RNA’s structural complexity stems from its ability to adopt multiple conformations, driven by base-pairing and tertiary interactions. These conformers often carry functional significance, influencing processes such as gene regulation, catalysis, and molecular recognition. Existing experimental techniques like X-ray crystallography and cryo-electron microscopy, while invaluable, are labor-intensive and limited in throughput. Computational methods have therefore become indispensable; however, most are either limited in accuracy or computationally expensive, inhibiting their broader application. The innovators behind trRosettaRNA2 have taken a novel path by leveraging advances in deep learning alongside a strategic integration of secondary structure information.

A key innovation in trRosettaRNA2 lies in its auxiliary secondary structure prior module, trained extensively on large datasets of RNA secondary structures. Given that secondary structures—which depict base-pairing interactions—are more abundant and easier to determine than full 3D structures, this module generates robust base-pairing priors that inform the 3D modeling process. Remarkably, this secondary structure module also functions as an independent RNA secondary structure prediction tool, termed trRNA2-SS, which has demonstrated state-of-the-art performance metrics on rigorous benchmarks. This dual capability not only strengthens the 3D predictions but also enriches secondary structure annotation techniques.

What sets trRosettaRNA2 apart is its end-to-end architecture implemented through a specialized SS-aware attention mechanism. This approach allows the model to holistically incorporate secondary structure information during the prediction of RNA 3D conformations, ensuring consistency between 2D and 3D representations. This fusion effectively bridges the gap between relatively easy-to-predict secondary structures and the more elusive spatial arrangements. Moreover, this end-to-end paradigm provides a unified framework that can concurrently generate multiple RNA conformers, capturing the molecule’s intrinsic flexibility without depending heavily on experimental inputs.

Benchmarking results published alongside the development of trRosettaRNA2 are compelling. Across a diverse set of RNA molecules, the model consistently outperforms leading RNA 3D structure prediction tools in both accuracy and computational efficiency. Notably, trRosettaRNA2 achieves this while employing fewer parameters and significantly reduced computational overhead. This aspect is crucial, as it promises more accessible and scalable modeling workflows for the broader scientific community, ranging from academic researchers to pharmaceutical developers.

The flexibility of trRosettaRNA2 in accepting diverse secondary structure inputs is another milestone. RNA molecules often have ambiguous or multiple experimentally derived secondary structure models. The ability of trRosettaRNA2 to leverage such ambiguous or ensemble secondary structures enables it to explore alternative 3D conformers, mapping out the conformational landscape of RNA. This capability is a substantial advance toward better understanding the structural heterogeneity of RNA and its biological implications.

A tangible testament to the robustness of trRosettaRNA2 was its performance in the CASP16 blind test, a community-wide competition that benchmarks structure prediction methods. The Yang-Server, based on trRosettaRNA2, emerged as the top automated server for RNA structure prediction, outperforming even highly acclaimed models like AlphaFold 3. This achievement highlights the efficacy of integrating secondary structure priors and structure-aware attention within a streamlined deep learning framework and puts trRosettaRNA2 at the forefront of computational RNA biology.

Beyond structure prediction, the ability of trRosettaRNA2 to capture structural heterogeneity paves the way for exploring the conformational ensembles intrinsic to RNA function. For example, application of the method to the canonical ribonuclease P RNA revealed its nuanced conformational variability. Importantly, these insights were gleaned without relying on any experimental structural data, underscoring the model’s potential to predict dynamic ensembles purely computationally. Such predictive power opens new avenues to investigate RNA dynamics in regulatory mechanisms and disease contexts.

From a technical standpoint, the model capitalizes on a multi-scale representation of RNA, combining sequence, secondary structure, and spatial features. The SS-aware attention mechanism ensures that base-pairing constraints guide the folding pathways proposed during inference. By training on a curated dataset that spans a variety of RNA families, the model learns generalized folding principles while retaining sensitivity to sequence-specific variations, enabling accurate modeling of previously uncharacterized RNA sequences.

Moreover, the significant reduction in computational requirements achieved by trRosettaRNA2 ensures that researchers without access to expensive GPUs or clusters can still benefit from high-quality RNA structural predictions. This democratization of RNA modeling invites broader participation across disciplines, including synthetic biology, where designing RNA with programmable structures is becoming a linchpin technology.

Looking ahead, trRosettaRNA2’s framework is poised for integration with experimental data modalities, such as SHAPE probing or cryo-EM density maps, which could further enhance the fidelity of model predictions. The modular design of the system allows for straightforward incorporation of such complementary datasets, potentially enabling hybrid modeling approaches that marry data-driven priors with physical constraints.

Furthermore, the concept of conformer ensembles predicted by trRosettaRNA2 may be critical for drug discovery efforts targeting RNA. RNA molecules have increasingly become attractive therapeutic targets, especially in viral diseases and genetic disorders. Knowledge of RNA conformational landscapes facilitates the identification of druggable pockets and allosteric sites, which are often concealed in static structures. The ability to computationally sample these ensembles accelerates hit identification and lead optimization campaigns.

The influence of trRosettaRNA2 extends beyond immediate RNA structure prediction. Its successful deployment highlights the transformative impact of deep learning in biological macromolecule modeling, particularly when enriched by prior biological knowledge. The clever use of pre-trained models on secondary structure data represents a paradigm for other complex systems where full structural data is limited but more facile intermediate representations are available.

In conclusion, trRosettaRNA2 marks a definitive advance in the quest to decode RNA structures and their functional conformers. By harnessing a pre-trained secondary structure module and a novel structure-aware attention mechanism, it achieves unparalleled accuracy and computational efficiency. This achievement not only elevates RNA structural biology but also opens fertile ground for exploring RNA’s dynamic roles in health and disease. The model’s impressive performance in community contests like CASP16 confirms its readiness for widespread adoption, promising to fuel discoveries in RNA research, therapeutics, and beyond.

As RNA continues to reveal its multifaceted roles across biological processes, methods like trRosettaRNA2 will be indispensable tools pushing the frontier of molecular biology. The integration of data-driven machine learning with biological insight exemplifies how emerging computational methodologies are reshaping our understanding of life’s molecular fabric. With ongoing enhancements and applications, trRosettaRNA2 sets a new gold standard for predictive RNA modeling, heralding a new era in nucleic acid research.

Subject of Research: RNA 3D structure and conformer prediction using advanced deep learning techniques

Article Title: Predicting RNA 3D structure and conformers using a pre-trained secondary structure model and structure-aware attention

Article References:
Wang, W., Peng, Z. & Yang, J. Predicting RNA 3D structure and conformers using a pre-trained secondary structure model and structure-aware attention. Nat Mach Intell (2026). https://doi.org/10.1038/s42256-026-01223-x

Image Credits: AI Generated

DOI: https://doi.org/10.1038/s42256-026-01223-x

Ribonucleic acid, or RNA, serves as a crucial player in gene expression and regulation, acting as a messenger that conveys genetic information from DNA to protein synthesis. However, despite its fundamental involvement in cellular processes, a majority of RNA structures remain undetermined experimentally, primarily due to the complexities associated with their formation. Traditional methods for establishing RNA structures are often time-consuming and labor-intensive, creating a significant bottleneck in research endeavors. The advent of NuFold promises to alleviate such constraints by employing sophisticated computational algorithms that can rapidly predict RNA’s three-dimensional configuration based on its nucleotide sequence.

The novelty of NuFold lies in its end-to-end approach to RNA tertiary structure prediction, which adopts a flexible representation of nucleobases while accurately considering the intrinsic flexibility vital to RNA molecules. While previous models struggled to incorporate these factors, NuFold sets itself apart by effectively modeling the dynamic nature of RNA, allowing researchers to visualize potential structural conformations more reliably. This represents a significant advancement in computational biology, particularly for researchers focused on the mechanistic understanding of RNA and its myriad roles in health and disease.

