Transferring knowledge of bacterial protein interaction networks to predict pathogen targeted human genes and immune signaling pathways: a case study on M. tuberculosis

Abstract

BackgroundBacterial invasive infection and host immune response is fundamental to the understanding of pathogen pathogenesis and the discovery of effective therapeutic drugs. However, there are very few experimental studies on the signaling cross-talks between bacteria and human host to date.MethodsIn this work, taking M. tuberculosis H37Rv (MTB) that is co-evolving with its human host as an example, we propose a general computational framework that exploits the known bacterial pathogen protein interaction networks in STRING database to predict pathogen-host protein interactions and their signaling cross-talks. In this framework, significant interlogs are derived from the known pathogen protein interaction networks to train a predictive l2-regularized logistic regression model.ResultsThe computational results show that the proposed method achieves excellent performance of cross validation as well as low predicted positive rates on the less significant interlogs and non-interlogs, indicating a low risk of false discovery. We further conduct gene ontology (GO) and pathway enrichment analyses of the predicted pathogen-host protein interaction networks, which potentially provides insights into the machinery that M. tuberculosis H37Rv targets human genes and signaling pathways. In addition, we analyse the pathogen-host protein interactions related to drug resistance, inhibition of which potentially provides an alternative solution to M. tuberculosis H37Rv drug resistance.ConclusionsThe proposed machine learning framework has been verified effective for predicting bacteria-host protein interactions via known bacterial protein interaction networks. For a vast majority of bacterial pathogens that lacks experimental studies of bacteria-host protein interactions, this framework is supposed to achieve a general-purpose applicability. The predicted protein interaction networks between M. tuberculosis H37Rv and Homo sapiens, provided in the Additional files, promise to gain applications in the two fields: (1) providing an alternative solution to drug resistance; (2) revealing the patterns that M. tuberculosis H37Rv genes target human immune signaling pathways.Electronic supplementary materialThe online version of this article (10.1186/s12864-018-4873-9) contains supplementary material, which is available to authorized users.

Computational Biology and Machine Learning Approaches to Understand Mechanistic Microbiome-Host Interactions

“…Supervised methods can also be differentiated by the kind of ML methodology/model used for the task of rightly classifying truly interacting protein pairs. Several supervised studies employing individual ML models [such as I2-regularized logistic regression ( Mei et al, 2018 ), random forests (RF) ( Kösesoy et al, 2019 ), etc], support vector machine (SVM) ( Cui et al, 2012 ; Shoombuatong et al, 2012 ; Kim et al, 2017 ) have been applied to infer PPIs between microbial and host species. SVMs use a framework of searching and finding the best hyperplane (aka decision boundary represented by a mathematical equation) to separate sample with different labels corresponding to a class.…”

Genome-scale host-pathogen prediction for non-medical microbes

“…Secreted and membrane proteins. Bacterial proteins that interact with host are often external, secreted or membrane proteins (28,29). To determine whether the bacterial proteins from predicted HPI belonged to this category, we evaluated the GO associated with these proteins for the following GO terms (or their child terms): GO:0005576 extracellular region, GO:0005615 extracellular space, GO:0016020 membrane, GO:0009274 peptidoglycan-based cell wall, GO:0009289 pilus, GO:0030115 S-layer, GO:0043657 host cell and GO:0009288 bacterial-type flagellum.…”