MOTIVATION: Predicting the 3D structure of RNA is an ongoing challenge that has yet to be completely addressed despite continuous advancements. RNA 3D structures rely on distances between residues and base interactions but also backbone torsional angles. Knowing the torsional angles for each residue could help reconstruct its global folding, which is what we tackle in this work. This paper presents a novel approach for directly predicting RNA torsional angles from raw sequence data. Our method draws inspiration from the successful application of language models in various domains and adapts them to RNA. RESULTS: We have developed a language-based model, RNA-TorsionBERT, incorporating better sequential interactions for predicting RNA torsional and pseudo-torsional angles from the sequence only. Through extensive benchmarking, we demonstrate that our method improves the prediction of torsional angles compared to state-of-the-art methods. In addition, by using our predictive model, we have inferred a torsion angle-dependent scoring function, called TB-MCQ, that replaces the true reference angles by our model prediction. We show that it accurately evaluates the quality of near-native predicted structures, in terms of RNA backbone torsion angle values. Our work demonstrates promising results, suggesting the potential utility of language models in advancing RNA 3D structure prediction. AVAILABILITY AND IMPLEMENTATION: Source code is freely available on the EvryRNA platform: https://evryrna.ibisc.univ-evry.fr/evryrna/RNA-TorsionBERT.

MOTIVATION: As the biological roles and disease implications of non-coding RNAs continue to emerge, the need to thoroughly characterize previously unexplored non-coding RNAs becomes increasingly urgent. These molecules hold potential as biomarkers and therapeutic targets. However, the vast and complex nature of non-coding RNAs data presents a challenge. We introduce MMnc, an interpretable deep-learning approach designed to classify non-coding RNAs into functional groups. MMnc leverages multiple data sources-such as the sequence, secondary structure, and expression-using attention-based multi-modal data integration. This ensures the learning of meaningful representations while accounting for missing sources in some samples. RESULTS: Our findings demonstrate that MMnc achieves high classification accuracy across diverse non-coding RNA classes. The method's modular architecture allows for the consideration of multiple types of modalities, whereas other tools only consider one or two at most. MMnc is resilient to missing data, ensuring that all available information is effectively utilized. Importantly, the generated attention scores offer interpretable insights into the underlying patterns of the different non-coding RNA classes, potentially driving future non-coding RNA research and applications. AVAILABILITY AND IMPLEMENTATION: Data and source code can be found at EvryRNA.ibisc.univ-evry.fr/EvryRNA/MMnc.

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

The involvement of non-coding RNAs in biological processes and diseases has made the exploration of their functions crucial. Most non-coding RNAs have yet to be studied, creating the need for methods that can rapidly classify large sets of non-coding RNAs into functional groups, or classes. In recent years, the success of deep learning in various domains led to its application to non-coding RNA classification. Multiple novel architectures have been developed, but these advancements are not covered by current literature reviews. We present an exhaustive comparison of the different methods proposed in the state-of-the-art and describe their associated datasets. Moreover, the literature lacks objective benchmarks. We perform experiments to fairly evaluate the performance of various tools for non-coding RNA classification on popular datasets. The robustness of methods to non-functional sequences and sequence boundary noise is explored. We also measure computation time and CO2 emissions. With regard to these results, we assess the relevance of the different architectural choices and provide recommendations to consider in future methods.

Accurately predicting the secondary structure of RNA, particularly for long non-coding RNA, has direct implications in healthcare, where it can be used for diagnostic, therapeutic, and drug discovery purposes. However, the majority of previous approaches are too costly in terms of computation budget to cope with the increasing complexity of long RNAs, and the ones that can scale to long RNAs lack accuracy to reliably predict their structures. We propose a new approach combining recursive cutting and machine learning techniques for predicting the secondary structures of long non-coding RNAs. In comparison, our method proves to be computationally efficient by recursively partitioning a sequence into smaller fragments until they can be easily managed by an existing model. We perform a benchmark of different state-of-the-art models and show that our approach indeed demonstrates better performance for long RNAs and a potential to bring significant improvements in the future, as well as interesting enhancing properties, which we discuss.

