% 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”.

@ARTICLE{Upadhyay:1043532,
      author       = {Upadhyay, Utkarsh and Pucci, Fabrizio and Herold, Julian
                      and Schug, Alexander},
      title        = {{N}ucleo{S}eeker—precision filtering of {RNA} databases
                      to curate high-quality datasets},
      journal      = {NAR: genomics and bioinformatics},
      volume       = {7},
      number       = {1},
      issn         = {2631-9268},
      address      = {Oxford},
      publisher    = {Oxford University Press},
      reportid     = {FZJ-2025-02908},
      pages        = {lqaf021},
      year         = {2025},
      abstract     = {The structural prediction of biomolecules via computational
                      methods complements the often involved wet-lab experiments.
                      Unlike protein structure prediction, RNA structure
                      prediction remains a significant challenge in
                      bioinformatics, primarily due to the scarcity of annotated
                      RNA structure data and its varying quality. Many methods
                      have used this limited data to train deep learning models
                      but redundancy, data leakage and bad data quality hampers
                      their performance. In this work, we present NucleoSeeker, a
                      tool designed to curate high-quality, tailored datasets from
                      the Protein Data Bank (PDB) database. It is a unified
                      framework that combines multiple tools and streamlines an
                      otherwise complicated process of data curation. It offers
                      multiple filters at structure, sequence, and annotation
                      levels, giving researchers full control over data curation.
                      Further, we present several use cases. In particular, we
                      demonstrate how NucleoSeeker allows the creation of a
                      nonredundant RNA structure dataset to assess AlphaFold3’s
                      performance for RNA structure prediction. This demonstrates
                      NucleoSeeker’s effectiveness in curating valuable
                      nonredundant tailored datasets to both train novel and judge
                      existing methods. NucleoSeeker is very easy to use, highly
                      flexible, and can significantly increase the quality of RNA
                      structure datasets.},
      cin          = {JSC},
      ddc          = {570},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {5111 - Domain-Specific Simulation $\&$ Data Life Cycle Labs
                      (SDLs) and Research Groups (POF4-511) / Helmholtz AI -
                      Helmholtz Artificial Intelligence Coordination Unit –
                      Local Unit FZJ (E.40401.62)},
      pid          = {G:(DE-HGF)POF4-5111 / G:(DE-Juel-1)E.40401.62},
      typ          = {PUB:(DE-HGF)16},
      pubmed       = {40104673},
      UT           = {WOS:001446715300001},
      doi          = {10.1093/nargab/lqaf021},
      url          = {https://juser.fz-juelich.de/record/1043532},
}