@phdthesis{Yu2019,
  author    = {Yu, Sung-Huan},
  title     = {Development and application of computational tools for RNA-Seq based transcriptome annotations},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-176468},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2019},
  abstract  = {In order to understand the regulation of gene expression in organisms, precise genome annotation is essential. In recent years, RNA-Seq has become a potent method for generating and improving genome annotations. However, this Approach is time consuming and often inconsistently performed when done manually. In particular, the discovery of non-coding RNAs benefits strongly from the application of RNA-Seq data but requires significant amounts of expert knowledge and is labor-intensive. As a part of my doctoral study, I developed a modular tool called ANNOgesic that can detect numerous transcribed genomic features, including non-coding RNAs, based on RNA-Seq data in a precise and automatic fashion with a focus on bacterial and achaeal species. The software performs numerous analyses and generates several visualizations. It can generate annotations of high-Resolution that are hard to produce using traditional annotation tools that are based only on genome sequences. ANNOgesic can detect numerous novel genomic Features like UTR-derived small non-coding RNAs for which no other tool has been developed before. ANNOgesic is available under an open source license (ISCL) at https://github.com/Sung-Huan/ANNOgesic. My doctoral work not only includes the development of ANNOgesic but also its application to annotate the transcriptome of Staphylococcus aureus HG003 - a strain which has been a insightful model in infection biology. Despite its potential as a model, a complete genome sequence and annotations have been lacking for HG003. In order to fill this gap, the annotations of this strain, including sRNAs and their functions, were generated using ANNOgesic by analyzing differential RNA-Seq data from 14 different samples (two media conditions with seven time points), as well as RNA-Seq data generated after transcript fragmentation. ANNOgesic was also applied to annotate several bacterial and archaeal genomes, and as part of this its high performance was demonstrated. In summary, ANNOgesic is a powerful computational tool for RNA-Seq based annotations and has been successfully applied to several species.},
  subject      = {Genom},
  language  = {en}
}