Kihara and his team embarked on this ambitious project over three years ago, a span during which rigorous testing and development were paramount. Yuki Kagaya, the main developer of NuFold and a postdoctoral research assistant within Kihara’s group, commented on the robust foundation of the developed algorithms. Through extensive benchmarking, NuFold demonstrated its superior performance over conventional energy-based methodologies and even outperformed some prominent recent deep learning approaches in local structure prediction accuracy. This puts NuFold on the forefront of RNA modeling tools, poised to transform the landscape of RNA research.

One of the key implications of NuFold’s capabilities is its potential to significantly enhance drug development processes targeting RNA-based diseases. The ability to accurately predict RNA structures opens up opportunities for designing therapeutics that specifically engage with RNA molecules, thereby understanding their interactions better. As RNA-targeted therapies continue to garner attention—particularly in the realms of oncology, viral infections, and genetic disorders—NuFold offers a vital computational resource for accelerating such innovation in drug discovery.

Moreover, the open-access nature of NuFold enhances its usability across varied research sectors. By making the tool available through a Google Colab notebook, Purdue University ensures that researchers worldwide can leverage its capabilities without significant barriers to entry. This democratization of technology not only fosters collaboration among scientists but also invites interdisciplinary participation, as individuals from different fields experiment with RNA structure predictions within their own research contexts.

Purdue researchers have established strong collaborations, synergizing skills from computer science and biological sciences. This interdisciplinary approach has proven essential, as modeling RNA structures necessitates a deep understanding of both computational methodologies and the intricate biological roles RNA plays. Kihara’s work in the Structural Biology Group exemplifies this integration, as it simultaneously addresses biological questions and computational challenges.

Reflecting on the broader impact of their work, Kihara likened NuFold to AlphaFold, the revolutionary protein structure prediction tool that received significant accolades, including a Nobel Prize in Chemistry in 2024. Just as AlphaFold transformed protein research, NuFold aspires to bring a similar transformation to the field of RNA. Kihara emphasized that extending the breakthroughs of protein modeling into RNA is a critical step in enhancing our understanding of this essential molecule’s functions and implications in health.

NuFold’s sophisticated computational approaches also promise to expedite the discovery of novel RNA structures. The predictions generated by NuFold could lead to the identification of previously unrecognized structural conformations, sparking new research directions focused on unraveling the functional significance of these variants. Furthermore, as researchers continue to map the interconnected network of RNA functions, the ability to visualize RNA structures effectively will prove invaluable.

The intellectual endeavor that brought NuFold to fruition is representative of the continuous evolution of scientific inquiry driven by technological advancements. Purdue University’s commitment to fostering innovative research is evidenced not only by the tool itself but also by the collaborative efforts that underpin it, involving significant computational resources and expertise from its multiple institutes. The seamless integration of biology and computational science is a testament to the power of interdisciplinary collaboration in addressing complex scientific challenges.

In conclusion, NuFold stands as a testament to Purdue University’s ongoing dedication to advancing the fields of RNA research and computational biology. This innovative tool has the potential to reshape our understanding of RNA’s three-dimensional structures while also accelerating critical insights into RNA-targeted therapies. As scientists and researchers explore the capabilities of NuFold, the ripple effects of its implementation may resonate throughout the scientific community, ultimately contributing to the development of more effective medical interventions.

By harnessing state-of-the-art machine learning techniques, NuFold can transform RNA sequences into full atomic structures, catering to the pressing needs for understanding the vast landscape of RNA-related diseases. As the research community continues to grapple with these complexities, NuFold emerges as a beacon of hope, signifying a new era in RNA structural biology.

Subject of Research: Computational Modeling of RNA Structures
Article Title: NuFold: A Revolutionary Solution for RNA Structure Prediction
News Publication Date: TBD
Web References: TBD
References: TBD
Image Credits: Purdue University photo/Alisha Willett

Keywords
RNA structure, computational biology, drug discovery, structural biology, Daisuke Kihara, Purdue University