2025-09-16 バージニア工科大学(Virginia Tech)
A 3D image of viral RNA interacting with host protein created by the ProRNA3D-single tool.
<関連情報>
- https://news.vt.edu/articles/2025/09/eng-cs-groundbreaking-AI-aims-to-speed-lifesaving-therapies.html
- https://www.cell.com/cell-systems/abstract/S2405-4712(25)00233-9
幾何学的アテンション機構を組み込んだ生物言語モデルのペアリングによる単一配列タンパク質-RNA複合体構造予測 Single-sequence protein-RNA complex structure prediction by geometric attention-enabled pairing of biological language models
Rahmatullah Roche ∙ Sumit Tarafder ∙ Debswapna Bhattacharya
Cell Systems Published:September 16, 2025
DOI:https://doi.org/10.1016/j.cels.2025.101400
Highlights
- A protein-RNA complex structure prediction method with single-sequence input
- Employs geometric attention-enabled pairing of heterogenous biological language models
- Outperforms state-of-the-art methods when evolutionary information is limited
Summary
Groundbreaking progress has been made in structure prediction of biomolecular assemblies, including the recent breakthrough of AlphaFold 3. However, it remains challenging for AlphaFold 3 and other state-of-the-art deep-learning-based methods to accurately predict protein-RNA complex structures, in part due to the limited availability of evolutionary information related to protein-RNA interactions that are used as inputs to the existing approaches. Here, we introduce ProRNA3D-single, a deep-learning framework for protein-RNA complex structure prediction. Using a geometric attention-enabled pairing of biological language models of protein and RNA, a previously unexplored avenue, ProRNA3D-single predicts interatomic protein-RNA interaction maps, which are then transformed into multi-scale geometric restraints for modeling 3D structures of protein-RNA complexes via geometry optimization. Benchmark tests show that ProRNA3D-single outperforms state-of-the-art methods, including AlphaFold 3, particularly when evolutionary information is limited, and exhibits robustness and performance resilience by attaining state-of-the-art accuracy with only single-sequence input.
