Improved RNA Secondary Structure and Tertiary Base-pairing Prediction Using Evolutionary Profile, Mutational Coupling and Two-dimensional Transfer Learning

Comparative analysis of RNA 3D structure prediction methods: towards enhanced modeling of RNA-ligand interactions

Accurate RNA structure models are crucial for designing small molecule ligands that modulate their functions. This study assesses six standalone RNA 3D structure prediction methods-DeepFoldRNA, RhoFold, BRiQ, FARFAR2, SimRNA and Vfold2, excluding web-based tools due to intellectual property concerns. We focus on reproducing the RNA structure existing in RNA-small molecule complexes, particularly on the ability to model ligand binding sites. Using a comprehensive set of RNA structures from the PDB, which includes diverse structural elements, we found that machine learning (ML)-based methods effectively predict global RNA folds but are less accurate with local interactions. Conversely, non-ML-based methods demonstrate higher precision in modeling intramolecular interactions, particularly with secondary structure restraints. Importantly, ligand-binding site accuracy can remain sufficiently high for practical use, even if the overall model quality is not optimal. With the recent release of AlphaFold 3, we included this advanced method in our tests. Benchmark subsets containing new structures, not used in the training of the tested ML methods, show that AlphaFold 3's performance was comparable to other ML-based methods, albeit with some challenges in accurately modeling ligand binding sites. This study underscores the importance of enhancing binding site prediction accuracy and the challenges in modeling RNA-ligand interactions accurately.

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.

DEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning

It is now known that RNAs play more active roles in cellular pathways beyond simply serving as transcription templates. These biological mechanisms might be mediated by higher RNA stereo conformations, triggering the need to understand RNA secondary structures first. However, experimental protocols for solving RNA structures are unavailable for large-scale investigation due to their high costs and time-consuming nature. Various computational tools were thus developed to predict the RNA secondary structures from sequences. Recently, deep networks have been investigated to help predict RNA structures directly from their sequences. However, existing deep-learning-based tools are more or less suffering from model overfitting due to their complicated problem formulation and defective model training processes, limiting their applications across sequences from different structural families. In this research, we designed a two-stage RNA structure prediction strategy called DEBFold (deep ensemble boosting and folding) based on convolution encoding/decoding and self-attention mechanisms to enhance the existing thermodynamic structure models. Moreover, the model training process followed rigorous steps to achieve an acceptable prediction generalization. On the family-wise reserved test sets and the PDB-derived test set, DEBFold achieves better structure prediction performance over traditional tools and existing deep-learning methods. In summary, we obtained a cutting-edge deep-learning-based structure prediction tool with supreme across-family generalization performance. The DEBFold tool can be accessed at https://cobis.bme.ncku.edu.tw/DEBFold/.

MARS and RNAcmap3: The Master Database of All Possible RNA Sequences Integrated with RNAcmap for RNA Homology Search

Recent success of AlphaFold2 in protein structure prediction relied heavily on co-evolutionary information derived from homologous protein sequences found in the huge, integrated database of protein sequences (Big Fantastic Database). In contrast, the existing nucleotide databases were not consolidated to facilitate wider and deeper homology search. Here, we built a comprehensive database by incorporating the non-coding RNA (ncRNA) sequences from RNAcentral, the transcriptome assembly and metagenome assembly from metagenomics RAST (MG-RAST), the genomic sequences from Genome Warehouse (GWH), and the genomic sequences from MGnify, in addition to the nucleotide (nt) database and its subsets in National Center of Biotechnology Information (NCBI). The resulting Master database of All possible RNA sequences (MARS) is 20-fold larger than NCBI's nt database or 60-fold larger than RNAcentral. The new dataset along with a new split-search strategy allows a substantial improvement in homology search over existing state-of-the-art techniques. It also yields more accurate and more sensitive multiple sequence alignments (MSAs) than manually curated MSAs from Rfam for the majority of structured RNAs mapped to Rfam. The results indicate that MARS coupled with the fully automatic homology search tool RNAcmap will be useful for improved structural and functional inference of ncRNAs and RNA language models based on MSAs. MARS is accessible at https://ngdc.cncb.ac.cn/omix/release/OMIX003037, and RNAcmap3 is accessible at http://zhouyq-lab.szbl.ac.cn/download/.

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.

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.

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.

