RNA Tertiary Structure Prediction Research Articles

RNA secondary structure prediction using transformer-based deep learning models

The Human Genome Project has led to an exponential increase in data related to the sequence, structure, and function of biomolecules. Bioinformatics is an interdisciplinary research field that primarily uses computational methods to analyze large amounts of biological macromolecule data. Its goal is to discover hidden biological patterns and related information. Furthermore, analysing additional relevant information can enhance the study of biological operating mechanisms. This paper discusses the fundamental concepts of RNA, RNA secondary structure, and its prediction.Subsequently, the application of machine learning technologies in predicting the structure of biological macromolecules is explored. This chapter describes the relevant knowledge of algorithms and computational complexity and presents a RNA tertiary structure prediction algorithm based on ResNet. To address the issue of the current scoring function's unsuitability for long RNA, a scoring model based on ResNet is proposed, and a structure prediction algorithm is designed. The chapter concludes by presenting some open and interesting challenges in the field of RNA tertiary structure prediction.

RNA tertiary structure prediction using RNAComposer in CASP15.

As CASP15 participants, in the new category of 3D RNA structure prediction, we applied expert modeling with the support of our proprietary system RNAComposer. Although RNAComposer is primarily known as an automated web server, its features allow it to be used interactively, for example, for homology-based modeling or assembling models from user-provided structural elements. In the paper, we present various scenarios of applying the system to predict the 3D RNA structures that we employed. Their combination with expert input, comparative analysis of models, and routines to select representative resultant structures form a ready-for-reuse workflow. With selected examples, we demonstrate its application for the in silico modeling of natural and synthetic RNA molecules targeted in CASP15.

Combining Experimental Restraints and RNA 3D Structure Prediction in RNA Nanotechnology.

Precise RNA tertiary structure prediction can aid in the design of RNA nanoparticles. However, most existing RNA tertiary structure prediction methods are limited to small RNAs with relatively simple secondary structures. Large RNA molecules usually have complex secondary structures, including multibranched loops and pseudoknots, allowing for highly flexible RNA geometries and multiple stable states. Various experiments and bioinformatics analyses can often provide information about the distance between atoms (or residues) in RNA, which can be used to guide the prediction of RNA tertiary structure. In this chapter, we will introduce a platform, iFoldNMR, that can incorporate non-exchangeable imino protons resonance data from NMR as restraints for RNA 3D structure prediction. We also introduce an algorithm, DVASS, which optimizes distance restraints for better RNA 3D structure prediction.

RNA 3D Structure Comparison Using RNA-Puzzles Toolkit.

Computational modeling of RNA three-dimensional (3D) structure may help in unrevealing the molecular mechanisms of RNA molecules and in designing molecules with novel functions. An unbiased blind assessment to benchmark the computational modeling is required to understand the achievements and bottlenecks of the prediction, while a standard structure comparison protocol is necessary. RNA-Puzzles is a community-wide effort on the assessment of blind prediction of RNA tertiary structures. And RNA-Puzzles toolkit is a computational resource derived from RNA-Puzzles, which includes (i) decoy sets generated by different RNA 3D structure prediction methods; (ii) 3D structure normalization, analysis, manipulation, and visualization tools; and (iii) 3D structure comparison metric tools. In this chapter, we illustrate a standard RNA 3D structure prediction assessment protocol using the selected tools from RNA-Puzzles toolkit: rna-tools and RNA_assessment.

The Structural Annotations of The Mir-122 Non-Coding RNA from The Tilapia Fish (Oreochromis niloticus)

Tilapia (Oreochromis niloticus) is an important fisheries commodity. Scientific efforts have been done to increase its quality. One of them is staging a premium diet such as a fat-enriched diet. The transcriptomics approach is able to provide the signatures of the diet outcomes by observing the micro(mi)RNA signature in transcriptional regulation. Hence, it was found that the availability of mir-122 is essential in the regulation of a high-fat diet in tilapia. However, this transcriptomics signature is lacking structural annotations and the complete interaction annotations with its silencing(si)RNA. RNAcentral website was navigated for the latest annotation of mir-122 from tilapia and other species as a comparison. MEGA X was employed to comprehend the miRNA evolutionary repertoire. The RNA secondary structure prediction tools from the Vienna RNA package and the RNA tertiary structure prediction tools from simRNA and modeRNA are secured with default parameters. The HNADOCK tools were leveraged to observe the interaction between mir-122 and its siRNA. The post-processing was conducted with the Chimera visualization tool. The secondary and tertiary structure of the mir-122 and its siRNA could be elucidated, docked, and visualized. In this end, further effort to develop a comprehensive molecular breeding tool could be secured with the structural annotation information.

