RNA3DCNN: Local and global quality assessments of RNA 3D structures using 3D deep convolutional neural networks

Artificial intelligence for RNA-ligand interaction prediction: advances and prospects

Accurate prediction of RNA-ligand interactions is vital for understanding biological processes and advancing RNA-targeted drug discovery. Given their complexity, artificial intelligence (AI) is revolutionizing the study of RNA-ligand interactions, offering insights into the complex dynamics and therapeutic potential of RNA. In this review, we highlight advances in AI-driven RNA-ligand binding site identification, structure modeling, binding mode and binding affinity prediction, and virtual screening (VS). We also discuss key challenges, such as data set scarcity and modeling RNA flexibility. Future directions emphasize integrating cutting-edge AI techniques with physics-based models and expanding experimental data sets to enhance RNA-ligand interaction predictions.

mRNA vaccine sequence and structure design and optimization: Advances and challenges

Messenger RNA (mRNA) vaccines have emerged as a powerful tool against communicable diseases and cancers, as demonstrated by their huge success during the coronavirus disease 2019 (COVID-19) pandemic. Despite the outstanding achievements, mRNA vaccines still face challenges such as stringent storage requirements, insufficient antigen expression, and unexpected immune responses. Since the intrinsic properties of mRNA molecules significantly impact vaccine performance, optimizing mRNA design is crucial in preclinical development. In this review, we outline four key principles for optimal mRNA sequence design: enhancing ribosome loading and translation efficiency through untranslated region (UTR) optimization, improving translation efficiency via codon optimization, increasing structural stability by refining global RNA sequence and extending in-cell lifetime and expression fidelity by adjusting local RNA structures. We also explore recent advancements in computational models for designing and optimizing mRNA vaccine sequences following these principles. By integrating current mRNA knowledge, addressing challenges, and examining advanced computational methods, this review aims to promote the application of computational approaches in mRNA vaccine development and inspire novel solutions to existing obstacles.

RNA Structure: Past, Future, and Gene Therapy Applications

First believed to be a simple intermediary between the information encoded in deoxyribonucleic acid and that functionally displayed in proteins, ribonucleic acid (RNA) is now known to have many functions through its abundance and intricate, ubiquitous, diverse, and dynamic structure. About 70-90% of the human genome is transcribed into protein-coding and noncoding RNAs as main determinants along with regulatory sequences of cellular to populational biological diversity. From the nucleotide sequence or primary structure, through Watson-Crick pairing self-folding or secondary structure, to compaction via longer distance Watson-Crick and non-Watson-Crick interactions or tertiary structure, and interactions with RNA or other biopolymers or quaternary structure, or with metabolites and biomolecules or quinary structure, RNA structure plays a critical role in RNA's lifecycle from transcription to decay and many cellular processes. In contrast to the success of 3-dimensional protein structure prediction using AlphaFold, RNA tertiary and beyond structures prediction remains challenging. However, approaches involving machine learning and artificial intelligence, sequencing of RNA and its modifications, and structural analyses at the single-cell and intact tissue levels, among others, provide an optimistic outlook for the continued development and refinement of RNA-based applications. Here, we highlight those in gene therapy.

lociPARSE: A Locality-aware Invariant Point Attention Model for Scoring RNA 3D Structures

A scoring function that can reliably assess the accuracy of a 3D RNA structural model in the absence of experimental structure is not only important for model evaluation and selection but also useful for scoring-guided conformational sampling. However, high-fidelity RNA scoring has proven to be difficult using conventional knowledge-based statistical potentials and currently available machine learning-based approaches. Here, we present lociPARSE, a locality-aware invariant point attention architecture for scoring RNA 3D structures. Unlike existing machine learning methods that estimate superposition-based root-mean-square deviation (RMSD), lociPARSE estimates Local Distance Difference Test (lDDT) scores capturing the accuracy of each nucleotide and its surrounding local atomic environment in a superposition-free manner, before aggregating information to predict global structural accuracy. Tested on multiple datasets including CASP15, lociPARSE significantly outperforms existing statistical potentials (rsRNASP, cgRNASP, DFIRE-RNA, and RASP) and machine learning methods (ARES and RNA3DCNN) across complementary assessment metrics. lociPARSE is freely available at https://github.com/Bhattacharya-Lab/lociPARSE.

Structure Prediction of Large RNAs with AlphaFold3 Highlights its Capabilities and Limitations

DeepMind's AlphaFold3 webserver offers exciting new opportunities to make structural predictions of heterogeneous macromolecular systems. Here we attempt to apply AlphaFold3 to large RNA molecules whose 3D atomic structures are unknown but whose physical dimensions have been studied experimentally. One difficulty that we encounter is that models returned by AlphaFold3 often contain severe steric clashes and, less frequently, clear breaks in the phosphodiester backbone, with the probability of both events increasing with the length of the RNA. Restricting attention to those RNAs for which non-clashing models can be obtained, we find that hydrodynamic radii computed from the AlphaFold3 models are much larger than those reported experimentally under low salt conditions but are in better agreement with those reported in the presence of polyvalent cations. For two RNAs whose shapes have been imaged experimentally, the computed anisotropies of the AlphaFold3-predicted structures are too low, indicating that they are excessively spherical; extending this analysis to larger RNAs shows that they become progressively more spherical with increasing length. Overall, the results suggest that AlphaFold3 is capable of producing plausible models for RNAs up to ∼2000 nucleotides in length, but that thousands of predictions may be required to obtain models free of geometric problems.