Multiple sequence alignment-based RNA language model and its application to structural inference

Compared with proteins, DNA and RNA are more difficult languages to interpret because four-letter coded DNA/RNA sequences have less information content than 20-letter coded protein sequences. While BERT (Bidirectional Encoder Representations from Transformers)-like language models have been developed for RNA, they are ineffective at capturing the evolutionary information from homologous sequences because unlike proteins, RNA sequences are less conserved. Here, we have developed an unsupervised multiple sequence alignment-based RNA language model (RNA-MSM) by utilizing homologous sequences from an automatic pipeline, RNAcmap, as it can provide significantly more homologous sequences than manually annotated Rfam. We demonstrate that the resulting unsupervised, two-dimensional attention maps and one-dimensional embeddings from RNA-MSM contain structural information. In fact, they can be directly mapped with high accuracy to 2D base pairing probabilities and 1D solvent accessibilities, respectively. Further fine-tuning led to significantly improved performance on these two downstream tasks compared with existing state-of-the-art techniques including SPOT-RNA2 and RNAsnap2. By comparison, RNA-FM, a BERT-based RNA language model, performs worse than one-hot encoding with its embedding in base pair and solvent-accessible surface area prediction. We anticipate that the pre-trained RNA-MSM model can be fine-tuned on many other tasks related to RNA structure and function.

Targeting non-coding RNAs: Perspectives and challenges of in-silico approaches

The growing information currently available on the central role of non-coding RNAs (ncRNAs) including microRNAs (miRNAS) and long non-coding RNAs (lncRNAs) for chronic and degenerative human diseases makes them attractive therapeutic targets. RNAs carry out different functional roles in human biology and are deeply deregulated in several diseases. So far, different attempts to therapeutically target the 3D RNA structures with small molecules have been reported. In this scenario, the development of computational tools suitable for describing RNA structures and their potential interactions with small molecules is gaining more and more interest. Here, we describe the most suitable strategies to study ncRNAs through computational tools. We focus on methods capable of predicting 2D and 3D ncRNA structures. Furthermore, we describe computational tools to identify, design and optimize small molecule ncRNA binders. This review aims to outline the state of the art and perspectives of computational methods for ncRNAs over the past decade.

Advancing RNA 3D structure prediction: Exploring hierarchical and hybrid approaches in CASP15

In CASP15, we used an integrated hierarchical and hybrid approach to predict RNA structures. The approach involves three steps. First, with the use of physics-based methods, Vfold2D-MC and VfoldMCPX, we predict the 2D structures from the sequence. Second, we employ template-based methods, Vfold3D and VfoldLA, to build 3D scaffolds for the predicted 2D structures. Third, using the 3D scaffolds as initial structures and the predicted 2D structures as constraints, we predict the 3D structure from coarse-grained molecular dynamics simulations, IsRNA and RNAJP. Our approach was evaluated on 12 RNA targets in CASP15 and ranked second among all the 34 participating teams. The result demonstrated the reliability of our method in predicting RNA 2D structures with high accuracy and RNA 3D structures with moderate accuracy. Further improvements in RNA structure prediction for the next round of CASP may come from the incorporation of the physics-based method with machine learning techniques.

RNA contact prediction by data efficient deep learning

On the path to full understanding of the structure-function relationship or even design of RNA, structure prediction would offer an intriguing complement to experimental efforts. Any deep learning on RNA structure, however, is hampered by the sparsity of labeled training data. Utilizing the limited data available, we here focus on predicting spatial adjacencies ("contact maps") as a proxy for 3D structure. Our model, BARNACLE, combines the utilization of unlabeled data through self-supervised pre-training and efficient use of the sparse labeled data through an XGBoost classifier. BARNACLE shows a considerable improvement over both the established classical baseline and a deep neural network. In order to demonstrate that our approach can be applied to tasks with similar data constraints, we show that our findings generalize to the related setting of accessible surface area prediction.

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.

Modeling the 3D structure and conformational dynamics of very large RNAs using coarse-grained molecular simulations

We describe a computational approach to building and simulating realistic 3D models of very large RNA molecules (>1000 nucleotides) at a resolution of one "bead" per nucleotide. The method starts with a predicted secondary structure and uses several stages of energy minimization and Brownian dynamics (BD) simulation to build 3D models. A key step in the protocol is the temporary addition of a 4 ^th spatial dimension that allows all predicted helical elements to become disentangled from each other in an effectively automated way. We then use the resulting 3D models as input to Brownian dynamics simulations that include hydrodynamic interactions (HIs) that allow the diffusive properties of the RNA to be modelled as well as enabling its conformational dynamics to be simulated. To validate the dynamics part of the method, we first show that when applied to small RNAs with known 3D structures the BD-HI simulation models accurately reproduce their experimental hydrodynamic radii (Rh). We then apply the modelling and simulation protocol to a variety of RNAs for which experimental Rh values have been reported ranging in size from 85 to 3569 nucleotides. We show that the 3D models, when used in BD-HI simulations, produce hydrodynamic radii that are usually in good agreement with experimental estimates for RNAs that do not contain tertiary contacts that persist even under very low salt conditions. Finally, we show that sampling of the conformational dynamics of large RNAs on timescales of 100 µs is computationally feasible with BD-HI simulations.

In silico methods for predicting functional synonymous variants

Single nucleotide variants (SNVs) contribute to human genomic diversity. Synonymous SNVs are previously considered to be "silent," but mounting evidence has revealed that these variants can cause RNA and protein changes and are implicated in over 85 human diseases and cancers. Recent improvements in computational platforms have led to the development of numerous machine-learning tools, which can be used to advance synonymous SNV research. In this review, we discuss tools that should be used to investigate synonymous variants. We provide supportive examples from seminal studies that demonstrate how these tools have driven new discoveries of functional synonymous SNVs.

RNA Folding Based on 5 Beads Model and Multiscale Simulation

RNA folding prediction is very meaningful and challenging. The molecular dynamics simulation (MDS) of all atoms (AA) is limited to the folding of small RNA molecules. At present, most of the practical models are coarse grained (CG) model, and the coarse-grained force field (CGFF) parameters usually depend on known RNA structures. However, the limitation of the CGFF is obvious that it is difficult to study the modified RNA. Based on the 3 beads model (AIMS_RNA_B3), we proposed the AIMS_RNA_B5 model with three beads representing a base and two beads representing the main chain (sugar group and phosphate group). We first run the all atom molecular dynamic simulation (AAMDS), and fit the CGFF parameter with the AA trajectory. Then perform the coarse-grained molecular dynamic simulation (CGMDS). AAMDS is the foundation of CGMDS. CGMDS is mainly to carry out the conformation sampling based on the current AAMDS state and improve the folding speed. We simulated the folding of three RNAs, which belong to hairpin, pseudoknot and tRNA respectively. Compared to the AIMS_RNA_B3 model, the AIMS_RNA_B5 model is more reasonable and performs better.

Machine learning for RNA 2D structure prediction benchmarked on experimental data

Since the 1980s, dozens of computational methods have addressed the problem of predicting RNA secondary structure. Among them are those that follow standard optimization approaches and, more recently, machine learning (ML) algorithms. The former were repeatedly benchmarked on various datasets. The latter, on the other hand, have not yet undergone extensive analysis that could suggest to the user which algorithm best fits the problem to be solved. In this review, we compare 15 methods that predict the secondary structure of RNA, of which 6 are based on deep learning (DL), 3 on shallow learning (SL) and 6 control methods on non-ML approaches. We discuss the ML strategies implemented and perform three experiments in which we evaluate the prediction of (I) representatives of the RNA equivalence classes, (II) selected Rfam sequences and (III) RNAs from new Rfam families. We show that DL-based algorithms (such as SPOT-RNA and UFold) can outperform SL and traditional methods if the data distribution is similar in the training and testing set. However, when predicting 2D structures for new RNA families, the advantage of DL is no longer clear, and its performance is inferior or equal to that of SL and non-ML methods.

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.

Biomotors, viral assembly, and RNA nanobiotechnology: Current achievements and future directions

The International Society of RNA Nanotechnology and Nanomedicine (ISRNN) serves to further the development of a wide variety of functional nucleic acids and other related nanotechnology platforms. To aid in the dissemination of the most recent advancements, a biennial discussion focused on biomotors, viral assembly, and RNA nanobiotechnology has been established where international experts in interdisciplinary fields such as structural biology, biophysical chemistry, nanotechnology, cell and cancer biology, and pharmacology share their latest accomplishments and future perspectives. The results summarized here highlight advancements in our understanding of viral biology and the structure-function relationship of frame-shifting elements in genomic viral RNA, improvements in the predictions of SHAPE analysis of 3D RNA structures, and the understanding of dynamic RNA structures through a variety of experimental and computational means. Additionally, recent advances in the drug delivery, vaccine design, nanopore technologies, biomotor and biomachine development, DNA packaging, RNA nanotechnology, and drug delivery are included in this critical review. We emphasize some of the novel accomplishments, major discussion topics, and present current challenges and perspectives of these emerging fields.

