K-mer-based machine learning method to classify LTR-retrotransposons in plant genomes.
Ontology highlight
ABSTRACT:
SUBMITTER: Orozco-Arias S
PROVIDER: S-EPMC8140598 | biostudies-literature | 2021
REPOSITORIES: biostudies-literature
Publications
<i>K</i>-mer-based machine learning method to classify LTR-retrotransposons in plant genomes.
Orozco-Arias Simon S Candamil-Cortés Mariana S MS Jaimes Paula A PA Piña Johan S JS Tabares-Soto Reinel R Guyot Romain R Isaza Gustavo G
PeerJ 20210519
Every day more plant genomes are available in public databases and additional massive sequencing projects (i.e., that aim to sequence thousands of individuals) are formulated and released. Nevertheless, there are not enough automatic tools to analyze this large amount of genomic information. LTR retrotransposons are the most frequent repetitive sequences in plant genomes; however, their detection and classification are commonly performed using semi-automatic and time-consuming programs. Despite ...[more]
Similar Datasets
Project description:LTR-retrotransposons are the most abundant repeat sequences in plant genomes and play an important role in evolution and biodiversity. Their characterization is of great importance to understand their dynamics. However, the identification and classification of these elements remains a challenge today. Moreover, current software can be relatively slow (from hours to days), sometimes involve a lot of manual work and do not reach satisfactory levels in terms of precision and sensitivity. Here we present Inpactor2, an accurate and fast application that creates LTR-retrotransposon reference libraries in a very short time. Inpactor2 takes an assembled genome as input and follows a hybrid approach (deep learning and structure-based) to detect elements, filter partial sequences and finally classify intact sequences into superfamilies and, as very few tools do, into lineages. This tool takes advantage of multi-core and GPU architectures to decrease execution times. Using the rice genome, Inpactor2 showed a run time of 5 minutes (faster than other tools) and has the best accuracy and F1-Score of the tools tested here, also having the second best accuracy and specificity only surpassed by EDTA, but achieving 28% higher sensitivity. For large genomes, Inpactor2 is up to seven times faster than other available bioinformatics tools.
| S-EPMC9851300 | biostudies-literature
Project description:Transposable elements are mobile sequences that can move and insert themselves into chromosomes, activating under internal or external stimuli, giving the organism the ability to adapt to the environment. Annotating transposable elements in genomic data is currently considered a crucial task to understand key aspects of organisms such as phenotype variability, species evolution, and genome size, among others. Because of the way they replicate, LTR retrotransposons are the most common transposable elements in plants, accounting in some cases for up to 80% of all DNA information. To annotate these elements, a reference library is usually created, a curation process is performed, eliminating TE fragments and false positives and then annotated in the genome using the homology method. However, the curation process can take weeks, requires extensive manual work and the execution of multiple time-consuming bioinformatics software. Here, we propose a machine learning-based approach to perform this process automatically on plant genomes, obtaining up to 91.18% F1-score. This approach was tested with four plant species, obtaining up to 93.6% F1-score (Oryza granulata) in only 22.61 s, where bioinformatics methods took approximately 6 h. This acceleration demonstrates that the ML-based approach is efficient and could be used in massive sequencing projects.
| S-EPMC9521825 | biostudies-literature
Project description:Transposable elements (TEs) are repetitive nucleotide sequences that make up a large portion of eukaryotic genomes. They can move and duplicate within a genome, increasing genome size and contributing to genetic diversity within and across species. Accurate identification and classification of TEs present in a genome is an important step towards understanding their effects on genes and their role in genome evolution. We introduce TE-Learner, a framework based on machine learning that automatically identifies TEs in a given genome and assigns a classification to them. We present an implementation of our framework towards LTR retrotransposons, a particular type of TEs characterized by having long terminal repeats (LTRs) at their boundaries. We evaluate the predictive performance of our framework on the well-annotated genomes of Drosophila melanogaster and Arabidopsis thaliana and we compare our results for three LTR retrotransposon superfamilies with the results of three widely used methods for TE identification or classification: RepeatMasker, Censor and LtrDigest. In contrast to these methods, TE-Learner is the first to incorporate machine learning techniques, outperforming these methods in terms of predictive performance, while able to learn models and make predictions efficiently. Moreover, we show that our method was able to identify TEs that none of the above method could find, and we investigated TE-Learner's predictions which did not correspond to an official annotation. It turns out that many of these predictions are in fact strongly homologous to a known TE.
| S-EPMC5933816 | biostudies-literature
Project description:LTR retrotransposons (LTR-RTs) are ubiquitous and represent the dominant repeat element in plant genomes, playing important roles in functional variation, genome plasticity and evolution. With the advent of new sequencing technologies, a growing number of whole-genome sequences have been made publicly available, making it possible to carry out systematic analyses of LTR-RTs. However, a comprehensive and unified annotation of LTR-RTs in plant groups is still lacking. Here, we constructed a plant intact LTR-RTs dataset, which is designed to classify and annotate intact LTR-RTs with a standardized procedure. The dataset currently comprises a total of 2,593,685 intact LTR-RTs from genomes of 300 plant species representing 93 families of 46 orders. The dataset is accompanied by sequence, diverse structural and functional annotation, age determination and classification information associated with the LTR-RTs. This dataset will contribute valuable resources for investigating the evolutionary dynamics and functional implications of LTR-RTs in plant genomes.
| S-EPMC8282616 | biostudies-literature
Project description:BackgroundLong terminal repeats (LTRs) represent important parts of LTR retrotransposons and retroviruses found in high copy numbers in a majority of eukaryotic genomes. LTRs contain regulatory sequences essential for the life cycle of the retrotransposon. Previous experimental and sequence studies have provided only limited information about LTR structure and composition, mostly from model systems. To enhance our understanding of these key sequence modules, we focused on the contrasts between LTRs of various retrotransposon families and other genomic regions. Furthermore, this approach can be utilized for the classification and prediction of LTRs.ResultsWe used machine learning methods suitable for DNA sequence classification and applied them to a large dataset of plant LTR retrotransposon sequences. We trained three machine learning models using (i) traditional model ensembles (Gradient Boosting), (ii) hybrid convolutional/long and short memory network models, and (iii) a DNA pre-trained transformer-based model using k-mer sequence representation. All three approaches were successful in classifying and isolating LTRs in this data, as well as providing valuable insights into LTR sequence composition. The best classification (expressed as F1 score) achieved for LTR detection was 0.85 using the hybrid network model. The most accurate classification task was superfamily classification (F1=0.89) while the least accurate was family classification (F1=0.74). The trained models were subjected to explainability analysis. Positional analysis identified a mixture of interesting features, many of which had a preferred absolute position within the LTR and/or were biologically relevant, such as a centrally positioned TATA-box regulatory sequence, and TG..CA nucleotide patterns around both LTR edges.ConclusionsOur results show that the models used here recognized biologically relevant motifs, such as core promoter elements in the LTR detection task, and a development and stress-related subclass of transcription factor binding sites in the family classification task. Explainability analysis also highlighted the importance of 5'- and 3'- edges in LTR identity and revealed need to analyze more than just dinucleotides at these ends. Our work shows the applicability of machine learning models to regulatory sequence analysis and classification, and demonstrates the important role of the identified motifs in LTR detection.
| S-EPMC11656987 | biostudies-literature
Project description:BackgroundLTR retrotransposons are a class of mobile genetic elements containing two similar long terminal repeats (LTRs). Currently, LTR retrotransposons are annotated in eukaryotic genomes mainly through the conventional homology searching approach. Hence, it is limited to annotating known elements.ResultsIn this paper, we report a de novo computational method that can identify new LTR retrotransposons without relying on a library of known elements. Specifically, our method identifies intact LTR retrotransposons by using an approximate string matching technique and protein domain analysis. In addition, it identifies partially deleted or solo LTRs using profile Hidden Markov Models (pHMMs). As a result, this method can de novo identify all types of LTR retrotransposons. We tested this method on the two pairs of eukaryotic genomes, C. elegans vs. C. briggsae and D. melanogaster vs. D. pseudoobscura. LTR retrotransposons in C. elegans and D. melanogaster have been intensively studied using conventional annotation methods. Comparing with previous work, we identified new intact LTR retroelements and new putative families, which may imply that there may still be new retroelements that are left to be discovered even in well-studied organisms. To assess the sensitivity and accuracy of our method, we compared our results with a previously published method, LTR_STRUC, which predominantly identifies full-length LTR retrotransposons. In summary, both methods identified comparable number of intact LTR retroelements. But our method can identify nearly all known elements in C. elegans, while LTR_STRUCT missed about 1/3 of them. Our method also identified more known LTR retroelements than LTR_STRUCT in the D. melanogaster genome. We also identified some LTR retroelements in the other two genomes, C. briggsae and D. pseudoobscura, which have not been completely finished. In contrast, the conventional method failed to identify those elements. Finally, the phylogenetic and chromosomal distributions of the identified elements are discussed.ConclusionWe report a novel method for de novo identification of LTR retrotransposons in eukaryotic genomes with favorable performance over the existing methods.
| S-EPMC1858694 | biostudies-literature
Project description:LTR-retrotransposons (LTR-RTs) are a class of RNA-replicating transposon elements (TEs) that can alter genome structure and function by moving positions, repositioning genes, shifting exons, and causing chromosomal rearrangements. LTR-RTs are widespread in many plant genomes and constitute a significant portion of the genome. Their movement and activity in eukaryotic genomes can provide insight into genome evolution and gene function, especially when LTR-RTs are located near or within genes. Building the redundant and non-redundant LTR-RTs libraries and their annotations for species lacking this resource requires extensive bioinformatics pipelines and expensive computing power to analyze large amounts of genomic data. This increases the need for online services that provide computational resources with minimal overhead and maximum efficiency. Here, we present MegaLTR as a web server and standalone pipeline that detects intact LTR-RTs at the whole-genome level and integrates multiple tools for structure-based, homologybased, and de novo identification, classification, annotation, insertion time determination, and LTR-RT gene chimera analysis. MegaLTR also provides statistical analysis and visualization with multiple tools and can be used to accelerate plant species discovery and assist breeding programs in their efforts to improve genomic resources. We hope that the development of online services such as MegaLTR, which can analyze large amounts of genomic data, will become increasingly important for the automated detection and annotation of LTR-RT elements.
| S-EPMC10552921 | biostudies-literature
Project description:BackgroundThe three superfamilies of Long Terminal Repeat (LTR) retrotransposons are a widespread kind of transposable element and a major factor in eukaryotic genome evolution. In metazoans, recent studies suggested that Copia LTR-retrotransposons display specific dynamic compared to the more abundant and diverse Gypsy elements. Indeed, Copia elements show a relative scarcity and the prevalence of only a few clades in specific hosts. Thus, BEL/Pao seems to be the second most abundant superfamily. However, the generality of these assumptions remains to be assessed. Therefore, we carried out the first large-scale comparative genomic analysis of LTR-retrotransposons in molluscs. The aim of this study was to analyse the diversity, copy numbers, genomic proportions and distribution of LTR-retrotransposons in a large host phylum.ResultsWe compare nine genomes of molluscs and further added LTR-retrotransposons sequences detected in databases for 47 additional species. We identified 1709 families, which enabled us to define 31 clades. We show that clade richness was highly dependent on the considered superfamily. We found only three Copia clades, including GalEa and Hydra which appear to be widely distributed and highly dominant as they account for 96% of the characterised Copia elements. Among the seven BEL/Pao clades identified, Sparrow and Surcouf are characterised for the first time. We find no BEL or Pao elements, but the rare clades Dan and Flow are present in molluscs. Finally, we characterised 21 Gypsy clades, only five of which had been previously described, the C-clade being the most abundant one. Even if they are found in the same number of host species, Copia elements are clearly less abundant than BEL/Pao elements in copy number or genomic proportions, while Gypsy elements are always the most abundant ones whatever the parameter considered.ConclusionsOur analysis confirms the contrasting dynamics of Copia and Gypsy elements in metazoans and indicates that BEL/Pao represents the second most abundant superfamily, probably reflecting an intermediate dynamic. Altogether, the data obtained in several taxa highly suggest that these patterns can be generalised for most metazoans. Finally, we highlight the importance of using database information in complement of genome analyses when analyzing transposable element diversity.
| S-EPMC6238403 | biostudies-literature
Project description:Computational methods for genome-wide identification of mobile genetic elements (MGEs) have become increasingly necessary for both genome annotation and evolutionary studies. Non-long terminal repeat (non-LTR) retrotransposons are a class of MGEs that have been found in most eukaryotic genomes, sometimes in extremely high numbers. In this article, we present a computational tool, MGEScan-non-LTR, for the identification of non-LTR retrotransposons in genomic sequences, following a computational approach inspired by a generalized hidden Markov model (GHMM). Three different states represent two different protein domains and inter-domain linker regions encoded in the non-LTR retrotransposons, and their scores are evaluated by using profile hidden Markov models (for protein domains) and Gaussian Bayes classifiers (for linker regions), respectively. In order to classify the non-LTR retrotransposons into one of the 12 previously characterized clades using the same model, we defined separate states for different clades. MGEScan-non-LTR was tested on the genome sequences of four eukaryotic organisms, Drosophila melanogaster, Daphnia pulex, Ciona intestinalis and Strongylocentrotus purpuratus. For the D. melanogaster genome, MGEScan-non-LTR found all known 'full-length' elements and simultaneously classified them into the clades CR1, I, Jockey, LOA and R1. Notably, for the D. pulex genome, in which no non-LTR retrotransposon has been annotated, MGEScan-non-LTR found a significantly larger number of elements than did RepeatMasker, using the current version of the RepBase Update library. We also identified novel elements in the other two genomes, which have only been partially studied for non-LTR retrotransposons.
| S-EPMC2790886 | biostudies-literature
Project description:LTR-retrotransposons (LTR-RTs) are a large group of transposable elements that replicate through an RNA intermediate and alter genome structure. The activities of LTR-RTs in plant genomes provide helpful information about genome evolution and gene function. LTR-RTs near or within genes can directly alter gene function. This work introduces PlantLTRdb, an intact LTR-RT database for 195 plant species. Using homology- and de novo structure-based methods, a total of 150.18 Gbp representing 3,079,469 pseudomolecules/scaffolds were analyzed to identify, characterize, annotate LTR-RTs, estimate insertion ages, detect LTR-RT-gene chimeras, and determine nearby genes. Accordingly, 520,194 intact LTR-RTs were discovered, including 29,462 autonomous and 490,732 nonautonomous LTR-RTs. The autonomous LTR-RTs included 10,286 Gypsy and 19,176 Copia, while the nonautonomous were divided into 224,906 Gypsy, 218,414 Copia, 1,768 BARE-2, 3,147 TR-GAG and 4,2497 unknown. Analysis of the identified LTR-RTs located within genes showed that a total of 36,236 LTR-RTs were LTR-RT-gene chimeras and 11,619 LTR-RTs were within pseudo-genes. In addition, 50,026 genes are within 1 kbp of LTR-RTs, and 250,587 had a distance of 1 to 10 kbp from LTR-RTs. PlantLTRdb allows researchers to search, visualize, BLAST and analyze plant LTR-RTs. PlantLTRdb can contribute to the understanding of structural variations, genome organization, functional genomics, and the development of LTR-RT target markers for molecular plant breeding. PlantLTRdb is available at https://bioinformatics.um6p.ma/PlantLTRdb.
| S-EPMC10025401 | biostudies-literature