When will RNA get its AlphaFold moment?

Ribonanza: deep learning of RNA structure through dual crowdsourcing

Prediction of RNA structure from sequence remains an unsolved problem, and progress has been slowed by a paucity of experimental data. Here, we present Ribonanza, a dataset of chemical mapping measurements on two million diverse RNA sequences collected through Eterna and other crowdsourced initiatives. Ribonanza measurements enabled solicitation, training, and prospective evaluation of diverse deep neural networks through a Kaggle challenge, followed by distillation into a single, self-contained model called RibonanzaNet. When fine tuned on auxiliary datasets, RibonanzaNet achieves state-of-the-art performance in modeling experimental sequence dropout, RNA hydrolytic degradation, and RNA secondary structure, with implications for modeling RNA tertiary structure.

Towards parsimonious generative modeling of RNA families

Generative probabilistic models emerge as a new paradigm in data-driven, evolution-informed design of biomolecular sequences. This paper introduces a novel approach, called Edge Activation Direct Coupling Analysis (eaDCA), tailored to the characteristics of RNA sequences, with a strong emphasis on simplicity, efficiency, and interpretability. eaDCA explicitly constructs sparse coevolutionary models for RNA families, achieving performance levels comparable to more complex methods while utilizing a significantly lower number of parameters. Our approach demonstrates efficiency in generating artificial RNA sequences that closely resemble their natural counterparts in both statistical analyses and SHAPE-MaP experiments, and in predicting the effect of mutations. Notably, eaDCA provides a unique feature: estimating the number of potential functional sequences within a given RNA family. For example, in the case of cyclic di-AMP riboswitches (RF00379), our analysis suggests the existence of approximately 1039 functional nucleotide sequences. While huge compared to the known <4000 natural sequences, this number represents only a tiny fraction of the vast pool of nearly 1082 possible nucleotide sequences of the same length (136 nucleotides). These results underscore the promise of sparse and interpretable generative models, such as eaDCA, in enhancing our understanding of the expansive RNA sequence space.

State-of-the-RNArt: benchmarking current methods for RNA 3D structure prediction

RNAs are essential molecules involved in numerous biological functions. Understanding RNA functions requires the knowledge of their 3D structures. Computational methods have been developed for over two decades to predict the 3D conformations from RNA sequences. These computational methods have been widely used and are usually categorised as either ab initio or template-based. The performances remain to be improved. Recently, the rise of deep learning has changed the sight of novel approaches. Deep learning methods are promising, but their adaptation to RNA 3D structure prediction remains difficult. In this paper, we give a brief review of the ab initio, template-based and novel deep learning approaches. We highlight the different available tools and provide a benchmark on nine methods using the RNA-Puzzles dataset. We provide an online dashboard that shows the predictions made by benchmarked methods, freely available on the EvryRNA platform: https://evryrna.ibisc.univ-evry.fr/evryrna/state_of_the_rnart/.

Structure prediction of protein-ligand complexes from sequence information with Umol

Protein-ligand docking is an established tool in drug discovery and development to narrow down potential therapeutics for experimental testing. However, a high-quality protein structure is required and often the protein is treated as fully or partially rigid. Here we develop an AI system that can predict the fully flexible all-atom structure of protein-ligand complexes directly from sequence information. We find that classical docking methods are still superior, but depend upon having crystal structures of the target protein. In addition to predicting flexible all-atom structures, predicted confidence metrics (plDDT) can be used to select accurate predictions as well as to distinguish between strong and weak binders. The advances presented here suggest that the goal of AI-based drug discovery is one step closer, but there is still a way to go to grasp the complexity of protein-ligand interactions fully. Umol is available at: https://github.com/patrickbryant1/Umol .

gRNAde: Geometric Deep Learning for 3D RNA inverse design

Computational RNA design tasks are often posed as inverse problems, where sequences are designed based on adopting a single desired secondary structure without considering 3D geometry and conformational diversity. We introduce gRNAde, a geometric RNA design pipeline operating on 3D RNA backbones to design sequences that explicitly account for structure and dynamics. Under the hood, gRNAde is a multi-state Graph Neural Network that generates candidate RNA sequences conditioned on one or more 3D backbone structures where the identities of the bases are unknown. On a single-state fixed backbone re-design benchmark of 14 RNA structures from the PDB identified by Das et al. [2010], gRNAde obtains higher native sequence recovery rates (56% on average) compared to Rosetta (45% on average), taking under a second to produce designs compared to the reported hours for Rosetta. We further demonstrate the utility of gRNAde on a new benchmark of multi-state design for structurally flexible RNAs, as well as zero-shot ranking of mutational fitness landscapes in a retrospective analysis of a recent RNA polymerase ribozyme structure.

sincFold: end-to-end learning of short- and long-range interactions in RNA secondary structure

MOTIVATION

Coding and noncoding RNA molecules participate in many important biological processes. Noncoding RNAs fold into well-defined secondary structures to exert their functions. However, the computational prediction of the secondary structure from a raw RNA sequence is a long-standing unsolved problem, which after decades of almost unchanged performance has now re-emerged due to deep learning. Traditional RNA secondary structure prediction algorithms have been mostly based on thermodynamic models and dynamic programming for free energy minimization. More recently deep learning methods have shown competitive performance compared with the classical ones, but there is still a wide margin for improvement.

