bioRxiv Science⌕ Search
Home/Archive/bioRxiv

bioRxiv · 10.64898/2026.02.06.704425

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

Murugadass, C.·Rana, H.·Znosko, B. M.·Hou, J.·Si, D.
View original source ↗Export metadata ↓

Abstract

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

Source connections

Explore related subjects

bioinformaticsPreprint

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Murugadass, C., Rana, H., Znosko, B. M., Hou, J., Si, D.. 2026-02-09. A Large-Scale Cryo-EM RNA Motif Dataset and Benchmark for Machine Learning-Based Structure Modeling. https://doi.org/10.64898/2026.02.06.704425

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

bioRxiv2026

Targeted finetuning enables co-folding models to learn ligand-induced protein conformational states

Advances in protein structure prediction have enabled all-atom protein-ligand co-folding models that predict bound conformations directly from sequence and small-molecule structure. However, these models often fail to generalize to novel binding sites or alternative protein conformational states, limiting their utility for chemical biology and drug discovery. Here we show this limitation reflects training data bias rather than architectural constraints and can be overcome through targeted finetuning. Using ten previously unseen X-ray structures of Werner (WRN) helicase from a drug discovery program, we finetune Boltz-1 to learn both an allosteric binding site and a large conformational change locking the enzyme in an inactive state, while preserving accuracy on the ATP-bound state. The finetuned model generalizes to different chemical series and transfers the conformational logic across RecQ-family helicases in a binding-site sequence-dependent manner. This approach provides a blueprint for adapting foundation models as new structural and mechanistic data emerge, enabling co-folding networks to capture ligand-induced conformational switches and binding poses absent from their training data but central to biological regulation and therapeutic intervention.

bioinformatics↗
bioRxiv2026

Benchmarking single-cell foundation models for aging biology

Single cell foundation models (scFMs) provide representations of cellular states, but their utility across biological questions in aging research remains unclear. We established a benchmark of cellular representations for aging research, evaluating ten general-purpose scFMs, three aging-specific models and conventional methods across five biological questions using more than 2.5 million single cell transcriptomes. Using frozen pretrained representations, Geneformer performed best among scFMs for chronological age prediction and age pseudotime concordance, although 2,000 highly variable genes achieved higher mean performance. Several scFMs captured positive molecular age shifts across three disease contexts, consistent with reported aging-associated changes. SCimilarity performed well for rare cellular state identification across out-of-distribution datasets, exceeding aging specific models and conventional baselines. At the gene level, scGPT showed the highest recovery of reference TF target interactions, including aging-related regulatory hubs. Overall, scFMs supported diverse aging analyses, but performance depended on the biological question, highlighting their utility for rare cellular state identification and regulatory analysis.

bioinformatics↗
bioRxiv2026

CryoMV: Structure-Prior-Guided Modeling and Real-Particle Validation of Continuous Conformational Transitions in Cryo-EM

Continuous protein conformations are essential for understanding fundamental biological processes and supporting drug discovery. Although cryo-EM can resolve individual states at high resolution, recovering continuous heterogeneity from 2D particle images remains challenging. High noise, motion blur, and limited structural priors make it difficult to accurately generate and validate high-resolution continuous conformations using raw particle data. Here, we introduce cryoMV, a framework that integrates structure-prior-guided modeling with real-particle validation for continuous conformational transitions. CryoMV uses reference density maps to establish structural anchors and motion priors, models candidate transition paths between selected conformations, and transfers the learned representation to raw 2D cryo-EM particle images. Each candidate conformation is subsequently evaluated using the estimated particle poses and contrast transfer functions. Supported conformations are reconstructed through raw particle back-projection and assessed using canonical half-maps and Fourier shell correlation. On EMPIAR-10516 and EMPIAR-10345, cryoMV achieves excellent performance in terms of robustness, verifiability, and reconstruction resolution. By incorporating structure-prior modeling and evidence from the raw particles, cryoMV offers an explicit mechanism for assessing whether generated conformations are supported by experimental data and provides a practical approach to reducing model-induced artifacts in continuous cryo-EM heterogeneity analysis.

bioinformatics↗