DMfold: A Novel Method to Predict RNA Secondary Structure With Pseudoknots Based on Deep Learning and Improved Base Pair Maximization Principle

Knotify_V2.0: Deciphering RNA Secondary Structures with H-Type Pseudoknots and Hairpin Loops

Accurately predicting the pairing order of bases in RNA molecules is essential for anticipating RNA secondary structures. Consequently, this task holds significant importance in unveiling previously unknown biological processes. The urgent need to comprehend RNA structures has been accentuated by the unprecedented impact of the widespread COVID-19 pandemic. This paper presents a framework, Knotify_V2.0, which makes use of syntactic pattern recognition techniques in order to predict RNA structures, with a specific emphasis on tackling the demanding task of predicting H-type pseudoknots that encompass bulges and hairpins. By leveraging the expressive capabilities of a Context-Free Grammar (CFG), the suggested framework integrates the inherent benefits of CFG and makes use of minimum free energy and maximum base pairing criteria. This integration enables the effective management of this inherently ambiguous task. The main contribution of Knotify_V2.0 compared to earlier versions lies in its capacity to identify additional motifs like bulges and hairpins within the internal loops of the pseudoknot. Notably, the proposed methodology, Knotify_V2.0, demonstrates superior accuracy in predicting core stems compared to state-of-the-art frameworks. Knotify_V2.0 exhibited exceptional performance by accurately identifying both core base pairing that form the ground truth pseudoknot in 70% of the examined sequences. Furthermore, Knotify_V2.0 narrowed the performance gap with Knotty, which had demonstrated better performance than Knotify and even surpassed it in Recall and F1-score metrics. Knotify_V2.0 achieved a higher count of true positives (tp) and a significantly lower count of false negatives (fn) compared to Knotify, highlighting improvements in Prediction and Recall metrics, respectively. Consequently, Knotify_V2.0 achieved a higher F1-score than any other platform. The source code and comprehensive implementation details of Knotify_V2.0 are publicly available on GitHub.

GERWR: Identifying the Key Pathogenicity- Associated sRNAs of Magnaporthe Oryzae Infection in Rice Based on Graph Embedding and Random Walk With Restart

Rice blast, caused by Magnaporthe oryzae(M.oryzae), is a destructive rice disease that reduces rice yield by 10% to 30% annually. It also affects other cereal crops such as barley, wheat, rye, millet, sorghum, and maize. Small RNAs (sRNAs) play an essential regulatory role in fungus-plant interaction during the fungal invasion, but studies on pathogenic sRNAs during the fungal invasion of plants based on multi-omics data integration are rare. This paper proposes a novel approach called Graph Embedding combined with Random Walk with Restart (GERWR) to identify pathogenic sRNAs based on multi-omics data integration during M.oryzae invasion. By constructing a multi-omics network (MRMO), we identified 29 pathogenic sRNAs of rice blast fungus. Further analysis revealed that these sRNAs regulate rice genes in a many-to-many relationship, playing a significant regulatory role in the pathogenesis of rice blast disease. This paper explores the pathogenic factors of rice blast disease from the perspective of multi-omics data analysis, revealing the inherent connection between pathogenic factors of different omics. It has essential scientific significance for studying the pathogenic mechanism of rice blast fungus, the rice blast fungus-rice model system, and the pathogen-host interaction in related fields.

Graph Convolutional Network for predicting secondary structure of RNA

The prediction of RNA secondary structures is essential for understanding its underlying principles and applications in diverse fields, including molecular diagnostics and RNA-based therapeutic strategies. However, the complexity of the search space presents a challenge. This work proposes a Graph Convolutional Network (GCNfold) for predicting the RNA secondary structure. GCNfold considers an RNA sequence as graph-structured data and predicts posterior base-pairing probabilities given the prior base-pairing probabilities, calculated using McCaskill's partition function. The performance of GCNfold surpasses that of the state-of-the-art folding algorithms, as we have incorporated minimum free energy information into the richly parameterized network, enhancing its robustness in predicting non-homologous RNA secondary structures. A Symmetric Argmax Post-processing algorithm ensures that GCNfold formulates valid structures. To validate our algorithm, we applied it to the SARS-CoV-2 E gene and determined the secondary structure of the E-gene across the Betacoronavirus subgenera.

