Dataset Information

A machine learning based framework to identify and classify long terminal repeat retrotransposons.

ABSTRACT: 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.

SUBMITTER: Schietgat L

PROVIDER: S-EPMC5933816 | biostudies-literature | 2018 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A machine learning based framework to identify and classify long terminal repeat retrotransposons.

Schietgat Leander L Vens Celine C Cerri Ricardo R Fischer Carlos N CN Costa Eduardo E Ramon Jan J Carareto Claudia M A CMA Blockeel Hendrik H

PLoS computational biology 20180423 4

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 automatical ...[more]

PMID: 29684010

Similar Datasets

Project description:We identified putative long terminal repeat- (LTR) retrotransposon sequences among the 50,000 random sequence tags (RSTs) obtained by the Génolevures project from genomic libraries of 13 Hemiascomycetes species. In most cases additional sequencing enabled us to assemble the whole sequences of these retrotransposons. These approaches identified 17 distinct families, 10 of which are defined by full-length elements. We also identified five families of solo LTRs that were not associated with retrotransposons. Ty1-like retrotransposons were found in four of five species that are phylogenetically related to Saccharomyces cerevisiae (S. uvarum, S. exiguus, S. servazzii, and S. kluyveri but not Zygosaccharomyces rouxii), and in two of three Kluyveromyces species (K. lactis and K. marxianus but not K. thermotolerans). Only multiply crippled elements could be identified in the K. lactis and S. servazzii strains analyzed, and only solo LTRs could be identified in S. uvarum. Ty4-like elements were only detected in S. uvarum, indicating that these elements appeared recently before speciation of the Saccharomyces sensu stricto species. Ty5-like elements were detected in S. exiguus, Pichia angusta, and Debaryomyces hansenii. A retrotransposon homologous with Tca2 from Candida albicans, an element absent from S. cerevisiae, was detected in the closely related species D. hansenii. A complete Ty3/gypsy element was present in S. exiguus, whereas only partial, often degenerate, sequences resembling this element were found in S. servazzii, Z. rouxii, S. kluyveri, C. tropicalis, and Yarrowica lipolytica. P. farinosa (syn. P. sorbitophila) is currently the only yeast species in which no LTR retrotransposons or remnants have been found. Thorough analysis of protein sequences, structural characteristics of the elements, and phylogenetic relationships deduced from these data allowed us to propose a classification for the Ty1/copia elements of hemiascomycetous yeasts and a model of LTR-retrotransposon evolution in yeasts.

Project description:BackgroundLong terminal repeat retrotransposons are the most abundant transposons in plants. They play important roles in alternative splicing, recombination, gene regulation, and defense mechanisms. Large-scale sequencing projects for plant genomes are currently underway. Software tools are important for annotating long terminal repeat retrotransposons in these newly available genomes. However, the available tools are not very sensitive to known elements and perform inconsistently on different genomes. Some are hard to install or obsolete. They may struggle to process large plant genomes. None can be executed in parallel out of the box and very few have features to support visual review of new elements. To overcome these limitations, we developed LtrDetector, which uses techniques inspired by signal-processing.ResultsWe compared LtrDetector to LTR_Finder and LTRharvest, the two most successful predecessor tools, on six plant genomes. For each organism, we constructed a ground truth data set based on queries from a consensus sequence database. According to this evaluation, LtrDetector was the most sensitive tool, achieving 16-23% improvement in sensitivity over LTRharvest and 21% improvement over LTR_Finder. All three tools had low false positive rates, with LtrDetector achieving 98.2% precision, in between its two competitors. Overall, LtrDetector provides the best compromise between high sensitivity and low false positive rate while requiring moderate time and utilizing memory available on personal computers.ConclusionsLtrDetector uses a novel methodology revolving around k-mer distributions, which allows it to produce high-quality results using relatively lightweight procedures. It is easy to install and use. It is not species specific, performing well using its default parameters on genomes of varying size and repeat content. It is automatically configured for parallel execution and runs efficiently on an ordinary personal computer. It includes a k-mer scores visualization tool to facilitate manual review of the identified elements. These features make LtrDetector an attractive tool for future annotation projects involving long terminal repeat retrotransposons.

Project description:BackgroundIn eukaryotes, long terminal repeat (LTR) retrotransposons such as Copia, BEL and Gypsy integrate their DNA copies into the host genome using a particular type of DDE transposase called integrase (INT). The Gypsy INT-like transposase is also conserved in the Polinton/Maverick self-synthesizing DNA transposons and in the 'cut and paste' DNA transposons known as TDD-4 and TDD-5. Moreover, it is known that INT is similar to bacterial transposases that belong to the IS3, IS481, IS30 and IS630 families. It has been suggested that LTR retrotransposons evolved from a non-LTR retrotransposon fused with a DNA transposon in early eukaryotes. In this paper we analyze a diverse superfamily of eukaryotic cut and paste DNA transposons coding for INT-like transposase and discuss their evolutionary relationship to LTR retrotransposons.ResultsA new diverse eukaryotic superfamily of DNA transposons, named Ginger (for 'Gypsy INteGrasE Related') DNA transposons is defined and analyzed. Analogously to the IS3 and IS481 bacterial transposons, the Ginger termini resemble those of the Gypsy LTR retrotransposons. Currently, Ginger transposons can be divided into two distinct groups named Ginger1 and Ginger2/Tdd. Elements from the Ginger1 group are characterized by approximately 40 to 270 base pair (bp) terminal inverted repeats (TIRs), and are flanked by CCGG-specific or CCGT-specific target site duplication (TSD) sequences. The Ginger1-encoded transposases contain an approximate 400 amino acid N-terminal portion sharing high amino acid identity to the entire Gypsy-encoded integrases, including the YPYY motif, zinc finger, DDE domain, and, importantly, the GPY/F motif, a hallmark of Gypsy and endogenous retrovirus (ERV) integrases. Ginger1 transposases also contain additional C-terminal domains: ovarian tumor (OTU)-like protease domain or Ulp1 protease domain. In vertebrate genomes, at least two host genes, which were previously thought to be derived from the Gypsy integrases, apparently have evolved from the Ginger1 transposase genes. We also introduce a second Ginger group, designated Ginger2/Tdd, which includes the previously reported DNA transposon TDD-4.ConclusionsThe Ginger superfamily represents eukaryotic DNA transposons closely related to LTR retrotransposons. Ginger elements provide new insights into the evolution of transposable elements and certain transposable element (TE)-derived genes.

Dataset Information

A machine learning based framework to identify and classify long terminal repeat retrotransposons.

Publications

A machine learning based framework to identify and classify long terminal repeat retrotransposons.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets