Publication

array(14 items)
   uid => 935 (integer)
   title => 'BioDeepfuse: a hybrid deep learning approach with integrated feature extract
      ion techniques for enhanced non-coding RNA classification' (133 chars)
   abstract => 'The accurate classification of non-coding RNA (ncRNA) sequences is pivotal f
      or advanced non-coding genome annotation and analysis, a fundamental aspect 
      of genomics that facilitates understanding of ncRNA functions and regulatory
       mechanisms in various biological processes. While traditional machine learn
      ing approaches have been employed for distinguishing ncRNA, these often nece
      ssitate extensive feature engineering. Recently, deep learning algorithms ha
      ve provided advancements in ncRNA classification. This study presents BioDee
      pFuse, a hybrid deep learning framework integrating convolutional neural net
      works (CNN) or bidirectional long short-term memory (BiLSTM) networks with h
      andcrafted features for enhanced accuracy. This framework employs a combinat
      ion of k-mer one-hot, k-mer dictionary, and feature extraction techniques fo
      r input representation. Extracted features, when embedded into the deep netw
      ork, enable optimal utilization of spatial and sequential nuances of ncRNA s
      equences. Using benchmark datasets and real-world RNA samples from bacterial
       organisms, we evaluated the performance of BioDeepFuse. Results exhibited h
      igh accuracy in ncRNA classification, underscoring the robustness of our too
      l in addressing complex ncRNA sequence data challenges. The effective meldin
      g of CNN or BiLSTM with external features heralds promising directions for f
      uture research, particularly in refining ncRNA classifiers and deepening ins
      ights into ncRNAs in cellular processes and disease manifestations. In addit
      ion to its original application in the context of bacterial organisms, the m
      ethodologies and techniques integrated into our framework can potentially re
      nder BioDeepFuse effective in various and broader domains.' (1730 chars)
   authors => array(9 items)
      0 => array(3 items)
         last_name => 'Avila Santos' (12 chars)
         first_name => 'Anderson P.' (11 chars)
         sorting => 1 (integer)
      1 => array(3 items)
         last_name => 'de Almeida' (10 chars)
         first_name => 'Breno L.  S.' (12 chars)
         sorting => 2 (integer)
      2 => array(3 items)
         last_name => 'Bonidia' (7 chars)
         first_name => 'Robson P.' (9 chars)
         sorting => 3 (integer)
      3 => array(3 items)
         last_name => 'Stadler' (7 chars)
         first_name => 'Peter Florian' (13 chars)
         sorting => 4 (integer)
      4 => array(3 items)
         last_name => 'Štefanič' (10 chars)
         first_name => 'Polanca' (7 chars)
         sorting => 5 (integer)
      5 => array(3 items)
         last_name => 'Mandic-Mulec' (12 chars)
         first_name => 'Ines' (4 chars)
         sorting => 6 (integer)
      6 => array(3 items)
         last_name => 'da Rocha' (8 chars)
         first_name => 'Ulisses Nunes' (13 chars)
         sorting => 7 (integer)
      7 => array(3 items)
         last_name => 'Sanches' (7 chars)
         first_name => 'Danilo S.' (9 chars)
         sorting => 8 (integer)
      8 => array(3 items)
         last_name => 'Carvalho' (8 chars)
         first_name => 'André Carlos Ponce de Leon Ferreira de' (39 chars)
         sorting => 9 (integer)
   type => '0' (1 chars)
   keywords => '' (0 chars)
   year => 2024 (integer)
   affiliation => 0 (integer)
   link_paper => '' (0 chars)
   link_supplements => '' (0 chars)
   file_published => 0 (integer)
   journal => 'RNA Biology' (11 chars)
   doi => '10.1080/15476286.2024.2329451' (29 chars)
   preprint => '-1' (2 chars)