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.

Efficient Prediction Model of mRNA End-to-End Distance and Conformation: Three-Dimensional RNA Illustration Program (TRIP)

The secondary and tertiary structures of RNA play a vital role in the regulation of biological reactions. These structures have been experimentally studied through in vivo and in vitro analyses, and in silico models have become increasingly accurate in predicting them. Recent technologies have diversified RNA structure predictions, from the earliest thermodynamic and molecular dynamic-based RNA structure predictions to deep learning-based conformation predictions in the past decade. While most research on RNA structure prediction has focused on short non-coding RNAs, there has been limited research on predicting the conformation of longer mRNAs. Our study introduces a computer simulation model called the Three-dimensional RNA Illustration Program (TRIP). TRIP is based on single-chain models and angle restriction of each bead component from previously reported single-molecule fluorescence in situ hybridization (smFISH) experiments. TRIP is a fast and efficient application that only requires up to three inputs to acquire outputs. It can also provide a rough visualization of the 3D conformation of RNA, making it a valuable tool for predicting RNA end-to-end distance.

Automatic recognition of complementary strands: lessons regarding machine learning abilities in RNA folding

Introduction: Prediction of RNA secondary structure from single sequences still needs substantial improvements. The application of machine learning (ML) to this problem has become increasingly popular. However, ML algorithms are prone to overfitting, limiting the ability to learn more about the inherent mechanisms governing RNA folding. It is natural to use high-capacity models when solving such a difficult task, but poor generalization is expected when too few examples are available. Methods: Here, we report the relation between capacity and performance on a fundamental related problem: determining whether two sequences are fully complementary. Our analysis focused on the impact of model architecture and capacity as well as dataset size and nature on classification accuracy. Results: We observed that low-capacity models are better suited for learning with mislabelled training examples, while large capacities improve the ability to generalize to structurally dissimilar data. It turns out that neural networks struggle to grasp the fundamental concept of base complementarity, especially in lengthwise extrapolation context. Discussion: Given a more complex task like RNA folding, it comes as no surprise that the scarcity of useable examples hurdles the applicability of machine learning techniques to this field.

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.

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.

Sequence similarity governs generalizability of de novo deep learning models for RNA secondary structure prediction

Making no use of physical laws or co-evolutionary information, de novo deep learning (DL) models for RNA secondary structure prediction have achieved far superior performances than traditional algorithms. However, their statistical underpinning raises the crucial question of generalizability. We present a quantitative study of the performance and generalizability of a series of de novo DL models, with a minimal two-module architecture and no post-processing, under varied similarities between seen and unseen sequences. Our models demonstrate excellent expressive capacities and outperform existing methods on common benchmark datasets. However, model generalizability, i.e., the performance gap between the seen and unseen sets, degrades rapidly as the sequence similarity decreases. The same trends are observed from several recent DL and machine learning models. And an inverse correlation between performance and generalizability is revealed collectively across all learning-based models with wide-ranging architectures and sizes. We further quantitate how generalizability depends on sequence and structure identity scores via pairwise alignment, providing unique quantitative insights into the limitations of statistical learning. Generalizability thus poses a major hurdle for deploying de novo DL models in practice and various pathways for future advances are discussed.

cRNAsp12 Web Server for the Prediction of Circular RNA Secondary Structures and Stabilities

Circular RNAs (circRNAs) are a novel class of non-coding RNA that, unlike linear RNAs, form a covalently closed loop without the 5' and 3' ends. Growing evidence shows that circular RNAs play important roles in life processes and have great potential implications in clinical and research fields. The accurate modeling of circRNAs structure and stability has far-reaching impact on our understanding of their functions and our ability to develop RNA-based therapeutics. The cRNAsp12 server offers a user-friendly web interface to predict circular RNA secondary structures and folding stabilities from the sequence. Through the helix-based landscape partitioning strategy, the server generates distinct ensembles of structures and predicts the minimal free energy structures for each ensemble with the recursive partition function calculation and backtracking algorithms. For structure predictions in the limited structural ensemble, the server also provides users with the option to set the structural constraints of forcing the base pairs and/or forcing the unpaired bases, such that only structures that meet the criteria are enumerated recursively.

