1
|
Bugnon LA, Di Persia L, Gerard M, Raad J, Prochetto S, Fenoy E, Chorostecki U, Ariel F, Stegmayer G, Milone DH. sincFold: end-to-end learning of short- and long-range interactions in RNA secondary structure. Brief Bioinform 2024; 25:bbae271. [PMID: 38855913 PMCID: PMC11163250 DOI: 10.1093/bib/bbae271] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/18/2024] [Revised: 05/03/2024] [Accepted: 05/24/2024] [Indexed: 06/11/2024] Open
Abstract
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.
Collapse
Affiliation(s)
- Leandro A Bugnon
- Research Institute for Signals, Systems and Computational Intelligence, sinc(i), FICH-UNL, CONICET, Ciudad Universitaria UNL, 3000, Santa Fe, Argentina
| | - Leandro Di Persia
- Research Institute for Signals, Systems and Computational Intelligence, sinc(i), FICH-UNL, CONICET, Ciudad Universitaria UNL, 3000, Santa Fe, Argentina
| | - Matias Gerard
- Research Institute for Signals, Systems and Computational Intelligence, sinc(i), FICH-UNL, CONICET, Ciudad Universitaria UNL, 3000, Santa Fe, Argentina
| | - Jonathan Raad
- Research Institute for Signals, Systems and Computational Intelligence, sinc(i), FICH-UNL, CONICET, Ciudad Universitaria UNL, 3000, Santa Fe, Argentina
| | - Santiago Prochetto
- Research Institute for Signals, Systems and Computational Intelligence, sinc(i), FICH-UNL, CONICET, Ciudad Universitaria UNL, 3000, Santa Fe, Argentina
- Instituto de Agrobiotecnología del Litoral, CONICET-UNL, CCT-Santa Fe, Ruta Nacional N° 168 Km 0, s/n, Paraje el Pozo, 3000, Santa Fe, Argentina
| | - Emilio Fenoy
- Research Institute for Signals, Systems and Computational Intelligence, sinc(i), FICH-UNL, CONICET, Ciudad Universitaria UNL, 3000, Santa Fe, Argentina
| | - Uciel Chorostecki
- Faculty of Medicine and Health Sciences, Universitat Internacional de Catalunya, Barcelona, Spain
| | - Federico Ariel
- Instituto de Agrobiotecnología del Litoral, CONICET-UNL, CCT-Santa Fe, Ruta Nacional N° 168 Km 0, s/n, Paraje el Pozo, 3000, Santa Fe, Argentina
| | - Georgina Stegmayer
- Research Institute for Signals, Systems and Computational Intelligence, sinc(i), FICH-UNL, CONICET, Ciudad Universitaria UNL, 3000, Santa Fe, Argentina
| | - Diego H Milone
- Research Institute for Signals, Systems and Computational Intelligence, sinc(i), FICH-UNL, CONICET, Ciudad Universitaria UNL, 3000, Santa Fe, Argentina
| |
Collapse
|
2
|
Weghorst F, Torres Marcén M, Faridi G, Lee YCG, Cramer KS. Deep Conservation and Unexpected Evolutionary History of Neighboring lncRNAs MALAT1 and NEAT1. J Mol Evol 2024; 92:30-41. [PMID: 38189925 PMCID: PMC10869381 DOI: 10.1007/s00239-023-10151-y] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/15/2023] [Accepted: 11/29/2023] [Indexed: 01/09/2024]
Abstract
Long non-coding RNAs (lncRNAs) have begun to receive overdue attention for their regulatory roles in gene expression and other cellular processes. Although most lncRNAs are lowly expressed and tissue-specific, notable exceptions include MALAT1 and its genomic neighbor NEAT1, two highly and ubiquitously expressed oncogenes with roles in transcriptional regulation and RNA splicing. Previous studies have suggested that NEAT1 is found only in mammals, while MALAT1 is present in all gnathostomes (jawed vertebrates) except birds. Here we show that these assertions are incomplete, likely due to the challenges associated with properly identifying these two lncRNAs. Using phylogenetic analysis and structure-aware annotation of publicly available genomic and RNA-seq coverage data, we show that NEAT1 is a common feature of tetrapod genomes except birds and squamates. Conversely, we identify MALAT1 in representative species of all major gnathostome clades, including birds. Our in-depth examination of MALAT1, NEAT1, and their genomic context in a wide range of vertebrate species allows us to reconstruct the series of events that led to the formation of the locus containing these genes in taxa from cartilaginous fish to mammals. This evolutionary history includes the independent loss of NEAT1 in birds and squamates, since NEAT1 is found in the closest living relatives of both clades (crocodilians and tuataras, respectively). These data clarify the origins and relationships of MALAT1 and NEAT1 and highlight an opportunity to study the change and continuity in lncRNA structure and function over deep evolutionary time.