Advances in the field of RNA 3D structure prediction and modeling, with purely theoretical approaches, and with the use of experimental data

Recent advancements in RNA three-dimensional (3D) structure prediction have provided significant insights into RNA biology, highlighting the essential role of RNA in cellular functions and its therapeutic potential. This review summarizes the latest developments in computational methods, particularly the incorporation of artificial intelligence and machine learning, which have improved the efficiency and accuracy of RNA structure predictions. We also discuss the integration of new experimental data types, including cryoelectron microscopy (cryo-EM) techniques and high-throughput sequencing, which have transformed RNA structure modeling. The combination of experimental advances with computational methods represents a significant leap in RNA structure determination. We review the outcomes of RNA-Puzzles and critical assessment of structure prediction (CASP) challenges, which assess the state of the field and limitations of existing methods. Future perspectives are discussed, focusing on the impact of RNA 3D structure prediction on understanding RNA mechanisms and its implications for drug discovery and RNA-targeted therapies, opening new avenues in molecular biology.

Targeting RNA with small molecules, from RNA structures to precision medicines: IUPHAR review: 40

RNA plays important roles in regulating both health and disease biology in all kingdoms of life. Notably, RNA can form intricate three-dimensional structures, and their biological functions are dependent on these structures. Targeting the structured regions of RNA with small molecules has gained increasing attention over the past decade, because it provides both chemical probes to study fundamental biology processes and lead medicines for diseases with unmet medical needs. Recent advances in RNA structure prediction and determination and RNA biology have accelerated the rational design and development of RNA-targeted small molecules to modulate disease pathology. However, challenges remain in advancing RNA-targeted small molecules towards clinical applications. This review summarizes strategies to study RNA structures, to identify small molecules recognizing these structures, and to augment the functionality of RNA-binding small molecules. We focus on recent advances in developing RNA-targeted small molecules as potential therapeutics in a variety of diseases, encompassing different modes of actions and targeting strategies. Furthermore, we present the current gaps between early-stage discovery of RNA-binding small molecules and their clinical applications, as well as a roadmap to overcome these challenges in the near future.

smFRET-assisted RNA structure prediction

Single-molecule Förster Resonance Energy Transfer (smFRET) is a powerful biophysical technique that utilizes the distance-dependent energy transfer between donor and acceptor dyes linked to individual molecules, providing insights into molecular conformational changes and interactions at the single-molecule level. Prior investigations leveraged smFRET to study the conformational dynamics of single truncated Ubc4 pre-mRNA molecules during splicing, yet these efforts did not prioritize structural modeling. In this study, we develop an smFRET-assisted RNA prediction method to predict the 2D and 3D structures of this pre-mRNA. To achieve this, we initiate the process by generating RNA structural ensembles through coarse-grained molecular dynamics (MD) simulations. Subsequently, inter-dye distances are calculated for these RNA structural ensembles by performing all-atom MD simulations of the dye groups. The ultimate determination of the 2D and 3D structures for the pre-mRNA is achieved by comparing the calculated inter-dye distances with experimental counterparts. Notably, our computational results demonstrate a significant alignment with experimental findings, which involve a conformational change at the 2D level.

Advances and Challenges in Scoring Functions for RNA-Protein Complex Structure Prediction

RNA-protein complexes play a crucial role in cellular functions, providing insights into cellular mechanisms and potential therapeutic targets. However, experimental determination of these complex structures is often time-consuming and resource-intensive, and it rarely yields high-resolution data. Many computational approaches have been developed to predict RNA-protein complex structures in recent years. Despite these advances, achieving accurate and high-resolution predictions remains a formidable challenge, primarily due to the limitations inherent in current RNA-protein scoring functions. These scoring functions are critical tools for evaluating and interpreting RNA-protein interactions. This review comprehensively explores the latest advancements in scoring functions for RNA-protein docking, delving into the fundamental principles underlying various approaches, including coarse-grained knowledge-based, all-atom knowledge-based, and machine-learning-based methods. We critically evaluate the strengths and limitations of existing scoring functions, providing a detailed performance assessment. Considering the significant progress demonstrated by machine learning techniques, we discuss emerging trends and propose future research directions to enhance the accuracy and efficiency of scoring functions in RNA-protein complex prediction. We aim to inspire the development of more sophisticated and reliable computational tools in this rapidly evolving field.

3dDNAscoreA: A scoring function for evaluation of DNA 3D structures

DNA molecules are vital macromolecules that play a fundamental role in many cellular processes and have broad applications in medicine. For example, DNA aptamers have been rapidly developed for diagnosis, biosensors, and clinical therapy. Recently, we proposed a computational method of predicting DNA 3D structures, called 3dDNA. However, it lacks a scoring function to evaluate the predicted DNA 3D structures, and so they are not ranked for users. Here, we report a scoring function, 3dDNAscoreA, for evaluation of DNA 3D structures based on a deep learning model ARES for RNA 3D structure evaluation but using a new strategy for training. 3dDNAscoreA is benchmarked on two test sets to show its ability to rank DNA 3D structures and select the native and near-native structures.

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.

3dRNA/DNA: 3D Structure Prediction from RNA to DNA

There is an increasing need for determining 3D structures of DNAs, e.g., for increasing the efficiency of DNA aptamer selection. Recently, we have proposed a computational method of 3D structure prediction of DNAs, called 3dDNA, which has been integrated into our original web server 3dRNA, now renamed 3dRNA/DNA (http://biophy.hust.edu.cn/new/3dRNA). Currently, 3dDNA can only output the predicted DNA 3D structures for users but cannot rank them as an energy function for assessing DNA 3D structures is still lacking. Here, we first provide a brief introduction to 3dDNA and then introduce a new energy function, 3dDNAscore, for the assessment of DNA 3D structures. 3dDNAscore is an all-atom knowledge-based potential by integrating 86 atomic types from nucleic acids. Benchmarks demonstrate that 3dDNAscore can effectively identify near-native structures from the decoys generated by 3dDNA, thus enhancing the completeness of 3dDNA.