Knotify+: Toward the Prediction of RNA H-Type Pseudoknots, Including Bulges and Internal Loops

The accurate "base pairing" in RNA molecules, which leads to the prediction of RNA secondary structures, is crucial in order to explain unknown biological operations. Recently, COVID-19, a widespread disease, has caused many deaths, affecting humanity in an unprecedented way. SARS-CoV-2, a single-stranded RNA virus, has shown the significance of analyzing these molecules and their structures. This paper aims to create a pioneering framework in the direction of predicting specific RNA structures, leveraging syntactic pattern recognition. The proposed framework, Knotify+, addresses the problem of predicting H-type pseudoknots, including bulges and internal loops, by featuring the power of context-free grammar (CFG). We combine the grammar's advantages with maximum base pairing and minimum free energy to tackle this ambiguous task in a performant way. Specifically, our proposed methodology, Knotify+, outperforms state-of-the-art frameworks with regards to its accuracy in core stems prediction. Additionally, it performs more accurately in small sequences and presents a comparable accuracy rate in larger ones, while it requires a smaller execution time compared to well-known platforms. The Knotify+ source code and implementation details are available as a public repository on GitHub.

Implementing computational methods in tandem with synonymous gene recoding for therapeutic development

Synonymous gene recoding, the substitution of synonymous variants into the genetic sequence, has been used to overcome many production limitations in therapeutic development. However, the safety and efficacy of recoded therapeutics can be difficult to evaluate because synonymous codon substitutions can result in subtle, yet impactful changes in protein features and require sensitive methods for detection. Given that computational approaches have made significant leaps in recent years, we propose that machine-learning (ML) tools may be leveraged to assess gene-recoded therapeutics and foresee an opportunity to adapt codon contexts to enhance some powerful existing tools. Here, we examine how synonymous gene recoding has been used to address challenges in therapeutic development, explain the biological mechanisms underlying its effects, and explore the application of computational platforms to improve the surveillance of functional variants in therapeutic design.

High-throughput biochemistry in RNA sequence space: predicting structure and function

RNAs are central to fundamental biological processes in all known organisms. The set of possible intramolecular interactions of RNA nucleotides defines the range of alternative structural conformations of a specific RNA that can coexist, and these structures enable functional catalytic properties of RNAs and/or their productive intermolecular interactions with other RNAs or proteins. However, the immense combinatorial space of potential RNA sequences has precluded predictive mapping between RNA sequence and molecular structure and function. Recent advances in high-throughput approaches in vitro have enabled quantitative thermodynamic and kinetic measurements of RNA-RNA and RNA-protein interactions, across hundreds of thousands of sequence variations. In this Review, we explore these techniques, how they can be used to understand RNA function and how they might form the foundations of an accurate model to predict the structure and function of an RNA directly from its nucleotide sequence. The experimental techniques and modelling frameworks discussed here are also highly relevant for the sampling of sequence-structure-function space of DNAs and proteins.

Non-coding RNAs in human health and disease: potential function as biomarkers and therapeutic targets

Human diseases have been a critical threat from the beginning of human history. Knowing the origin, course of action and treatment of any disease state is essential. A microscopic approach to the molecular field is a more coherent and accurate way to explore the mechanism, progression, and therapy with the introduction and evolution of technology than a macroscopic approach. Non-coding RNAs (ncRNAs) play increasingly important roles in detecting, developing, and treating all abnormalities related to physiology, pathology, genetics, epigenetics, cancer, and developmental diseases. Noncoding RNAs are becoming increasingly crucial as powerful, multipurpose regulators of all biological processes. Parallel to this, a rising amount of scientific information has revealed links between abnormal noncoding RNA expression and human disorders. Numerous non-coding transcripts with unknown functions have been found in addition to advancements in RNA-sequencing methods. Non-coding linear RNAs come in a variety of forms, including circular RNAs with a continuous closed loop (circRNA), long non-coding RNAs (lncRNA), and microRNAs (miRNA). This comprises specific information on their biogenesis, mode of action, physiological function, and significance concerning disease (such as cancer or cardiovascular diseases and others). This study review focuses on non-coding RNA as specific biomarkers and novel therapeutic targets.

