% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@PHDTHESIS{Sprenger:877844,
      author       = {Sprenger, Julia},
      title        = {{T}ools and {W}orkflows for {D}ata $\&$ {M}etadata
                      {M}anagement of {C}omplex {E}xperiments - {B}uilding a
                      {F}oundation for {R}eproducible $\&$ {C}ollaborative
                      {A}nalysis in the {N}eurosciences},
      volume       = {222},
      school       = {RWTH Aachen},
      type         = {Dissertation},
      address      = {Jülich},
      publisher    = {Forschungszentrum Jülich GmbH Zentralbibliothek, Verlag},
      reportid     = {FZJ-2020-02468},
      isbn         = {978-3-95806-478-2},
      series       = {Schriften des Forschungszentrums Jülich. Reihe
                      Schlüsseltechnologien / Key Technologies},
      pages        = {X, 168 S.},
      year         = {2020},
      note         = {Dissertation, RWTH Aachen, 2020},
      abstract     = {The scientific knowledge of mankind is based on the
                      verification of hypotheses by carrying out experiments. As
                      the construction and conduct of an experiment becomes
                      increasingly complex more and more scientists are involved
                      in a single project. In order to make the generated data
                      easily accessible to all scientists and, at best, to the
                      entire scientific community, it is essential to
                      comprehensively document the circumstances of the data
                      generation, as these contain essential information for later
                      analysis and interpretation. In this thesis, I present two
                      complex neuroscience projects and the strategies, tools, and
                      concepts that were used to comprehensively track, process,
                      organize, and prepare the collected data for joint analysis.
                      First, I describe the older of the two experiments and
                      explain in detail the generation of data and metadata and
                      the pipeline used for aggregating metadata. A hierarchical
                      approach based on the open source software $\textit{odML}$
                      for metadata organization was implemented to capture the
                      complex meta information of this project. I evaluate the
                      design concepts and tools used and derive a general
                      catalogue of requirements for scientific collaboration in
                      complex projects. Also, I identify issues and requirements
                      that were not yet addressed by this pipeline. There were, in
                      particular, the difficulties in i) entering manual metadata
                      and structuring the metadata collection,ii) combining
                      metadata with the actual data, and iii) setting up the
                      pipeline in a modular generic and transparent manner. Guided
                      by this analysis, I describe concept and tool
                      implementations to address these identified issues. I
                      developed a complementary tool ($\textit{odMLtables}$) to i)
                      facilitate the capture of metadata in a structured way and
                      to ii) convert these easily into the hierarchical,
                      standardized metadata format $\textit{odML. odMLtables}$
                      provides an interface between the easy-to-read tabular
                      metadata representation in the formats commonly used in
                      laboratory environments (csv/xls) and the hierarchically
                      organized $\textit{odML}$ format based on xml, which is
                      designed for a comprehensive collection of complex metadata
                      records in an easily machine-readable manner. Supplementing
                      the coordinated capture of metadata, I contributed to and
                      shaped the $\textit{Neo}$ toolbox for the standardized
                      representation of electrophysiological data. This toolbox is
                      a key component for electrophysiological data analysis as it
                      integrates different proprietary and non-proprietary file
                      formats and serves as a bridge between different file
                      formats. I emphasize new features that simplify the process
                      of data and metadata handling in the data acquisition
                      workflow. I introduce the concept of workflow management
                      into the field of scientific data processing, based on the
                      common Python-based snakemake package. For the second, more
                      recent electrophysiological experiment, I designed and
                      implemented the workflow for capturing and packaging
                      metadata and data in a comprehensive form. Here I used the
                      generic neuroscience information exchange format
                      ($\textit{Nix}$) for the user-friendly packaging of data
                      sets including data and metadata in combined form. Finally,
                      I evaluate the improved workflow against the requirements of
                      collaborative scientific work in complex projects. I
                      establish general guidelines for conducting such experiments
                      and workflows in a scientific environment. In conclusion, I
                      present the next development steps for the presented
                      workflow and potential avenues for deploying this prototype
                      as a production prototype to a wider scientific community.},
      cin          = {INM-6 / IAS-6 / INM-10},
      cid          = {I:(DE-Juel1)INM-6-20090406 / I:(DE-Juel1)IAS-6-20130828 /
                      I:(DE-Juel1)INM-10-20170113},
      pnm          = {899 - ohne Topic (POF3-899)},
      pid          = {G:(DE-HGF)POF3-899},
      typ          = {PUB:(DE-HGF)3 / PUB:(DE-HGF)11},
      urn          = {urn:nbn:de:0001-2020072301},
      url          = {https://juser.fz-juelich.de/record/877844},
}