Embracing exascale computing in nucleic acid simulations

This mini-review reports the recent advances in biomolecular simulations, particularly for nucleic acids, and provides the potential effects of the emerging exascale computing on nucleic acid simulations, emphasizing the need for advanced computational strategies to fully exploit this technological frontier. Specifically, we introduce recent breakthroughs in computer architectures for large-scale biomolecular simulations and review the simulation protocols for nucleic acids regarding force fields, enhanced sampling methods, coarse-grained models, and interactions with ligands. We also explore the integration of machine learning methods into simulations, which promises to significantly enhance the predictive modeling of biomolecules and the analysis of complex data generated by the exascale simulations. Finally, we discuss the challenges and perspectives for biomolecular simulations as we enter the dawning exascale computing era.

lociPARSE: a locality-aware invariant point attention model for scoring RNA 3D structures

A scoring function that can reliably assess the accuracy of a 3D RNA structural model in the absence of experimental structure is not only important for model evaluation and selection but also useful for scoring-guided conformational sampling. However, high-fidelity RNA scoring has proven to be difficult using conventional knowledge-based statistical potentials and currently-available machine learning-based approaches. Here we present lociPARSE, a locality-aware invariant point attention architecture for scoring RNA 3D structures. Unlike existing machine learning methods that estimate superposition-based root mean square deviation (RMSD), lociPARSE estimates Local Distance Difference Test (lDDT) scores capturing the accuracy of each nucleotide and its surrounding local atomic environment in a superposition-free manner, before aggregating information to predict global structural accuracy. Tested on multiple datasets including CASP15, lociPARSE significantly outperforms existing statistical potentials (rsRNASP, cgRNASP, DFIRE-RNA, and RASP) and machine learning methods (ARES and RNA3DCNN) across complementary assessment metrics. lociPARSE is freely available at https://github.com/Bhattacharya-Lab/lociPARSE.

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/.

Recent applications of artificial intelligence in RNA-targeted small molecule drug discovery

INTRODUCTION

Targeting RNAs with small molecules offers an alternative to the conventional protein-targeted drug discovery and can potentially address unmet and emerging medical needs. The recent rise of interest in the strategy has already resulted in large amounts of data on disease associated RNAs, as well as on small molecules that bind to such RNAs. Artificial intelligence (AI) approaches, including machine learning and deep learning, present an opportunity to speed up the discovery of RNA-targeted small molecules by improving decision-making efficiency and quality.

AREAS COVERED

The topics described in this review include the recent applications of AI in the identification of RNA targets, RNA structure determination, screening of chemical compound libraries, and hit-to-lead optimization. The impact and limitations of the recent AI applications are discussed, along with an outlook on the possible applications of next-generation AI tools for the discovery of novel RNA-targeted small molecule drugs.

EXPERT OPINION

Key areas for improvement include developing AI tools for understanding RNA dynamics and RNA - small molecule interactions. High-quality and comprehensive data still need to be generated especially on the biological activity of small molecules that target RNAs.

ABC2A: A Straightforward and Fast Method for the Accurate Backmapping of RNA Coarse-Grained Models to All-Atom Structures

RNAs play crucial roles in various essential biological functions, including catalysis and gene regulation. Despite the widespread use of coarse-grained (CG) models/simulations to study RNA 3D structures and dynamics, their direct application is challenging due to the lack of atomic detail. Therefore, the reconstruction of full atomic structures is desirable. In this study, we introduced a straightforward method called ABC2A for reconstructing all-atom structures from RNA CG models. ABC2A utilizes diverse nucleotide fragments from known structures to assemble full atomic structures based on the CG atoms. The diversification of assembly fragments beyond standard A-form ones, commonly used in other programs, combined with a highly simplified structure refinement process, ensures that ABC2A achieves both high accuracy and rapid speed. Tests on a recent large dataset of 361 RNA experimental structures (30-692 nt) indicate that ABC2A can reconstruct full atomic structures from three-bead CG models with a mean RMSD of ~0.34 Å from experimental structures and an average runtime of ~0.5 s (maximum runtime < 2.5 s). Compared to the state-of-the-art Arena, ABC2A achieves a ~25% improvement in accuracy and is five times faster in speed.

Frontiers and Challenges of Computing ncRNAs Biogenesis, Function and Modulation

Non-coding RNAs (ncRNAs), generated from nonprotein coding DNA sequences, constitute 98-99% of the human genome. Non-coding RNAs encompass diverse functional classes, including microRNAs, small interfering RNAs, PIWI-interacting RNAs, small nuclear RNAs, small nucleolar RNAs, and long non-coding RNAs. With critical involvement in gene expression and regulation across various biological and physiopathological contexts, such as neuronal disorders, immune responses, cardiovascular diseases, and cancer, non-coding RNAs are emerging as disease biomarkers and therapeutic targets. In this review, after providing an overview of non-coding RNAs' role in cell homeostasis, we illustrate the potential and the challenges of state-of-the-art computational methods exploited to study non-coding RNAs biogenesis, function, and modulation. This can be done by directly targeting them with small molecules or by altering their expression by targeting the cellular engines underlying their biosynthesis. Drawing from applications, also taken from our work, we showcase the significance and role of computer simulations in uncovering fundamental facets of ncRNA mechanisms and modulation. This information may set the basis to advance gene modulation tools and therapeutic strategies to address unmet medical needs.

RNAdvisor: a comprehensive benchmarking tool for the measure and prediction of RNA structural model quality

RNA is a complex macromolecule that plays central roles in the cell. While it is well known that its structure is directly related to its functions, understanding and predicting RNA structures is challenging. Assessing the real or predictive quality of a structure is also at stake with the complex 3D possible conformations of RNAs. Metrics have been developed to measure model quality while scoring functions aim at assigning quality to guide the discrimination of structures without a known and solved reference. Throughout the years, many metrics and scoring functions have been developed, and no unique assessment is used nowadays. Each developed assessment method has its specificity and might be complementary to understanding structure quality. Therefore, to evaluate RNA 3D structure predictions, it would be important to calculate different metrics and/or scoring functions. For this purpose, we developed RNAdvisor, a comprehensive automated software that integrates and enhances the accessibility of existing metrics and scoring functions. In this paper, we present our RNAdvisor tool, as well as state-of-the-art existing metrics, scoring functions and a set of benchmarks we conducted for evaluating them. Source code is freely available on the EvryRNA platform: https://evryrna.ibisc.univ-evry.fr.

