ARES Helps Improve Computational Prediction of RNA Structures

Researchers present a new machine learning method—called ARES (Atomic Rotationally Equivariant Scorer)—that significantly improves the computational prediction of RNA structures over previous approaches. Their findings were published in Science. 

Experimentally solving RNA structure remains a challenge despite decades of effort, and only a few RNA structures are currently known. Additionally, using machine learning to predict RNA structure has proven far more difficult—and less successful—than it has for protein structure prediction.

To address these challenges, Raphael Townshend and colleagues developed ARES, a deep neural network that can consistently produce accurate RNA structural models, despite being trained using data for only 18 recently experimentally determined RNA structures. According to the authors, ARES significantly outperformed other computational approaches in the community-wide RNA-Puzzles structure prediction challenge. 

The team notes that ARES’s performance is particularly notable as it learned to make its predictions based solely on atomic structure and does not incorporate prior assumptions about what RNA-specific structural features might be important, such as base pairs, nucleotides, or hydrogen bonds. As well, it was able to accurately predict the structures of RNAs larger and more complex than those it was trained on.