good performance. Conclusion: The feature types identified in our study are simple yet powerful in predicting pathogen-human PPIs. Although preliminary, our method will be useful for finding unknown target host proteins or pathogen proteins and designing in vitro or in vivo experiments.

An improved method for predicting interactions between virus and human proteins

The interaction of virus proteins with host proteins plays a key role in viral infection and consequent pathogenesis. Many computational methods have been proposed to predict protein–protein interactions (PPIs), but most of the computational methods are intended for PPIs within a species rather than PPIs across different species such as virus–host PPIs. We developed a method that represents key features of virus and human proteins of variable length into a feature vector of fixed length. The key features include the relative frequency of amino acid triplets (RFAT), the frequency difference of amino acid triplets (FDAT) between virus and host proteins, and amino acid composition (AC). We constructed several support vector machine (SVM) models to evaluate our method and to compare our method with others on PPIs between human and two types of viruses: human papillomaviruses (HPV) and hepatitis C virus (HCV). Comparison of our method to others with same datasets of HPV–human PPIs and HCV–human PPIs showed that the performance of our method is significantly higher than others in all performance measures. Using the SVM model with gene ontology (GO) annotations of proteins, we predicted new HPV–human PPIs. We believe our approach will be useful in predicting heterogeneous PPIs.