Evaluation of DNA-protein complex structures using the deep learning method

Biological processes such as transcription, repair, and regulation require interactions between DNA and proteins. To unravel their functions, it is imperative to determine the high-resolution structures of DNA-protein complexes. However, experimental methods for this purpose are costly and technically demanding. Consequently, there is an urgent need for computational techniques to identify the structures of DNA-protein complexes. Despite technological advancements, accurately identifying DNA-protein complexes through computational methods still poses a challenge. Our team has developed a cutting-edge deep-learning approach called DDPScore that assesses DNA-protein complex structures. DDPScore utilizes a 4D convolutional neural network to overcome limited training data. This approach effectively captures local and global features while comprehensively considering the conformational changes arising from the flexibility during the DNA-protein docking process. DDPScore consistently outperformed the available methods in comprehensive DNA-protein complex docking evaluations, even for the flexible docking challenges. DDPScore has a wide range of applications in predicting and designing structures of DNA-protein complexes.

Predicting RNA structures and functions by artificial intelligence

RNA functions by interacting with its intended targets structurally. However, due to the dynamic nature of RNA molecules, RNA structures are difficult to determine experimentally or predict computationally. Artificial intelligence (AI) has revolutionized many biomedical fields and has been progressively utilized to deduce RNA structures, target binding, and associated functionality. Integrating structural and target binding information could also help improve the robustness of AI-based RNA function prediction and RNA design. Given the rapid development of deep learning (DL) algorithms, AI will provide an unprecedented opportunity to elucidate the sequence-structure-function relation of RNAs.

RNA 3D Structure Prediction: Progress and Perspective

Ribonucleic acid (RNA) molecules play vital roles in numerous important biological functions such as catalysis and gene regulation. The functions of RNAs are strongly coupled to their structures or proper structure changes, and RNA structure prediction has been paid much attention in the last two decades. Some computational models have been developed to predict RNA three-dimensional (3D) structures in silico, and these models are generally composed of predicting RNA 3D structure ensemble, evaluating near-native RNAs from the structure ensemble, and refining the identified RNAs. In this review, we will make a comprehensive overview of the recent advances in RNA 3D structure modeling, including structure ensemble prediction, evaluation, and refinement. Finally, we will emphasize some insights and perspectives in modeling RNA 3D structures.

Machine learning modeling of RNA structures: methods, challenges and future perspectives

The three-dimensional structure of RNA molecules plays a critical role in a wide range of cellular processes encompassing functions from riboswitches to epigenetic regulation. These RNA structures are incredibly dynamic and can indeed be described aptly as an ensemble of structures that shifts in distribution depending on different cellular conditions. Thus, the computational prediction of RNA structure poses a unique challenge, even as computational protein folding has seen great advances. In this review, we focus on a variety of machine learning-based methods that have been developed to predict RNA molecules' secondary structure, as well as more complex tertiary structures. We survey commonly used modeling strategies, and how many are inspired by or incorporate thermodynamic principles. We discuss the shortcomings that various design decisions entail and propose future directions that could build off these methods to yield more robust, accurate RNA structure predictions.

Computational Modeling of DNA 3D Structures: From Dynamics and Mechanics to Folding

DNA carries the genetic information required for the synthesis of RNA and proteins and plays an important role in many processes of biological development. Understanding the three-dimensional (3D) structures and dynamics of DNA is crucial for understanding their biological functions and guiding the development of novel materials. In this review, we discuss the recent advancements in computer methods for studying DNA 3D structures. This includes molecular dynamics simulations to analyze DNA dynamics, flexibility, and ion binding. We also explore various coarse-grained models used for DNA structure prediction or folding, along with fragment assembly methods for constructing DNA 3D structures. Furthermore, we also discuss the advantages and disadvantages of these methods and highlight their differences.

RNAJP: enhanced RNA 3D structure predictions with non-canonical interactions and global topology sampling

RNA 3D structures are critical for understanding their functions. However, only a limited number of RNA structures have been experimentally solved, so computational prediction methods are highly desirable. Nevertheless, accurate prediction of RNA 3D structures, especially those containing multiway junctions, remains a significant challenge, mainly due to the complicated non-canonical base pairing and stacking interactions in the junction loops and the possible long-range interactions between loop structures. Here we present RNAJP ('RNA Junction Prediction'), a nucleotide- and helix-level coarse-grained model for the prediction of RNA 3D structures, particularly junction structures, from a given 2D structure. Through global sampling of the 3D arrangements of the helices in junctions using molecular dynamics simulations and in explicit consideration of non-canonical base pairing and base stacking interactions as well as long-range loop-loop interactions, the model can provide significantly improved predictions for multibranched junction structures than existing methods. Moreover, integrated with additional restraints from experiments, such as junction topology and long-range interactions, the model may serve as a useful structure generator for various applications.

Predicting 3D structures and stabilities for complex RNA pseudoknots in ion solutions

RNA pseudoknots are a kind of important tertiary motif, and the structures and stabilities of pseudoknots are generally critical to the biological functions of RNAs with the motifs. In this work, we have carefully refined our previously developed coarse-grained model with salt effect through involving a new coarse-grained force field and a replica-exchange Monte Carlo algorithm, and employed the model to predict structures and stabilities of complex RNA pseudoknots in ion solutions beyond minimal H-type pseudoknots. Compared with available experimental data, the newly refined model can successfully predict 3D structures from sequences for the complex RNA pseudoknots including SARS-CoV-2 programming-1 ribosomal frameshifting element and Zika virus xrRNA, and can reliably predict the thermal stabilities of RNA pseudoknots with various sequences and lengths over broad ranges of monovalent/divalent salts. In addition, for complex pseudoknots including SARS-CoV-2 frameshifting element, our analyses show that their thermally unfolding pathways are mainly dependent on the relative stabilities of unfolded intermediate states, in analogy to those of minimal H-type pseudoknots.

