@article{fdi:010086744,
  title = {{I}npactor2 : a software based on deep learning to identify and classify {LTR}-retrotransposons in plant genomes},
  author = {{O}rozco-{A}rias, {S}. and {L}opez-{M}urillo, {L}. {H}. and {C}andamil-{C}ortes, {M}. {S}. and {A}rias, {M}. and {J}aimes, {P}. {A}. and {P}aschoal, {A}. {R}. and {T}abares-{S}oto, {R}. and {I}saza, {G}. and {G}uyot, {R}omain},
  editor = {},
  language = {{ENG}},
  abstract = {{LTR}-retrotransposons are the most abundant repeat sequences in plant genomes and play an important role in evolution and biodiversity. {T}heir characterization is of great importance to understand their dynamics. {H}owever, the identification and classification of these elements remains a challenge today. {M}oreover, 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. {H}ere we present {I}npactor2, an accurate and fast application that creates {LTR}-retrotransposon reference libraries in a very short time. {I}npactor2 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. {T}his tool takes advantage of multi-core and {GPU} architectures to decrease execution times. {U}sing the rice genome, {I}npactor2 showed a run time of 5 minutes (faster than other tools) and has the best accuracy and {F}1-{S}core of the tools tested here, also having the second best accuracy and specificity only surpassed by {EDTA}, but achieving 28% higher sensitivity. {F}or large genomes, {I}npactor2 is up to seven times faster than other available bioinformatics tools.},
  keywords = {{I}npactor2 ; {LTR}-retrotransposons ; plant genomes ; deep learning ; neural networks ; detection ; classification},
  booktitle = {},
  journal = {{B}riefings in {B}ioinformatics},
  numero = {},
  pages = {[10 p.]},
  ISSN = {1467-5463},
  year = {2023},
  DOI = {10.1093/bib/bbac511},
  URL = {https://www.documentation.ird.fr/hor/fdi:010086744},
}