@article{fdi:010086138,
  title = {{SENMAP} : a convolutional neural network architecture for curation of {LTR}-{RT} libraries from plant genomes},
  author = {{O}rozco-{A}rias, {S}. and {C}andamil-{C}ortes, {M}. {S}. and {V}alencia-{C}astrillon, {E}. and {J}aimes, {P}. {A}. and {O}rozco, {N}. {T}. and {A}rias-{M}endoza, {M}. and {T}abares-{S}oto, {R}. and {G}uyot, {R}omain and {I}saza, {G}. and {IEEE},},
  editor = {},
  language = {{ENG}},
  abstract = {{T}ransposable elements ({TE}s) are specific structures of the genome of species, which can move from one location to another. {F}or that reason, they can cause mutations or changes that can be negative, such as the appearance of diseases, or beneficial, such as participating in fundamental roles in the evolution of genomes and genetic diversity. {L}ong {T}erminal {R}epeat retrotransposons ({LTR}-{RT}) are the most abundant in plant species, hence the importance of studying these structures in particular. {O}ver the time, these elements can suffer changes called nested insertions, which can inactivate or modify the functioning of the element, for that they are no longer consider as intact element and cannot be used for identification and classification studies. {I}n this work we present {SENMAP}, a convolutional neural network architecture to obtain intact {LTR}-{RT} sequences in plant genomes, which is composed by four convolutional layers, {L}eaky{R}e{LU} as activation function and {B}inary{F}ocal{L}oss as loss function. {A}chieving an {F}1-score percentage of 91.37% with test data, identifying low quality sequences rapidly and efficiently, contributing to curate libraries of {LTR} retrotransposons of plants genomes published in large-scale sequencing projects due to the post-genomic era.},
  keywords = {{C}uration ; nested insertions ; {LTR} retrotransposons ; deep neural network ; convolutional neural network},
  booktitle = {},
  journal = {2021 {IEEE} 2nd {I}nternational {C}ongress of {B}iomedical {E}ngineering and {B}ioengineering},
  numero = {},
  pages = {341660 [4 p.]},
  year = {2021},
  DOI = {10.1109/ci-ibbi54220.2021.9626130},
  URL = {https://www.documentation.ird.fr/hor/fdi:010086138},
}