RNAs can interact with other molecules in their environment, such as ions, proteins or other RNAs, to form complexes with important biological roles. The prediction of the structure of these complexes is therefore an important issue and a difficult task. We are interested in RNA complexes composed of several (more than two) interacting RNAs. We show how available knowledge on the considered RNAs can help predict their secondary structure. We propose an interactive tool for the prediction of RNA complexes, called C-RCPRed, that considers user knowledge and probing data (which can be generated experimentally or artificially). C-RCPred is based on a multi-objective optimization algorithm. Through an extensive benchmarking procedure, which includes state-of-the-art methods, we show the efficiency of the multi-objective approach and the positive impact of considering user knowledge and probing data on the prediction results. C-RCPred is freely available as an open-source program and web server on the EvryRNA website (https://evryrna.ibisc.univ-evry.fr).

MOTIVATION: Applied research in machine learning progresses faster when a clean dataset is available and ready to use. Several datasets have been proposed and released over the years for specific tasks such as image classification, speech-recognition and more recently for protein structure prediction. However, for the fundamental problem of RNA structure prediction, information is spread between several databases depending on the level we are interested in: sequence, secondary structure, 3D structure or interactions with other macromolecules. In order to speed-up advances in machine-learning based approaches for RNA secondary and/or 3D structure prediction, a dataset integrating all this information is required, to avoid spending time on data gathering and cleaning. RESULTS: Here, we propose the first attempt of a standardized and automatically generated dataset dedicated to RNA combining together: RNA sequences, homology information (under the form of position-specific scoring matrices) and information derived by annotation of available 3D structures (including secondary structure, canonical and non-canonical interactions and backbone torsion angles). The data are retrieved from public databases PDB, Rfam and SILVA. The paper describes the procedure to build such dataset and the RNA structure descriptors we provide. Some statistical descriptions of the resulting dataset are also provided. AVAILABILITY AND IMPLEMENTATION: The dataset is updated every month and available online (in flat-text file format) on the EvryRNA software platform (https://evryrna.ibisc.univ-evry.fr/evryrna/rnanet). An efficient parallel pipeline to build the dataset is also provided for easy reproduction or modification. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: RNA loops have been modelled and clustered from solved 3D structures into ordered collections of recurrent non-canonical interactions called 'RNA modules', available in databases. This work explores what information from such modules can be used to improve secondary structure prediction. We propose a bi-objective method for predicting RNA secondary structures by minimizing both an energy-based and a knowledge-based potential. The tool, called BiORSEO, outputs secondary structures corresponding to the optimal solutions from the Pareto set. RESULTS: We compare several approaches to predict secondary structures using inserted RNA modules information: two module data sources, Rna3Dmotif and the RNA 3D Motif Atlas, and different ways to score the module insertions: module size, module complexity or module probability according to models like JAR3D and BayesPairing. We benchmark them against a large set of known secondary structures, including some state-of-the-art tools, and comment on the usefulness of the half physics-based, half data-based approach. AVAILABILITY AND IMPLEMENTATION: The software is available for download on the EvryRNA website, as well as the datasets. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

BACKGROUND: RNAs can interact and form complexes, which have various biological roles. The secondary structure prediction of those complexes is a first step towards the identification of their 3D structure. We propose an original approach that takes advantage of the high number of RNA secondary structure and RNA-RNA interaction prediction tools. We formulate the problem of RNA complex prediction as the determination of the best combination (according to the free energy) of predicted RNA secondary structures and RNA-RNA interactions. RESULTS: We model those predicted structures and interactions as a graph in order to have a combinatorial optimization problem that is a constrained maximum weight clique problem. We propose an heuristic based on Breakout Local Search to solve this problem and a tool, called RCPred, that returns several solutions, including motifs like internal and external pseudoknots. On a large number of complexes, RCPred gives competitive results compared to the methods of the state of the art. CONCLUSIONS: We propose in this paper a method called RCPred for the prediction of several secondary structures of RNA complexes, including internal and external pseudoknots. As further works we will propose an improved computation of the global energy and the insertion of 3D motifs in the RNA complexes.

