Scientists have created an innovative AI-driven platform with the ability to analyze the way in which pathogens infect our cells with the accuracy of a trained biologist.
High-resolution rendering of the AI attention map superimposed on Toxoplasma Gondii. (Image credit: Artur Yakimovich)
The platform, named HRMAn (“Herman”), an acronym for Host Response to Microbe Analysis, is easy-to-use, open-source, and can be customized for distinct pathogens, including
Developed for the first time by researchers at the
Francis Crick Institute and UCL, HRMAn employs deep neural networks to investigate complex patterns in images of pathogen and human (“host”) cell interactions, extracting the same detailed properties that researchers carry out by hand. The study has been reported in the open access journal eLife, which has a link to download the platform and access tutorial videos.
The Scientist that Never Sleeps
What used to be a manual, time-consuming task for biologists now takes us a matter of minutes on a computer, enabling us to learn more about infectious pathogens and how our bodies respond to them, more quickly and more precisely,” stated Eva Frickel, Group Leader at the Crick, who headed the project. “ HRMAn can actually see host-pathogen interactions like a biologist, but unlike us, it doesn’t get tired and need to sleep!”
The researchers demonstrated the power of HRMAn, which runs on the KNIME platform, by using it to analyze the response of the body to
Toxoplasma gondii, a parasite that multiplies in cats and is considered to be borne by more than one-third of the world’s population.
Scientists at the Crick’s High Throughput Screening facility gathered more than 30,000 microscope images of five distinct types of Toxoplasma-infected human cells and loaded them into HRMAn for analysis. HRMAn detected and analyzed more than 175,000 pathogen-containing cellular compartments, offering detailed information related to the number of parasites per cell, the number of cell proteins that interacted with the parasites, the location of the parasites inside the cells, apart from other variables.
Revolutionizing Lab Work
Previous attempts at automating host-pathogen image analysis failed to capture this level of detail. Using the same sorts of algorithms that run self-driving cars, we’ve created a platform that boosts the precision of high volume biological data analysis, which has revolutionised what we can do in the lab. AI algorithms come in handy when the platform evaluates the image-based data in a way a trained specialist would. It’s also really easy to use, even for scientists with little to no knowledge of coding.
Artur Yakimovich, Study Co-First Author, University College London.
Yakimovich is also a research associate in Jason Mercer’s lab at the MRC LMCB at UCL.
The researchers also employed HRMAn to analyze
Salmonella enterica—a bacterial pathogen with a size 16 times smaller compared to Toxoplasma, showing its versatility for analyzing different pathogens.
Our team uses HRMAn to answer specific questions about host-pathogen interactions, but it has far-reaching implications outside the field too. HRMAn can analyse any fluorescence image, making it relevant for lots of different areas of biology, including cancer research.
Daniel Fisch, Study Co-First Author and PhD student, Francis Crick Institute.