Ribonucleic Acid Folding Prediction Based on Iterative Multiscale Simulation

RNA folding prediction is a challenge. Currently, many RNA folding models are coarse-grained (CG) with the potential derived from the known RNA structures. However, this potential is not suitable for modified and entirely new RNA. It is also not suitable for the folding simulation of RNA in the real cellular environment, including many kinds of molecular interactions. In contrast, our proposed model has the potential to address these issues, which is a multiscale simulation scheme based on all-atom (AA) force fields. We fit the CG force field using the trajectories generated by the AA force field and then iteratively perform molecular dynamics (MD) simulations of the two scales. The all-atom molecular dynamics (AAMD) simulation is mainly responsible for the correction of RNA structure, and the CGMD simulation is mainly responsible for efficient conformational sampling. On the basis of this scheme, we can successfully fold three RNAs belonging to a hairpin, a pseudoknot, and a four-way junction.

Transfer learning: a friendly introduction

Infinite numbers of real-world applications use Machine Learning (ML) techniques to develop potentially the best data available for the users. Transfer learning (TL), one of the categories under ML, has received much attention from the research communities in the past few years. Traditional ML algorithms perform under the assumption that a model uses limited data distribution to train and test samples. These conventional methods predict target tasks undemanding and are applied to small data distribution. However, this issue conceivably is resolved using TL. TL is acknowledged for its connectivity among the additional testing and training samples resulting in faster output with efficient results. This paper contributes to the domain and scope of TL, citing situational use based on their periods and a few of its applications. The paper provides an in-depth focus on the techniques; Inductive TL, Transductive TL, Unsupervised TL, which consists of sample selection, and domain adaptation, followed by contributions and future directions.

Transfer learning: a friendly introduction

Infinite numbers of real-world applications use Machine Learning (ML) techniques to develop potentially the best data available for the users. Transfer learning (TL), one of the categories under ML, has received much attention from the research communities in the past few years. Traditional ML algorithms perform under the assumption that a model uses limited data distribution to train and test samples. These conventional methods predict target tasks undemanding and are applied to small data distribution. However, this issue conceivably is resolved using TL. TL is acknowledged for its connectivity among the additional testing and training samples resulting in faster output with efficient results. This paper contributes to the domain and scope of TL, citing situational use based on their periods and a few of its applications. The paper provides an in-depth focus on the techniques; Inductive TL, Transductive TL, Unsupervised TL, which consists of sample selection, and domain adaptation, followed by contributions and future directions.

Predicting RNA solvent accessibility from multi-scale context feature via multi-shot neural network

Knowledge of RNA solvent accessibility has recently become attractive due to the increasing awareness of its importance for key biological process. Accurately predicting the solvent accessibility of RNA is crucial for understanding its 3D structure and biological function. In this study, we develop a novel computational method, termed M²pred, for accurately predicting the solvent accessibility of RNA from sequence-based multi-scale context feature. In M²pred, three single-view features, i.e., base-pairing probabilities, position-specific frequency matrix, and a binary one-hot encoding, are first generated as three feature sources, and immediately concatenated to engender a super feature. Secondly, for the super feature, the matrix-format features of each nucleotide are extracted using an initialized sliding window technique, and regularly stacked into a cube-format feature. Then, using multi-scale context feature extraction strategy, a pyramid feature constructed of contextual feature of four scales related to target nucleotides is extracted from the cube-format feature. Finally, a customized multi-shot neural network framework, which is equipped with four different scales of receptive fields mainly integrating several residual attention blocks, is designed to dig discrimination information from the contextual pyramid feature. Experimental results demonstrate that the proposed M²pred achieve a high prediction performance and outperforms existing state-of-the-art prediction methods of RNA solvent accessibility.