Collapse
Affiliation(s)
- Forrest Weghorst
- Department of Neurobiology and Behavior, University of California, Irvine, USA
| | - Martí Torres Marcén
- Department of Neurobiology and Behavior, University of California, Irvine, USA
| | - Garrison Faridi
- Department of Neurobiology and Behavior, University of California, Irvine, USA
| | - Yuh Chwen G Lee
- Department of Ecology and Evolutionary Biology, University of California, Irvine, USA
| | - Karina S Cramer
- Department of Neurobiology and Behavior, University of California, Irvine, USA.
| |
Collapse
|
3
|
Schneider B, Sweeney BA, Bateman A, Cerny J, Zok T, Szachniuk M. When will RNA get its AlphaFold moment? Nucleic Acids Res 2023; 51:9522-9532. [PMID: 37702120 PMCID: PMC10570031 DOI: 10.1093/nar/gkad726] [Citation(s) in RCA: 21] [Impact Index Per Article: 21.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/10/2023] [Revised: 08/13/2023] [Accepted: 08/22/2023] [Indexed: 09/14/2023] Open
Abstract
The protein structure prediction problem has been solved for many types of proteins by AlphaFold. Recently, there has been considerable excitement to build off the success of AlphaFold and predict the 3D structures of RNAs. RNA prediction methods use a variety of techniques, from physics-based to machine learning approaches. We believe that there are challenges preventing the successful development of deep learning-based methods like AlphaFold for RNA in the short term. Broadly speaking, the challenges are the limited number of structures and alignments making data-hungry deep learning methods unlikely to succeed. Additionally, there are several issues with the existing structure and sequence data, as they are often of insufficient quality, highly biased and missing key information. Here, we discuss these challenges in detail and suggest some steps to remedy the situation. We believe that it is possible to create an accurate RNA structure prediction method, but it will require solving several data quality and volume issues, usage of data beyond simple sequence alignments, or the development of new less data-hungry machine learning methods.
Collapse
Affiliation(s)
- Bohdan Schneider
- Institute of Biotechnology of the Czech Academy of Sciences, Prumyslova 595, CZ-252 50 Vestec, Czech Republic
| | - Blake Alexander Sweeney
- European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, CB10 1SD, UK
| | - Alex Bateman
- European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, CB10 1SD, UK
| | - Jiri Cerny
- Institute of Biotechnology of the Czech Academy of Sciences, Prumyslova 595, CZ-252 50 Vestec, Czech Republic
| | - Tomasz Zok
- Institute of Computing Science and European Centre for Bioinformatics and Genomics, Poznan University of Technology, Piotrowo 2, 60-965 Poznan, Poland
| | - Marta Szachniuk
- Institute of Computing Science and European Centre for Bioinformatics and Genomics, Poznan University of Technology, Piotrowo 2, 60-965 Poznan, Poland
- Institute of Bioorganic Chemistry, Polish Academy of Sciences, Noskowskiego 12/14, 61-704 Poznan, Poland
| |
Collapse
|
4
|
Ballarino M, Pepe G, Helmer-Citterich M, Palma A. Exploring the landscape of tools and resources for the analysis of long non-coding RNAs. Comput Struct Biotechnol J 2023; 21:4706-4716. [PMID: 37841333 PMCID: PMC10568309 DOI: 10.1016/j.csbj.2023.09.041] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/12/2023] [Revised: 09/28/2023] [Accepted: 09/28/2023] [Indexed: 10/17/2023] Open
Abstract
In recent years, research on long non-coding RNAs (lncRNAs) has gained considerable attention due to the increasing number of newly identified transcripts. Several characteristics make their functional evaluation challenging, which called for the urgent need to combine molecular biology with other disciplines, including bioinformatics. Indeed, the recent development of computational pipelines and resources has greatly facilitated both the discovery and the mechanisms of action of lncRNAs. In this review, we present a curated collection of the most recent computational resources, which have been categorized into distinct groups: databases and annotation, identification and classification, interaction prediction, and structure prediction. As the repertoire of lncRNAs and their analysis tools continues to expand over the years, standardizing the computational pipelines and improving the existing annotation of lncRNAs will be crucial to facilitate functional genomics studies.
