Single-sequence protein-RNA complex structure prediction by geometric attention-enabled pairing of biological language models.

Abstract

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.