@article{fdi:010085408,
  title = {{A}utomatic curation of {LTR} retrotransposon libraries from plant genomes through machine learning},
  author = {{O}rozco-{A}rias, {S}. and {C}andamil-{C}ortes, {M}. {S}. and {J}aimes, {P}. {A}. and {V}alencia-{C}astrillon, {E}. and {T}abares-{S}oto, {R}. and {I}saza, {G}. and {G}uyot, {R}omain},
  editor = {},
  language = {{ENG}},
  abstract = {{T}ransposable 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. {A}nnotating 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. {B}ecause 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. {T}o 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. {H}owever, the curation process can take weeks, requires extensive manual work and the execution of multiple time-consuming bioinformatics software. {H}ere, we propose a machine learning-based approach to perform this process automatically on plant genomes, obtaining up to 91.18% {F}1-score. {T}his approach was tested with four plant species, obtaining up to 93.6% {F}1-score ({O}ryza granulata) in only 22.61 s, where bioinformatics methods took approximately 6 h. {T}his acceleration demonstrates that the {ML}-based approach is efficient and could be used in massive sequencing projects.},
  keywords = {curation ; deep neural networks ; k-mer-based methods ; {LTR} ; retrotransposons ; machine learning ; nesting insertions},
  booktitle = {},
  journal = {{J}ournal of {I}ntegrative {B}ioinformatics},
  volume = {19},
  numero = {3},
  pages = {20210036 [15 ]},
  year = {2022},
  DOI = {10.1515/jib-2021-0036},
  URL = {https://www.documentation.ird.fr/hor/fdi:010085408},
}