Examples of Structural Motifs in Viral Genomes and Approaches for RNA Structure Characterization

The relationship between conserved structural motifs and their biological function in the virus replication cycle is the interest of many researchers around the world. RNA structure is closely related to RNA function. Therefore, technological progress in high-throughput approaches for RNA structure analysis and the development of new ones are very important. In this mini review, we discuss a few perspectives on the structural elements of viral genomes and some methods used for RNA structure prediction and characterization. Based on the recent literature, we describe several examples of studies concerning the viral genomes, especially severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and influenza A virus (IAV). Herein, we emphasize that a better understanding of viral genome architecture allows for the discovery of the structure-function relationship, and as a result, the discovery of new potential antiviral therapeutics.

Predicting RNA secondary structure by a neural network: what features may be learned?

Deep learning is a class of machine learning techniques capable of creating internal representation of data without explicit preprogramming. Hence, in addition to practical applications, it is of interest to analyze what features of biological data may be learned by such models. Here, we describe PredPair, a deep learning neural network trained to predict base pairs in RNA structure from sequence alone, without any incorporated prior knowledge, such as the stacking energies or possible spatial structures. PredPair learned the Watson-Crick and wobble base-pairing rules and created an internal representation of the stacking energies and helices. Application to independent experimental (DMS-Seq) data on nucleotide accessibility in mRNA showed that the nucleotides predicted as paired indeed tend to be involved in the RNA structure. The performance of the constructed model was comparable with the state-of-the-art method based on the thermodynamic approach, but with a higher false positives rate. On the other hand, it successfully predicted pseudoknots. t-SNE clusters of embeddings of RNA sequences created by PredPair tend to contain embeddings from particular Rfam families, supporting the predictions of PredPair being in line with biological classification.

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.

Advances and opportunities in RNA structure experimental determination and computational modeling

Beyond transferring genetic information, RNAs are molecules with diverse functions that include catalyzing biochemical reactions and regulating gene expression. Most of these activities depend on RNAs' specific structures. Therefore, accurately determining RNA structure is integral to advancing our understanding of RNA functions. Here, we summarize the state-of-the-art experimental and computational technologies developed to evaluate RNA secondary and tertiary structures. We also highlight how the rapid increase of experimental data facilitates the integrative modeling approaches for better resolving RNA structures. Finally, we provide our thoughts on the latest advances and challenges in RNA structure determination methods, as well as on future directions for both experimental approaches and artificial intelligence-based computational tools to model RNA structure. Ultimately, we hope the technological advances will deepen our understanding of RNA biology and facilitate RNA structure-based biomedical research such as designing specific RNA structures for therapeutics and deploying RNA-targeting small-molecule drugs.

Deep learning models for RNA secondary structure prediction (probably) do not generalize across families

MOTIVATION

The secondary structure of RNA is of importance to its function. Over the last few years, several papers attempted to use machine learning to improve de novo RNA secondary structure prediction. Many of these papers report impressive results for intra-family predictions but seldom address the much more difficult (and practical) inter-family problem.

RESULTS

We demonstrate that it is nearly trivial with convolutional neural networks to generate pseudo-free energy changes, modelled after structure mapping data that improve the accuracy of structure prediction for intra-family cases. We propose a more rigorous method for inter-family cross-validation that can be used to assess the performance of learning-based models. Using this method, we further demonstrate that intra-family performance is insufficient proof of generalization despite the widespread assumption in the literature and provide strong evidence that many existing learning-based models have not generalized inter-family.

AVAILABILITY AND IMPLEMENTATION

Source code and data are available at https://github.com/marcellszi/dl-rna.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Deep Learning in RNA Structure Studies

Deep learning, or artificial neural networks, is a type of machine learning algorithm that can decipher underlying relationships from large volumes of data and has been successfully applied to solve structural biology questions, such as RNA structure. RNA can fold into complex RNA structures by forming hydrogen bonds, thereby playing an essential role in biological processes. While experimental effort has enabled resolving RNA structure at the genome-wide scale, deep learning has been more recently introduced for studying RNA structure and its functionality. Here, we discuss successful applications of deep learning to solve RNA problems, including predictions of RNA structures, non-canonical G-quadruplex, RNA-protein interactions and RNA switches. Following these cases, we give a general guide to deep learning for solving RNA structure problems.