Collapse
Affiliation(s)
- Monica Ballarino
- Department of Biology and Biotechnologies “Charles Darwin”, Sapienza University of Rome, Piazzale Aldo Moro 5, 00161 Rome, Italy
| | - Gerardo Pepe
- Department of Biology, University of Rome Tor Vergata, Via della Ricerca Scientifica, 1, 00133 Rome, Italy
| | - Manuela Helmer-Citterich
- Department of Biology, University of Rome Tor Vergata, Via della Ricerca Scientifica, 1, 00133 Rome, Italy
| | - Alessandro Palma
- Department of Biology and Biotechnologies “Charles Darwin”, Sapienza University of Rome, Piazzale Aldo Moro 5, 00161 Rome, Italy
| |
Collapse
|
5
|
Rivas E. RNA covariation at helix-level resolution for the identification of evolutionarily conserved RNA structure. PLoS Comput Biol 2023; 19:e1011262. [PMID: 37450549 PMCID: PMC10370758 DOI: 10.1371/journal.pcbi.1011262] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/08/2023] [Accepted: 06/12/2023] [Indexed: 07/18/2023] Open
Abstract
Many biologically important RNAs fold into specific 3D structures conserved through evolution. Knowing when an RNA sequence includes a conserved RNA structure that could lead to new biology is not trivial and depends on clues left behind by conservation in the form of covariation and variation. For that purpose, the R-scape statistical test was created to identify from alignments of RNA sequences, the base pairs that significantly covary above phylogenetic expectation. R-scape treats base pairs as independent units. However, RNA base pairs do not occur in isolation. The Watson-Crick (WC) base pairs stack together forming helices that constitute the scaffold that facilitates the formation of the non-WC base pairs, and ultimately the complete 3D structure. The helix-forming WC base pairs carry most of the covariation signal in an RNA structure. Here, I introduce a new measure of statistically significant covariation at helix-level by aggregation of the covariation significance and covariation power calculated at base-pair-level resolution. Performance benchmarks show that helix-level aggregated covariation increases sensitivity in the detection of evolutionarily conserved RNA structure without sacrificing specificity. This additional helix-level sensitivity reveals an artifact that results from using covariation to build an alignment for a hypothetical structure and then testing the alignment for whether its covariation significantly supports the structure. Helix-level reanalysis of the evolutionary evidence for a selection of long non-coding RNAs (lncRNAs) reinforces the evidence against these lncRNAs having a conserved secondary structure.
Collapse
Affiliation(s)
- Elena Rivas
- Department of Molecular and Cellular Biology, Harvard University, Cambridge, Massachusetts, United States of America
| |
Collapse
|
6
|
Rivas E. RNA covariation at helix-level resolution for the identification of evolutionarily conserved RNA structure. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2023:2023.04.14.536965. [PMID: 37131783 PMCID: PMC10153129 DOI: 10.1101/2023.04.14.536965] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/04/2023]
Abstract
Many biologically important RNAs fold into specific 3D structures conserved through evolution. Knowing when an RNA sequence includes a conserved RNA structure that could lead to new biology is not trivial and depends on clues left behind by conservation in the form of covariation and variation. For that purpose, the R-scape statistical test was created to identify from alignments of RNA sequences, the base pairs that significantly covary above phylogenetic expectation. R-scape treats base pairs as independent units. However, RNA base pairs do not occur in isolation. The Watson-Crick (WC) base pairs stack together forming helices that constitute the scaffold that facilitates the formation of the non-WC base pairs, and ultimately the complete 3D structure. The helix-forming WC base pairs carry most of the covariation signal in an RNA structure. Here, I introduce a new measure of statistically significant covariation at helix-level by aggregation of the covariation significance and covariation power calculated at base-pair-level resolution. Performance benchmarks show that helix-level aggregated covariation increases sensitivity in the detection of evolutionarily conserved RNA structure without sacrificing specificity. This additional helix-level sensitivity reveals an artifact that results from using covariation to build an alignment for a hypothetical structure and then testing the alignment for whether its covariation significantly supports the structure. Helix-level reanalysis of the evolutionary evidence for a selection of long non-coding RNAs (lncRNAs) reinforces the evidence against these lncRNAs having a conserved secondary structure. Availability Helix aggregated E-values are integrated in the R-scape software package (version 2.0.0.p and higher). The R-scape web server eddylab.org/R-scape includes a link to download the source code. Contact elenarivas@fas.harvard.edu. Supplementary information Supplementary data and code are provided with this manuscript at rivaslab.org .
Collapse
|
7
|
Kilar AM, Fajkus P, Fajkus J. GERONIMO: A tool for systematic retrieval of structural RNAs in a broad evolutionary context. Gigascience 2022; 12:giad080. [PMID: 37848616 PMCID: PMC10580375 DOI: 10.1093/gigascience/giad080] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/08/2023] [Revised: 08/04/2023] [Accepted: 09/11/2023] [Indexed: 10/19/2023] Open
Abstract
BACKGROUND While web-based tools such as BLAST have made identifying conserved gene homologs appear easy, genes with variable sequences pose significant challenges. Functionally important noncoding RNAs (ncRNA) often show low sequence conservation due to genetic variations, including insertions and deletions. Rather than conserved sequences, these RNAs possess highly conserved structural features across a broad phylogenetic range. Such features can be identified using the covariance models approach, which combines sequence alignment with a secondary RNA structure consensus. However, running standard implementation of that approach (Infernal) requires advanced bioinformatics knowledge compared to user-friendly web services like BLAST. The issue is partially addressed by RNAcentral, which can be used to search for homologs across a broad range of ncRNA sequence collections from diverse organisms but not across the genome assemblies. RESULTS Here, we present GERONIMO, which conducts evolutionary searches across hundreds of genomes in a fully automated way. It provides results extended with taxonomy context, as summary tables and visualizations, to facilitate analysis for user convenience. Additionally, GERONIMO supplements homologous sequences with genomic regions to analyze promoter motifs or gene collinearity, enhancing the validation of results. CONCLUSION GERONIMO, built using Snakemake, has undergone extensive testing on hundreds of genomes, establishing itself as a valuable tool in the identification of ncRNA homologs across diverse taxonomic groups. Consequently, GERONIMO facilitates the investigation of the evolutionary patterns of functionally significant ncRNA players, whose understanding has previously been limited to individual organisms and close relatives.
Collapse
Affiliation(s)
- Agata M Kilar
- Mendel Centre for Plant Genomics and Proteomics, CEITEC Masaryk University, Brno CZ-62500, Czech Republic
- Laboratory of Functional Genomics and Proteomics, NCBR, Faculty of Science, Masaryk University, Brno CZ-61137, Czech Republic
| | - Petr Fajkus
- Mendel Centre for Plant Genomics and Proteomics, CEITEC Masaryk University, Brno CZ-62500, Czech Republic
- Department of Cell Biology and Radiobiology, Institute of Biophysics of the Czech Academy of Sciences, Brno CZ-61265, Czech Republic
| | - Jiří Fajkus
- Mendel Centre for Plant Genomics and Proteomics, CEITEC Masaryk University, Brno CZ-62500, Czech Republic
- Laboratory of Functional Genomics and Proteomics, NCBR, Faculty of Science, Masaryk University, Brno CZ-61137, Czech Republic
- Department of Cell Biology and Radiobiology, Institute of Biophysics of the Czech Academy of Sciences, Brno CZ-61265, Czech Republic
| |
Collapse
|