stub AI Model Links Immune Cells to Targets - Unite.AI
Connect with us


AI Model Links Immune Cells to Targets



A new artificial intelligence (AI) model developed by researchers at Aalto University and University of Helsinki is able to link immune cells to their targets. This means, for example, the AI can uncouple which white blood cells recognize COVID-19. According to the researchers, the new model will help create a better understanding of the immune system during infections, autoimmune disorders, and cancer.

The research was published last month in the journal PLOS Computational Biology.

Human Immune System

The human immune system relies on white blood cells accurately identifying pathogens that cause disease, and they then develop a defense against them. The immune system is also capable of recalling pathogens it previously encountered, which is the basis of the effectiveness of vaccines. This means that the human immune system holds a lot of data on which pathogens an individual has already encountered, but that data is often hard to obtain from patient samples.

The immune system contains B cells that are responsible for the production of antibodies, and T cells that are responsible for destroying targets. The measurement of antibodies is considered a relatively simple process. 

Satu Mustjoki is Professor of Translational Hematology. 

“Although it is known that the role of T cells in the defense response against for example viruses and cancer is essential, identifying the targets of T cells has been difficult despite extensive research,” says Mustjoki.

In order to identify their targets, T cells rely on a key and a lock principle. The T cell receptor is the key on the surface of the T cell, and the lock is the protein on the surface of an infected cell. It is difficult to map T cell targets with traditional lab techniques, as a single individual carries a massive amount.

AI Model Predicting Targets 

The researchers set out to study previously profiled key-lock pairs, which enabled them to develop an AI model capable of predicting targets for previously unmapped T cells. 

Emmi Jokinen is M.Sc and a Ph.D student at Aalto University. 

The study provides insight into how a T cell applies different parts of its key to identify its locks. Some of the common viruses studied by the researchers included influenza, HI-, and hepatitis B-virus.

The researchers say AI-generated tools are cost-effective research topics. 

Harri Lähdesmäki is Professor of Computational Biology and Machine Learning at Aalto University. 

“With the help of these tools, we are able to make better use of the already published vast patient cohorts and gain additional understanding of them,” Lähdesmäki says. 

One of the major findings with the AI tools was how the intensity of the defense reaction relates to its target in different disease states, which they say is a direct result of this study.

M.D. Jani Huuhtanen is a Ph.D. student at the University of Helsinki. 

“For example, in addition to COVID19 infection, we have investigated the role of the defense system in the development of various autoimmune disorders and explained why some cancer patients benefit from new drugs and some do not,” Huuhtanen says. 


Alex McFarland is an AI journalist and writer exploring the latest developments in artificial intelligence. He has collaborated with numerous AI startups and publications worldwide.