@article{LindgreenUmuLaietal.2014,
  author    = {Lindgreen, Stinus and Umu, Sinan Uğur and Lai, Alicia Sook-Wei and Eldai, Hisham and Liu, Wenting and McGimpsey, Stephanie and Wheeler, Nicole E. and Biggs, Patrick J. and Thomson, Nick R. and Barquist, Lars and Poole, Anthony M. and Gardner, Paul P.},
  title     = {Robust Identification of Noncoding RNA from Transcriptomes Requires Phylogenetically-Informed Sampling},
  series = {PLOS Computational Biology},
  volume    = {10},
  journal   = {PLOS Computational Biology},
  number    = {10},
  doi       = {10.1371/journal.pcbi.1003907},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-115259},
  pages     = {e1003907},
  year      = {2014},
  abstract  = {Noncoding RNAs are integral to a wide range of biological processes, including translation, gene regulation, host-pathogen interactions and environmental sensing. While genomics is now a mature field, our capacity to identify noncoding RNA elements in bacterial and archaeal genomes is hampered by the difficulty of de novo identification. The emergence of new technologies for characterizing transcriptome outputs, notably RNA-seq, are improving noncoding RNA identification and expression quantification. However, a major challenge is to robustly distinguish functional outputs from transcriptional noise. To establish whether annotation of existing transcriptome data has effectively captured all functional outputs, we analysed over 400 publicly available RNA-seq datasets spanning 37 different Archaea and Bacteria. Using comparative tools, we identify close to a thousand highly-expressed candidate noncoding RNAs. However, our analyses reveal that capacity to identify noncoding RNA outputs is strongly dependent on phylogenetic sampling. Surprisingly, and in stark contrast to protein-coding genes, the phylogenetic window for effective use of comparative methods is perversely narrow: aggregating public datasets only produced one phylogenetic cluster where these tools could be used to robustly separate unannotated noncoding RNAs from a null hypothesis of transcriptional noise. Our results show that for the full potential of transcriptomics data to be realized, a change in experimental design is paramount: effective transcriptomics requires phylogeny-aware sampling.},
  language  = {en}
}