RESULTS

In this work we present sincFold, an end-to-end deep learning approach, that predicts the nucleotides contact matrix using only the RNA sequence as input. The model is based on 1D and 2D residual neural networks that can learn short- and long-range interaction patterns. We show that structures can be accurately predicted with minimal physical assumptions. Extensive experiments were conducted on several benchmark datasets, considering sequence homology and cross-family validation. sincFold was compared with classical methods and recent deep learning models, showing that it can outperform the state-of-the-art methods.

Resolving the intricate binding of neomycin B to multiple binding motifs of a neomycin-sensing riboswitch aptamer by native top-down mass spectrometry and NMR spectroscopy

Understanding small molecule binding to RNA can be complicated by an intricate interplay between binding stoichiometry, multiple binding motifs, different occupancies of different binding motifs, and changes in the structure of the RNA under study. Here, we use native top-down mass spectrometry (MS) and nuclear magnetic resonance (NMR) spectroscopy to experimentally resolve these factors and gain a better understanding of the interactions between neomycin B and the 40 nt aptamer domain of a neomycin-sensing riboswitch engineered in yeast. Data from collisionally activated dissociation of the 1:1, 1:2 and 1:3 RNA-neomycin B complexes identified a third binding motif C of the riboswitch in addition to the two motifs A and B found in our previous study, and provided occupancies of the different binding motifs for each complex stoichiometry. Binding of a fourth neomycin B molecule was unspecific according to both MS and NMR data. Intriguingly, all major changes in the aptamer structure can be induced by the binding of the first neomycin B molecule regardless of whether it binds to motif A or B as evidenced by stoichiometry-resolved MS data together with titration data from 1H NMR spectroscopy in the imino proton region. Specific binding of the second and third neomycin B molecules further stabilizes the riboswitch aptamer, thereby allowing for a gradual response to increasing concentrations of neomycin B, which likely leads to a fine-tuning of the cellular regulatory mechanism.

Discovery and Quantification of Long-Range RNA Base Pairs in Coronavirus Genomes with SEARCH-MaP and SEISMIC-RNA

RNA molecules perform a diversity of essential functions for which their linear sequences must fold into higher-order structures. Techniques including crystallography and cryogenic electron microscopy have revealed 3D structures of ribosomal, transfer, and other well-structured RNAs; while chemical probing with sequencing facilitates secondary structure modeling of any RNAs of interest, even within cells. Ongoing efforts continue increasing the accuracy, resolution, and ability to distinguish coexisting alternative structures. However, no method can discover and quantify alternative structures with base pairs spanning arbitrarily long distances - an obstacle for studying viral, messenger, and long noncoding RNAs, which may form long-range base pairs. Here, we introduce the method of Structure Ensemble Ablation by Reverse Complement Hybridization with Mutational Profiling (SEARCH-MaP) and software for Structure Ensemble Inference by Sequencing, Mutation Identification, and Clustering of RNA (SEISMIC-RNA). We use SEARCH-MaP and SEISMIC-RNA to discover that the frameshift stimulating element of SARS coronavirus 2 base-pairs with another element 1 kilobase downstream in nearly half of RNA molecules, and that this structure competes with a pseudoknot that stimulates ribosomal frameshifting. Moreover, we identify long-range base pairs involving the frameshift stimulating element in other coronaviruses including SARS coronavirus 1 and transmissible gastroenteritis virus, and model the full genomic secondary structure of the latter. These findings suggest that long-range base pairs are common in coronaviruses and may regulate ribosomal frameshifting, which is essential for viral RNA synthesis. We anticipate that SEARCH-MaP will enable solving many RNA structure ensembles that have eluded characterization, thereby enhancing our general understanding of RNA structures and their functions. SEISMIC-RNA, software for analyzing mutational profiling data at any scale, could power future studies on RNA structure and is available on GitHub and the Python Package Index.