Prediction of the RNA Tertiary Structure Based on a Random Sampling Strategy and Parallel Mechanism

Background: Macromolecule structure prediction remains a fundamental challenge of bioinformatics. Over the past several decades, the Rosetta framework has provided solutions to diverse challenges in computational biology. However, it is challenging to model RNA tertiary structures effectively when the de novo modeling of RNA involves solving a well-defined small puzzle. Methods: In this study, we introduce a stepwise Monte Carlo parallelization (SMCP) algorithm for RNA tertiary structure prediction. Millions of conformations were randomly searched using the Monte Carlo algorithm and stepwise ansatz hypothesis, and SMCP uses a parallel mechanism for efficient sampling. Moreover, to achieve better prediction accuracy and completeness, we judged and processed the modeling results. Results: A benchmark of nine single-stranded RNA loops drawn from riboswitches establishes the general ability of the algorithm to model RNA with high accuracy and integrity, including six motifs that cannot be solved by knowledge mining–based modeling algorithms. Experimental results show that the modeling accuracy of the SMCP algorithm is up to 0.14 Å, and the modeling integrity on this benchmark is extremely high. Conclusion: SMCP is an ab initio modeling algorithm that substantially outperforms previous algorithms in the Rosetta framework, especially in improving the accuracy and completeness of the model. It is expected that the work will provide new research ideas for macromolecular structure prediction in the future. In addition, this work will provide theoretical basis for the development of the biomedical field.

RNAcmap: a fully automatic pipeline for predicting contact maps of RNAs by evolutionary coupling analysis.

The accuracy of RNA secondary and tertiary structure prediction can be significantly improved by using structural restraints derived from evolutionary coupling or direct coupling analysis. Currently, these coupling analyses relied on manually curated multiple sequence alignments collected in the Rfam database, which contains 3016 families. By comparison, millions of non-coding RNA sequences are known. Here, we established RNAcmap, a fully automatic pipeline that enables evolutionary coupling analysis for any RNA sequences. The homology search was based on the covariance model built by INFERNAL according to two secondary structure predictors: a folding-based algorithm RNAfold and the latest deep-learning method SPOT-RNA. We showed that the performance of RNAcmap is less dependent on the specific evolutionary coupling tool but is more dependent on the accuracy of secondary structure predictor with the best performance given by RNAcmap (SPOT-RNA). The performance of RNAcmap (SPOT-RNA) is comparable to that based on Rfam-supplied alignment and consistent for those sequences that are not in Rfam collections. Further improvement can be made with a simple meta predictor RNAcmap (SPOT-RNA/RNAfold) depending on which secondary structure predictor can find more homologous sequences. Reliable base-pairing information generated from RNAcmap, for RNAs with high effective homologous sequences, in particular, will be useful for aiding RNA structure prediction. RNAcmap is available as a web server at https://sparks-lab.org/server/rnacmap/ and as a standalone application along with the datasets at https://github.com/sparks-lab-org/RNAcmap_standalone. A platform independent and fully configured docker image of RNAcmap is also provided at https://hub.docker.com/r/jaswindersingh2/rnacmap. Supplementary data are available at Bioinformatics online.

A Comprehensive Review of Predicting Method of RNA Tertiary Structure

In recent years, great progress has been made in the research of RNA function, and more and more RNA functions have been discovered. The function of RNA is highly dependent on its 3D structure, the RNA tertiary structure includes the RNA 3D structure and RNA tertiary interaction, so the RNA tertiary structure prediction has also attracted extensive attention. There are many RNA tertiary structure prediction algorithms. According to the traditional classification methods, the existing RNA tertiary structure prediction algorithms can be divided into two categories: the RNA tertiary structure prediction algorithm based on knowledge mining and the RNA tertiary structure prediction algorithm based on physics. On this basis, this paper further refines the RNA tertiary structure prediction algorithm based on physics in traditional classification, and proposes a new refinement classification method based on conformational sampling method, namely RNA tertiary structure prediction algorithm based on physical fragment assembly conformational sampling method and RNA tertiary structure prediction algorithm based on Stepwise ansatz conformational sampling method. We make a comparative analysis of RNA tertiary structure prediction algorithms, and put forward some suggestions for improving the energy function in the next step, in order to find an RNA tertiary structure prediction algorithm that can achieve atomic accuracy.

ATTfold: RNA Secondary Structure Prediction With Pseudoknots Based on Attention Mechanism.

