HPiP: an R/Bioconductor package for predicting host–pathogen protein–protein interactions from protein sequences using ensemble machine learning approach

Abstract

Motivation Despite arduous and time-consuming experimental efforts, protein-protein interactions (PPIs) for many pathogenic microbes with their human host are still unknown, limiting our understanding of the intricate interactions during infection and the identification of therapeutic targets. Since computational tools offer a promising alternative, we developed an R/Bioconductor package, HPiP (Host-Pathogen Interaction Prediction) software with a series of amino acid sequence property descriptors and an ensemble machine-learning (ML) classifiers to predict the yet unmapped interactions between pathogen and host proteins. Results Using SARS-CoV-1 or the novel SARS-CoV-2 coronavirus-human PPI training sets as a case study, we show that HPiP achieves a good performance with PPI predictions between SARS-CoV-2 and human proteins, which we confirmed experimentally in human monocyte THP-1 cells, and with several quality control metrics. HPiP also exhibited strong performance in accurately predicting the previously reported PPIs when tested against the sequences of pathogenic bacteria, Mycobacterium tuberculosis and human proteins. Collectively, our fully documented HPiP software will hasten the exploration of PPIs for a systems-level understanding of many understudied pathogens, and uncover molecular targets for repurposing existing drugs. Availability and implementation HPiP is released as an open-source code under the MIT license that is freely available on GitHub (https://github.com/BabuLab-UofR/HPiP) as well as on Bioconductor (http://bioconductor.org/packages/devel/bioc/html/HPiP.html). Supplementary information Supplementary data are available at Bioinformatics Advances online.

Prediction of mammalian virus cross-species transmission based on host proteins

“…Understanding the interaction network between viruses and hosts may help much in clarifying the mechanism of virus cross-species transmission and improving the prediction model of predicting virus cross-species transmission ( 35 , 36 ). Despite extensive efforts to uncover virus-host protein-protein interactions, the current knowledge remains incomplete ( 20 , 22 , 34 ). For example, the HVIDB, which is an up-to-date database of virus-human protein-protein interactions, contains less than 100,000 entries.…”

“…Reliable computational methods are required to systematically identify high-confidence protein-protein interactions between viruses and hosts ( 20 ). While several methods for predicting virus-host protein-protein interactions have been developed in recent years, substantial improvements are still necessary to enhance their practical applications ( 22 , 34 , 37 ).…”