Inverse folding based pre-training for the reliable identification of intrinsic transcription terminators

It is well-established that neural networks can predict or identify structural motifs of non-coding RNAs (ncRNAs). Yet, the neural network based identification of RNA structural motifs is limited by the availability of training data that are often insufficient for learning features of specific ncRNA families or structural motifs. Aiming to reliably identify intrinsic transcription terminators in bacteria, we introduce a novel pre-training approach that uses inverse folding to generate training data for predicting or identifying a specific family or structural motif of ncRNA. We assess the ability of neural networks to identify secondary structure by systematic in silico mutagenesis experiments. In a study to identify intrinsic transcription terminators as functionally well-understood RNA structural motifs, our inverse folding based pre-training approach significantly boosts the performance of neural network topologies, which outperform previous approaches to identify intrinsic transcription terminators. Inverse-folding based pre-training provides a simple, yet highly effective way to integrate the well-established thermodynamic energy model into deep neural networks for identifying ncRNA families or motifs. The pre-training technique is broadly applicable to a range of network topologies as well as different types of ncRNA families and motifs.

Intrinsic transcriptional terminators are essential regulators in determining the 3’ end of transcripts in bacteria. The underlying mechanism involves RNA secondary structure, where nucleotides fold into a specific hairpin motif. Identifying terminator sequences in bacterial genomes has conventionally been approached with well-established energy models for structural motifs. However, the folding mechanism of transcription terminators is understood only partially, limiting the success of energy-model based identification.

Neural networks have been proposed to overcome these limitations. However, their adoption for predicting and identifying RNA secondary structure has been a double edged sword: Neural networks promise to learn features that are not represented by the energy models, while they are black boxes that lack explicit modeling assumptions and may fail to account for features that are well understandable based on decades-old energy models.

Here, we introduce a pre-training approach for neural networks that uses energy-model based inverse folding of structural motifs. As we demonstrate, this approach “brings back the energy model” to identify transcriptional terminators and overcomes the limitations of previous energy-model based predictions. Our approach works for diverse types of neural networks, and is suitable for the identification of structural motifs of many other RNA molecules beyond transcriptional terminators.

Recent advances in RNA structurome

RNA structures are essential to support RNA functions and regulation in various biological processes. Recently, a range of novel technologies have been developed to decode genome-wide RNA structures and novel modes of functionality across a wide range of species. In this review, we summarize key strategies for probing the RNA structurome and discuss the pros and cons of representative technologies. In particular, these new technologies have been applied to dissect the structural landscape of the SARS-CoV-2 RNA genome. We also summarize the functionalities of RNA structures discovered in different regulatory layers-including RNA processing, transport, localization, and mRNA translation-across viruses, bacteria, animals, and plants. We review many versatile RNA structural elements in the context of different physiological and pathological processes (e.g., cell differentiation, stress response, and viral replication). Finally, we discuss future prospects for RNA structural studies to map the RNA structurome at higher resolution and at the single-molecule and single-cell level, and to decipher novel modes of RNA structures and functions for innovative applications.

Predicting RNA distance-based contact maps by integrated deep learning on physics-inferred secondary structure and evolutionary-derived mutational coupling

MOTIVATION

Recently, AlphaFold2 achieved high experimental accuracy for the majority of proteins in Critical Assessment of Structure Prediction (CASP 14). This raises the hope that one day, we may achieve the same feat for RNA structure prediction for those structured RNAs, which is as fundamentally and practically important similar to protein structure prediction. One major factor in the recent advancement of protein structure prediction is the highly accurate prediction of distance-based contact maps of proteins.

RESULTS

Here, we showed that by integrated deep learning with physics-inferred secondary structures, co-evolutionary information and multiple sequence-alignment sampling, we can achieve RNA contact-map prediction at a level of accuracy similar to that in protein contact-map prediction. More importantly, highly accurate prediction for top L long-range contacts can be assured for those RNAs with a high effective number of homologous sequences (Neff > 50). The initial use of the predicted contact map as distance-based restraints confirmed its usefulness in 3D structure prediction.

AVAILABILITY AND IMPLEMENTATION

SPOT-RNA-2D is available as a web server at https://sparks-lab.org/server/spot-rna-2d/ and as a standalone program at https://github.com/jaswindersingh2/SPOT-RNA-2D.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Secondary structure prediction of long noncoding RNA: review and experimental comparison of existing approaches

MOTIVATION

In contrast to messenger RNAs, the function of the wide range of existing long noncoding RNAs (lncRNAs) largely depends on their structure, which determines interactions with partner molecules. Thus, the determination or prediction of the secondary structure of lncRNAs is critical to uncover their function. Classical approaches for predicting RNA secondary structure have been based on dynamic programming and thermodynamic calculations. In the last 4 years, a growing number of machine learning (ML)-based models, including deep learning (DL), have achieved breakthrough performance in structure prediction of biomolecules such as proteins and have outperformed classical methods in short transcripts folding. Nevertheless, the accurate prediction for lncRNA still remains far from being effectively solved. Notably, the myriad of new proposals has not been systematically and experimentally evaluated.