Identification of metal ion-binding sites in RNA structures using deep learning method

Metal ion is an indispensable factor for the proper folding, structural stability and functioning of RNA molecules. However, it is very difficult for experimental methods to detect them in RNAs. With the increase of experimentally resolved RNA structures, it becomes possible to identify the metal ion-binding sites in RNA structures through in-silico methods. Here, we propose an approach called Metal3DRNA to identify the binding sites of the most common metal ions (Mg2+, Na+ and K+) in RNA structures by using a three-dimensional convolutional neural network model. The negative samples, screened out based on the analysis for binding surroundings of metal ions, are more like positive ones than the randomly selected ones, which are beneficial to a powerful predictor construction. The microenvironments of the spatial distributions of C, O, N and P atoms around a sample are extracted as features. Metal3DRNA shows a promising prediction power, generally surpassing the state-of-the-art methods FEATURE and MetalionRNA. Finally, utilizing the visualization method, we inspect the contributions of nucleotide atoms to the classification in several cases, which provides a visualization that helps to comprehend the model. The method will be helpful for RNA structure prediction and dynamics simulation study. Availability and implementation: The source code is available at https://github.com/ChunhuaLiLab/Metal3DRNA.

cgRNASP: coarse-grained statistical potentials with residue separation for RNA structure evaluation

Knowledge-based statistical potentials are very important for RNA 3-dimensional (3D) structure prediction and evaluation. In recent years, various coarse-grained (CG) and all-atom models have been developed for predicting RNA 3D structures, while there is still lack of reliable CG statistical potentials not only for CG structure evaluation but also for all-atom structure evaluation at high efficiency. In this work, we have developed a series of residue-separation-based CG statistical potentials at different CG levels for RNA 3D structure evaluation, namely cgRNASP, which is composed of long-ranged and short-ranged interactions by residue separation. Compared with the newly developed all-atom rsRNASP, the short-ranged interaction in cgRNASP was involved more subtly and completely. Our examinations show that, the performance of cgRNASP varies with CG levels and compared with rsRNASP, cgRNASP has similarly good performance for extensive types of test datasets and can have slightly better performance for the realistic dataset-RNA-Puzzles dataset. Furthermore, cgRNASP is strikingly more efficient than all-atom statistical potentials/scoring functions, and can be apparently superior to other all-atom statistical potentials and scoring functions trained from neural networks for the RNA-Puzzles dataset. cgRNASP is available at https://github.com/Tan-group/cgRNASP.

Methods and Applications in Proteins and RNAs

Proteins and RNAs are primary biomolecules that are involved in most biological processes [...]

Evaluating native-like structures of RNA-protein complexes through the deep learning method

RNA-protein complexes underlie numerous cellular processes, including basic translation and gene regulation. The high-resolution structure determination of the RNA-protein complexes is essential for elucidating their functions. Therefore, computational methods capable of identifying the native-like RNA-protein structures are needed. To address this challenge, we thus develop DRPScore, a deep-learning-based approach for identifying native-like RNA-protein structures. DRPScore is tested on representative sets of RNA-protein complexes with various degrees of binding-induced conformation change ranging from fully rigid docking (bound-bound) to fully flexible docking (unbound-unbound). Out of the top 20 predictions, DRPScore selects native-like structures with a success rate of 91.67% on the testing set of bound RNA-protein complexes and 56.14% on the unbound complexes. DRPScore consistently outperforms existing methods with a roughly 10.53-15.79% improvement, even for the most difficult unbound cases. Furthermore, DRPScore significantly improves the accuracy of the native interface interaction predictions. DRPScore should be broadly useful for modeling and designing RNA-protein complexes.

RNA-targeted small-molecule drug discoveries: a machine-learning perspective

In the past two decades, machine learning (ML) has been extensively adopted in protein-targeted small molecule (SM) discovery. Once trained, ML models could exert their predicting abilities on large volumes of molecules within a short time. However, applying ML approaches to discover RNA-targeted SMs is still in its early stages. This is primarily because of the intrinsic structural instability of RNA molecules that impede the structure-based screening or designing of RNA-targeted SMs. Recently, with more studies revealing RNA structures and a growing number of RNA-targeted ligands being identified, it resulted in an increased interest in the field of drugging RNA. Undeniably, intracellular RNA is much more abundant than protein and, if successfully targeted, will be a major alternative target for therapeutics. Therefore, in this context, as well as under the premise of having RNA-related research data, ML-based methods can get involved in improving the speed of traditional experimental processes. [Figure: see text].

Advances in RNA 3D Structure Prediction

RNA molecules carry out various cellular functions, and understanding the mechanisms behind their functions requires the knowledge of their 3D structures. Different types of computational methods have been developed to model RNA 3D structures over the past decade. These methods were widely used by researchers although their performance needs to be further improved. Recently, along with these traditional methods, machine-learning techniques have been increasingly applied to RNA 3D structure prediction and show significant improvement in performance. Here we shall give a brief review of the traditional methods and recent related advances in machine-learning approaches for RNA 3D structure prediction.

Ab initio predictions for 3D structure and stability of single- and double-stranded DNAs in ion solutions

The three-dimensional (3D) structure and stability of DNA are essential to understand/control their biological functions and aid the development of novel materials. In this work, we present a coarse-grained (CG) model for DNA based on the RNA CG model proposed by us, to predict 3D structures and stability for both dsDNA and ssDNA from the sequence. Combined with a Monte Carlo simulated annealing algorithm and CG force fields involving the sequence-dependent base-pairing/stacking interactions and an implicit electrostatic potential, the present model successfully folds 20 dsDNAs (≤52nt) and 20 ssDNAs (≤74nt) into the corresponding native-like structures just from their sequences, with an overall mean RMSD of 3.4Å from the experimental structures. For DNAs with various lengths and sequences, the present model can make reliable predictions on stability, e.g., for 27 dsDNAs with/without bulge/internal loops and 24 ssDNAs including pseudoknot, the mean deviation of predicted melting temperatures from the corresponding experimental data is only ~2.0°C. Furthermore, the model also quantificationally predicts the effects of monovalent or divalent ions on the structure stability of ssDNAs/dsDNAs.