Motivation: Non-coding RNAs (ncRNAs) play important roles in many biological processes and are involved in many diseases. Their identification is an important task, and many tools exist in the literature for this purpose. However, almost all of them are focused on the discrimination of coding and ncRNAs without giving more biological insight. In this paper, we propose a new reliable method called IRSOM, based on a supervised Self-Organizing Map (SOM) with a rejection option, that overcomes these limitations. The rejection option in IRSOM improves the accuracy of the method and also allows identifing the ambiguous transcripts. Furthermore, with the visualization of the SOM, we analyze the rejected predictions and highlight the ambiguity of the transcripts. Results: IRSOM was tested on datasets of several species from different reigns, and shown better results compared to state-of-art. The accuracy of IRSOM is always greater than 0.95 for all the species with an average specificity of 0.98 and an average sensitivity of 0.99. Besides, IRSOM is fast (it takes around 254 s to analyze a dataset of 147 000 transcripts) and is able to handle very large datasets. Availability and implementation: IRSOM is implemented in Python and C++. It is available on our software platform EvryRNA (http://EvryRNA.ibisc.univ-evry.fr).

RNA structure prediction is an important field in bioinformatics, and numerous methods and tools have been proposed. Pseudoknots are specific motifs of RNA secondary structures that are difficult to predict. Almost all existing methods are based on a single model and return one solution, often missing the real structure. An alternative approach would be to combine different models and return a (small) set of solutions, maximizing its quality and diversity in order to increase the probability that it contains the real structure. We propose here an original method for predicting RNA secondary structures with pseudoknots, based on integer programming. We developed a generic bi-objective integer programming algorithm allowing to return optimal and sub-optimal solutions optimizing simultaneously two models. This algorithm was then applied to the combination of two known models of RNA secondary structure prediction, namely MEA and MFE. The resulting tool, called BiokoP, is compared with the other methods in the literature. The results show that the best solution (structure with the highest F1-score) is, in most cases, given by BiokoP. Moreover, the results of BiokoP are homogeneous, regardless of the pseudoknot type or the presence or not of pseudoknots. Indeed, the F1-scores are always higher than 70% for any number of solutions returned. The results obtained by BiokoP show that combining the MEA and the MFE models, as well as returning several optimal and several sub-optimal solutions, allow to improve the prediction of secondary structures. One perspective of our work is to combine better mono-criterion models, in particular to combine a model based on the comparative approach with the MEA and the MFE models. This leads to develop in the future a new multi-objective algorithm to combine more than two models. BiokoP is available on the EvryRNA platform: https://EvryRNA.ibisc.univ-evry.fr .

MOTIVATION: Piwi-interacting RNA (piRNA) is the most recently discovered and the least investigated class of Argonaute/Piwi protein-interacting small non-coding RNAs. The piRNAs are mostly known to be involved in protecting the genome from invasive transposable elements. But recent discoveries suggest their involvement in the pathophysiology of diseases, such as cancer. Their identification is therefore an important task, and computational methods are needed. However, the lack of conserved piRNA sequences and structural elements makes this identification challenging and difficult. RESULTS: In the present study, we propose a new modular and extensible machine learning method based on multiple kernels and a support vector machine (SVM) classifier for piRNA identification. Very few piRNA features are known to date. The use of a multiple kernels approach allows editing, adding or removing piRNA features that can be heterogeneous in a modular manner according to their relevance in a given species. Our algorithm is based on a combination of the previously identified features [sequence features (k-mer motifs and a uridine at the first position) and piRNAs cluster feature] and a new telomere/centromere vicinity feature. These features are heterogeneous, and the kernels allow to unify their representation. The proposed algorithm, named piRPred, gives promising results on Drosophila and Human data and outscores previously published piRNA identification algorithms. AVAILABILITY AND IMPLEMENTATION: piRPred is freely available to non-commercial users on our Web server EvryRNA http://EvryRNA.ibisc.univ-evry.fr.

BACKGROUND: Inverted repeat genes encode precursor RNAs characterized by hairpin structures. These RNA hairpins are then metabolized by biosynthetic pathways to produce functional small RNAs. In eukaryotic genomes, short non-autonomous transposable elements can have similar size and hairpin structures as non-coding precursor RNAs. This resemblance leads to problems annotating small RNAs. RESULTS: We mapped all microRNA precursors from miRBASE to several genomes and studied the repetition and dispersion of the corresponding loci. We then searched for repetitive elements overlapping these loci. We developed an automatic method called ncRNAclassifier to classify pre-ncRNAs according to their relationship with transposable elements (TEs). We showed that there is a correlation between the number of scattered occurrences of ncRNA precursor candidates and the presence of TEs. We applied ncRNAclassifier on six chordate genomes and report our findings. Among the 1,426 human and 721 mouse pre-miRNAs of miRBase, we identified 235 and 68 mis-annotated pre-miRNAs respectively corresponding completely to TEs. CONCLUSIONS: We provide a tool enabling the identification of repetitive elements in precursor ncRNA sequences. ncRNAclassifier is available at http://EvryRNA.ibisc.univ-evry.fr.