RNAhugs web server for customized 3D RNA structure alignment

Alignment of 3D molecular structures involves overlaying their sets of atoms in space in such a way as to minimize the distance between the corresponding atoms. The purpose of this procedure is usually to analyze and assess structural similarity on a global (e.g. evaluating predicted 3D models and clustering structures) or a local level (e.g. searching for common substructures). Although the idea of alignment is simple, combinatorial algorithms that implement it require considerable computational resources, even when processing relatively small structures. In this paper, we introduce RNAhugs, a web server for custom and flexible alignment of 3D RNA structures. Using two efficient heuristics, GEOS and GENS, it finds the longest corresponding fragments within 3D structures that may differ in sizes-given in the PDB or PDBx/mmCIF formats-that manage to align with user-specified accuracy (i.e. with an RMSD not exceeding a cutoff value given as an input parameter). A distinctive advantage of the system lies in its ability to process multi-model files and compare the results of 1-25 alignments in a single task. RNAhugs has an intuitive interface and is publicly available at https://rnahugs.cs.put.poznan.pl/.

RNA language models predict mutations that improve RNA function

Structured RNA lies at the heart of many central biological processes, from gene expression to catalysis. While advances in deep learning enable the prediction of accurate protein structural models, RNA structure prediction is not possible at present due to a lack of abundant high-quality reference data. Furthermore, available sequence data are generally not associated with organismal phenotypes that could inform RNA function. We created GARNET (Gtdb Acquired RNa with Environmental Temperatures), a new database for RNA structural and functional analysis anchored to the Genome Taxonomy Database (GTDB). GARNET links RNA sequences derived from GTDB genomes to experimental and predicted optimal growth temperatures of GTDB reference organisms. This enables construction of deep and diverse RNA sequence alignments to be used for machine learning. Using GARNET, we define the minimal requirements for a sequence- and structure-aware RNA generative model. We also develop a GPT-like language model for RNA in which triplet tokenization provides optimal encoding. Leveraging hyperthermophilic RNAs in GARNET and these RNA generative models, we identified mutations in ribosomal RNA that confer increased thermostability to the Escherichia coli ribosome. The GTDB-derived data and deep learning models presented here provide a foundation for understanding the connections between RNA sequence, structure, and function.

RNA3DB: A structurally-dissimilar dataset split for training and benchmarking deep learning models for RNA structure prediction

With advances in protein structure prediction thanks to deep learning models like AlphaFold, RNA structure prediction has recently received increased attention from deep learning researchers. RNAs introduce substantial challenges due to the sparser availability and lower structural diversity of the experimentally resolved RNA structures in comparison to protein structures. These challenges are often poorly addressed by the existing literature, many of which report inflated performance due to using training and testing sets with significant structural overlap. Further, the most recent Critical Assessment of Structure Prediction (CASP15) has shown that deep learning models for RNA structure are currently outperformed by traditional methods. In this paper we present RNA3DB, a dataset of structured RNAs, derived from the Protein Data Bank (PDB), that is designed for training and benchmarking deep learning models. The RNA3DB method arranges the RNA 3D chains into distinct groups (Components) that are non-redundant both with regard to sequence as well as structure, providing a robust way of dividing training, validation, and testing sets. Any split of these structurally-dissimilar Components are guaranteed to produce test and validations sets that are distinct by sequence and structure from those in the training set. We provide the RNA3DB dataset, a particular train/test split of the RNA3DB Components (in an approximate 70/30 ratio) that will be updated periodically. We also provide the RNA3DB methodology along with the source-code, with the goal of creating a reproducible and customizable tool for producing structurally-dissimilar dataset splits for structural RNAs.

Discovery of a trefoil knot in the RydC RNA: Challenging previous notions of RNA topology

Knots are very common in polymers, including DNA and protein molecules. Yet, no genuine knot has been identified in natural RNA molecules to date. Upon re-examining experimentally determined RNA 3D structures, we discovered a trefoil knot 31, the most basic non-trivial knot, in the RydC RNA. This knotted RNA is a member of a small family of short bacterial RNAs, whose secondary structure is characterized by an H-type pseudoknot. Molecular dynamics simulations suggest a folding pathway of the RydC RNA that starts with a native twisted loop. Based on sequence analyses and computational RNA 3D structure predictions, we postulate that this trefoil knot is a conserved feature of all RydC-related RNAs. The first discovery of a knot in a natural RNA molecule introduces a novel perspective on RNA 3D structure formation and on fundamental research on the relationship between function and spatial structure of biopolymers.