Rapid and accurate identification of ribosomal RNA sequences via deep learning

Advances in transcriptomic and translatomic techniques enable in-depth studies of RNA activity profiles and RNA-based regulatory mechanisms. Ribosomal RNA (rRNA) sequences are highly abundant among cellular RNA, but if the target sequences do not include polyadenylation, these cannot be easily removed in library preparation, requiring their post-hoc removal with computational techniques to accelerate and improve downstream analyses. Here, we describe RiboDetector, a novel software based on a Bi-directional Long Short-Term Memory (BiLSTM) neural network, which rapidly and accurately identifies rRNA reads from transcriptomic, metagenomic, metatranscriptomic, noncoding RNA, and ribosome profiling sequence data. Compared with state-of-the-art approaches, RiboDetector produced at least six times fewer misclassifications on the benchmark datasets. Importantly, the few false positives of RiboDetector were not enriched in certain Gene Ontology (GO) terms, suggesting a low bias for downstream functional profiling. RiboDetector also demonstrated a remarkable generalizability for detecting novel rRNA sequences that are divergent from the training data with sequence identities of <90%. On a personal computer, RiboDetector processed 40M reads in less than 6 min, which was ∼50 times faster in GPU mode and ∼15 times in CPU mode than other methods. RiboDetector is available under a GPL v3.0 license at https://github.com/hzi-bifo/RiboDetector.

Length-Dependent Deep Learning Model for RNA Secondary Structure Prediction

Deep learning methods for RNA secondary structure prediction have shown higher performance than traditional methods, but there is still much room to improve. It is known that the lengths of RNAs are very different, as are their secondary structures. However, the current deep learning methods all use length-independent models, so it is difficult for these models to learn very different secondary structures. Here, we propose a length-dependent model that is obtained by further training the length-independent model for different length ranges of RNAs through transfer learning. 2dRNA, a coupled deep learning neural network for RNA secondary structure prediction, is used to do this. Benchmarking shows that the length-dependent model performs better than the usual length-independent model.

Knotify: An Efficient Parallel Platform for RNA Pseudoknot Prediction Using Syntactic Pattern Recognition

Obtaining valuable clues for noncoding RNA (ribonucleic acid) subsequences remains a significant challenge, acknowledging that most of the human genome transcribes into noncoding RNA parts related to unknown biological operations. Capturing these clues relies on accurate “base pairing” prediction, also known as “RNA secondary structure prediction”. As COVID-19 is considered a severe global threat, the single-stranded SARS-CoV-2 virus reveals the importance of establishing an efficient RNA analysis toolkit. This work aimed to contribute to that by introducing a novel system committed to predicting RNA secondary structure patterns (i.e., RNA’s pseudoknots) that leverage syntactic pattern-recognition strategies. Having focused on the pseudoknot predictions, we formalized the secondary structure prediction of the RNA to be primarily a parsing and, secondly, an optimization problem. The proposed methodology addresses the problem of predicting pseudoknots of the first order (H-type). We introduce a context-free grammar (CFG) that affords enough expression power to recognize potential pseudoknot pattern. In addition, an alternative methodology of detecting possible pseudoknots is also implemented as well, using a brute-force algorithm. Any input sequence may highlight multiple potential folding patterns requiring a strict methodology to determine the single biologically realistic one. We conscripted a novel heuristic over the widely accepted notion of free-energy minimization to tackle such ambiguity in a performant way by utilizing each pattern’s context to unveil the most prominent pseudoknot pattern. The overall process features polynomial-time complexity, while its parallel implementation enhances the end performance, as proportional to the deployed hardware. The proposed methodology does succeed in predicting the core stems of any RNA pseudoknot of the test dataset by performing a 76.4% recall ratio. The methodology achieved a F1-score equal to 0.774 and MCC equal 0.543 in discovering all the stems of an RNA sequence, outperforming the particular task. Measurements were taken using a dataset of 262 RNA sequences establishing a performance speed of 1.31, 3.45, and 7.76 compared to three well-known platforms. The implementation source code is publicly available under knotify github repo.