To determine 3D structures and quantify stability of single- (ss) and double-stranded (ds) DNAs is essential to unveil the mechanisms of their functions and to further guide the production and development of novel materials. Although many DNA models have been proposed to reproduce the basic structural, mechanical, or thermodynamic properties of dsDNAs based on the secondary structure information or preset constraints, there are very few models can be used to investigate the ssDNA folding or dsDNA assembly from the sequence. Furthermore, due to the polyanionic nature of DNAs, metal ions (e.g., Na⁺ and Mg²⁺) in solutions can play an essential role in DNA folding and dynamics. Nevertheless, ab initio predictions for DNA folding in ion solutions are still an unresolved problem. In this work, we developed a novel coarse-grained model to predict 3D structures and thermodynamic stabilities for both ssDNAs and dsDNAs in monovalent/divalent ion solutions from their sequences. As compared with the extensive experimental data and available existing models, we showed that the present model can successfully fold simple DNAs into their native-like structures, and can also accurately reproduce the effects of sequence and monovalent/divalent ions on structure stability for ssDNAs including pseudoknot and dsDNAs with/without bulge/internal loops.

FebRNA: An automated fragment-ensemble-based model for building RNA 3D structures

Knowledge of RNA three-dimensional (3D) structures is critical to understanding the important biological functions of RNAs. Although various structure prediction models have been developed, the high-accuracy predictions of RNA 3D structures are still limited to the RNAs with short lengths or with simple topology. In this work, we proposed a new model, namely FebRNA, for building RNA 3D structures through fragment assembly based on coarse-grained (CG) fragment ensembles. Specifically, FebRNA is composed of four processes: establishing the library of different types of non-redundant CG fragment ensembles regardless of the sequences, building CG 3D structure ensemble through fragment assembly, identifying top-scored CG structures through a specific CG scoring function, and rebuilding the all-atom structures from the top-scored CG ones. Extensive examination against different types of RNA structures indicates that FebRNA consistently gives the reliable predictions on RNA 3D structures, including pseudoknots, three-way junctions, four-way and five-way junctions, and RNAs in the RNA-Puzzles. FebRNA is available on the Web site: https://github.com/Tan-group/FebRNA.

RNAStat: An Integrated Tool for Statistical Analysis of RNA 3D Structures

The 3D architectures of RNAs are essential for understanding their cellular functions. While an accurate scoring function based on the statistics of known RNA structures is a key component for successful RNA structure prediction or evaluation, there are few tools or web servers that can be directly used to make comprehensive statistical analysis for RNA 3D structures. In this work, we developed RNAStat, an integrated tool for making statistics on RNA 3D structures. For given RNA structures, RNAStat automatically calculates RNA structural properties such as size and shape, and shows their distributions. Based on the RNA structure annotation from DSSR, RNAStat provides statistical information of RNA secondary structure motifs including canonical/non-canonical base pairs, stems, and various loops. In particular, the geometry of base-pairing/stacking can be calculated in RNAStat by constructing a local coordinate system for each base. In addition, RNAStat also supplies the distribution of distance between any atoms to the users to help build distance-based RNA statistical potentials. To test the usability of the tool, we established a non-redundant RNA 3D structure dataset, and based on the dataset, we made a comprehensive statistical analysis on RNA structures, which could have the guiding significance for RNA structure modeling. The python code of RNAStat, the dataset used in this work, and corresponding statistical data files are freely available at GitHub (https://github.com/RNA-folding-lab/RNAStat).

A novel algorithm for ranking RNA structure candidates

RNA research is advancing at an ever increasing pace. The newest and most state-of-the-art instruments and techniques have made possible the discoveries of new RNAs, and they have carried the field to new frontiers of disease research, vaccine development, therapeutics, and architectonics. Like proteins, RNAs show a marked relationship between structure and function. A deeper grasp of RNAs requires a finer understanding of their elaborate structures. In pursuit of this, cutting-edge experimental and computational structure-probing techniques output several candidate geometries for a given RNA, each of which is perfectly aligned with experimentally determined parameters. Identifying which structure is the most accurate, however, remains a major obstacle. In recent years, several algorithms have been developed for ranking candidate RNA structures in order from most to least probable, though their levels of accuracy and transparency leave room for improvement. Most recently, advances in both areas are demonstrated by rsRNASP, a novel algorithm proposed by Tan et al. rsRNASP is a residue-separation-based statistical potential for three-dimensional structure evaluation, and it outperforms the leading algorithms in the field.

rsRNASP: A residue-separation-based statistical potential for RNA 3D structure evaluation

Knowledge-based statistical potentials have been shown to be rather effective in protein 3-dimensional (3D) structure evaluation and prediction. Recently, several statistical potentials have been developed for RNA 3D structure evaluation, while their performances are either still at a low level for the test datasets from structure prediction models or dependent on the "black-box" process through neural networks. In this work, we have developed an all-atom distance-dependent statistical potential based on residue separation for RNA 3D structure evaluation, namely rsRNASP, which is composed of short- and long-ranged potentials distinguished by residue separation. The extensive examinations against available RNA test datasets show that rsRNASP has apparently higher performance than the existing statistical potentials for the realistic test datasets with large RNAs from structure prediction models, including the newly released RNA-Puzzles dataset, and is comparable to the existing top statistical potentials for the test datasets with small RNAs or near-native decoys. In addition, rsRNASP is superior to RNA3DCNN, a recently developed scoring function through 3D convolutional neural networks. rsRNASP and the relevant databases are available to the public.