Accurate RNA secondary structure information is the cornerstone of gene function research and RNA tertiary structure prediction. However, most traditional RNA secondary structure prediction algorithms are based on the dynamic programming (DP) algorithm, according to the minimum free energy theory, with both hard and soft constraints. The accuracy is particularly dependent on the accuracy of soft constraints (from experimental data like chemical and enzyme detection). With the elongation of the RNA sequence, the time complexity of DP-based algorithms will increase geometrically, as a result, they are not good at coping with relatively long sequences. Furthermore, due to the complexity of the pseudoknots structure, the secondary structure prediction method, based on traditional algorithms, has great defects which cannot predict the secondary structure with pseudoknots well. Therefore, few algorithms have been available for pseudoknots prediction in the past. The ATTfold algorithm proposed in this article is a deep learning algorithm based on an attention mechanism. It analyzes the global information of the RNA sequence via the characteristics of the attention mechanism, focuses on the correlation between paired bases, and solves the problem of long sequence prediction. Moreover, this algorithm also extracts the effective multi-dimensional features from a great number of RNA sequences and structure information, by combining the exclusive hard constraints of RNA secondary structure. Hence, it accurately determines the pairing position of each base, and obtains the real and effective RNA secondary structure, including pseudoknots. Finally, after training the ATTfold algorithm model through tens of thousands of RNA sequences and their real secondary structures, this algorithm was compared with four classic RNA secondary structure prediction algorithms. The results show that our algorithm significantly outperforms others and more accurately showed the secondary structure of RNA. As the data in RNA sequence databases increase, our deep learning-based algorithm will have superior performance. In the future, this kind of algorithm will be more indispensable.

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.

Identification and Characterization of New RNA Tetraloop Sequence Families.

There is an abundance of RNA sequence information available due to the efforts of sequencing projects. However, current techniques implemented to solve the tertiary structures of RNA, such as NMR and X-ray crystallography, are difficult and time-consuming. Therefore, biophysical techniques are not able to keep pace with the abundance of sequence information available. Because of this, there is a need to develop quick and efficient ways to predict RNA tertiary structure from sequence. One promising approach is to identify structural patterns within previously solved 3D structures and apply these patterns to new sequences. RNA tetraloops are one of the most common naturally occurring secondary structure motifs. Here, we use RNA Characterization of Secondary Structure Motifs (CoSSMos), Dissecting the Spatial Structure of RNA (DSSR), and a bioinformatic approach to search for and characterize tertiary structure patterns among tetraloops. Not surprising, we identified the well-known GNRA and UNCG tetraloops, as well as the previously identified RNYA tetraloop. However, some previously identified characteristics of these families were not observed in this data set, and some new characteristics were identified. In addition, we also identified and characterized three new tetraloop sequence families: YGAR, UGGU, and RMSA. This new structural information sheds light on the tertiary structure of tetraloops and contributes to the efforts of RNA tertiary structure prediction from sequence.

Limits in accuracy and a strategy of RNA structure prediction using experimental information.

RNA structural complexity and flexibility present a challenge for computational modeling efforts. Experimental information and bioinformatics data can be used as restraints to improve the accuracy of RNA tertiary structure prediction. Regarding utilization of restraints, the fundamental questions are: (i) What is the limit in prediction accuracy that one can achieve with arbitrary number of restraints? (ii) Is there a strategy for selection of the minimal number of restraints that would result in the best structural model? We address the first question by testing the limits in prediction accuracy using native contacts as restraints. To address the second question, we develop an algorithm based on the distance variation allowed by secondary structure (DVASS), which ranks restraints according to their importance to RNA tertiary structure prediction. We find that due to kinetic traps, the greatest improvement in the structure prediction accuracy is achieved when we utilize only 40–60% of the total number of native contacts as restraints. When the restraints are sorted by DVASS algorithm, using only the first 20% ranked restraints can greatly improve the prediction accuracy. Our findings suggest that only a limited number of strategically selected distance restraints can significantly assist in RNA structure modeling.

ToGo-WF: prediction of RNA tertiary structures and RNA-RNA/protein interactions using the KNIME workflow.

