@article{SchmidtKorbAbell2017,
  author    = {Schmidt, Marco F. and Korb, Oliver and Abell, Chris},
  title     = {Antagonists of the miRNA-Argonaute 2 Protein Complex},
  series = {Drug Target miRNA: Methods and Protocols},
  volume    = {1517},
  journal   = {Drug Target miRNA: Methods and Protocols},
  publisher = {Springer},
  address   = {New York},
  isbn      = {978-1-4939-6563-2},
  issn      = {1064-3745},
  doi       = {10.1007/978-1-4939-6563-2_17},
  pages     = {239 -- 249},
  year      = {2017},
  abstract  = {microRNAs (miRNAs) have been identified as high-value drug targets. A widely applied strategy in miRNA inhibition is the use of antisense agents. However, it has been shown that oligonucleotides are poorly cell permeable because of their complex chemical structure and due to their negatively charged backbone. Consequently, the general application of oligonucleotides in therapy is limited. Since miRNAs' functions are executed exclusively by the Argonaute 2 protein, we therefore describe a protocol for the design of a novel miRNA inhibitor class: antagonists of the miRNA-Argonaute 2 protein complex, so-called anti-miR-AGOs, that not only block the crucial binding site of the target miRNA but also bind to the protein's active site. Due to their lower molecular weight and, thus, more drug-like chemical structure, the novel inhibitor class may show better pharmacokinetic properties than reported oligonucleotide inhibitors, enabling them for potential therapeutic use.},
  language  = {en}
}
@article{Schmidt2017,
  author    = {Schmidt, Marco F.},
  title     = {miRNA Targeting Drugs},
  series = {Drug Target miRNA: Methods and Protocols},
  volume    = {1517},
  journal   = {Drug Target miRNA: Methods and Protocols},
  publisher = {Springer},
  address   = {New York},
  isbn      = {978-1-4939-6563-2},
  issn      = {1064-3745},
  doi       = {10.1007/978-1-4939-6563-2_1},
  pages     = {3 -- 22},
  year      = {2017},
  abstract  = {Only 20 years after the discovery of small non-coding, single-stranded ribonucleic acids, so-called microRNAs (miRNAs), as post-transcriptional gene regulators, the first miRNA-targeting drug Miravirsen for the treatment of hepatitis C has been successfully tested in clinical Phase II trials. Addressing miRNAs as drug targets may enable the cure, or at least the treatment of diseases, which presently seems impossible. However, due to miRNAs' chemical structure, generation of potential drug molecules with necessary pharmacokinetic properties is still challenging and requires a re-thinking of the drug discovery process. Therefore, this chapter highlights the potential of miRNAs as drug targets, discusses the challenges, and tries to give a complete overview of recent strategies in miRNA drug discovery.},
  language  = {en}
}
@incollection{Schmidt2017,
  author    = {Schmidt, Marco F.},
  title     = {Preface},
  series = {Drug target miRNA},
  volume    = {1517},
  booktitle = {Drug target miRNA},
  editor    = {Schmidt, Marco F.},
  publisher = {Springer},
  address   = {New York},
  isbn      = {978-1-4939-6563-2},
  issn      = {1064-3745},
  doi       = {10.1007/978-1-4939-6563-2},
  pages     = {V -- V},
  year      = {2017},
  language  = {en}
}
@article{CopeBaukmannKlingeretal.2021,
  author    = {Cope, Justin L. and Baukmann, Hannes A. and Klinger, J{\"o}rn E. and Ravarani, Charles N. J. and B{\"o}ttinger, Erwin and Konigorski, Stefan and Schmidt, Marco F.},
  title     = {Interaction-based feature selection algorithm outperforms polygenic risk score in predicting Parkinson's Disease status},
  series = {Frontiers in genetics},
  volume    = {12},
  journal   = {Frontiers in genetics},
  publisher = {Frontiers Media},
  address   = {Lausanne},
  issn      = {1664-8021},
  doi       = {10.3389/fgene.2021.744557},
  pages     = {9},
  year      = {2021},
  abstract  = {Polygenic risk scores (PRS) aggregating results from genome-wide association studies are the state of the art in the prediction of susceptibility to complex traits or diseases, yet their predictive performance is limited for various reasons, not least of which is their failure to incorporate the effects of gene-gene interactions. Novel machine learning algorithms that use large amounts of data promise to find gene-gene interactions in order to build models with better predictive performance than PRS. Here, we present a data preprocessing step by using data-mining of contextual information to reduce the number of features, enabling machine learning algorithms to identify gene-gene interactions. We applied our approach to the Parkinson's Progression Markers Initiative (PPMI) dataset, an observational clinical study of 471 genotyped subjects (368 cases and 152 controls). With an AUC of 0.85 (95\% CI = [0.72; 0.96]), the interaction-based prediction model outperforms the PRS (AUC of 0.58 (95\% CI = [0.42; 0.81])). Furthermore, feature importance analysis of the model provided insights into the mechanism of Parkinson's disease. For instance, the model revealed an interaction of previously described drug target candidate genes TMEM175 and GAPDHP25. These results demonstrate that interaction-based machine learning models can improve genetic prediction models and might provide an answer to the missing heritability problem.},
  language  = {en}
}