RESULTS

In this work, we compare the performance of the classical methods as well as the most recently proposed approaches for secondary structure prediction of RNA sequences using a unified and consistent experimental setup. We use the publicly available structural profiles for 3023 yeast RNA sequences, and a novel benchmark of well-characterized lncRNA structures from different species. Moreover, we propose a novel metric to assess the predictive performance of methods, exclusively based on the chemical probing data commonly used for profiling RNA structures, avoiding any potential bias incorporated by computational predictions when using dot-bracket references. Our results provide a comprehensive comparative assessment of existing methodologies, and a novel and public benchmark resource to aid in the development and comparison of future approaches.

AVAILABILITY

Full source code and benchmark datasets are available at: https://github.com/sinc-lab/lncRNA-folding.

CONTACT

lbugnon@sinc.unl.edu.ar.

Probing RNA structures and functions by solvent accessibility: an overview from experimental and computational perspectives

Characterizing RNA structures and functions have mostly been focused on 2D, secondary and 3D, tertiary structures. Recent advances in experimental and computational techniques for probing or predicting RNA solvent accessibility make this 1D representation of tertiary structures an increasingly attractive feature to explore. Here, we provide a survey of these recent developments, which indicate the emergence of solvent accessibility as a simple 1D property, adding to secondary and tertiary structures for investigating complex structure–function relations of RNAs.

ToxIBTL: prediction of peptide toxicity based on information bottleneck and transfer learning

MOTIVATION

Recently, peptides have emerged as a promising class of pharmaceuticals for various diseases treatment poised between traditional small molecule drugs and therapeutic proteins. However, one of the key bottlenecks preventing them from therapeutic peptides is their toxicity toward human cells, and few available algorithms for predicting toxicity are specially designed for short-length peptides.

RESULTS

We present ToxIBTL, a novel deep learning framework by utilizing the information bottleneck principle and transfer learning to predict the toxicity of peptides as well as proteins. Specifically, we use evolutionary information and physicochemical properties of peptide sequences and integrate the information bottleneck principle into a feature representation learning scheme, by which relevant information is retained and the redundant information is minimized in the obtained features. Moreover, transfer learning is introduced to transfer the common knowledge contained in proteins to peptides, which aims to improve the feature representation capability. Extensive experimental results demonstrate that ToxIBTL not only achieves a higher prediction performance than state-of-the-art methods on the peptide dataset, but also has a competitive performance on the protein dataset. Furthermore, a user-friendly online web server is established as the implementation of the proposed ToxIBTL.

AVAILABILITY AND IMPLEMENTATION

The proposed ToxIBTL and data can be freely accessible at http://server.wei-group.net/ToxIBTL. Our source code is available at https://github.com/WLYLab/ToxIBTL.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

SPOT-Contact-LM: improving single-sequence-based prediction of protein contact map using a transformer language model

MOTIVATION

Accurate prediction of protein contact-map is essential for accurate protein structure and function prediction. As a result, many methods have been developed for protein contact map prediction. However, most methods rely on protein-sequence-evolutionary information, which may not exist for many proteins due to lack of naturally occurring homologous sequences. Moreover, generating evolutionary profiles is computationally intensive. Here, we developed a contact-map predictor utilizing the output of a pre-trained language model ESM-1b as an input along with a large training set and an ensemble of residual neural networks.

RESULTS

We showed that the proposed method makes a significant improvement over a single-sequence-based predictor SSCpred with 15% improvement in the F1-score for the independent CASP14-FM test set. It also outperforms evolutionary-profile-based methods trRosetta and SPOT-Contact with 48.7% and 48.5% respective improvement in the F1-score on the proteins without homologs (Neff = 1) in the independent SPOT-2018 set. The new method provides a much faster and reasonably accurate alternative to evolution-based methods, useful for large-scale prediction.

