@phdthesis{Perscheid2023,
  author    = {Perscheid, Cindy},
  title     = {Integrative biomarker detection using prior knowledge on gene expression data sets},
  doi       = {10.25932/publishup-58241},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-582418},
  school      = {Universit{\"a}t Potsdam},
  pages     = {ix, 197},
  year      = {2023},
  abstract  = {Gene expression data is analyzed to identify biomarkers, e.g. relevant genes, which serve for diagnostic, predictive, or prognostic use. Traditional approaches for biomarker detection select distinctive features from the data based exclusively on the signals therein, facing multiple shortcomings in regards to overfitting, biomarker robustness, and actual biological relevance. Prior knowledge approaches are expected to address these issues by incorporating prior biological knowledge, e.g. on gene-disease associations, into the actual analysis. However, prior knowledge approaches are currently not widely applied in practice because they are often use-case specific and seldom applicable in a different scope. This leads to a lack of comparability of prior knowledge approaches, which in turn makes it currently impossible to assess their effectiveness in a broader context. Our work addresses the aforementioned issues with three contributions. Our first contribution provides formal definitions for both prior knowledge and the flexible integration thereof into the feature selection process. Central to these concepts is the automatic retrieval of prior knowledge from online knowledge bases, which allows for streamlining the retrieval process and agreeing on a uniform definition for prior knowledge. We subsequently describe novel and generalized prior knowledge approaches that are flexible regarding the used prior knowledge and applicable to varying use case domains. Our second contribution is the benchmarking platform Comprior. Comprior applies the aforementioned concepts in practice and allows for flexibly setting up comprehensive benchmarking studies for examining the performance of existing and novel prior knowledge approaches. It streamlines the retrieval of prior knowledge and allows for combining it with prior knowledge approaches. Comprior demonstrates the practical applicability of our concepts and further fosters the overall development and comparability of prior knowledge approaches. Our third contribution is a comprehensive case study on the effectiveness of prior knowledge approaches. For that, we used Comprior and tested a broad range of both traditional and prior knowledge approaches in combination with multiple knowledge bases on data sets from multiple disease domains. Ultimately, our case study constitutes a thorough assessment of a) the suitability of selected knowledge bases for integration, b) the impact of prior knowledge being applied at different integration levels, and c) the improvements in terms of classification performance, biological relevance, and overall robustness. In summary, our contributions demonstrate that generalized concepts for prior knowledge and a streamlined retrieval process improve the applicability of prior knowledge approaches. Results from our case study show that the integration of prior knowledge positively affects biomarker results, particularly regarding their robustness. Our findings provide the first in-depth insights on the effectiveness of prior knowledge approaches and build a valuable foundation for future research.},
  language  = {en}
}
@article{Perscheid2021,
  author    = {Perscheid, Cindy},
  title     = {Integrative biomarker detection on high-dimensional gene expression data sets},
  series = {Briefings in bioinformatics},
  volume    = {22},
  journal   = {Briefings in bioinformatics},
  number    = {3},
  publisher = {Oxford Univ. Press},
  address   = {Oxford},
  issn      = {1467-5463},
  doi       = {10.1093/bib/bbaa151},
  pages     = {18},
  year      = {2021},
  abstract  = {Gene expression data provide the expression levels of tens of thousands of genes from several hundred samples. These data are analyzed to detect biomarkers that can be of prognostic or diagnostic use. Traditionally, biomarker detection for gene expression data is the task of gene selection. The vast number of genes is reduced to a few relevant ones that achieve the best performance for the respective use case. Traditional approaches select genes based on their statistical significance in the data set. This results in issues of robustness, redundancy and true biological relevance of the selected genes. Integrative analyses typically address these shortcomings by integrating multiple data artifacts from the same objects, e.g. gene expression and methylation data. When only gene expression data are available, integrative analyses instead use curated information on biological processes from public knowledge bases. With knowledge bases providing an ever-increasing amount of curated biological knowledge, such prior knowledge approaches become more powerful. This paper provides a thorough overview on the status quo of biomarker detection on gene expression data with prior biological knowledge. We discuss current shortcomings of traditional approaches, review recent external knowledge bases, provide a classification and qualitative comparison of existing prior knowledge approaches and discuss open challenges for this kind of gene selection.},
  language  = {en}
}
@inproceedings{HaaseMatthiesenSchueffleretal.2020,
  author    = {Haase, Jennifer and Matthiesen, Julia and Sch{\"u}ffler, Arnulf and Kluge, Annette},
  title     = {Retentivity beats prior knowledge as predictor for the acquisition and adaptation of new production processes},
  series = {Proceedings of the 53rd Hawaii International Conference on System Sciences},
  volume    = {53},
  booktitle = {Proceedings of the 53rd Hawaii International Conference on System Sciences},
  publisher = {Western Periodicals Co.},
  address   = {North Hollywood, Calif.},
  doi       = {10125/64331},
  pages     = {4797 -- 4805},
  year      = {2020},
  abstract  = {In the time of digitalization the demand for organizational change is rising and demands ways to cope with fundamental changes on the organizational as well as individual level. As a basis, learning and forgetting mechanisms need to be understood in order to guide a change process efficiently and successfully. Our research aims to get a better understanding of individual differences and mechanisms in the change context by performing an experiment where individuals learn and later re-learn a complex production process using a simulation setting. The individual's performance, as well as retentivity and prior knowledge is assessed. Our results show that higher retentivity goes along with better learning and forgetting performances. Prior knowledge did not reveal such relation to the learning and forgetting performances. The influence of age and gender is discussed in detail.},
  language  = {en}
}