Dataset Information

Defining host-pathogen interactions employing an artificial intelligence workflow.

ABSTRACT: For image-based infection biology, accurate unbiased quantification of host-pathogen interactions is essential, yet often performed manually or using limited enumeration employing simple image analysis algorithms based on image segmentation. Host protein recruitment to pathogens is often refractory to accurate automated assessment due to its heterogeneous nature. An intuitive intelligent image analysis program to assess host protein recruitment within general cellular pathogen defense is lacking. We present HRMAn (Host Response to Microbe Analysis), an open-source image analysis platform based on machine learning algorithms and deep learning. We show that HRMAn has the capacity to learn phenotypes from the data, without relying on researcher-based assumptions. Using Toxoplasma gondii and Salmonella enterica Typhimurium we demonstrate HRMAn's capacity to recognize, classify and quantify pathogen killing, replication and cellular defense responses. HRMAn thus presents the only intelligent solution operating at human capacity suitable for both single image and high content image analysis.

Editorial note

This article has been through an editorial process in which the authors decide how to respond to the issues raised during peer review. The Reviewing Editor's assessment is that all the issues have been addressed (see decision letter).

SUBMITTER: Fisch D

PROVIDER: S-EPMC6372283 | biostudies-literature | 2019 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Defining host-pathogen interactions employing an artificial intelligence workflow.

Fisch Daniel D Yakimovich Artur A Clough Barbara B Wright Joseph J Bunyan Monique M Howell Michael M Mercer Jason J Frickel Eva E

eLife 20190212

For image-based infection biology, accurate unbiased quantification of host-pathogen interactions is essential, yet often performed manually or using limited enumeration employing simple image analysis algorithms based on image segmentation. Host protein recruitment to pathogens is often refractory to accurate automated assessment due to its heterogeneous nature. An intuitive intelligent image analysis program to assess host protein recruitment within general cellular pathogen defense is lacking ...[more]

PMID: 30744806

Similar Datasets

Project description:The goal of this project is to understand the etiology and pathology of host-pathogen interaction using high-throughput cellular phenotyping. By combining the expertise in pathogen biology, informatics and stem cell biology across the institute, this project will use targeted genetic modification in mouse embryonic stem cells to identify functions of host genes in innate immunity. We will also explore the biology of mouse embryonic stem cells and their differentiation into immune competent cells. To this end we will generate homozygous and inducible knockout lines in mouse embryonic stem cells, which will be differentiated into immune competent cells, such as macrophages or dendritic cells. These will be subjected to a panel of immune challenge and stimulation assays to characterise the functions of the disrupted genes. To identify new functions for mammalian genes in innate immunity we will:\Generate a panel of homozygous inducible gene knockout mouse ES cell lines working from a list of ca. 80 candidate genes (MGP phenotyping and GWAS hits). \Scale up differentiation protocols for immune challenge and stimulation assays.\Benchmark in vitro differentiated ES cell models against primary immune cells from selected MGP mouse lines and eventually against human iPS cells.\Screen a panel of 30 genetically modified cell lines in immunological challenge and stimulation assays, defining phenotypes at the cellular level by high content imaging, biochemically by assaying cytokine production, and at the molecular level by transcriptome analysis.\Define novel gene functions in innate immunity through network analysis of gene expression data from all challenged cell lines.\In the longer term scale up the production and phenotyping of genetically modified cell lines (mouse or human as appropriate).This data is part of a pre-publication release. For information on the proper use of pre-publication data shared by the Wellcome Trust Sanger Institute (including details of any publication moratoria), please see http://www.sanger.ac.uk/datasharing/

Project description:MotivationAn important aspect of infectious disease research involves understanding the differences and commonalities in the infection mechanisms underlying various diseases. Systems biology-based approaches study infectious diseases by analyzing the interactions between the host species and the pathogen organisms. This work aims to combine the knowledge from experimental studies of host-pathogen interactions in several diseases to build stronger predictive models. Our approach is based on a formalism from machine learning called 'multitask learning', which considers the problem of building models across tasks that are related to each other. A 'task' in our scenario is the set of host-pathogen protein interactions involved in one disease. To integrate interactions from several tasks (i.e. diseases), our method exploits the similarity in the infection process across the diseases. In particular, we use the biological hypothesis that similar pathogens target the same critical biological processes in the host, in defining a common structure across the tasks.ResultsOur current work on host-pathogen protein interaction prediction focuses on human as the host, and four bacterial species as pathogens. The multitask learning technique we develop uses a task-based regularization approach. We find that the resulting optimization problem is a difference of convex (DC) functions. To optimize, we implement a Convex-Concave procedure-based algorithm. We compare our integrative approach to baseline methods that build models on a single host-pathogen protein interaction dataset. Our results show that our approach outperforms the baselines on the training data. We further analyze the protein interaction predictions generated by the models, and find some interesting insights.AvailabilityThe predictions and code are available at: http://www.cs.cmu.edu/?mkshirsa/ismb2013_paper320.html .Supplementary informationSupplementary data are available at Bioinformatics online.

Dataset Information

Defining host-pathogen interactions employing an artificial intelligence workflow.

Editorial note

Publications

Defining host-pathogen interactions employing an artificial intelligence workflow.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets