AI Insight
ReTIF is a new computational framework designed to predict RNA-compound interactions and identify specific nucleotide binding sites simultaneously. Unlike existing methods that use shared representations for both tasks, ReTIF creates separate interaction representations: one that captures overall compatibility between RNA and compounds, and another that preserves nucleotide-level details for binding-site identification. The model incorporates structural information from RNA and compound molecules and outperforms 13 baseline methods across multiple evaluation scenarios, particularly excelling at binding-site prediction.
Why it matters
This work addresses a critical bottleneck in RNA-targeted drug discovery by improving both the prediction of which compounds interact with RNA molecules and the precise identification of where these interactions occur. Better computational tools for RNA-compound interaction prediction could accelerate the development of RNA-targeting therapeutics, an emerging class of drugs with potential applications in treating diseases caused by RNA dysfunction.
Understand the Science
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
RNA-targeted drug discovery requires both RNA-compound interaction prediction and nucleotide-level binding-site (BS) localization. These two tasks rely on different levels of interaction information: DTI prediction summarizes overall RNA-compound compatibility, whereas BS localization requires preserving nucleotide-level compound-associated signals. However, existing multitask models often use shared cross-modal representations for both tasks before task-specific prediction layers, which may limit their ability to preserve task-dependent interaction patterns. We therefore propose ReTIF (Relation-enhanced Task-specific Interaction Framework), which constructs separate cross-modal interaction representations for DTI prediction and BS localization before aggregation. ReTIF integrates multi-source RNA-compound representations from frozen RNA-FM, StructRFM, Mole-BERT, and MolFormer encoders, and builds separate interaction representations for DTI scoring and BS localization. The DTI branch captures global compatibility through aggregation, whereas the BS branch preserves nucleotide-compound resolution and enhances local evidence through relation-guided propagation with RNA structural and compound topological priors. An asymmetric DTI-derived compatibility signal provides global context to BS prediction while maintaining local evidence. Across five-fold evaluations under unseen pair, RNA, compound, and joint shifts with 13 baselines, ReTIF has the highest mean in 13 of 16 scenario-metric combinations, including BS AUPR in all four settings.