Znosko, B. M. | Search bioRxiv

bioRxiv2026

A Large-Scale Cryo-EM RNA Motif Dataset and Benchmark for Machine Learning-Based Structure Modeling

MotivationRNA molecules play critical roles in gene regulation, viral replication, and cellular control, with their functions tightly coupled to three-dimensional structure. Advances in cryogenic electron microscopy (cryo-EM) now enable RNA structure characterization across a broad resolution range. RNA secondary structural motifs, including hairpins, internal loops, and bulges, act as fundamental building blocks of RNA tertiary architecture and are key targets in RNA-focused therapeutic design. Despite this, most computational approaches for RNA structure prediction from cryo-EM density maps do not explicitly utilize secondary structural motifs as intermediate representations, largely due to the absence of large-scale, high-quality, and motif-resolved datasets suitable for machine learning. ResultsHere, we present a large, open-source dataset containing over 125,000 motif-resolved cryo-EM density maps paired with corresponding atomic structures, spanning 25 classes of RNA secondary structural motifs. The dataset covers resolutions from 1.5 [A] to 34.0 [A], encompassing both near-atomic and low-resolution density maps relevant to RNA modeling. Each motif instance includes a segmented cryo-EM density map represented as a standardized 3D voxel grid, with atomic-level motif annotations propagated to voxel-level labels for RNA backbone, ribose sugar, and nucleobase components. Segmentation quality is validated via cross-correlation analysis, demonstrating strong agreement between motif-level density maps and atomic reference models. To illustrate the datasets utility, high-resolution maps (1.5-2.8 [A]) were used to train a machine learning classifier that distinguished five motif classes with a specificity of 0.948. Availability and ImplementationSource code, implementation of the fully automated pipeline, and the benchmark datasets are publicly available at GitHubhttps://github.com/DrDongSi/3DEM-RNA-Motif-Dataset Zenodohttps://zenodo.org/communities/3dem-rna-motif-dataset Contacthoujie@msu.edu, dongsi@uw.edu

bioinformatics↗

bioRxiv2024

Exploring the Efficiency of Deep Graph Neural Networks for RNA Secondary Structure Prediction

Ribonucleic acid (RNA) plays a vital role in various biological processes and forms intricate secondary and tertiary structures associated with its functions. Predicting RNA secondary structures is essential for understanding the functional and regulatory roles of RNA molecules in biological processes. Traditional free-energy-based methods for predicting these structures often fail to capture complex interactions and long-range dependencies within RNA sequences. Recent advancements in machine learning, particularly with graph neural networks (GNNs), have shown promise in enhancing the ability to model the relationships between molecular sequences and their structures. This work specifically explores the efficacy of various GNN architectures in modeling RNA secondary structure. Through benchmarking the GNN methods against traditional energy-based models on standard datasets, our analysis demonstrates that GNN models improves traditional methods, offering a robust framework for accurate RNA structure prediction.

bioinformatics↗