Using an artificial intelligence (AI) method developed by researchers at Aalto University and the University of Helsinki, researchers can now link immune cells to their targets and, for example, decouple which white blood cells recognize SARS-CoV-2. The tool developed has wide applications in understanding the function of the immune system in infections, autoimmune diseases and cancer.
Human immune defense relies on the ability of white blood cells to accurately identify pathogenic pathogens and initiate a defensive reaction against them. The immune defense is able to recall the pathogens that it has encountered previously, on which, for example, the effectiveness of vaccines is based. Thus, immune defense is the most accurate patient record system that contains a history of all the pathogens an individual has encountered. However, this information was previously difficult to obtain from patient samples.
The learning immune system can be divided into two parts, of which B cells are responsible for producing antibodies against pathogens, while T cells are responsible for destroying their targets. Measuring antibodies by traditional laboratory methods is relatively straightforward, which is why antibodies already have many health uses.
“Although it is known that the role of T cells in the defense response against, for example, viruses and cancer is essential, the identification of T cell targets has been difficult despite extensive research”, explains Satu Mustjoki, professor of translational hematology.
AI helps identify new pairs of key locks
T cells identify their targets in a key and locking principle, where the key is the T cell receptor on the surface of the T cell and the key is the protein presented on the surface of an infected cell. It is estimated that an individual carries more different T cell keys than there are stars in the Milky Way, which makes mapping T cell targets with laboratory techniques cumbersome.
Researchers at Aalto University and the University of Helsinki therefore studied pairs of previously profiled key locks and were able to create an AI model capable of predicting targets for previously unmapped T cells.
“The AI model we created is flexible and is applicable to all possible pathogens – as long as we have enough experimentally produced locked key pairs. For example, we were quickly able to apply our model to the SARS-CoV-2 coronavirus when a sufficient number of these pairs were available, ”explains Emmi Jokinen, M.Sc. and a Ph.D. student at Aalto University.
The results of the study help us understand how a T cell applies different parts of its key to identify its locks. The researchers studied T cells that recognize common viruses such as influenza, HI, and hepatitis B viruses. The researchers also used their tool to analyze the role of hepatitis B-recognizing T cells, which had lost its destructive ability after hepatitis progressed to liver cell cancer.
The study was published in the scientific journal Computational Biology PLOS.
New life for published data with new AI models
AI-powered tools are profitable research topics.
“With the help of these tools, we are able to better use and understand the large patient cohorts already published,” says Harri Lähdesmäki, professor of computational biology and machine learning at Aalto University.
Using the artificial intelligence tool, the researchers understood, among other things, how the intensity of the defense reaction is linked to its target in different disease states, which would not have been possible without this study.
“For example, in addition to the COVID19 infection, we studied the role of the defense system in the development of various autoimmune diseases and explained why some cancer patients benefit from new drugs and others do not,” reveals the doctor Jani Huuhtanen, Ph. RÉ. student at the University of Helsinki, on upcoming work with the new model.