Machine Learning Approaches on High Throughput NGS Data to Unveil Mechanisms of Function in Biology and Disease

In this review, the fundamental basis of machine learning (ML) and data mining (DM) are summarized together with the techniques for distilling knowledge from state-of-the-art omics experiments. This includes an introduction to the basic mathematical principles of unsupervised/supervised learning methods, dimensionality reduction techniques, deep neural networks architectures and the applications of these in bioinformatics. Several case studies under evaluation mainly involve next generation sequencing (NGS) experiments, like deciphering gene expression from total and single cell (scRNA-seq) analysis; for the latter, a description of all recent artificial intelligence (AI) methods for the investigation of cell sub-types, biomarkers and imputation techniques are described. Other areas of interest where various ML schemes have been investigated are for providing information regarding transcription factors (TF) binding sites, chromatin organization patterns and RNA binding proteins (RBPs), while analyses on RNA sequence and structure as well as 3D dimensional protein structure predictions with the use of ML are described. Furthermore, we summarize the recent methods of using ML in clinical oncology, when taking into consideration the current omics data with pharmacogenomics to determine personalized treatments. With this review we wish to provide the scientific community with a thorough investigation of main novel ML applications which take into consideration the latest achievements in genomics, thus, unraveling the fundamental mechanisms of biology towards the understanding and cure of diseases.

Geometric deep learning of RNA structure

RNA molecules adopt three-dimensional structures that are critical to their function and of interest in drug discovery. Few RNA structures are known, however, and predicting them computationally has proven challenging. We introduce a machine learning approach that enables identification of accurate structural models without assumptions about their defining characteristics, despite being trained with only 18 known RNA structures. The resulting scoring function, the Atomic Rotationally Equivariant Scorer (ARES), substantially outperforms previous methods and consistently produces the best results in community-wide blind RNA structure prediction challenges. By learning effectively even from a small amount of data, our approach overcomes a major limitation of standard deep neural networks. Because it uses only atomic coordinates as inputs and incorporates no RNA-specific information, this approach is applicable to diverse problems in structural biology, chemistry, materials science, and beyond.

Salt-Dependent RNA Pseudoknot Stability: Effect of Spatial Confinement

Macromolecules, such as RNAs, reside in crowded cell environments, which could strongly affect the folded structures and stability of RNAs. The emergence of RNA-driven phase separation in biology further stresses the potential functional roles of molecular crowding. In this work, we employed the coarse-grained model that was previously developed by us to predict 3D structures and stability of the mouse mammary tumor virus (MMTV) pseudoknot under different spatial confinements over a wide range of salt concentrations. The results show that spatial confinements can not only enhance the compactness and stability of MMTV pseudoknot structures but also weaken the dependence of the RNA structure compactness and stability on salt concentration. Based on our microscopic analyses, we found that the effect of spatial confinement on the salt-dependent RNA pseudoknot stability mainly comes through the spatial suppression of extended conformations, which are prevalent in the partially/fully unfolded states, especially at low ion concentrations. Furthermore, our comprehensive analyses revealed that the thermally unfolding pathway of the pseudoknot can be significantly modulated by spatial confinements, since the intermediate states with more extended conformations would loss favor when spatial confinements are introduced.

Energy-based graph convolutional networks for scoring protein docking models

Structural information about protein-protein interactions, often missing at the interactome scale, is important for mechanistic understanding of cells and rational discovery of therapeutics. Protein docking provides a computational alternative for such information. However, ranking near-native docked models high among a large number of candidates, often known as the scoring problem, remains a critical challenge. Moreover, estimating model quality, also known as the quality assessment problem, is rarely addressed in protein docking. In this study, the two challenging problems in protein docking are regarded as relative and absolute scoring, respectively, and addressed in one physics-inspired deep learning framework. We represent protein and complex structures as intra- and inter-molecular residue contact graphs with atom-resolution node and edge features. And we propose a novel graph convolutional kernel that aggregates interacting nodes' features through edges so that generalized interaction energies can be learned directly from 3D data. The resulting energy-based graph convolutional networks (EGCN) with multihead attention are trained to predict intra- and inter-molecular energies, binding affinities, and quality measures (interface RMSD) for encounter complexes. Compared to a state-of-the-art scoring function for model ranking, EGCN significantly improves ranking for a critical assessment of predicted interactions (CAPRI) test set involving homology docking; and is comparable or slightly better for Score_set, a CAPRI benchmark set generated by diverse community-wide docking protocols not known to training data. For Score_set quality assessment, EGCN shows about 27% improvement to our previous efforts. Directly learning from 3D structure data in graph representation, EGCN represents the first successful development of graph convolutional networks for protein docking.

RNA-Puzzles toolkit: a computational resource of RNA 3D structure benchmark datasets, structure manipulation, and evaluation tools

Significant improvements have been made in the efficiency and accuracy of RNA 3D structure prediction methods during the succeeding challenges of RNA-Puzzles, a community-wide effort on the assessment of blind prediction of RNA tertiary structures. The RNA-Puzzles contest has shown, among others, that the development and validation of computational methods for RNA fold prediction strongly depend on the benchmark datasets and the structure comparison algorithms. Yet, there has been no systematic benchmark set or decoy structures available for the 3D structure prediction of RNA, hindering the standardization of comparative tests in the modeling of RNA structure. Furthermore, there has not been a unified set of tools that allows deep and complete RNA structure analysis, and at the same time, that is easy to use. Here, we present RNA-Puzzles toolkit, a computational resource including (i) decoy sets generated by different RNA 3D structure prediction methods (raw, for-evaluation and standardized datasets), (ii) 3D structure normalization, analysis, manipulation, visualization tools (RNA_format, RNA_normalizer, rna-tools) and (iii) 3D structure comparison metric tools (RNAQUA, MCQ4Structures). This resource provides a full list of computational tools as well as a standard RNA 3D structure prediction assessment protocol for the community.

