@article{Schulze2014,
  author    = {Schulze, Gunnar},
  title     = {Workflow for rapid metagenome analysis},
  series = {Process design for natural scientists: an agile model-driven approach},
  journal   = {Process design for natural scientists: an agile model-driven approach},
  number    = {500},
  publisher = {Springer},
  address   = {Berlin},
  isbn      = {978-3-662-45005-5},
  issn      = {1865-0929},
  pages     = {88 -- 100},
  year      = {2014},
  abstract  = {Analyses of metagenomes in life sciences present new opportunities as well as challenges to the scientific community and call for advanced computational methods and workflows. The large amount of data collected from samples via next-generation sequencing (NGS) technologies render manual approaches to sequence comparison and annotation unsuitable. Rather, fast and efficient computational pipelines are needed to provide comprehensive statistics and summaries and enable the researcher to choose appropriate tools for more specific analyses. The workflow presented here builds upon previous pipelines designed for automated clustering and annotation of raw sequence reads obtained from next-generation sequencing technologies such as 454 and Illumina. Employing specialized algorithms, the sequence reads are processed at three different levels. First, raw reads are clustered at high similarity cutoff to yield clusters which can be exported as multifasta files for further analyses. Independently, open reading frames (ORFs) are predicted from raw reads and clustered at two strictness levels to yield sets of non-redundant sequences and ORF families. Furthermore, single ORFs are annotated by performing searches against the Pfam database},
  language  = {en}
}