Computer-aided comprehensive explorations of RNA structural polymorphism through complementary simulation methods

While RNA folding was originally seen as a simple problem to solve, it has been shown that the promiscuous interactions of the nucleobases result in structural polymorphism, with several competing structures generally observed for non-coding RNA. This inherent complexity limits our understanding of these molecules from experiments alone, and computational methods are commonly used to study RNA. Here, we discuss three advanced sampling schemes, namely Hamiltonian-replica exchange molecular dynamics (MD), ratchet-and-pawl MD and discrete path sampling, as well as the HiRE-RNA coarse-graining scheme, and highlight how these approaches are complementary with reference to recent case studies. While all computational methods have their shortcomings, the plurality of simulation methods leads to a better understanding of experimental findings and can inform and guide experimental work on RNA polymorphism.

RNA Structure Prediction, Analysis, and Design: An Introduction to Web-Based Tools

Understanding RNA structure has become critical in the study of RNA in their roles as mediators of biological processes. To aid in these studies, computational algorithms that utilize thermodynamics have been developed to predict RNA secondary structure. Due to the importance of intermolecular interactions, the algorithms have been expanded to determine and predict RNA-RNA hybridization. This chapter discusses popular webservers with the tools for RNA secondary structure prediction, RNA-RNA hybridization, and design. We address key features that distinguish common-functioning programs and their purposes for the interests of the user. Ultimately, we hope this review elucidates web-based tools researchers may take advantage of in their investigations of RNA structure and function.

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.

Decoding LncRNAs

Non-coding RNAs (ncRNAs) have been considered as unimportant additions to the transcriptome. Yet, in light of numerous studies, it has become clear that ncRNAs play important roles in development, health and disease. Long-ignored, long non-coding RNAs (lncRNAs), ncRNAs made of more than 200 nucleotides have gained attention due to their involvement as drivers or suppressors of a myriad of tumours. The detailed understanding of some of their functions, structures and interactomes has been the result of interdisciplinary efforts, as in many cases, new methods need to be created or adapted to characterise these molecules. Unlike most reviews on lncRNAs, we summarize the achievements on lncRNA studies by taking into consideration the approaches for identification of lncRNA functions, interactomes, and structural arrangements. We also provide information about the recent data on the involvement of lncRNAs in diseases and present applications of these molecules, especially in medicine.

ncRFP: A Novel end-to-end Method for Non-Coding RNAs Family Prediction Based on Deep Learning

Evidence has accumulated enough to prove non-coding RNAs (ncRNAs) play important roles in cellular biological processes and disease pathogenesis. High throughput techniques have produced a large number of ncRNAs whose function remains unknown. Since the accurate identification of ncRNAs family is helpful to the research of their function, it is of necessity and urgency to predict the family of each ncRNAs. Although several traditional excellent methods are applicable to predict the family of ncRNAs, their complex procedures or inaccurate performance remain major problems confronting us. The main idea of those methods is first to predict the secondary structure, and then identify ncRNAs family according to properties of the secondary structure. Unfortunately, the multi-step error superposition, especially the imperfection of RNA secondary structure prediction tools, maybe the cause of low accuracy. In this paper, a novel end-to-end method 'ncRFP' was proposed to complete the prediction task based on Deep Learning. Instead of predicting the secondary structure, ncRFP predicts the ncRNAs family by automatically extracting features from ncRNAs sequences. Compared with other methods, ncRFP not only simplifies the process but also improves accuracy. The source code of ncRFP can be available at https://github.com/linyuwangPHD/ncRFP.