BACKGROUND: Most known eukaryotic genomes contain mobile copied elements called transposable elements. In some species, these elements account for the majority of the genome sequence. They have been subject to many mutations and other genomic events (copies, deletions, captures) during transposition. The identification of these transformations remains a difficult issue. The study of families of transposable elements is generally founded on a multiple alignment of their sequences, a critical step that is adapted to transposons containing mostly localized nucleotide mutations. Many transposons that have lost their protein-coding capacity have undergone more complex rearrangements, needing the development of more complex methods in order to characterize the architecture of sequence variations. RESULTS: In this study, we introduce the concept of a transposable element module, a flexible motif present in at least two sequences of a family of transposable elements and built on a succession of maximal repeats. The paper proposes an assembly method working on a set of exact maximal repeats of a set of sequences to create such modules. It results in a graphical view of sequences segmented into modules, a representation that allows a flexible analysis of the transformations that have occurred between them. We have chosen as a demonstration data set in depth analysis of the transposable element Foldback in Drosophila melanogaster. Comparison with multiple alignment methods shows that our method is more sensitive for highly variable sequences. The study of this family and the two other families AtREP21 and SIDER2 reveals new copies of very different sizes and various combinations of modules which show the potential of our method. CONCLUSIONS: ModuleOrganizer is available on the Genouest bioinformatics center at http://moduleorganizer.genouest.org.

The main contribution of this work is a mathematical theorem which establishes a necessary and sufficient condition to preserve the behaviour of a genetic regulatory network when it is embedded into a larger network. We adopt the modelling approach of René Thomas, which provides a discrete representation of biological regulatory networks. This framework is entirely formalized using labelled graphs with semantics defined in terms of state graphs with transitions. Our theorem offers the possibility to automatically verify whether a subnetwork has autonomous behaviour. It will allow biologists to better identify relevant sets of genes which should be studied together.

BACKGROUND: The secondary structure of an RNA must be known before the relationship between its structure and function can be determined. One way to predict the secondary structure of an RNA is to identify covarying residues that maintain the pairings (Watson-Crick, Wobble and non-canonical pairings). This "comparative approach" consists of identifying mutations from homologous sequence alignments. The sequences must covary enough for compensatory mutations to be revealed, but comparison is difficult if they are too different. Thus the choice of homologous sequences is critical. While many possible combinations of homologous sequences may be used for prediction, only a few will give good structure predictions. This can be due to poor quality alignment in stems or to the variability of certain sequences. This problem of sequence selection is currently unsolved. RESULTS: This paper describes an algorithm, SSCA, which measures the suitability of sequences for the comparative approach. It is based on evolutionary models with structure constraints, particularly those on sequence variations and stem alignment. We propose three models, based on different constraints on sequence alignments. We show the results of the SSCA algorithm for predicting the secondary structure of several RNAs. SSCA enabled us to choose sets of homologous sequences that gave better predictions than arbitrarily chosen sets of homologous sequences. CONCLUSION: SSCA is an algorithm for selecting combinations of RNA homologous sequences suitable for secondary structure predictions with the comparative approach.

Many important RNA molecules contain pseudoknots, which are generally excluded by the definition of the secondary structure, mainly for computational reasons. Still, most existing algorithms for secondary structure prediction are not satisfactory in results and complexities, even when pseudoknots are not allowed. We present an algorithm, called P-DCFold, for the prediction of RNA secondary structures including all kinds of pseudoknots. It is based on the comparative approach. The helices are searched recursively, from more "likely" to less "likely", using the "Divide and Conquer" approach. This approach, which allows to limit the amount of searching, is possible when only non-interleaved helices are searched for. The pseudoknots are therefore searched in several steps, each helix of the pseudoknot being selected in a different step. P-DCFold has been applied to tmRNA and RnaseP sequences. In less than two seconds, their respective secondary structures, including their pseudoknots, have been recovered very efficiently.

The authors propose a lossless algorithm based on regularities, such as the presence of palindromes, in the DNA. The results obtained, although not satisfactory, are far beyond classical algorithms.>