% 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”.

@INPROCEEDINGS{Khler:885612,
      author       = {Köhler, Cristiano and Ulianych, Danylo and Gerkin, Richard
                      C. and Davison, Andrew P. and Grün, Sonja and Denker,
                      Michael},
      title        = {{P}rovenance capture in the analysis of electrophysiology
                      data: an example based on the {E}lephant package},
      reportid     = {FZJ-2020-03964},
      year         = {2020},
      abstract     = {Workflows for the analysis of electrophysiology data
                      typically comprise multiple steps, which should be fully
                      documented when aiming at the reproducibility of the
                      results. Considering the complexity, modularity and often
                      iterative nature of such workflows, robust tools forming the
                      basis of the workflow are necessary [1]. We focus here on
                      two open-source tools used for the analysis of
                      electrophysiology data. The Neo $(RRID:SCR_000634)$
                      framework provides a data object model to standardize data
                      of different origins [2]. Elephant $(RRID:SCR_003833)$ is a
                      toolbox for both standard and highly sophisticated analyses
                      of simulated and experimental data [3]. The characterization
                      of all data manipulations and the parameters throughout the
                      workflow provides provenance information [4] that improves
                      reproducibility of the results. This requires complete and
                      self-explanatory descriptions of the data objects in the
                      workflow and a method to minimize the need for manually
                      tracking its execution. While the Neo framework provides a
                      model to structure the neuronal data and associated
                      metadata, a similar representation for the outputs of the
                      analysis part of the workflow is still missing. Moreover,
                      automated provenance capture is not available at the
                      function level for a single Python script. Thus, existing
                      tools must be improved to implement a data model that
                      captures analysis outputs and workflow provenance and,
                      ultimately, represents the analysis and its results in
                      accordance with the FAIR principles [5].Here we present a
                      conceptual solution to capture provenance during the
                      analysis of electrophysiology data. First, we introduce a
                      standardization of the outputs of the Elephant functions,
                      which is inspired by the Neo model. Thus, the information
                      about the generation of an analysis output will be
                      encapsulated in a new set of Python objects that can be
                      easily re-used or shared. These objects will be integrated
                      into the existing code bases with minimal disruption. This
                      will free the scientist from the need to manually annotate
                      the output of the analysis. Second, we will show how to
                      capture provenance information throughout the Python
                      analysis script by using function decorators. These track
                      the Elephant and user-defined functions in the script while
                      mapping the inputs to the outputs, thereby also yielding a
                      provenance trace in the form of a graph. We present a
                      prototype implementation and demonstrate its use in a
                      scenario where spike and LFP data are analyzed by standard
                      methods. References: [1] Denker, M. and Grün, S. (2016).
                      Designing Workflows for the Reproducible Analysis of
                      Electrophysiological Data. In Brain-Inspired Computing,
                      Amunts, K. et al., eds. (Cham: Springer International
                      Publishing), pp. 58-72. [2] Garcia, S. et al. (2014) Neo: an
                      object model for handling electrophysiology data in multiple
                      formats. Frontiers in Neuroinformatics 8:10. [3]
                      http://python-elephant.org [4] Ragan, E.D. et al. (2016).
                      Characterizing Provenance in Visualization and Data
                      Analysis: An Organizational Framework of Provenance Types
                      and Purposes. IEEE Transactions on Visualization and
                      Computer Graphics. 22(1):31–40. [5] Wilkinson, M.D. et al.
                      (2016). The FAIR Guiding Principles for scientific data
                      management and stewardship. Scientific Data 3, 160018.},
      month         = {Sep},
      date          = {2020-09-29},
      organization  = {Online Bernstein Conference 2020,
                       online (Germany), 29 Sep 2020 - 1 Oct
                       2020},
      subtyp        = {Other},
      cin          = {INM-6 / INM-10 / IAS-6},
      cid          = {I:(DE-Juel1)INM-6-20090406 / I:(DE-Juel1)INM-10-20170113 /
                      I:(DE-Juel1)IAS-6-20130828},
      pnm          = {571 - Connectivity and Activity (POF3-571) / 574 - Theory,
                      modelling and simulation (POF3-574) / HDS LEE - Helmholtz
                      School for Data Science in Life, Earth and Energy (HDS LEE)
                      (HDS-LEE-20190612) / HBP SGA2 - Human Brain Project Specific
                      Grant Agreement 2 (785907) / HBP SGA3 - Human Brain Project
                      Specific Grant Agreement 3 (945539) / HAF - Helmholtz
                      Analytics Framework (ZT-I-0003) / PhD no Grant - Doktorand
                      ohne besondere Förderung (PHD-NO-GRANT-20170405)},
      pid          = {G:(DE-HGF)POF3-571 / G:(DE-HGF)POF3-574 /
                      G:(DE-Juel1)HDS-LEE-20190612 / G:(EU-Grant)785907 /
                      G:(EU-Grant)945539 / G:(DE-HGF)ZT-I-0003 /
                      G:(DE-Juel1)PHD-NO-GRANT-20170405},
      typ          = {PUB:(DE-HGF)24},
      doi          = {10.12751/NNCN.BC2020.0098},
      url          = {https://juser.fz-juelich.de/record/885612},
}