Science & Tech · Science & Environment · 2 hrs ago
Pusan National University team develops AI model to predict RNA binding sites
A team at Pusan National University developed circMAC, an AI model for studying RNA interactions.
It predicts likely binding sites between circular RNA and microRNA, two types of RNA involved in regulating gene activity.
These interactions are linked to the development and progression of diseases, including cancer.
Until now, identifying the precise places where the two types of RNA bind has been difficult.
The model could help researchers understand RNA regulation and identify potential treatment targets.
The findings appeared in the journal Briefings in Bioinformatics, and the team says experimental testing is a next step.
A team at Pusan National University developed an AI model called circMAC to predict likely binding sites between circular RNA and microRNA.
The model predicts specific locations where the two types of RNA may bind.
The team said circMAC effectively predicted candidate binding sites in disease-related circular RNA and microRNA.
The research was published in the journal Briefings in Bioinformatics.
The findings may help explain RNA regulation and identify potential treatment targets.
- Who
- A research team led by Professor Song Gil-tae of Pusan National University's Department of Information and Computer Engineering.
- What
- The team developed circMAC, an AI model that predicts likely binding sites between circular RNA and microRNA.
- When
- The university announced the development on November 6, 2026.
- Where
- Pusan National University in Busan, South Korea.
- Why
- To predict specific RNA binding locations and support research into RNA regulation and potential treatment targets.
This story does not have two clearly opposing sides.
This story does not have a timeline yet.
- Model
- circMAC
- RNA types
- Circular RNA and microRNA
- Institution
- Pusan National University
- Journal
- Briefings in Bioinformatics
1 source
What people are saying
The significance of this research is that it goes beyond predicting whether RNAs interact and specifically indicates the locations where they are likely to bind.
We expect that, in conjunction with future experimental validation, it will contribute to understanding the regulatory mechanisms of disease-related RNA and improving the efficiency of follow-up life science research.