The lncRNA Toolkit: Databases and In Silico Tools for lncRNA Analysis

Long non-coding RNAs (lncRNAs) are a rapidly expanding field of research, with many new transcripts identified each year. However, only a small subset of lncRNAs has been characterized functionally thus far. To aid investigating the mechanisms of action by which new lncRNAs act, bioinformatic tools and databases are invaluable. Here, we review a selection of computational tools and databases for the in silico analysis of lncRNAs, including tissue-specific expression, protein coding potential, subcellular localization, structural conformation, and interaction partners. The assembled lncRNA toolkit is aimed primarily at experimental researchers as a useful starting point to guide wet-lab experiments, mainly containing multi-functional, user-friendly interfaces. With more and more new lncRNA analysis tools available, it will be essential to provide continuous updates and maintain the availability of key software in the future.

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.

FARFAR2: Improved De Novo Rosetta Prediction of Complex Global RNA Folds

Predicting RNA three-dimensional structures from sequence could accelerate understanding of the growing number of RNA molecules being discovered across biology. Rosetta's Fragment Assembly of RNA with Full-Atom Refinement (FARFAR) has shown promise in community-wide blind RNA-Puzzle trials, but lack of a systematic and automated benchmark has left unclear what limits FARFAR performance. Here, we benchmark FARFAR2, an algorithm integrating RNA-Puzzle-inspired innovations with updated fragment libraries and helix modeling. In 16 of 21 RNA-Puzzles revisited without experimental data or expert intervention, FARFAR2 recovers native-like structures more accurate than models submitted during the RNA-Puzzles trials. Remaining bottlenecks include conformational sampling for >80-nucleotide problems and scoring function limitations more generally. Supporting these conclusions, preregistered blind models for adenovirus VA-I RNA and five riboswitch complexes predicted native-like folds with 3- to 14 Å root-mean-square deviation accuracies. We present a FARFAR2 webserver and three large model archives (FARFAR2-Classics, FARFAR2-Motifs, and FARFAR2-Puzzles) to guide future applications and advances.

Characterization of lncRNA-Perturbed TLR-Signaling Network Identifies Novel lncRNA Prognostic Biomarkers in Colorectal Cancer

Increasing evidence has suggested that long non-coding RNAs (lncRNAs) are critical regulators in the Toll-like receptors (TLR)-signaling network to modulate colorectal cancer (CRC) development and progression. However, the mechanism and clinical significance for lncRNAs regulating TLR signaling pathways in CRC remained largely unknown. In this study, we performed an integrative network analysis of transcriptomics by focusing on a lncRNA-perturbed TLR-signaling network, identifying 280 lncRNAs and 122 mRNAs. We found a profound phenomenon that abnormal expression of some lncRNAs can perturb the TLR-signaling network to contribute to CRC development and progression. Furthermore, we identified a novel TLR-related prognostic gene signature (TLRLncSig) composed of three lncRNAs (MCHR2, AC011472.4, and AC063944.1), and one mRNA (CDKN2B). Utilizing TLRLncSig could classify CRC patients of training set into two groups with significantly different overall survival. The prognostic value of the TLRLncSig was further validated in the other two independent CRC datasets with different platforms. Results of multivariate and stratification analysis indicated that the TLRLncSig is an independent prognostic factor, and our study underscores the clinical significance of TLR-related lncRNAs in CRC development and progression.

SDN2GO: An Integrated Deep Learning Model for Protein Function Prediction

The assignment of function to proteins at a large scale is essential for understanding the molecular mechanism of life. However, only a very small percentage of the more than 179 million proteins in UniProtKB have Gene Ontology (GO) annotations supported by experimental evidence. In this paper, we proposed an integrated deep-learning-based classification model, named SDN2GO, to predict protein functions. SDN2GO applies convolutional neural networks to learn and extract features from sequences, protein domains, and known PPI networks, and then utilizes a weight classifier to integrate these features and achieve accurate predictions of GO terms. We constructed the training set and the independent test set according to the time-delayed principle of the Critical Assessment of Function Annotation (CAFA) and compared it with two highly competitive methods and the classic BLAST method on the independent test set. The results show that our method outperforms others on each sub-ontology of GO. We also investigated the performance of using protein domain information. We learned from the Natural Language Processing (NLP) to process domain information and pre-trained a deep learning sub-model to extract the comprehensive features of domains. The experimental results demonstrate that the domain features we obtained are much improved the performance of our model. Our deep learning models together with the data pre-processing scripts are publicly available as an open source software at https://github.com/Charrick/SDN2GO.