@article{WheelerBarquistKingsleyetal.2016,
  author    = {Wheeler, Nicole E. and Barquist, Lars and Kingsley, Robert A. and Gardner, Paul P.},
  title     = {A profile-based method for identifying functional divergence of orthologous genes in bacterial genomes},
  series = {Bioinformatics},
  volume    = {32},
  journal   = {Bioinformatics},
  number    = {23},
  doi       = {10.1093/bioinformatics/btw518},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-186502},
  pages     = {3566-3574},
  year      = {2016},
  abstract  = {Motivation: Next generation sequencing technologies have provided us with a wealth of information on genetic variation, but predi cting the functional significance of this variation is a difficult task. While many comparative genomics studies have focused on gene flux and large scale changes, relatively little attention has been paid to quantifying the effects of single nucleotide polymorphisms and indels on protein function, particularly in bacterial genomics. Results: We present a hidden Markov model based approach we call delta-bitscore (DBS) for identifying orthologous proteins that have diverged at the amino acid sequence level in a way that is likely to impact biological function. We benchmark this approach with several widely used datasets and apply it to a proof-of-concept study of orthologous proteomes in an investigation of host adaptation in Salmonella enterica. We highlight the value of the method in identifying functional divergence of genes, and suggest that this tool may be a better approach than the commonly used dN/dS metric for identifying functionally significant genetic changes occurring in recently diverged organisms.},
  language  = {en}
}
@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}
}