RNA3DB: A structurally-dissimilar dataset split for training and benchmarking deep learning models for RNA structure prediction

With advances in protein structure prediction thanks to deep learning models like AlphaFold, RNA structure prediction has recently received increased attention from deep learning researchers. RNAs introduce substantial challenges due to the sparser availability and lower structural diversity of the experimentally resolved RNA structures in comparison to protein structures. These challenges are often poorly addressed by the existing literature, many of which report inflated performance due to using training and testing sets with significant structural overlap. Further, the most recent Critical Assessment of Structure Prediction (CASP15) has shown that deep learning models for RNA structure are currently outperformed by traditional methods. In this paper we present RNA3DB, a dataset of structured RNAs, derived from the Protein Data Bank (PDB), that is designed for training and benchmarking deep learning models. The RNA3DB method arranges the RNA 3D chains into distinct groups (Components) that are non-redundant both with regard to sequence as well as structure, providing a robust way of dividing training, validation, and testing sets. Any split of these structurally-dissimilar Components are guaranteed to produce test and validations sets that are distinct by sequence and structure from those in the training set. We provide the RNA3DB dataset, a particular train/test split of the RNA3DB Components (in an approximate 70/30 ratio) that will be updated periodically. We also provide the RNA3DB methodology along with the source-code, with the goal of creating a reproducible and customizable tool for producing structurally-dissimilar dataset splits for structural RNAs.

De novo prediction of RNA 3D structures with deep generative models

We present a Deep Learning approach to predict 3D folding structures of RNAs from their nucleic acid sequence. Our approach combines an autoregressive Deep Generative Model, Monte Carlo Tree Search, and a score model to find and rank the most likely folding structures for a given RNA sequence. We show that RNA de novo structure prediction by deep learning is possible at atom resolution, despite the low number of experimentally measured structures that can be used for training. We confirm the predictive power of our approach by achieving competitive results in a retrospective evaluation of the RNA-Puzzles prediction challenges, without using structural contact information from multiple sequence alignments or additional data from chemical probing experiments. Blind predictions for recent RNA-Puzzle challenges under the name "Dfold" further support the competitive performance of our approach.

Machine learning in RNA structure prediction: Advances and challenges

RNA molecules play a crucial role in various biological processes, with their functionality closely tied to their structures. The remarkable advancements in machine learning techniques for protein structure prediction have shown promise in the field of RNA structure prediction. In this perspective, we discuss the advances and challenges encountered in constructing machine learning-based models for RNA structure prediction. We explore topics including model building strategies, specific challenges involved in predicting RNA secondary (2D) and tertiary (3D) structures, and approaches to these challenges. In addition, we highlight the advantages and challenges of constructing RNA language models. Given the rapid advances of machine learning techniques, we anticipate that machine learning-based models will serve as important tools for predicting RNA structures, thereby enriching our understanding of RNA structures and their corresponding functions.

Regulation of bacterial gene expression by non-coding RNA: It is all about time!

Commensal and pathogenic bacteria continuously evolve to survive in diverse ecological niches by efficiently coordinating gene expression levels in their ever-changing environments. Regulation through the RNA transcript itself offers a faster and more cost-effective way to adapt than protein-based mechanisms and can be leveraged for diagnostic or antimicrobial purposes. However, RNA can fold into numerous intricate, not always functional structures that both expand and obscure the plethora of roles that regulatory RNAs serve within the cell. Here, we review the current knowledge of bacterial non-coding RNAs in relation to their folding pathways and interactions. We posit that co-transcriptional folding of these transcripts ultimately dictates their downstream functions. Elucidating the spatiotemporal folding of non-coding RNAs during transcription therefore provides invaluable insights into bacterial pathogeneses and predictive disease diagnostics. Finally, we discuss the implications of co-transcriptional folding andapplications of RNAs for therapeutics and drug targets.

Structural Insights into Protein-Aptamer Recognitions Emerged from Experimental and Computational Studies

Aptamers are synthetic nucleic acids that are developed to target with high affinity and specificity chemical entities ranging from single ions to macromolecules and present a wide range of chemical and physical properties. Their ability to selectively bind proteins has made these compounds very attractive and versatile tools, in both basic and applied sciences, to such an extent that they are considered an appealing alternative to antibodies. Here, by exhaustively surveying the content of the Protein Data Bank (PDB), we review the structural aspects of the protein-aptamer recognition process. As a result of three decades of structural studies, we identified 144 PDB entries containing atomic-level information on protein-aptamer complexes. Interestingly, we found a remarkable increase in the number of determined structures in the last two years as a consequence of the effective application of the cryo-electron microscopy technique to these systems. In the present paper, particular attention is devoted to the articulated architectures that protein-aptamer complexes may exhibit. Moreover, the molecular mechanism of the binding process was analyzed by collecting all available information on the structural transitions that aptamers undergo, from their protein-unbound to the protein-bound state. The contribution of computational approaches in this area is also highlighted.