Structure folding of RNA kissing complexes in salt solutions: predicting 3D structure, stability, and folding pathway

RNA kissing complexes are essential for genomic RNA dimerization and regulation of gene expression, and their structures and stability are critical to their biological functions. In this work, we used our previously developed coarse-grained model with an implicit structure-based electrostatic potential to predict three-dimensional (3D) structures and stability of RNA kissing complexes in salt solutions. For extensive RNA kissing complexes, our model shows great reliability in predicting 3D structures from their sequences, and our additional predictions indicate that the model can capture the dependence of 3D structures of RNA kissing complexes on monovalent/divalent ion concentrations. Moreover, the comparisons with extensive experimental data show that the model can make reliable predictions on the stability for various RNA kissing complexes over wide ranges of monovalent/divalent ion concentrations. Notably, for RNA kissing complexes, our further analyses show the important contribution of coaxial stacking to the 3D structures and stronger stability than the corresponding kissing-interface duplexes at high salts. Furthermore, our comprehensive analyses for RNA kissing complexes reveal that the thermally folding pathway for a complex sequence is mainly determined by the relative stability of two possible folded states of kissing complex and extended duplex, which can be significantly modulated by its sequence.

3D structure stability of the HIV-1 TAR RNA in ion solutions: A coarse-grained model study

As an extremely common structural motif, RNA hairpins with bulge loops [e.g., the human immunodeficiency virus type 1 (HIV-1) transactivation response (TAR) RNA] can play essential roles in normal cellular processes by binding to proteins and small ligands, which could be very dependent on their three-dimensional (3D) structures and stability. Although the structures and conformational dynamics of the HIV-1 TAR RNA have been extensively studied, there are few investigations on the thermodynamic stability of the TAR RNA, especially in ion solutions, and the existing studies also have some divergence on the unfolding process of the RNA. Here, we employed our previously developed coarse-grained model with implicit salt to predict the 3D structure, stability, and unfolding pathway for the HIV-1 TAR RNA over a wide range of ion concentrations. As compared with the extensive experimental/theoretical results, the present model can give reliable predictions on the 3D structure stability of the TAR RNA from the sequence. Based on the predictions, our further comprehensive analyses on the stability of the TAR RNA as well as its variants revealed that the unfolding pathway of an RNA hairpin with a bulge loop is mainly determined by the relative stability between different states (folded state, intermediate state, and unfolded state) and the strength of the coaxial stacking between two stems in folded structures, both of which can be apparently modulated by the ion concentrations as well as the sequences.

All-Atom Knowledge-Based Potential for RNA Structure Discrimination Based on the Distance-Scaled Finite Ideal-Gas Reference State

Noncoding RNAs are increasingly found to play a wide variety of roles in living organisms. Yet, their functional mechanisms are poorly understood because their structures are difficult to determine experimentally. As a result, developing more effective computational techniques to predict RNA structures becomes increasingly an urgent task. One key challenge in RNA structure prediction is the lack of an accurate free energy function to guide RNA folding and discriminate native and near-native structures from decoy conformations. In this study, we developed an all-atom distance-dependent knowledge-based energy function for RNA that is based on a reference state (distance-scaled finite ideal-gas reference state, DFIRE) proven successful for protein structure discrimination. Using four separate benchmarks including RNA puzzles, we found that this DFIRE-based RNA statistical energy function is able to discriminate native and near-native structures against decoys with performance comparable with or better than several existing scoring functions compared. The energy function is expected to be useful for improving the detection of RNA near-native structures.

Systemically modeling the relationship between climate change and wheat aphid abundance

Climate change influences all living beings. Wheat aphids deplete the nutritional value of wheat and affect the production of wheat in changing climate. In this study, we attempt to explain the ecological mechanisms of how climate change affects wheat aphids by simulating the relationship between climate and the abundance of wheat aphids, which will not only aid in improving wheat aphid forecasting and the effectiveness of prevention and treatment, but also help mitigate food crises. Fuzzy cognitive maps (FCM) are an effective tool for portraying complex systems. Using Sitobion avenae and climatological data collected in China, we made use of differential evolution (DE) algorithms to construct FCM models that directly illustrate the effect of climate on wheat aphid abundance. The relationships among climate and wheat aphids at different growth stages (I-III instar larvae, IV instar larvae with wings, IV instar larvae without wings, adult with wings, adult without wings) were established. The analysis results from the FCM models show that temperature positively influences wheat aphids most. Moreover, these models can be used to determine the numerical value of each climate factor and the abundance of wheat aphids quantitatively. Furthermore, the two overall relationship models between climate and wheat aphids were constructed and the experimental results show that natural enemies and highest daily temperature affect wheat aphids most. Natural enemies and highest daily temperature exert negative and positive impacts on wheat aphids respectively. Some interrelationships among wheat aphids at all growth stages and the internal relationships among climate factors were also shown.

What is the best reference state for building statistical potentials in RNA 3D structure evaluation?

Knowledge-based statistical potentials have been shown to be efficient in protein structure evaluation/prediction, and the core difference between various statistical potentials is attributed to the choice of reference states. However, for RNA 3D structure evaluation, a comprehensive examination on reference states is still lacking. In this work, we built six statistical potentials based on six reference states widely used in protein structure evaluation, including averaging, quasi-chemical approximation, atom-shuffled, finite-ideal-gas, spherical-noninteracting, and random-walk-chain reference states, and we examined the six reference states against three RNA test sets including six subsets. Our extensive examinations show that, overall, for identifying native structures and ranking decoy structures, the finite-ideal-gas and random-walk-chain reference states are slightly superior to others, while for identifying near-native structures, there is only a slight difference between these reference states. Our further analyses show that the performance of a statistical potential is apparently dependent on the quality of the training set. Furthermore, we found that the performance of a statistical potential is closely related to the origin of test sets, and for the three realistic test subsets, the six statistical potentials have overall unsatisfactory performance. This work presents a comprehensive examination on the existing reference states and statistical potentials for RNA 3D structure evaluation.