Recent progress in molecular biology has revealed that many non-coding RNAs regulate gene expression or catalyze biochemical reactions in tumors, viruses and several other diseases. The tertiary structure of RNA molecules and RNA–RNA/protein interaction sites are of increasing importance as potential targets for new medicines that treat a broad array of human diseases. Current RNA drugs are split into two groups: antisense RNA molecules and aptamers. In this report, we present a novel workflow to predict RNA tertiary structures and RNA–RNA/protein interactions using the KNIME environment, which enabled us to assemble a combination of RNA-related analytical tools and databases. In this study, three analytical workflows for comprehensive structural analysis of RNA are introduced: (1) prediction of the tertiary structure of RNA; (2) prediction of the structure of RNA–RNA complexes and analysis of their interactions; and (3) prediction of the structure of RNA–protein complexes and analysis of their interactions. In an RNA–protein case study, we modeled the tertiary structure of pegaptanib, an aptamer drug, and performed docking calculations of the pegaptanib-vascular endothelial growth factor complex using a fragment of the interaction site of the aptamer. We also present molecular dynamics simulations of the RNA–protein complex to evaluate the affinity of the complex by mutating bases at the interaction interface. The results provide valuable information for designing novel features of aptamer-protein complexes.Electronic supplementary materialThe online version of this article (10.1007/s10822-019-00195-y) contains supplementary material, which is available to authorized users.

An RNA Scoring Function for Tertiary Structure Prediction Based on Multi-layer Neural Networks

A good scoring function is necessary for ab inito prediction of RNA tertiary structures. In this study, we explored the power of a machine learning based approach as a scoring function. Compared with the traditional scoring functions, the present approach is more flexible in incorporating different kinds of features; it is also free of the difficult problem of choosing the reference state. Two multi-layer neural networks were constructed and trained. They took RNA a structural candidate as input and then output its likeness score that evaluates the likeness of the candidate to the native structure. The first network was working at the coarse-grained level of RNA structures, while the second at the all-atom level. We also built an RNA database and split it into the training, validation, and testing sets, containing 322, 70, and 70 RNAs, respectively. Each RNA was accompanied with 300 decoys generated by high-temperature molecular dynamics simulations. The networks were trained on the training set and then optimized with an early-stop strategy, based on the loss of the validation set. We then tested the performance of the networks on the testing set. The results were found to be consistently better than a recent knowledge-based all-atom potential.

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

Quality assessment is essential for the computational prediction and design of RNA tertiary structures. To date, several knowledge-based statistical potentials have been proposed and proved to be effective in identifying native and near-native RNA structures. All these potentials are based on the inverse Boltzmann formula, while differing in the choice of the geometrical descriptor, reference state, and training dataset. Via an approach that diverges completely from the conventional statistical potentials, our work explored the power of a 3D convolutional neural network (CNN)-based approach as a quality evaluator for RNA 3D structures, which used a 3D grid representation of the structure as input without extracting features manually. The RNA structures were evaluated by examining each nucleotide, so our method can also provide local quality assessment. Two sets of training samples were built. The first one included 1 million samples generated by high-temperature molecular dynamics (MD) simulations and the second one included 1 million samples generated by Monte Carlo (MC) structure prediction. Both MD and MC procedures were performed for a non-redundant set of 414 RNAs. For two training datasets (one including only MD training samples and the other including both MD and MC training samples), we trained two neural networks, named RNA3DCNN_MD and RNA3DCNN_MDMC, respectively. The former is suitable for assessing near-native structures, while the latter is suitable for assessing structures covering large structural space. We tested the performance of our method and made comparisons with four other traditional scoring functions. On two of three test datasets, our method performed similarly to the state-of-the-art traditional scoring function, and on the third test dataset, our method was far superior to other scoring functions. Our method can be downloaded from https://github.com/lijunRNA/RNA3DCNN.

Enhanced prediction of RNA solvent accessibility with long short-term memory neural networks and improved sequence profiles.

The de novo prediction of RNA tertiary structure remains a grand challenge. Predicted RNA solvent accessibility provides an opportunity to address this challenge. To the best of our knowledge, there is only one method (RNAsnap) available for RNA solvent accessibility prediction. However, its performance is unsatisfactory for protein-free RNAs. We developed RNAsol, a new algorithm to predict RNA solvent accessibility. RNAsol was built based on improved sequence profiles from the covariance models and trained with the long short-term memory (LSTM) neural networks. Independent tests on the same datasets from RNAsnap show that RNAsol achieves the mean Pearson's correlation coefficient (PCC) of 0.43/0.26 for the protein-bound/protein-free RNA molecules, which is 26.5%/136.4% higher than that of RNAsnap. When the training set is enlarged to include both types of RNAs, the PCCs increase to 0.49 and 0.46 for protein-bound and protein-free RNAs, respectively. The success of RNAsol is attributed to two aspects, including the improved sequence profiles constructed by the sequence-profile alignment and the enhanced training by the LSTM neural networks. http://yanglab.nankai.edu.cn/RNAsol/. Supplementary data are available at Bioinformatics online.

