Researchers from the Francis Crick Institute in London released a new AI-driven toolkit that analyzes complex patterns in images of pathogen and human cell interactions, and do so in a fraction of the time normally required.
Affectionately called ‘Herman,’ or Host Response to Microbe Analysis (HRMAn), the deep neural network extracts the same characteristics of cell interactions in minutes, compared to the laborious process of doing so manually.
“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,” said Eva Frickel, with the Host-Toxoplasma Interaction Laboratory at the Crick Institute, in a news release. “HRMAn can actually see host-pathogen interactions like a biologist, but unlike us, it doesn’t get tired and need to sleep!”
To test HRMAn, the team loaded the platform with more than 30,000 microscope images of five different types of Toxoplasma-infected human cells, a parasite thought to be carried by more than one-third of the world’s population. The platform detected more than 175,000 pathogen-containing cellular compartments, according to the team, provided specific information about the number of parasites per cell, their location in the cell and how many cell proteins interacted with the parasites.
Herman can also be modified for various pathogens, including Salmonella enterica, which Frickel et al. demonstrated as part of their research.
"Our team uses HRMAn to answer specific questions about host-pathogen interactions, but it has far-reaching implications outside the field too," said co-first author Daniel Fisch, Crick PhD student, in the same release. "HRMAn can analyze any fluorescence image, making it relevant for lots of different areas of biology, including cancer research."
The research is detailed in the open access journal eLife, which also includes a link to download the AI platform and tutorials on how to us it.