AVAILABILITY AND IMPLEMENTATION

Stand-alone-version of SPOT-Contact-LM is available at https://github.com/jas-preet/SPOT-Contact-Single. Direct prediction can also be made at https://sparks-lab.org/server/spot-contact-single. The datasets used in this research can also be downloaded from the GitHub.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

UFold: fast and accurate RNA secondary structure prediction with deep learning

For many RNA molecules, the secondary structure is essential for the correct function of the RNA. Predicting RNA secondary structure from nucleotide sequences is a long-standing problem in genomics, but the prediction performance has reached a plateau over time. Traditional RNA secondary structure prediction algorithms are primarily based on thermodynamic models through free energy minimization, which imposes strong prior assumptions and is slow to run. Here, we propose a deep learning-based method, called UFold, for RNA secondary structure prediction, trained directly on annotated data and base-pairing rules. UFold proposes a novel image-like representation of RNA sequences, which can be efficiently processed by Fully Convolutional Networks (FCNs). We benchmark the performance of UFold on both within- and cross-family RNA datasets. It significantly outperforms previous methods on within-family datasets, while achieving a similar performance as the traditional methods when trained and tested on distinct RNA families. UFold is also able to predict pseudoknots accurately. Its prediction is fast with an inference time of about 160 ms per sequence up to 1500 bp in length. An online web server running UFold is available at https://ufold.ics.uci.edu. Code is available at https://github.com/uci-cbcl/UFold.

Review of machine learning methods for RNA secondary structure prediction

Secondary structure plays an important role in determining the function of noncoding RNAs. Hence, identifying RNA secondary structures is of great value to research. Computational prediction is a mainstream approach for predicting RNA secondary structure. Unfortunately, even though new methods have been proposed over the past 40 years, the performance of computational prediction methods has stagnated in the last decade. Recently, with the increasing availability of RNA structure data, new methods based on machine learning (ML) technologies, especially deep learning, have alleviated the issue. In this review, we provide a comprehensive overview of RNA secondary structure prediction methods based on ML technologies and a tabularized summary of the most important methods in this field. The current pending challenges in the field of RNA secondary structure prediction and future trends are also discussed.

RNA Backbone Torsion and Pseudotorsion Angle Prediction Using Dilated Convolutional Neural Networks

RNA three-dimensional structure prediction has been relied on using a predicted or experimentally determined secondary structure as a restraint to reduce the conformational sampling space. However, the secondary-structure restraints are limited to paired bases, and the conformational space of the ribose-phosphate backbone is still too large to be sampled efficiently. Here, we employed the dilated convolutional neural network to predict backbone torsion and pseudotorsion angles using a single RNA sequence as input. The method called SPOT-RNA-1D was trained on a high-resolution training data set and tested on three independent, nonredundant, and high-resolution test sets. The proposed method yields substantially smaller mean absolute errors than the baseline predictors based on random predictions and based on helix conformations according to actual angle distributions. The mean absolute errors for three test sets range from 14°-44° for different angles, compared to 17°-62° by random prediction and 14°-58° by helix prediction. The method also accurately recovers the overall patterns of single or pairwise angle distributions. In general, torsion angles further away from the bases and associated with unpaired bases and paired bases involved in tertiary interactions are more difficult to predict. Compared to the best models in RNA-puzzles experiments, SPOT-RNA-1D yielded more accurate dihedral angles and, thus, are potentially useful as model quality indicators and restraints for RNA structure prediction as in protein structure prediction.

RNAcmap: A Fully Automatic Pipeline for Predicting Contact Maps of RNAs by Evolutionary Coupling Analysis

MOTIVATION

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.

RESULTS

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.

AVAILABILITY

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.

Pairing a high-resolution statistical potential with a nucleobase-centric sampling algorithm for improving RNA model refinement

Refining modelled structures to approach experimental accuracy is one of the most challenging problems in molecular biology. Despite many years’ efforts, the progress in protein or RNA structure refinement has been slow because the global minimum given by the energy scores is not at the experimentally determined “native” structure. Here, we propose a fully knowledge-based energy function that captures the full orientation dependence of base–base, base–oxygen and oxygen–oxygen interactions with the RNA backbone modelled by rotameric states and internal energies. A total of 4000 quantum-mechanical calculations were performed to reweight base–base statistical potentials for minimizing possible effects of indirect interactions. The resulting BRiQ knowledge-based potential, equipped with a nucleobase-centric sampling algorithm, provides a robust improvement in refining near-native RNA models generated by a wide variety of modelling techniques.

Predicting RNA structure from sequence is challenging due to the relative sparsity of experimentally-determined RNA 3D structures for model training. Here, the authors propose a way to incorporate knowledge on interactions at the atomic and base–base level to refine the prediction of RNA structures.