Researchers are working hard to find better ways to predict whether a transplanted organ will be rejected by a patient’s immune system. Currently, doctors often detect rejection only after it has started, and sometimes the damage is already permanent. But what if we could spot signs of rejection before the transplant even happens?

A team led by researchers at Juntendo University has taken an important step in that direction. They used RNA sequencing to analyze gene activity in immune cells collected from patients before they received a liver or kidney transplant. By using machine learning and a method called weighted gene co-expression network analysis, they identified patterns in gene activity that were linked to later organ rejection.

Weighted co-expression network based rejection prediction strategy

(a) Identifying modules in weighted co-expression networks that are related to traits (NR and R). (b) Using gene expression levels and gene significance in modules to perform feature engineering, and using the computed features to train and predict on machine learning models.

In patients who had liver transplants, genes involved in antiviral responses and the production of the immune molecule IL-1 were more active in those who later experienced rejection. For kidney transplants, genes related to innate immunity, such as IL-8 and toll-like receptor signaling, as well as T cell responses, were linked to rejection risk.

This approach shows that gene expression data from a patient’s own immune cells could help doctors estimate the risk of organ rejection in advance. In the future, this method might help tailor treatment plans to reduce the risk of rejection and improve transplant outcomes.