Base pair probability estimates improve the prediction accuracy of RNA non-canonical base pairs.

Prediction of RNA tertiary structure from sequence is an important problem, but generating accurate structure models for even short sequences remains difficult. Predictions of RNA tertiary structure tend to be least accurate in loop regions, where non-canonical pairs are important for determining the details of structure. Non-canonical pairs can be predicted using a knowledge-based model of structure that scores nucleotide cyclic motifs, or NCMs. In this work, a partition function algorithm is introduced that allows the estimation of base pairing probabilities for both canonical and non-canonical interactions. Pairs that are predicted to be probable are more likely to be found in the true structure than pairs of lower probability. Pair probability estimates can be further improved by predicting the structure conserved across multiple homologous sequences using the TurboFold algorithm. These pairing probabilities, used in concert with prior knowledge of the canonical secondary structure, allow accurate inference of non-canonical pairs, an important step towards accurate prediction of the full tertiary structure. Software to predict non-canonical base pairs and pairing probabilities is now provided as part of the RNAstructure software package.

LCS-TA to identify similar fragments in RNA 3D structures

BackgroundIn modern structural bioinformatics, comparison of molecular structures aimed to identify and assess similarities and differences between them is one of the most commonly performed procedures. It gives the basis for evaluation of in silico predicted models. It constitutes the preliminary step in searching for structural motifs. In particular, it supports tracing the molecular evolution. Faced with an ever-increasing amount of available structural data, researchers need a range of methods enabling comparative analysis of the structures from either global or local perspective.ResultsHerein, we present a new, superposition-independent method which processes pairs of RNA 3D structures to identify their local similarities. The similarity is considered in the context of structure bending and bonds’ rotation which are described by torsion angles. In the analyzed RNA structures, the method finds the longest continuous segments that show similar torsion within a user-defined threshold. The length of the segment is provided as local similarity measure. The method has been implemented as LCS-TA algorithm (Longest Continuous Segments in Torsion Angle space) and is incorporated into our MCQ4Structures application, freely available for download from http://www.cs.put.poznan.pl/tzok/mcq/.ConclusionsThe presented approach ties torsion-angle-based method of structure analysis with the idea of local similarity identification by handling continuous 3D structure segments. The first method, implemented in MCQ4Structures, has been successfully utilized in RNA-Puzzles initiative. The second one, originally applied in Euclidean space, is a component of LGA (Local-Global Alignment) algorithm commonly used in assessing protein models submitted to CASP. This unique combination of concepts implemented in LCS-TA provides a new perspective on structure quality assessment in local and quantitative aspect. A series of computational experiments show the first results of applying our method to comparison of RNA 3D models. LCS-TA can be used for identifying strengths and weaknesses in the prediction of RNA tertiary structures.

Structure Prediction of RNA Loops with a Probabilistic Approach.

The knowledge of the tertiary structure of RNA loops is important for understanding their functions. In this work we develop an efficient approach named RNApps, specifically designed for predicting the tertiary structure of RNA loops, including hairpin loops, internal loops, and multi-way junction loops. It includes a probabilistic coarse-grained RNA model, an all-atom statistical energy function, a sequential Monte Carlo growth algorithm, and a simulated annealing procedure. The approach is tested with a dataset including nine RNA loops, a 23S ribosomal RNA, and a large dataset containing 876 RNAs. The performance is evaluated and compared with a homology modeling based predictor and an ab initio predictor. It is found that RNApps has comparable performance with the former one and outdoes the latter in terms of structure predictions. The approach holds great promise for accurate and efficient RNA tertiary structure prediction.

RNAComposer and RNA 3D structure prediction for nanotechnology

RNAs adopt specific, stable tertiary architectures to perform their activities. Knowledge of RNA tertiary structure is fundamental to understand RNA functions beginning with transcription and ending with turnover. Contrary to advanced RNA secondary structure prediction algorithms, which allow good accuracy when experimental data are integrated into the prediction, tertiary structure prediction of large RNAs still remains a significant challenge. However, the field of RNA tertiary structure prediction is rapidly developing and new computational methods based on different strategies are emerging.RNAComposer is a user-friendly and freely available server for 3D structure prediction of RNA up to 500 nucleotide residues. RNAComposer employs fully automated fragment assembly based on RNA secondary structure specified by the user. Importantly, this method allows incorporation of distance restraints derived from the experimental data to strengthen the 3D predictions. The potential and limitations of RNAComposer are discussed and an application to RNA design for nanotechnology is presented.