Sep 2026· Journal of Chemical Information and Modeling· Vol 66 18, pp.
11711-11722
· 4 citations· 51 references
Medicine
TL;DR
A multimodal deep learning framework that integrates molecular surface fingerprints, contextual sequence embeddings from a pretrained RNA language model and dot bracket secondary structure encoding to predict ligand binding sites on RNA, which provides an accurate and generalizable tool for nucleotide resolution binding sites prediction.
Abstract
Identification of RNA-small-molecule binding sites is a critical first step in RNA-targeted drug discovery. Although several machine learning methods have made progress by integrating RNA sequence, secondary structure, and 3-dimensional (3D) atomic arrangement information to identify nucleotide level binding residues, most of them neglect the molecular surface that directly contacts small-molecule compounds and are highly dependent on accurate three-dimensional structures. Here, we present MultiRSF, a multimodal deep learning framework that integrates molecular surface fingerprints, contextual sequence embeddings from a pretrained RNA language model and dot bracket secondary structure encoding to predict ligand binding sites on RNA. MultiRSF fuses these features through a hierarchical Transformer encoder and demonstrates robust predictive performance on both ligand-free RNA structures (apo RNA) and ligand-bound RNA structures (holo RNA). On independent benchmark sets TE18 and APO8, MultiRSF outperforms state-of-the-art methods, achieving precision of 0.765/0.458, recall of 0.698/0.286, and Matthews correlation coefficient (MCC) of 0.535/0.279. Case studies on a ligand-induced riboswitch conformational change and an NMR conformational ensemble further illustrate the model's robustness to moderate RNA flexibility. In conclusion, MultiRSF provides an accurate and generalizable tool for nucleotide resolution binding sites prediction, with potential to accelerate early-stage RNA-targeted drug discovery.
By integrating structure selection with binding-preference inference, PRIS provides an efficient framework for large-scale RNA library screening and aptamer design.
Yi-Hao Zhao, Jing Han, Ji-Ke Wang et al.· bioRxiv· 0 citations
PNBind is presented, a multimodal deep learning framework that leverages protein language models, evolutionary information, and three-dimensional structural features via a geometric vector perceptron (GVP) backbone with an invariant point attention (IPA) layer for nucleic acid-binding site prediction.
In this study, InterActRNA is presented as a co-evolutionary geometric deep learning framework that consistently outperforms state-of-the-art baselines in both regression and classification tasks and has the potential to guide rational RNA-targeted drug design.
Jin-Miao Song, Qi-Lin Feng, Lei Deng et al.· IEEE transactions on computa...· 0 citations
LGBind is introduced, a structure-guided deep learning framework for generalized, ligand-conditioned binding site identification and demonstrates profound robustness and generalization in predicting novel ligand-target interactions, and demonstrates remarkable versatility.
Yun-Feng Li, Xing-Yu Liu, Yi-Jia Liu et al.· European journal of medicina...· 0 citations
An in silico method to facilitate RNA-targeting small-molecule discovery that integrates enhanced sampling molecular dynamics simulations using the classical Drude polarizable force field with site identification by ligand competitive saturation (SILCS) technology is developed.
Jihyeon Lee, Alexander D. MacKerell· Journal of Chemical Theory a...· 1 citation